Token | D |
Token ID | 360 |
Feature activation | -8.44e-02 |
Pos logit contributions | |
ration | +0.074 |
opoly | +0.074 |
abled | +0.072 |
Jacqu | +0.071 |
boarded | +0.069 |
Neg logit contributions | |
TIT | -0.088 |
\\\\\\\\ | -0.087 |
OTAL | -0.074 |
Merit | -0.074 |
Sessions | -0.073 |
Token | ich |
Token ID | 488 |
Feature activation | -8.33e-02 |
Pos logit contributions | |
TIT | +0.076 |
\\\\\\\\ | +0.075 |
OTAL | +0.066 |
Merit | +0.065 |
Sessions | +0.064 |
Neg logit contributions | |
ration | -0.049 |
opoly | -0.048 |
Jacqu | -0.047 |
abled | -0.047 |
marginalized | -0.045 |
Token | otom |
Token ID | 43125 |
Feature activation | -2.02e-02 |
Pos logit contributions | |
TIT | +0.075 |
\\\\\\\\ | +0.074 |
OTAL | +0.064 |
Merit | +0.063 |
Bank | +0.063 |
Neg logit contributions | |
ration | -0.049 |
opoly | -0.048 |
abled | -0.047 |
Jacqu | -0.047 |
marginalized | -0.045 |
Token | izing |
Token ID | 2890 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
TIT | +0.018 |
\\\\\\\\ | +0.018 |
OTAL | +0.016 |
Merit | +0.016 |
Bank | +0.015 |
Neg logit contributions | |
ration | -0.012 |
opoly | -0.012 |
abled | -0.011 |
Jacqu | -0.011 |
marginalized | -0.011 |
Token | Disc |
Token ID | 8444 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
ration | +0.155 |
opoly | +0.153 |
abled | +0.150 |
Jacqu | +0.147 |
boarded | +0.144 |
Neg logit contributions | |
TIT | -0.190 |
\\\\\\\\ | -0.188 |
OTAL | -0.162 |
Merit | -0.160 |
Sessions | -0.160 |
Token | ourse |
Token ID | 9047 |
Feature activation | +7.21e-01 |
Pos logit contributions | |
ration | +0.067 |
opoly | +0.064 |
abled | +0.062 |
Jacqu | +0.060 |
marginalized | +0.055 |
Neg logit contributions | |
TIT | -0.295 |
\\\\\\\\ | -0.293 |
OTAL | -0.265 |
Merit | -0.262 |
Bank | -0.261 |
Token | of |
Token ID | 286 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
ration | +0.459 |
opoly | +0.455 |
abled | +0.442 |
Jacqu | +0.435 |
marginalized | +0.423 |
Neg logit contributions | |
TIT | -0.613 |
\\\\\\\\ | -0.607 |
OTAL | -0.523 |
Merit | -0.515 |
Bank | -0.512 |
Token | Multiple |
Token ID | 20401 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
ration | +0.076 |
opoly | +0.076 |
abled | +0.074 |
Jacqu | +0.073 |
boarded | +0.071 |
Neg logit contributions | |
TIT | -0.080 |
\\\\\\\\ | -0.079 |
OTAL | -0.067 |
Sessions | -0.067 |
Merit | -0.067 |
Token | Tem |
Token ID | 5825 |
Feature activation | +2.59e-02 |
Pos logit contributions | |
ration | +0.133 |
opoly | +0.132 |
abled | +0.129 |
Jacqu | +0.127 |
marginalized | +0.124 |
Neg logit contributions | |
TIT | -0.140 |
\\\\\\\\ | -0.138 |
OTAL | -0.117 |
Merit | -0.115 |
Sessions | -0.115 |
Token | por |
Token ID | 1819 |
Feature activation | +3.70e-03 |
Pos logit contributions | |
ration | +0.015 |
opoly | +0.015 |
abled | +0.014 |
Jacqu | +0.014 |
marginalized | +0.014 |
Neg logit contributions | |
TIT | -0.023 |
\\\\\\\\ | -0.023 |
OTAL | -0.020 |
Sessions | -0.020 |
Merit | -0.020 |
Token | alities |
Token ID | 27969 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
ration | +0.002 |
opoly | +0.002 |
abled | +0.002 |
Jacqu | +0.002 |
marginalized | +0.002 |
Neg logit contributions | |
TIT | -0.003 |
\\\\\\\\ | -0.003 |
OTAL | -0.003 |
Merit | -0.003 |
Bank | -0.003 |
Token | � |
Token ID | 247 |
Feature activation | +7.53e-03 |
Pos logit contributions | |
TIT | +0.006 |
\\\\\\\\ | +0.006 |
OTAL | +0.004 |
Merit | +0.004 |
Bank | +0.004 |
Neg logit contributions | |
ration | -0.012 |
opoly | -0.012 |
abled | -0.012 |
Jacqu | -0.012 |
marginalized | -0.012 |
Token | s |
Token ID | 82 |
Feature activation | +4.00e-02 |
Pos logit contributions | |
ration | +0.005 |
opoly | +0.005 |
abled | +0.005 |
Jacqu | +0.005 |
marginalized | +0.005 |
Neg logit contributions | |
TIT | -0.006 |
\\\\\\\\ | -0.006 |
OTAL | -0.005 |
Merit | -0.005 |
Bank | -0.005 |
Token | languages |
Token ID | 8950 |
Feature activation | +8.32e-02 |
Pos logit contributions | |
opoly | +0.027 |
ration | +0.027 |
abled | +0.026 |
Jacqu | +0.026 |
boarded | +0.025 |
Neg logit contributions | |
TIT | -0.032 |
\\\\\\\\ | -0.032 |
OTAL | -0.027 |
Merit | -0.027 |
Sessions | -0.027 |
Token | critic |
Token ID | 4014 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
ration | +0.055 |
opoly | +0.055 |
abled | +0.054 |
Jacqu | +0.053 |
marginalized | +0.051 |
Neg logit contributions | |
TIT | -0.068 |
\\\\\\\\ | -0.067 |
OTAL | -0.057 |
Merit | -0.056 |
Bank | -0.056 |
Token | t |
Token ID | 256 |
Feature activation | -2.21e-02 |
Pos logit contributions | |
ration | +0.076 |
opoly | +0.076 |
abled | +0.073 |
Jacqu | +0.071 |
marginalized | +0.069 |
Neg logit contributions | |
TIT | -0.100 |
\\\\\\\\ | -0.099 |
OTAL | -0.085 |
Merit | -0.084 |
Sessions | -0.084 |
Token | abled |
Token ID | 4510 |
Feature activation | +7.10e-01 |
Pos logit contributions | |
TIT | +0.028 |
\\\\\\\\ | +0.028 |
OTAL | +0.026 |
Merit | +0.026 |
Sessions | +0.025 |
Neg logit contributions | |
opoly | -0.004 |
ration | -0.004 |
Jacqu | -0.004 |
marginalized | -0.003 |
abled | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | -4.26e-02 |
Pos logit contributions | |
opoly | +0.445 |
ration | +0.441 |
abled | +0.422 |
Jacqu | +0.418 |
marginalized | +0.406 |
Neg logit contributions | |
TIT | -0.612 |
\\\\\\\\ | -0.605 |
OTAL | -0.518 |
Sessions | -0.513 |
Merit | -0.512 |
Token | private |
Token ID | 2839 |
Feature activation | -5.78e-03 |
Pos logit contributions | |
TIT | +0.039 |
\\\\\\\\ | +0.038 |
OTAL | +0.033 |
Sessions | +0.033 |
Merit | +0.033 |
Neg logit contributions | |
opoly | -0.024 |
ration | -0.024 |
abled | -0.023 |
Jacqu | -0.023 |
marginalized | -0.022 |
Token | member |
Token ID | 2888 |
Feature activation | +6.39e-02 |
Pos logit contributions | |
TIT | +0.005 |
\\\\\\\\ | +0.005 |
OTAL | +0.004 |
Merit | +0.004 |
Sessions | +0.004 |
Neg logit contributions | |
opoly | -0.003 |
ration | -0.003 |
abled | -0.003 |
Jacqu | -0.003 |
marginalized | -0.003 |
Token | � |
Token ID | 447 |
Feature activation | -2.83e-02 |
Pos logit contributions | |
opoly | +0.041 |
ration | +0.041 |
abled | +0.039 |
Jacqu | +0.039 |
marginalized | +0.038 |
Neg logit contributions | |
TIT | -0.054 |
\\\\\\\\ | -0.054 |
OTAL | -0.046 |
Merit | -0.045 |
Bank | -0.045 |
Token | � |
Token ID | 247 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
TIT | +0.016 |
\\\\\\\\ | +0.016 |
OTAL | +0.012 |
Merit | +0.012 |
Bank | +0.012 |
Neg logit contributions | |
opoly | -0.026 |
ration | -0.026 |
abled | -0.025 |
Jacqu | -0.025 |
marginalized | -0.025 |
Token | � |
Token ID | 447 |
Feature activation | +4.87e-02 |
Pos logit contributions | |
TIT | +0.032 |
\\\\\\\\ | +0.032 |
OTAL | +0.027 |
Merit | +0.027 |
Sessions | +0.027 |
Neg logit contributions | |
ration | -0.027 |
opoly | -0.027 |
abled | -0.026 |
Jacqu | -0.026 |
marginalized | -0.025 |
Token | � |
Token ID | 247 |
Feature activation | -2.30e-02 |
Pos logit contributions | |
opoly | +0.045 |
ration | +0.045 |
abled | +0.044 |
Jacqu | +0.044 |
boarded | +0.043 |
Neg logit contributions | |
TIT | -0.027 |
\\\\\\\\ | -0.027 |
OTAL | -0.021 |
Merit | -0.021 |
Sessions | -0.021 |
Token | � |
Token ID | 564 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
TIT | +0.019 |
\\\\\\\\ | +0.019 |
OTAL | +0.016 |
Merit | +0.016 |
Bank | +0.016 |
Neg logit contributions | |
ration | -0.015 |
opoly | -0.015 |
abled | -0.014 |
Jacqu | -0.014 |
marginalized | -0.014 |
Token | � |
Token ID | 246 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
ration | +0.104 |
opoly | +0.104 |
abled | +0.101 |
Jacqu | +0.100 |
marginalized | +0.097 |
Neg logit contributions | |
TIT | -0.108 |
\\\\\\\\ | -0.107 |
OTAL | -0.090 |
Merit | -0.088 |
Bank | -0.087 |
Token | The |
Token ID | 464 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
ration | +0.082 |
opoly | +0.082 |
abled | +0.079 |
Jacqu | +0.078 |
marginalized | +0.077 |
Neg logit contributions | |
TIT | -0.079 |
\\\\\\\\ | -0.078 |
OTAL | -0.065 |
Merit | -0.064 |
Bank | -0.063 |
Token | Lor |
Token ID | 26068 |
Feature activation | +7.09e-01 |
Pos logit contributions | |
ration | +0.124 |
opoly | +0.123 |
abled | +0.120 |
Jacqu | +0.118 |
marginalized | +0.115 |
Neg logit contributions | |
TIT | -0.129 |
\\\\\\\\ | -0.127 |
OTAL | -0.108 |
Merit | -0.106 |
Sessions | -0.104 |
Token | ax |
Token ID | 897 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
ration | +0.313 |
opoly | +0.310 |
abled | +0.294 |
Jacqu | +0.291 |
marginalized | +0.279 |
Neg logit contributions | |
TIT | -0.742 |
\\\\\\\\ | -0.735 |
OTAL | -0.653 |
Merit | -0.644 |
Bank | -0.639 |
Token | � |
Token ID | 447 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
ration | +0.266 |
opoly | +0.265 |
abled | +0.258 |
Jacqu | +0.255 |
marginalized | +0.248 |
Neg logit contributions | |
TIT | -0.288 |
\\\\\\\\ | -0.285 |
OTAL | -0.241 |
Merit | -0.236 |
Bank | -0.234 |
Token | � |
Token ID | 246 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
opoly | +0.098 |
ration | +0.098 |
abled | +0.095 |
Jacqu | +0.094 |
boarded | +0.092 |
Neg logit contributions | |
TIT | -0.084 |
\\\\\\\\ | -0.083 |
OTAL | -0.069 |
Merit | -0.068 |
Sessions | -0.067 |
Token | : |
Token ID | 25 |
Feature activation | +9.24e-02 |
Pos logit contributions | |
ration | +0.096 |
opoly | +0.096 |
abled | +0.093 |
Jacqu | +0.092 |
marginalized | +0.090 |
Neg logit contributions | |
TIT | -0.103 |
\\\\\\\\ | -0.102 |
OTAL | -0.086 |
Merit | -0.085 |
Bank | -0.084 |
Token | The |
Token ID | 383 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
ration | +0.065 |
opoly | +0.064 |
abled | +0.063 |
Jacqu | +0.061 |
marginalized | +0.060 |
Neg logit contributions | |
TIT | -0.073 |
\\\\\\\\ | -0.072 |
OTAL | -0.061 |
Sessions | -0.060 |
Merit | -0.060 |
Token | , |
Token ID | 11 |
Feature activation | -5.11e-02 |
Pos logit contributions | |
TIT | +0.176 |
\\\\\\\\ | +0.174 |
OTAL | +0.147 |
Merit | +0.145 |
Bank | +0.143 |
Neg logit contributions | |
ration | -0.168 |
opoly | -0.168 |
abled | -0.163 |
Jacqu | -0.161 |
marginalized | -0.157 |
Token | following |
Token ID | 1708 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
TIT | +0.044 |
\\\\\\\\ | +0.043 |
OTAL | +0.038 |
Merit | +0.037 |
Sessions | +0.037 |
Neg logit contributions | |
ration | -0.032 |
opoly | -0.032 |
abled | -0.030 |
Jacqu | -0.030 |
marginalized | -0.029 |
Token | a |
Token ID | 257 |
Feature activation | +5.80e-03 |
Pos logit contributions | |
TIT | +0.164 |
\\\\\\\\ | +0.162 |
OTAL | +0.140 |
Merit | +0.138 |
Sessions | +0.137 |
Neg logit contributions | |
ration | -0.114 |
opoly | -0.114 |
abled | -0.109 |
Jacqu | -0.108 |
marginalized | -0.105 |
Token | question |
Token ID | 1808 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
opoly | +0.004 |
ration | +0.004 |
abled | +0.004 |
Jacqu | +0.004 |
marginalized | +0.003 |
Neg logit contributions | |
TIT | -0.005 |
\\\\\\\\ | -0.005 |
OTAL | -0.004 |
Merit | -0.004 |
Sessions | -0.004 |
Token | t |
Token ID | 256 |
Feature activation | +2.19e-02 |
Pos logit contributions | |
TIT | +0.102 |
\\\\\\\\ | +0.100 |
OTAL | +0.086 |
Merit | +0.085 |
Sessions | +0.084 |
Neg logit contributions | |
ration | -0.081 |
opoly | -0.080 |
abled | -0.077 |
Jacqu | -0.077 |
marginalized | -0.075 |
Token | abled |
Token ID | 4510 |
Feature activation | +7.04e-01 |
Pos logit contributions | |
ration | +0.002 |
opoly | +0.002 |
Jacqu | +0.001 |
marginalized | +0.001 |
boarded | +0.001 |
Neg logit contributions | |
TIT | -0.031 |
\\\\\\\\ | -0.030 |
OTAL | -0.028 |
Sessions | -0.028 |
Merit | -0.028 |
Token | by |
Token ID | 416 |
Feature activation | -5.23e-02 |
Pos logit contributions | |
ration | +0.488 |
opoly | +0.487 |
abled | +0.470 |
Jacqu | +0.466 |
marginalized | +0.454 |
Neg logit contributions | |
TIT | -0.560 |
\\\\\\\\ | -0.554 |
OTAL | -0.471 |
Merit | -0.463 |
Sessions | -0.459 |
Token | Lord |
Token ID | 4453 |
Feature activation | +1.00e-02 |
Pos logit contributions | |
TIT | +0.043 |
\\\\\\\\ | +0.042 |
OTAL | +0.036 |
Sessions | +0.036 |
Merit | +0.036 |
Neg logit contributions | |
opoly | -0.035 |
ration | -0.035 |
abled | -0.033 |
Jacqu | -0.032 |
marginalized | -0.032 |
Token | Ave |
Token ID | 12761 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
ration | +0.007 |
opoly | +0.007 |
abled | +0.007 |
Jacqu | +0.007 |
marginalized | +0.007 |
Neg logit contributions | |
TIT | -0.008 |
\\\\\\\\ | -0.007 |
OTAL | -0.006 |
Merit | -0.006 |
Bank | -0.006 |
Token | bury |
Token ID | 10711 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
TIT | +0.153 |
\\\\\\\\ | +0.151 |
OTAL | +0.127 |
Merit | +0.125 |
Bank | +0.124 |
Neg logit contributions | |
ration | -0.155 |
opoly | -0.154 |
abled | -0.149 |
Jacqu | -0.148 |
marginalized | -0.145 |
Token | in |
Token ID | 287 |
Feature activation | -2.01e-02 |
Pos logit contributions | |
TIT | +0.088 |
\\\\\\\\ | +0.087 |
OTAL | +0.074 |
Merit | +0.072 |
Sessions | +0.072 |
Neg logit contributions | |
ration | -0.078 |
opoly | -0.078 |
abled | -0.076 |
Jacqu | -0.075 |
marginalized | -0.073 |
Token | uk |
Token ID | 2724 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
ration | +0.024 |
opoly | +0.024 |
abled | +0.023 |
Jacqu | +0.023 |
marginalized | +0.023 |
Neg logit contributions | |
TIT | -0.029 |
\\\\\\\\ | -0.028 |
OTAL | -0.024 |
Merit | -0.024 |
Bank | -0.024 |
Token | id |
Token ID | 312 |
Feature activation | +7.37e-02 |
Pos logit contributions | |
ration | +0.187 |
opoly | +0.186 |
abled | +0.181 |
Jacqu | +0.179 |
marginalized | +0.175 |
Neg logit contributions | |
TIT | -0.203 |
\\\\\\\\ | -0.201 |
OTAL | -0.170 |
Merit | -0.167 |
Bank | -0.166 |
Token | ō |
Token ID | 13090 |
Feature activation | +4.63e-01 |
Pos logit contributions | |
ration | +0.033 |
opoly | +0.033 |
Jacqu | +0.031 |
abled | +0.031 |
marginalized | +0.030 |
Neg logit contributions | |
\\\\\\\\ | -0.076 |
TIT | -0.076 |
OTAL | -0.068 |
Merit | -0.067 |
Bank | -0.066 |
Token | and |
Token ID | 290 |
Feature activation | +5.49e-02 |
Pos logit contributions | |
opoly | +0.316 |
ration | +0.315 |
abled | +0.307 |
Jacqu | +0.303 |
marginalized | +0.294 |
Neg logit contributions | |
TIT | -0.371 |
\\\\\\\\ | -0.369 |
OTAL | -0.313 |
Merit | -0.307 |
Bank | -0.306 |
Token | Corps |
Token ID | 12778 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
opoly | +0.035 |
ration | +0.035 |
abled | +0.034 |
Jacqu | +0.033 |
marginalized | +0.032 |
Neg logit contributions | |
TIT | -0.047 |
\\\\\\\\ | -0.046 |
OTAL | -0.040 |
Merit | -0.039 |
Bank | -0.039 |
Token | Commander |
Token ID | 13353 |
Feature activation | +6.85e-01 |
Pos logit contributions | |
opoly | +0.262 |
ration | +0.261 |
abled | +0.252 |
Jacqu | +0.249 |
marginalized | +0.242 |
Neg logit contributions | |
TIT | -0.343 |
\\\\\\\\ | -0.339 |
OTAL | -0.292 |
Merit | -0.287 |
Bank | -0.285 |
Token | of |
Token ID | 286 |
Feature activation | +6.21e-02 |
Pos logit contributions | |
ration | +0.453 |
opoly | +0.451 |
abled | +0.437 |
Jacqu | +0.432 |
marginalized | +0.419 |
Neg logit contributions | |
TIT | -0.568 |
\\\\\\\\ | -0.562 |
OTAL | -0.482 |
Merit | -0.473 |
Bank | -0.468 |
Token | the |
Token ID | 262 |
Feature activation | +4.26e-02 |
Pos logit contributions | |
opoly | +0.039 |
ration | +0.039 |
abled | +0.038 |
Jacqu | +0.037 |
marginalized | +0.036 |
Neg logit contributions | |
TIT | -0.053 |
\\\\\\\\ | -0.053 |
OTAL | -0.046 |
Merit | -0.045 |
Bank | -0.044 |
Token | Corrections |
Token ID | 40526 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
opoly | +0.028 |
ration | +0.028 |
abled | +0.027 |
Jacqu | +0.027 |
marginalized | +0.026 |
Neg logit contributions | |
TIT | -0.035 |
\\\\\\\\ | -0.035 |
OTAL | -0.030 |
Merit | -0.029 |
Bank | -0.029 |
Token | Corps |
Token ID | 12778 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
TIT | +0.168 |
\\\\\\\\ | +0.166 |
OTAL | +0.143 |
Merit | +0.140 |
Bank | +0.139 |
Neg logit contributions | |
ration | -0.135 |
opoly | -0.135 |
abled | -0.130 |
Jacqu | -0.129 |
marginalized | -0.125 |
Token | . |
Token ID | 13 |
Feature activation | +4.81e-02 |
Pos logit contributions | |
ration | +0.281 |
opoly | +0.280 |
abled | +0.271 |
Jacqu | +0.269 |
marginalized | +0.261 |
Neg logit contributions | |
TIT | -0.342 |
\\\\\\\\ | -0.339 |
OTAL | -0.289 |
Merit | -0.284 |
Bank | -0.281 |
Token | democratic |
Token ID | 10518 |
Feature activation | -5.98e-02 |
Pos logit contributions | |
TIT | +0.003 |
\\\\\\\\ | +0.003 |
OTAL | +0.002 |
Sessions | +0.002 |
Merit | +0.002 |
Neg logit contributions | |
opoly | -0.002 |
ration | -0.002 |
abled | -0.002 |
Jacqu | -0.002 |
boarded | -0.002 |
Token | reform |
Token ID | 4975 |
Feature activation | -8.88e-02 |
Pos logit contributions | |
TIT | +0.049 |
\\\\\\\\ | +0.049 |
OTAL | +0.041 |
Merit | +0.041 |
Sessions | +0.041 |
Neg logit contributions | |
opoly | -0.039 |
ration | -0.039 |
abled | -0.038 |
Jacqu | -0.037 |
boarded | -0.036 |
Token | , |
Token ID | 11 |
Feature activation | -8.37e-02 |
Pos logit contributions | |
TIT | +0.072 |
\\\\\\\\ | +0.072 |
OTAL | +0.061 |
Merit | +0.060 |
Bank | +0.059 |
Neg logit contributions | |
ration | -0.060 |
opoly | -0.060 |
abled | -0.058 |
Jacqu | -0.057 |
marginalized | -0.055 |
Token | who |
Token ID | 508 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
TIT | +0.074 |
\\\\\\\\ | +0.073 |
OTAL | +0.063 |
Merit | +0.062 |
Sessions | +0.062 |
Neg logit contributions | |
opoly | -0.051 |
ration | -0.051 |
abled | -0.049 |
Jacqu | -0.048 |
marginalized | -0.047 |
Token | t |
Token ID | 256 |
Feature activation | -4.96e-02 |
Pos logit contributions | |
opoly | +0.135 |
ration | +0.134 |
abled | +0.128 |
Jacqu | +0.128 |
marginalized | +0.124 |
Neg logit contributions | |
TIT | -0.167 |
\\\\\\\\ | -0.165 |
OTAL | -0.141 |
Sessions | -0.139 |
Merit | -0.139 |
Token | abled |
Token ID | 4510 |
Feature activation | +6.84e-01 |
Pos logit contributions | |
TIT | +0.069 |
\\\\\\\\ | +0.069 |
OTAL | +0.063 |
Sessions | +0.063 |
Merit | +0.063 |
Neg logit contributions | |
opoly | -0.004 |
ration | -0.004 |
Jacqu | -0.003 |
marginalized | -0.002 |
rift | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | -3.17e-02 |
Pos logit contributions | |
ration | +0.413 |
opoly | +0.410 |
abled | +0.398 |
Jacqu | +0.393 |
marginalized | +0.379 |
Neg logit contributions | |
TIT | -0.607 |
\\\\\\\\ | -0.600 |
OTAL | -0.521 |
Merit | -0.513 |
Bank | -0.506 |
Token | bill |
Token ID | 2855 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
TIT | +0.025 |
\\\\\\\\ | +0.025 |
OTAL | +0.021 |
Merit | +0.021 |
Sessions | +0.021 |
Neg logit contributions | |
opoly | -0.022 |
ration | -0.022 |
abled | -0.021 |
Jacqu | -0.021 |
marginalized | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | -8.87e-02 |
Pos logit contributions | |
TIT | +0.079 |
\\\\\\\\ | +0.078 |
OTAL | +0.066 |
Merit | +0.065 |
Sessions | +0.065 |
Neg logit contributions | |
opoly | -0.070 |
ration | -0.070 |
abled | -0.067 |
Jacqu | -0.066 |
boarded | -0.064 |
Token |
|
Token ID | 198 |
Feature activation | -7.12e-02 |
Pos logit contributions | |
TIT | +0.080 |
\\\\\\\\ | +0.079 |
OTAL | +0.069 |
Merit | +0.068 |
Bank | +0.067 |
Neg logit contributions | |
ration | -0.052 |
opoly | -0.052 |
abled | -0.050 |
Jacqu | -0.050 |
marginalized | -0.048 |
Token |
|
Token ID | 198 |
Feature activation | -5.88e-02 |
Pos logit contributions | |
TIT | +0.060 |
\\\\\\\\ | +0.058 |
OTAL | +0.050 |
Merit | +0.050 |
Bank | +0.050 |
Neg logit contributions | |
ration | -0.047 |
opoly | -0.047 |
abled | -0.045 |
boarded | -0.044 |
Jacqu | -0.044 |
Token | � |
Token ID | 247 |
Feature activation | +4.21e-02 |
Pos logit contributions | |
TIT | +0.003 |
\\\\\\\\ | +0.003 |
OTAL | +0.002 |
Merit | +0.002 |
Bank | +0.002 |
Neg logit contributions | |
opoly | -0.005 |
ration | -0.005 |
abled | -0.005 |
Jacqu | -0.005 |
marginalized | -0.004 |
Token | t |
Token ID | 83 |
Feature activation | -3.12e-02 |
Pos logit contributions | |
ration | +0.032 |
opoly | +0.031 |
abled | +0.031 |
Jacqu | +0.030 |
marginalized | +0.029 |
Neg logit contributions | |
TIT | -0.031 |
\\\\\\\\ | -0.031 |
OTAL | -0.026 |
Merit | -0.025 |
Tuc | -0.025 |
Token | read |
Token ID | 1100 |
Feature activation | -2.17e-02 |
Pos logit contributions | |
TIT | +0.023 |
\\\\\\\\ | +0.023 |
OTAL | +0.019 |
Merit | +0.019 |
Sessions | +0.019 |
Neg logit contributions | |
opoly | -0.023 |
ration | -0.023 |
abled | -0.023 |
Jacqu | -0.022 |
marginalized | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | +1.93e-02 |
Pos logit contributions | |
TIT | +0.019 |
\\\\\\\\ | +0.019 |
OTAL | +0.016 |
Merit | +0.016 |
Sessions | +0.016 |
Neg logit contributions | |
ration | -0.013 |
opoly | -0.013 |
abled | -0.013 |
Jacqu | -0.013 |
marginalized | -0.012 |
Token | tag |
Token ID | 7621 |
Feature activation | +4.82e-02 |
Pos logit contributions | |
opoly | +0.014 |
ration | +0.014 |
abled | +0.013 |
Jacqu | +0.013 |
marginalized | +0.013 |
Neg logit contributions | |
TIT | -0.015 |
\\\\\\\\ | -0.015 |
OTAL | -0.013 |
Merit | -0.013 |
Sessions | -0.012 |
Token | lines |
Token ID | 6615 |
Feature activation | +6.63e-01 |
Pos logit contributions | |
ration | +0.022 |
opoly | +0.022 |
abled | +0.021 |
Jacqu | +0.021 |
marginalized | +0.020 |
Neg logit contributions | |
TIT | -0.049 |
\\\\\\\\ | -0.049 |
OTAL | -0.043 |
Merit | -0.043 |
Bank | -0.042 |
Token | on |
Token ID | 319 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
ration | +0.449 |
opoly | +0.446 |
abled | +0.432 |
Jacqu | +0.428 |
marginalized | +0.416 |
Neg logit contributions | |
TIT | -0.540 |
\\\\\\\\ | -0.534 |
OTAL | -0.456 |
Merit | -0.448 |
Bank | -0.443 |
Token | movie |
Token ID | 3807 |
Feature activation | -2.29e-02 |
Pos logit contributions | |
opoly | +0.081 |
ration | +0.081 |
abled | +0.079 |
Jacqu | +0.077 |
marginalized | +0.074 |
Neg logit contributions | |
TIT | -0.107 |
\\\\\\\\ | -0.105 |
OTAL | -0.090 |
Merit | -0.089 |
Sessions | -0.089 |
Token | billboards |
Token ID | 46696 |
Feature activation | +9.09e-03 |
Pos logit contributions | |
TIT | +0.021 |
\\\\\\\\ | +0.021 |
OTAL | +0.018 |
Merit | +0.018 |
Bank | +0.018 |
Neg logit contributions | |
opoly | -0.013 |
ration | -0.013 |
abled | -0.012 |
Jacqu | -0.012 |
marginalized | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | -5.56e-02 |
Pos logit contributions | |
ration | +0.006 |
opoly | +0.006 |
abled | +0.006 |
Jacqu | +0.006 |
marginalized | +0.006 |
Neg logit contributions | |
TIT | -0.007 |
\\\\\\\\ | -0.007 |
OTAL | -0.006 |
Merit | -0.006 |
Bank | -0.006 |
Token | a |
Token ID | 257 |
Feature activation | -1.65e-02 |
Pos logit contributions | |
TIT | +0.043 |
\\\\\\\\ | +0.042 |
OTAL | +0.036 |
Sessions | +0.035 |
Tuc | +0.035 |
Neg logit contributions | |
opoly | -0.039 |
ration | -0.039 |
abled | -0.038 |
Jacqu | -0.038 |
marginalized | -0.037 |
Token | Stay |
Token ID | 16160 |
Feature activation | +8.96e-02 |
Pos logit contributions | |
ration | +0.042 |
opoly | +0.041 |
abled | +0.040 |
Jacqu | +0.039 |
marginalized | +0.038 |
Neg logit contributions | |
TIT | -0.049 |
\\\\\\\\ | -0.048 |
OTAL | -0.041 |
Sessions | -0.041 |
Merit | -0.041 |
Token | tuned |
Token ID | 16524 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
opoly | +0.050 |
ration | +0.049 |
abled | +0.047 |
Jacqu | +0.047 |
marginalized | +0.045 |
Neg logit contributions | |
TIT | -0.084 |
\\\\\\\\ | -0.083 |
OTAL | -0.072 |
Sessions | -0.071 |
Tuc | -0.071 |
Token | ! |
Token ID | 0 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
opoly | +0.165 |
ration | +0.164 |
abled | +0.159 |
Jacqu | +0.156 |
marginalized | +0.152 |
Neg logit contributions | |
TIT | -0.213 |
\\\\\\\\ | -0.211 |
OTAL | -0.181 |
Merit | -0.178 |
Sessions | -0.177 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -5.40e-02 |
Pos logit contributions | |
ration | +0.167 |
opoly | +0.166 |
abled | +0.161 |
Jacqu | +0.160 |
marginalized | +0.155 |
Neg logit contributions | |
TIT | -0.192 |
\\\\\\\\ | -0.190 |
OTAL | -0.162 |
Merit | -0.158 |
Bank | -0.157 |
Token | Mer |
Token ID | 13102 |
Feature activation | -2.70e-02 |
Pos logit contributions | |
TIT | +0.039 |
\\\\\\\\ | +0.039 |
OTAL | +0.032 |
Merit | +0.032 |
Bank | +0.031 |
Neg logit contributions | |
ration | -0.041 |
opoly | -0.041 |
abled | -0.040 |
Jacqu | -0.040 |
marginalized | -0.039 |
Token | kel |
Token ID | 7750 |
Feature activation | +6.56e-01 |
Pos logit contributions | |
TIT | +0.024 |
\\\\\\\\ | +0.024 |
OTAL | +0.021 |
Merit | +0.020 |
Bank | +0.020 |
Neg logit contributions | |
ration | -0.016 |
opoly | -0.016 |
abled | -0.016 |
Jacqu | -0.015 |
marginalized | -0.015 |
Token | told |
Token ID | 1297 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
opoly | +0.418 |
ration | +0.418 |
abled | +0.405 |
Jacqu | +0.398 |
marginalized | +0.385 |
Neg logit contributions | |
TIT | -0.556 |
\\\\\\\\ | -0.549 |
OTAL | -0.473 |
Merit | -0.467 |
Sessions | -0.462 |
Token | parliament |
Token ID | 8540 |
Feature activation | +8.82e-02 |
Pos logit contributions | |
opoly | +0.122 |
ration | +0.121 |
abled | +0.118 |
Jacqu | +0.116 |
marginalized | +0.113 |
Neg logit contributions | |
TIT | -0.146 |
\\\\\\\\ | -0.144 |
OTAL | -0.123 |
Merit | -0.121 |
Sessions | -0.121 |
Token | that |
Token ID | 326 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
opoly | +0.053 |
ration | +0.053 |
abled | +0.050 |
Jacqu | +0.050 |
marginalized | +0.048 |
Neg logit contributions | |
TIT | -0.079 |
\\\\\\\\ | -0.078 |
OTAL | -0.067 |
Merit | -0.066 |
Sessions | -0.066 |
Token | while |
Token ID | 981 |
Feature activation | +9.46e-02 |
Pos logit contributions | |
opoly | +0.078 |
ration | +0.078 |
abled | +0.076 |
Jacqu | +0.075 |
marginalized | +0.072 |
Neg logit contributions | |
TIT | -0.096 |
\\\\\\\\ | -0.094 |
OTAL | -0.081 |
Merit | -0.080 |
Sessions | -0.079 |
Token | she |
Token ID | 673 |
Feature activation | +6.93e-02 |
Pos logit contributions | |
opoly | +0.062 |
ration | +0.062 |
abled | +0.060 |
Jacqu | +0.059 |
marginalized | +0.057 |
Neg logit contributions | |
TIT | -0.079 |
\\\\\\\\ | -0.077 |
OTAL | -0.066 |
Merit | -0.065 |
Sessions | -0.065 |
Token | the |
Token ID | 262 |
Feature activation | +8.94e-02 |
Pos logit contributions | |
opoly | +0.038 |
ration | +0.037 |
abled | +0.036 |
Jacqu | +0.036 |
boarded | +0.034 |
Neg logit contributions | |
TIT | -0.052 |
\\\\\\\\ | -0.051 |
OTAL | -0.044 |
Merit | -0.044 |
Sessions | -0.043 |
Token | program |
Token ID | 1430 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
opoly | +0.058 |
ration | +0.058 |
abled | +0.056 |
Jacqu | +0.055 |
marginalized | +0.053 |
Neg logit contributions | |
TIT | -0.075 |
\\\\\\\\ | -0.074 |
OTAL | -0.063 |
Merit | -0.063 |
Bank | -0.062 |
Token | and |
Token ID | 290 |
Feature activation | +9.86e-02 |
Pos logit contributions | |
ration | +0.085 |
opoly | +0.085 |
abled | +0.082 |
Jacqu | +0.081 |
marginalized | +0.079 |
Neg logit contributions | |
TIT | -0.113 |
\\\\\\\\ | -0.112 |
OTAL | -0.096 |
Merit | -0.095 |
Bank | -0.094 |
Token | its |
Token ID | 663 |
Feature activation | -2.64e-02 |
Pos logit contributions | |
opoly | +0.064 |
ration | +0.063 |
abled | +0.063 |
Jacqu | +0.061 |
boarded | +0.059 |
Neg logit contributions | |
TIT | -0.082 |
\\\\\\\\ | -0.081 |
OTAL | -0.070 |
Merit | -0.069 |
Sessions | -0.068 |
Token | stewards |
Token ID | 38030 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
TIT | +0.020 |
\\\\\\\\ | +0.020 |
OTAL | +0.017 |
Merit | +0.017 |
Bank | +0.016 |
Neg logit contributions | |
opoly | -0.019 |
ration | -0.019 |
abled | -0.018 |
Jacqu | -0.018 |
marginalized | -0.018 |
Token | hip |
Token ID | 1056 |
Feature activation | +6.53e-01 |
Pos logit contributions | |
ration | +0.026 |
opoly | +0.025 |
abled | +0.022 |
Jacqu | +0.021 |
marginalized | +0.018 |
Neg logit contributions | |
TIT | -0.193 |
\\\\\\\\ | -0.192 |
OTAL | -0.174 |
Merit | -0.173 |
Bank | -0.171 |
Token | ," |
Token ID | 553 |
Feature activation | +4.99e-02 |
Pos logit contributions | |
ration | +0.418 |
opoly | +0.415 |
abled | +0.401 |
Jacqu | +0.397 |
marginalized | +0.386 |
Neg logit contributions | |
TIT | -0.559 |
\\\\\\\\ | -0.552 |
OTAL | -0.476 |
Merit | -0.464 |
Bank | -0.462 |
Token | he |
Token ID | 339 |
Feature activation | +8.19e-02 |
Pos logit contributions | |
ration | +0.036 |
opoly | +0.035 |
abled | +0.034 |
Jacqu | +0.034 |
marginalized | +0.033 |
Neg logit contributions | |
TIT | -0.039 |
\\\\\\\\ | -0.038 |
OTAL | -0.032 |
Merit | -0.032 |
Bank | -0.032 |
Token | said |
Token ID | 531 |
Feature activation | -9.81e-03 |
Pos logit contributions | |
ration | +0.059 |
opoly | +0.059 |
abled | +0.057 |
Jacqu | +0.057 |
marginalized | +0.055 |
Neg logit contributions | |
TIT | -0.063 |
\\\\\\\\ | -0.062 |
OTAL | -0.052 |
Merit | -0.051 |
Bank | -0.051 |
Token | in |
Token ID | 287 |
Feature activation | +4.77e-02 |
Pos logit contributions | |
TIT | +0.008 |
\\\\\\\\ | +0.008 |
OTAL | +0.007 |
Merit | +0.007 |
Bank | +0.007 |
Neg logit contributions | |
ration | -0.006 |
opoly | -0.006 |
abled | -0.006 |
Jacqu | -0.006 |
marginalized | -0.006 |
Token | a |
Token ID | 257 |
Feature activation | +6.92e-02 |
Pos logit contributions | |
ration | +0.028 |
opoly | +0.028 |
abled | +0.027 |
Jacqu | +0.027 |
marginalized | +0.026 |
Neg logit contributions | |
TIT | -0.043 |
\\\\\\\\ | -0.043 |
OTAL | -0.037 |
Merit | -0.036 |
Bank | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
ration | +0.053 |
opoly | +0.053 |
abled | +0.051 |
Jacqu | +0.051 |
marginalized | +0.049 |
Neg logit contributions | |
TIT | -0.064 |
\\\\\\\\ | -0.063 |
OTAL | -0.054 |
Merit | -0.053 |
Bank | -0.053 |
Token | He |
Token ID | 679 |
Feature activation | +3.76e-02 |
Pos logit contributions | |
TIT | +0.009 |
\\\\\\\\ | +0.009 |
OTAL | +0.007 |
Bank | +0.007 |
Merit | +0.007 |
Neg logit contributions | |
ration | -0.008 |
opoly | -0.008 |
abled | -0.008 |
Jacqu | -0.008 |
marginalized | -0.008 |
Token | was |
Token ID | 373 |
Feature activation | -6.51e-02 |
Pos logit contributions | |
opoly | +0.025 |
ration | +0.025 |
abled | +0.024 |
Jacqu | +0.024 |
marginalized | +0.023 |
Neg logit contributions | |
TIT | -0.030 |
\\\\\\\\ | -0.030 |
OTAL | -0.026 |
Merit | -0.025 |
Bank | -0.025 |
Token | given |
Token ID | 1813 |
Feature activation | +7.14e-02 |
Pos logit contributions | |
TIT | +0.055 |
\\\\\\\\ | +0.054 |
OTAL | +0.047 |
Merit | +0.046 |
Sessions | +0.046 |
Neg logit contributions | |
opoly | -0.042 |
ration | -0.041 |
abled | -0.040 |
Jacqu | -0.039 |
rift | -0.038 |
Token | an |
Token ID | 281 |
Feature activation | +3.91e-02 |
Pos logit contributions | |
opoly | +0.044 |
ration | +0.044 |
abled | +0.043 |
Jacqu | +0.042 |
marginalized | +0.041 |
Neg logit contributions | |
TIT | -0.062 |
\\\\\\\\ | -0.061 |
OTAL | -0.052 |
Merit | -0.052 |
Sessions | -0.052 |
Token | ult |
Token ID | 3789 |
Feature activation | +6.43e-01 |
Pos logit contributions | |
opoly | +0.027 |
ration | +0.027 |
abled | +0.026 |
Jacqu | +0.026 |
marginalized | +0.025 |
Neg logit contributions | |
TIT | -0.031 |
\\\\\\\\ | -0.031 |
OTAL | -0.026 |
Merit | -0.026 |
Bank | -0.025 |
Token | im |
Token ID | 320 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
ration | +0.445 |
opoly | +0.445 |
Jacqu | +0.430 |
abled | +0.430 |
marginalized | +0.419 |
Neg logit contributions | |
TIT | -0.509 |
\\\\\\\\ | -0.503 |
OTAL | -0.430 |
Merit | -0.419 |
Bank | -0.418 |
Token | atum |
Token ID | 21307 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
ration | +0.138 |
opoly | +0.137 |
Jacqu | +0.133 |
abled | +0.133 |
marginalized | +0.130 |
Neg logit contributions | |
TIT | -0.150 |
\\\\\\\\ | -0.147 |
OTAL | -0.125 |
Bank | -0.122 |
Merit | -0.122 |
Token | and |
Token ID | 290 |
Feature activation | +6.10e-02 |
Pos logit contributions | |
opoly | +0.172 |
ration | +0.172 |
abled | +0.165 |
Jacqu | +0.164 |
marginalized | +0.160 |
Neg logit contributions | |
TIT | -0.217 |
\\\\\\\\ | -0.215 |
OTAL | -0.184 |
Merit | -0.181 |
Bank | -0.179 |
Token | a |
Token ID | 257 |
Feature activation | +5.33e-02 |
Pos logit contributions | |
opoly | +0.040 |
ration | +0.040 |
abled | +0.039 |
Jacqu | +0.038 |
rift | +0.037 |
Neg logit contributions | |
TIT | -0.050 |
\\\\\\\\ | -0.050 |
OTAL | -0.043 |
Tuc | -0.042 |
Sessions | -0.042 |
Token | day |
Token ID | 1110 |
Feature activation | +7.21e-02 |
Pos logit contributions | |
opoly | +0.036 |
ration | +0.035 |
abled | +0.034 |
Jacqu | +0.034 |
marginalized | +0.033 |
Neg logit contributions | |
TIT | -0.043 |
\\\\\\\\ | -0.043 |
OTAL | -0.037 |
Merit | -0.036 |
Tuc | -0.036 |
Token | what |
Token ID | 644 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
opoly | +0.026 |
ration | +0.026 |
abled | +0.025 |
Jacqu | +0.025 |
marginalized | +0.024 |
Neg logit contributions | |
TIT | -0.042 |
\\\\\\\\ | -0.042 |
OTAL | -0.037 |
Merit | -0.036 |
Sessions | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | +3.65e-02 |
Pos logit contributions | |
ration | +0.117 |
opoly | +0.117 |
abled | +0.113 |
Jacqu | +0.112 |
marginalized | +0.108 |
Neg logit contributions | |
TIT | -0.150 |
\\\\\\\\ | -0.148 |
OTAL | -0.127 |
Merit | -0.125 |
Bank | -0.124 |
Token | Cool |
Token ID | 34530 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
ration | +0.026 |
opoly | +0.026 |
abled | +0.026 |
Jacqu | +0.025 |
marginalized | +0.025 |
Neg logit contributions | |
TIT | -0.028 |
\\\\\\\\ | -0.028 |
OTAL | -0.024 |
Merit | -0.023 |
Bank | -0.023 |
Token | that |
Token ID | 326 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
TIT | +0.117 |
\\\\\\\\ | +0.116 |
OTAL | +0.099 |
Merit | +0.097 |
Bank | +0.096 |
Neg logit contributions | |
ration | -0.096 |
opoly | -0.096 |
abled | -0.093 |
Jacqu | -0.092 |
marginalized | -0.089 |
Token | Peter |
Token ID | 5613 |
Feature activation | +7.25e-02 |
Pos logit contributions | |
opoly | +0.072 |
ration | +0.072 |
abled | +0.069 |
Jacqu | +0.068 |
marginalized | +0.066 |
Neg logit contributions | |
TIT | -0.089 |
\\\\\\\\ | -0.088 |
OTAL | -0.076 |
Merit | -0.074 |
Sessions | -0.074 |
Token | Lor |
Token ID | 26068 |
Feature activation | +6.43e-01 |
Pos logit contributions | |
opoly | +0.023 |
ration | +0.023 |
abled | +0.021 |
Jacqu | +0.020 |
marginalized | +0.019 |
Neg logit contributions | |
TIT | -0.085 |
\\\\\\\\ | -0.085 |
OTAL | -0.076 |
Merit | -0.075 |
Sessions | -0.075 |
Token | re |
Token ID | 260 |
Feature activation | -3.66e-02 |
Pos logit contributions | |
ration | +0.513 |
opoly | +0.512 |
Jacqu | +0.500 |
abled | +0.497 |
marginalized | +0.489 |
Neg logit contributions | |
TIT | -0.439 |
\\\\\\\\ | -0.429 |
OTAL | -0.361 |
Merit | -0.354 |
Sessions | -0.348 |
Token | was |
Token ID | 373 |
Feature activation | -5.14e-04 |
Pos logit contributions | |
TIT | +0.030 |
\\\\\\\\ | +0.030 |
OTAL | +0.026 |
Sessions | +0.025 |
Merit | +0.025 |
Neg logit contributions | |
opoly | -0.024 |
ration | -0.024 |
abled | -0.023 |
Jacqu | -0.023 |
marginalized | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | +7.03e-02 |
Pos logit contributions | |
TIT | +0.000 |
\\\\\\\\ | +0.000 |
OTAL | +0.000 |
Merit | +0.000 |
Sessions | +0.000 |
Neg logit contributions | |
opoly | -0.000 |
ration | -0.000 |
abled | -0.000 |
Jacqu | -0.000 |
marginalized | -0.000 |
Token | first |
Token ID | 717 |
Feature activation | +4.33e-02 |
Pos logit contributions | |
opoly | +0.045 |
ration | +0.045 |
abled | +0.044 |
Jacqu | +0.043 |
marginalized | +0.042 |
Neg logit contributions | |
TIT | -0.059 |
\\\\\\\\ | -0.058 |
OTAL | -0.050 |
Merit | -0.049 |
Bank | -0.049 |
Token | Bond |
Token ID | 12812 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
opoly | +0.030 |
ration | +0.029 |
abled | +0.029 |
Jacqu | +0.028 |
marginalized | +0.027 |
Neg logit contributions | |
TIT | -0.035 |
\\\\\\\\ | -0.034 |
OTAL | -0.029 |
Merit | -0.029 |
Bank | -0.029 |
Token | he |
Token ID | 339 |
Feature activation | +5.02e-02 |
Pos logit contributions | |
ration | +0.006 |
opoly | +0.006 |
abled | +0.005 |
Jacqu | +0.005 |
marginalized | +0.005 |
Neg logit contributions | |
TIT | -0.007 |
\\\\\\\\ | -0.007 |
OTAL | -0.006 |
Merit | -0.006 |
Sessions | -0.006 |
Token | finished |
Token ID | 5201 |
Feature activation | +8.07e-02 |
Pos logit contributions | |
opoly | +0.034 |
ration | +0.034 |
abled | +0.033 |
Jacqu | +0.033 |
marginalized | +0.031 |
Neg logit contributions | |
TIT | -0.040 |
\\\\\\\\ | -0.040 |
OTAL | -0.034 |
Merit | -0.033 |
Sessions | -0.033 |
Token | sixth |
Token ID | 11695 |
Feature activation | +9.06e-02 |
Pos logit contributions | |
opoly | +0.057 |
ration | +0.056 |
abled | +0.055 |
Jacqu | +0.054 |
marginalized | +0.052 |
Neg logit contributions | |
TIT | -0.063 |
\\\\\\\\ | -0.063 |
OTAL | -0.053 |
Merit | -0.052 |
Sessions | -0.052 |
Token | on |
Token ID | 319 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
ration | +0.058 |
opoly | +0.057 |
abled | +0.055 |
Jacqu | +0.055 |
marginalized | +0.053 |
Neg logit contributions | |
TIT | -0.077 |
\\\\\\\\ | -0.076 |
OTAL | -0.066 |
Merit | -0.065 |
Bank | -0.064 |
Token | P |
Token ID | 350 |
Feature activation | -8.13e-02 |
Pos logit contributions | |
ration | +0.135 |
opoly | +0.134 |
abled | +0.129 |
Jacqu | +0.127 |
marginalized | +0.124 |
Neg logit contributions | |
TIT | -0.188 |
\\\\\\\\ | -0.186 |
OTAL | -0.161 |
Merit | -0.158 |
Sessions | -0.157 |
Token | FF |
Token ID | 5777 |
Feature activation | +6.31e-01 |
Pos logit contributions | |
TIT | +0.090 |
\\\\\\\\ | +0.089 |
OTAL | +0.080 |
Merit | +0.079 |
Bank | +0.078 |
Neg logit contributions | |
ration | -0.031 |
opoly | -0.031 |
abled | -0.029 |
Jacqu | -0.029 |
marginalized | -0.027 |
Token | � |
Token ID | 447 |
Feature activation | +3.51e-02 |
Pos logit contributions | |
ration | +0.401 |
opoly | +0.399 |
abled | +0.386 |
Jacqu | +0.382 |
marginalized | +0.370 |
Neg logit contributions | |
TIT | -0.540 |
\\\\\\\\ | -0.533 |
OTAL | -0.460 |
Merit | -0.452 |
Bank | -0.447 |
Token | � |
Token ID | 247 |
Feature activation | +7.55e-02 |
Pos logit contributions | |
opoly | +0.033 |
ration | +0.032 |
abled | +0.032 |
Jacqu | +0.032 |
boarded | +0.031 |
Neg logit contributions | |
TIT | -0.020 |
\\\\\\\\ | -0.020 |
OTAL | -0.015 |
Merit | -0.015 |
Bank | -0.015 |
Token | s |
Token ID | 82 |
Feature activation | +9.96e-02 |
Pos logit contributions | |
ration | +0.039 |
opoly | +0.039 |
abled | +0.038 |
Jacqu | +0.037 |
marginalized | +0.036 |
Neg logit contributions | |
TIT | -0.073 |
\\\\\\\\ | -0.072 |
OTAL | -0.064 |
Merit | -0.063 |
Bank | -0.062 |
Token | guard |
Token ID | 4860 |
Feature activation | -6.08e-02 |
Pos logit contributions | |
opoly | +0.066 |
ration | +0.066 |
abled | +0.064 |
Jacqu | +0.063 |
marginalized | +0.061 |
Neg logit contributions | |
TIT | -0.082 |
\\\\\\\\ | -0.081 |
OTAL | -0.070 |
Merit | -0.068 |
Sessions | -0.068 |
Token | list |
Token ID | 1351 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
TIT | +0.052 |
\\\\\\\\ | +0.052 |
OTAL | +0.045 |
Merit | +0.044 |
Sessions | +0.044 |
Neg logit contributions | |
opoly | -0.038 |
ration | -0.038 |
abled | -0.036 |
Jacqu | -0.036 |
marginalized | -0.035 |
Token | called |
Token ID | 1444 |
Feature activation | +3.71e-02 |
Pos logit contributions | |
TIT | +0.020 |
\\\\\\\\ | +0.019 |
OTAL | +0.017 |
Merit | +0.016 |
Sessions | +0.016 |
Neg logit contributions | |
opoly | -0.015 |
ration | -0.015 |
abled | -0.015 |
Jacqu | -0.014 |
marginalized | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | +1.86e-02 |
Pos logit contributions | |
opoly | +0.023 |
ration | +0.023 |
abled | +0.022 |
Jacqu | +0.022 |
marginalized | +0.021 |
Neg logit contributions | |
TIT | -0.032 |
\\\\\\\\ | -0.032 |
OTAL | -0.028 |
Merit | -0.027 |
Sessions | -0.027 |
Token | � |
Token ID | 564 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
opoly | +0.012 |
ration | +0.012 |
abled | +0.012 |
Jacqu | +0.011 |
marginalized | +0.011 |
Neg logit contributions | |
TIT | -0.016 |
\\\\\\\\ | -0.016 |
OTAL | -0.013 |
Merit | -0.013 |
Tuc | -0.013 |
Token | � |
Token ID | 250 |
Feature activation | +4.35e-02 |
Pos logit contributions | |
ration | +0.117 |
opoly | +0.117 |
abled | +0.114 |
Jacqu | +0.113 |
marginalized | +0.111 |
Neg logit contributions | |
TIT | -0.054 |
\\\\\\\\ | -0.053 |
OTAL | -0.039 |
Merit | -0.038 |
Bank | -0.037 |
Token | w |
Token ID | 86 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
ration | +0.030 |
opoly | +0.029 |
abled | +0.028 |
Jacqu | +0.028 |
marginalized | +0.028 |
Neg logit contributions | |
TIT | -0.035 |
\\\\\\\\ | -0.035 |
OTAL | -0.030 |
Merit | -0.029 |
Bank | -0.029 |
Token | hip |
Token ID | 1056 |
Feature activation | +6.25e-01 |
Pos logit contributions | |
ration | +0.116 |
opoly | +0.115 |
Jacqu | +0.111 |
abled | +0.110 |
marginalized | +0.108 |
Neg logit contributions | |
TIT | -0.152 |
\\\\\\\\ | -0.150 |
OTAL | -0.130 |
Merit | -0.127 |
Bank | -0.127 |
Token | � |
Token ID | 447 |
Feature activation | +1.90e-02 |
Pos logit contributions | |
ration | +0.391 |
opoly | +0.389 |
abled | +0.376 |
Jacqu | +0.373 |
marginalized | +0.362 |
Neg logit contributions | |
TIT | -0.537 |
\\\\\\\\ | -0.533 |
OTAL | -0.456 |
Merit | -0.447 |
Sessions | -0.447 |
Token | � |
Token ID | 251 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
ration | +0.018 |
opoly | +0.017 |
abled | +0.017 |
Jacqu | +0.017 |
marginalized | +0.017 |
Neg logit contributions | |
TIT | -0.011 |
\\\\\\\\ | -0.011 |
OTAL | -0.008 |
Merit | -0.008 |
Bank | -0.008 |
Token | stitch |
Token ID | 24695 |
Feature activation | -2.99e-02 |
Pos logit contributions | |
ration | +0.068 |
opoly | +0.068 |
abled | +0.065 |
Jacqu | +0.064 |
marginalized | +0.063 |
Neg logit contributions | |
TIT | -0.090 |
\\\\\\\\ | -0.089 |
OTAL | -0.076 |
Merit | -0.075 |
Bank | -0.075 |
Token | . |
Token ID | 13 |
Feature activation | -2.85e-02 |
Pos logit contributions | |
TIT | +0.024 |
\\\\\\\\ | +0.023 |
OTAL | +0.020 |
Sessions | +0.019 |
Merit | +0.019 |
Neg logit contributions | |
opoly | -0.021 |
ration | -0.021 |
abled | -0.020 |
Jacqu | -0.020 |
marginalized | -0.019 |
Token | Next |
Token ID | 7406 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
TIT | +0.022 |
\\\\\\\\ | +0.022 |
OTAL | +0.019 |
Sessions | +0.018 |
Tuc | +0.018 |
Neg logit contributions | |
ration | -0.021 |
opoly | -0.020 |
abled | -0.020 |
marginalized | -0.019 |
boarded | -0.019 |
Token | of |
Token ID | 286 |
Feature activation | +2.23e-02 |
Pos logit contributions | |
opoly | +0.175 |
ration | +0.173 |
abled | +0.170 |
Jacqu | +0.167 |
marginalized | +0.161 |
Neg logit contributions | |
TIT | -0.238 |
\\\\\\\\ | -0.234 |
OTAL | -0.201 |
Merit | -0.201 |
Sessions | -0.199 |
Token | a |
Token ID | 257 |
Feature activation | +5.40e-02 |
Pos logit contributions | |
opoly | +0.015 |
ration | +0.015 |
abled | +0.014 |
Jacqu | +0.014 |
marginalized | +0.013 |
Neg logit contributions | |
TIT | -0.019 |
\\\\\\\\ | -0.018 |
OTAL | -0.016 |
Bank | -0.015 |
Merit | -0.015 |
Token | false |
Token ID | 3991 |
Feature activation | -2.18e-02 |
Pos logit contributions | |
opoly | +0.034 |
ration | +0.034 |
abled | +0.034 |
Jacqu | +0.033 |
marginalized | +0.032 |
Neg logit contributions | |
TIT | -0.046 |
\\\\\\\\ | -0.045 |
OTAL | -0.039 |
Bank | -0.038 |
Merit | -0.038 |
Token | " |
Token ID | 366 |
Feature activation | +4.13e-02 |
Pos logit contributions | |
TIT | +0.018 |
\\\\\\\\ | +0.018 |
OTAL | +0.015 |
Bank | +0.015 |
Merit | +0.015 |
Neg logit contributions | |
opoly | -0.014 |
ration | -0.014 |
abled | -0.014 |
Jacqu | -0.014 |
marginalized | -0.013 |
Token | owners |
Token ID | 15605 |
Feature activation | +7.17e-02 |
Pos logit contributions | |
ration | +0.028 |
opoly | +0.028 |
Jacqu | +0.027 |
abled | +0.027 |
marginalized | +0.026 |
Neg logit contributions | |
TIT | -0.034 |
\\\\\\\\ | -0.033 |
OTAL | -0.028 |
Merit | -0.028 |
Bank | -0.028 |
Token | hip |
Token ID | 1056 |
Feature activation | +6.15e-01 |
Pos logit contributions | |
ration | +0.011 |
opoly | +0.011 |
abled | +0.010 |
Jacqu | +0.009 |
marginalized | +0.008 |
Neg logit contributions | |
TIT | -0.095 |
\\\\\\\\ | -0.095 |
OTAL | -0.086 |
Merit | -0.086 |
Bank | -0.085 |
Token | " |
Token ID | 1 |
Feature activation | +7.98e-02 |
Pos logit contributions | |
opoly | +0.437 |
ration | +0.436 |
abled | +0.426 |
Jacqu | +0.423 |
marginalized | +0.410 |
Neg logit contributions | |
TIT | -0.474 |
\\\\\\\\ | -0.468 |
OTAL | -0.396 |
Merit | -0.390 |
Bank | -0.386 |
Token | is |
Token ID | 318 |
Feature activation | -2.36e-04 |
Pos logit contributions | |
opoly | +0.050 |
abled | +0.049 |
ration | +0.049 |
Jacqu | +0.048 |
raq | +0.047 |
Neg logit contributions | |
TIT | -0.068 |
\\\\\\\\ | -0.066 |
OTAL | -0.057 |
Merit | -0.056 |
Bank | -0.056 |
Token | Wall |
Token ID | 5007 |
Feature activation | -3.80e-02 |
Pos logit contributions | |
TIT | +0.000 |
\\\\\\\\ | +0.000 |
OTAL | +0.000 |
Merit | +0.000 |
Bank | +0.000 |
Neg logit contributions | |
opoly | -0.000 |
ration | -0.000 |
abled | -0.000 |
Jacqu | -0.000 |
marginalized | -0.000 |
Token | Street |
Token ID | 3530 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
TIT | +0.027 |
\\\\\\\\ | +0.026 |
OTAL | +0.022 |
Merit | +0.022 |
Bank | +0.021 |
Neg logit contributions | |
ration | -0.030 |
opoly | -0.030 |
abled | -0.029 |
Jacqu | -0.029 |
marginalized | -0.028 |
Token | and |
Token ID | 290 |
Feature activation | +9.40e-02 |
Pos logit contributions | |
TIT | +0.108 |
\\\\\\\\ | +0.106 |
OTAL | +0.092 |
Bank | +0.090 |
Merit | +0.090 |
Neg logit contributions | |
ration | -0.085 |
opoly | -0.085 |
abled | -0.083 |
Jacqu | -0.082 |
marginalized | -0.079 |
Token | Ch |
Token ID | 609 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
TIT | +0.134 |
\\\\\\\\ | +0.132 |
OTAL | +0.113 |
Merit | +0.111 |
Bank | +0.110 |
Neg logit contributions | |
ration | -0.110 |
opoly | -0.110 |
abled | -0.106 |
Jacqu | -0.105 |
marginalized | -0.102 |
Token | iff |
Token ID | 733 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
TIT | +0.200 |
\\\\\\\\ | +0.197 |
OTAL | +0.170 |
Merit | +0.165 |
Sessions | +0.165 |
Neg logit contributions | |
ration | -0.178 |
opoly | -0.177 |
abled | -0.170 |
Jacqu | -0.170 |
marginalized | -0.166 |
Token | re |
Token ID | 260 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
opoly | +0.160 |
ration | +0.159 |
abled | +0.154 |
Jacqu | +0.153 |
marginalized | +0.150 |
Neg logit contributions | |
TIT | -0.147 |
\\\\\\\\ | -0.145 |
OTAL | -0.121 |
Merit | -0.118 |
Bank | -0.117 |
Token | ( |
Token ID | 357 |
Feature activation | +5.20e-03 |
Pos logit contributions | |
TIT | +0.120 |
\\\\\\\\ | +0.118 |
OTAL | +0.102 |
Merit | +0.100 |
Sessions | +0.100 |
Neg logit contributions | |
opoly | -0.085 |
ration | -0.085 |
abled | -0.082 |
Jacqu | -0.081 |
marginalized | -0.078 |
Token | Peter |
Token ID | 19727 |
Feature activation | +6.22e-02 |
Pos logit contributions | |
ration | +0.004 |
opoly | +0.004 |
abled | +0.003 |
Jacqu | +0.003 |
marginalized | +0.003 |
Neg logit contributions | |
TIT | -0.004 |
\\\\\\\\ | -0.004 |
OTAL | -0.004 |
Merit | -0.004 |
Bank | -0.004 |
Token | Lor |
Token ID | 26068 |
Feature activation | +6.10e-01 |
Pos logit contributions | |
ration | +0.047 |
opoly | +0.047 |
abled | +0.046 |
Jacqu | +0.045 |
marginalized | +0.044 |
Neg logit contributions | |
TIT | -0.046 |
\\\\\\\\ | -0.045 |
OTAL | -0.038 |
Merit | -0.037 |
Bank | -0.037 |
Token | re |
Token ID | 260 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
ration | +0.473 |
opoly | +0.471 |
abled | +0.456 |
Jacqu | +0.454 |
marginalized | +0.445 |
Neg logit contributions | |
TIT | -0.435 |
\\\\\\\\ | -0.429 |
OTAL | -0.358 |
Merit | -0.349 |
Bank | -0.347 |
Token | ) |
Token ID | 8 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
TIT | +0.065 |
\\\\\\\\ | +0.064 |
OTAL | +0.051 |
Merit | +0.050 |
Bank | +0.049 |
Neg logit contributions | |
ration | -0.096 |
opoly | -0.096 |
abled | -0.093 |
Jacqu | -0.093 |
marginalized | -0.091 |
Token | does |
Token ID | 857 |
Feature activation | -1.64e-02 |
Pos logit contributions | |
TIT | +0.130 |
\\\\\\\\ | +0.128 |
OTAL | +0.110 |
Sessions | +0.110 |
Merit | +0.109 |
Neg logit contributions | |
opoly | -0.094 |
ration | -0.092 |
abled | -0.090 |
Jacqu | -0.088 |
marginalized | -0.085 |
Token | something |
Token ID | 1223 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
TIT | +0.015 |
\\\\\\\\ | +0.014 |
OTAL | +0.013 |
Merit | +0.012 |
Bank | +0.012 |
Neg logit contributions | |
ration | -0.010 |
opoly | -0.010 |
abled | -0.009 |
Jacqu | -0.009 |
marginalized | -0.009 |
Token | to |
Token ID | 284 |
Feature activation | +4.68e-02 |
Pos logit contributions | |
opoly | +0.076 |
ration | +0.076 |
abled | +0.073 |
Jacqu | +0.072 |
marginalized | +0.070 |
Neg logit contributions | |
TIT | -0.097 |
\\\\\\\\ | -0.096 |
OTAL | -0.082 |
Merit | -0.081 |
Sessions | -0.080 |
Token | ub |
Token ID | 549 |
Feature activation | -1.54e-02 |
Pos logit contributions | |
TIT | +0.159 |
\\\\\\\\ | +0.157 |
OTAL | +0.134 |
Merit | +0.132 |
Bank | +0.131 |
Neg logit contributions | |
ration | -0.134 |
opoly | -0.134 |
abled | -0.129 |
Jacqu | -0.128 |
marginalized | -0.125 |
Token | ges |
Token ID | 3212 |
Feature activation | -5.38e-02 |
Pos logit contributions | |
TIT | +0.013 |
\\\\\\\\ | +0.012 |
OTAL | +0.011 |
Merit | +0.010 |
Bank | +0.010 |
Neg logit contributions | |
ration | -0.010 |
opoly | -0.010 |
abled | -0.010 |
Jacqu | -0.010 |
marginalized | -0.010 |
Token | hig |
Token ID | 25196 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
TIT | +0.043 |
\\\\\\\\ | +0.042 |
OTAL | +0.036 |
Merit | +0.035 |
Bank | +0.035 |
Neg logit contributions | |
ration | -0.038 |
opoly | -0.037 |
abled | -0.036 |
Jacqu | -0.036 |
marginalized | -0.035 |
Token | Rice |
Token ID | 13823 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
ration | +0.142 |
opoly | +0.141 |
abled | +0.137 |
Jacqu | +0.135 |
marginalized | +0.132 |
Neg logit contributions | |
TIT | -0.151 |
\\\\\\\\ | -0.149 |
OTAL | -0.126 |
Merit | -0.124 |
Bank | -0.122 |
Token | / |
Token ID | 14 |
Feature activation | -1.81e-02 |
Pos logit contributions | |
TIT | +0.107 |
\\\\\\\\ | +0.105 |
OTAL | +0.090 |
Merit | +0.088 |
Bank | +0.087 |
Neg logit contributions | |
ration | -0.092 |
opoly | -0.092 |
abled | -0.089 |
Jacqu | -0.088 |
marginalized | -0.086 |
Token | CBC |
Token ID | 29208 |
Feature activation | +6.06e-01 |
Pos logit contributions | |
TIT | +0.021 |
\\\\\\\\ | +0.020 |
OTAL | +0.018 |
Merit | +0.018 |
Bank | +0.018 |
Neg logit contributions | |
opoly | -0.006 |
ration | -0.006 |
Jacqu | -0.006 |
abled | -0.006 |
marginalized | -0.005 |
Token | ) |
Token ID | 8 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
ration | +0.540 |
opoly | +0.538 |
abled | +0.525 |
Jacqu | +0.523 |
marginalized | +0.510 |
Neg logit contributions | |
TIT | -0.364 |
\\\\\\\\ | -0.360 |
OTAL | -0.286 |
Merit | -0.277 |
Sessions | -0.274 |
Token | " |
Token ID | 366 |
Feature activation | +5.59e-02 |
Pos logit contributions | |
TIT | +0.099 |
\\\\\\\\ | +0.098 |
OTAL | +0.085 |
Merit | +0.084 |
Sessions | +0.083 |
Neg logit contributions | |
ration | -0.073 |
opoly | -0.072 |
abled | -0.070 |
Jacqu | -0.068 |
marginalized | -0.067 |
Token | It |
Token ID | 1026 |
Feature activation | +1.49e-03 |
Pos logit contributions | |
ration | +0.042 |
opoly | +0.042 |
abled | +0.040 |
Jacqu | +0.040 |
boarded | +0.039 |
Neg logit contributions | |
TIT | -0.042 |
\\\\\\\\ | -0.041 |
OTAL | -0.034 |
Merit | -0.034 |
Bank | -0.034 |
Token | 's |
Token ID | 338 |
Feature activation | +6.64e-02 |
Pos logit contributions | |
opoly | +0.001 |
ration | +0.001 |
abled | +0.001 |
Jacqu | +0.001 |
boarded | +0.001 |
Neg logit contributions | |
TIT | -0.001 |
\\\\\\\\ | -0.001 |
OTAL | -0.001 |
Merit | -0.001 |
Sessions | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | +5.30e-02 |
Pos logit contributions | |
opoly | +0.045 |
ration | +0.045 |
abled | +0.044 |
Jacqu | +0.043 |
marginalized | +0.042 |
Neg logit contributions | |
TIT | -0.054 |
\\\\\\\\ | -0.053 |
OTAL | -0.045 |
Merit | -0.045 |
Sessions | -0.044 |
Token | . |
Token ID | 13 |
Feature activation | +5.31e-02 |
Pos logit contributions | |
TIT | +0.205 |
\\\\\\\\ | +0.201 |
OTAL | +0.175 |
Bank | +0.170 |
Sessions | +0.170 |
Neg logit contributions | |
opoly | -0.163 |
ration | -0.161 |
Jacqu | -0.157 |
abled | -0.157 |
marginalized | -0.152 |
Token | Y |
Token ID | 575 |
Feature activation | -6.85e-02 |
Pos logit contributions | |
ration | +0.038 |
opoly | +0.037 |
abled | +0.037 |
marginalized | +0.035 |
Jacqu | +0.035 |
Neg logit contributions | |
TIT | -0.042 |
\\\\\\\\ | -0.041 |
OTAL | -0.035 |
Sessions | -0.034 |
Tuc | -0.034 |
Token | up |
Token ID | 929 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
TIT | +0.044 |
\\\\\\\\ | +0.043 |
OTAL | +0.035 |
Merit | +0.034 |
Bank | +0.034 |
Neg logit contributions | |
ration | -0.058 |
opoly | -0.058 |
abled | -0.056 |
Jacqu | -0.056 |
marginalized | -0.055 |
Token | , |
Token ID | 11 |
Feature activation | -1.21e-03 |
Pos logit contributions | |
TIT | +0.084 |
\\\\\\\\ | +0.083 |
OTAL | +0.071 |
Merit | +0.069 |
Bank | +0.068 |
Neg logit contributions | |
ration | -0.073 |
opoly | -0.073 |
abled | -0.071 |
Jacqu | -0.070 |
marginalized | -0.068 |
Token | the |
Token ID | 262 |
Feature activation | +4.19e-02 |
Pos logit contributions | |
TIT | +0.001 |
\\\\\\\\ | +0.001 |
OTAL | +0.001 |
Sessions | +0.001 |
Tuc | +0.001 |
Neg logit contributions | |
opoly | -0.001 |
ration | -0.001 |
abled | -0.001 |
Jacqu | -0.001 |
marginalized | -0.001 |
Token | Rebel |
Token ID | 24551 |
Feature activation | +6.03e-01 |
Pos logit contributions | |
opoly | +0.030 |
ration | +0.030 |
abled | +0.029 |
Jacqu | +0.029 |
marginalized | +0.028 |
Neg logit contributions | |
TIT | -0.032 |
\\\\\\\\ | -0.032 |
OTAL | -0.027 |
Merit | -0.026 |
Sessions | -0.026 |
Token | Alliance |
Token ID | 10302 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
ration | +0.408 |
opoly | +0.408 |
abled | +0.395 |
Jacqu | +0.390 |
marginalized | +0.379 |
Neg logit contributions | |
TIT | -0.491 |
\\\\\\\\ | -0.485 |
OTAL | -0.414 |
Merit | -0.406 |
Bank | -0.402 |
Token | thought |
Token ID | 1807 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
opoly | +0.181 |
ration | +0.180 |
abled | +0.176 |
Jacqu | +0.172 |
marginalized | +0.167 |
Neg logit contributions | |
TIT | -0.238 |
\\\\\\\\ | -0.236 |
OTAL | -0.203 |
Merit | -0.199 |
Bank | -0.198 |
Token | of |
Token ID | 286 |
Feature activation | -6.47e-02 |
Pos logit contributions | |
TIT | +0.154 |
\\\\\\\\ | +0.152 |
OTAL | +0.130 |
Merit | +0.127 |
Bank | +0.126 |
Neg logit contributions | |
opoly | -0.123 |
ration | -0.123 |
abled | -0.120 |
Jacqu | -0.117 |
marginalized | -0.114 |
Token | everything |
Token ID | 2279 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
TIT | +0.057 |
\\\\\\\\ | +0.057 |
OTAL | +0.049 |
Tuc | +0.048 |
Merit | +0.048 |
Neg logit contributions | |
opoly | -0.039 |
ration | -0.039 |
abled | -0.038 |
Jacqu | -0.037 |
marginalized | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | +1.94e-02 |
Pos logit contributions | |
opoly | +0.093 |
ration | +0.093 |
abled | +0.090 |
Jacqu | +0.089 |
marginalized | +0.086 |
Neg logit contributions | |
TIT | -0.114 |
\\\\\\\\ | -0.112 |
OTAL | -0.096 |
Merit | -0.094 |
Bank | -0.093 |
Token | Ferdinand |
Token ID | 44312 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
ration | +0.037 |
opoly | +0.037 |
abled | +0.036 |
Jacqu | +0.035 |
marginalized | +0.034 |
Neg logit contributions | |
TIT | -0.045 |
\\\\\\\\ | -0.044 |
OTAL | -0.038 |
Merit | -0.037 |
Sessions | -0.037 |
Token | 's |
Token ID | 338 |
Feature activation | +4.92e-02 |
Pos logit contributions | |
opoly | +0.167 |
ration | +0.166 |
abled | +0.161 |
Jacqu | +0.158 |
marginalized | +0.153 |
Neg logit contributions | |
TIT | -0.215 |
\\\\\\\\ | -0.213 |
OTAL | -0.183 |
Merit | -0.181 |
Sessions | -0.180 |
Token | deep |
Token ID | 2769 |
Feature activation | -8.37e-03 |
Pos logit contributions | |
opoly | +0.032 |
ration | +0.032 |
abled | +0.031 |
Jacqu | +0.031 |
marginalized | +0.030 |
Neg logit contributions | |
TIT | -0.041 |
\\\\\\\\ | -0.040 |
OTAL | -0.035 |
Merit | -0.034 |
Sessions | -0.034 |
Token | cross |
Token ID | 3272 |
Feature activation | +6.47e-02 |
Pos logit contributions | |
TIT | +0.007 |
\\\\\\\\ | +0.007 |
OTAL | +0.006 |
Merit | +0.006 |
Bank | +0.006 |
Neg logit contributions | |
opoly | -0.005 |
ration | -0.005 |
abled | -0.005 |
Jacqu | -0.005 |
marginalized | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
opoly | +0.042 |
ration | +0.042 |
abled | +0.040 |
Jacqu | +0.039 |
marginalized | +0.038 |
Neg logit contributions | |
TIT | -0.054 |
\\\\\\\\ | -0.054 |
OTAL | -0.046 |
Merit | -0.046 |
Sessions | -0.045 |
Token | Lor |
Token ID | 26068 |
Feature activation | +5.97e-01 |
Pos logit contributions | |
TIT | +0.012 |
\\\\\\\\ | +0.011 |
OTAL | +0.010 |
Merit | +0.010 |
Tuc | +0.010 |
Neg logit contributions | |
opoly | -0.010 |
ration | -0.010 |
abled | -0.010 |
Jacqu | -0.009 |
marginalized | -0.009 |
Token | ik |
Token ID | 1134 |
Feature activation | +3.87e-02 |
Pos logit contributions | |
ration | +0.413 |
opoly | +0.411 |
abled | +0.398 |
Jacqu | +0.394 |
marginalized | +0.383 |
Neg logit contributions | |
TIT | -0.478 |
\\\\\\\\ | -0.472 |
OTAL | -0.402 |
Merit | -0.395 |
Bank | -0.390 |
Token | Can |
Token ID | 1680 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
ration | +0.027 |
opoly | +0.027 |
abled | +0.026 |
Jacqu | +0.026 |
marginalized | +0.025 |
Neg logit contributions | |
TIT | -0.030 |
\\\\\\\\ | -0.030 |
OTAL | -0.026 |
Merit | -0.025 |
Bank | -0.025 |
Token | a |
Token ID | 64 |
Feature activation | +1.44e-02 |
Pos logit contributions | |
TIT | +0.132 |
\\\\\\\\ | +0.130 |
OTAL | +0.111 |
Merit | +0.109 |
Sessions | +0.108 |
Neg logit contributions | |
ration | -0.112 |
opoly | -0.110 |
abled | -0.107 |
Jacqu | -0.106 |
marginalized | -0.103 |
Token | sent |
Token ID | 1908 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
opoly | +0.009 |
ration | +0.009 |
abled | +0.009 |
Jacqu | +0.009 |
marginalized | +0.008 |
Neg logit contributions | |
TIT | -0.012 |
\\\\\\\\ | -0.012 |
OTAL | -0.010 |
Merit | -0.010 |
Sessions | -0.010 |
Token | another |
Token ID | 1194 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
ration | +0.127 |
opoly | +0.126 |
abled | +0.122 |
Jacqu | +0.121 |
marginalized | +0.117 |
Neg logit contributions | |
TIT | -0.152 |
\\\\\\\\ | -0.150 |
OTAL | -0.128 |
Merit | -0.126 |
Tuc | -0.125 |
Token | for |
Token ID | 329 |
Feature activation | +5.25e-02 |
Pos logit contributions | |
opoly | +0.085 |
ration | +0.084 |
abled | +0.082 |
Jacqu | +0.081 |
marginalized | +0.078 |
Neg logit contributions | |
TIT | -0.126 |
\\\\\\\\ | -0.124 |
OTAL | -0.108 |
Merit | -0.106 |
Sessions | -0.106 |
Token | public |
Token ID | 1171 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
opoly | +0.033 |
ration | +0.032 |
abled | +0.032 |
Jacqu | +0.031 |
marginalized | +0.030 |
Neg logit contributions | |
TIT | -0.045 |
\\\\\\\\ | -0.044 |
OTAL | -0.038 |
Merit | -0.038 |
Tuc | -0.038 |
Token | spending |
Token ID | 4581 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
opoly | +0.114 |
ration | +0.112 |
abled | +0.110 |
Jacqu | +0.109 |
marginalized | +0.105 |
Neg logit contributions | |
TIT | -0.121 |
\\\\\\\\ | -0.118 |
OTAL | -0.100 |
Merit | -0.099 |
Bank | -0.098 |
Token | to |
Token ID | 284 |
Feature activation | -2.04e-02 |
Pos logit contributions | |
opoly | +0.104 |
ration | +0.101 |
abled | +0.099 |
Jacqu | +0.098 |
marginalized | +0.094 |
Neg logit contributions | |
TIT | -0.138 |
\\\\\\\\ | -0.136 |
OTAL | -0.117 |
Merit | -0.115 |
Bank | -0.115 |
Token | out |
Token ID | 503 |
Feature activation | +5.69e-02 |
Pos logit contributions | |
TIT | +0.018 |
\\\\\\\\ | +0.018 |
OTAL | +0.015 |
Merit | +0.015 |
Sessions | +0.015 |
Neg logit contributions | |
opoly | -0.012 |
ration | -0.012 |
abled | -0.012 |
Jacqu | -0.012 |
boarded | -0.011 |
Token | pace |
Token ID | 10223 |
Feature activation | +5.97e-01 |
Pos logit contributions | |
opoly | +0.016 |
ration | +0.015 |
abled | +0.014 |
Jacqu | +0.014 |
boarded | +0.013 |
Neg logit contributions | |
TIT | -0.069 |
\\\\\\\\ | -0.069 |
OTAL | -0.062 |
Merit | -0.061 |
Bank | -0.061 |
Token | inflation |
Token ID | 10610 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
opoly | +0.410 |
ration | +0.403 |
abled | +0.395 |
Jacqu | +0.389 |
marginalized | +0.376 |
Neg logit contributions | |
TIT | -0.481 |
\\\\\\\\ | -0.475 |
OTAL | -0.408 |
Merit | -0.395 |
Bank | -0.395 |
Token | . |
Token ID | 13 |
Feature activation | +7.23e-02 |
Pos logit contributions | |
opoly | +0.009 |
ration | +0.009 |
abled | +0.008 |
Jacqu | +0.008 |
marginalized | +0.008 |
Neg logit contributions | |
TIT | -0.010 |
\\\\\\\\ | -0.010 |
OTAL | -0.009 |
Merit | -0.008 |
Bank | -0.008 |
Token | The |
Token ID | 383 |
Feature activation | +9.83e-02 |
Pos logit contributions | |
opoly | +0.051 |
ration | +0.051 |
abled | +0.050 |
boarded | +0.048 |
Jacqu | +0.048 |
Neg logit contributions | |
TIT | -0.057 |
\\\\\\\\ | -0.056 |
OTAL | -0.048 |
Tuc | -0.047 |
Bank | -0.047 |
Token | combination |
Token ID | 6087 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
opoly | +0.068 |
ration | +0.066 |
abled | +0.065 |
Jacqu | +0.064 |
boarded | +0.062 |
Neg logit contributions | |
TIT | -0.079 |
\\\\\\\\ | -0.078 |
OTAL | -0.067 |
Tuc | -0.065 |
Bank | -0.065 |
Token | of |
Token ID | 286 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
opoly | +0.093 |
ration | +0.093 |
abled | +0.090 |
Jacqu | +0.089 |
marginalized | +0.086 |
Neg logit contributions | |
TIT | -0.116 |
\\\\\\\\ | -0.114 |
OTAL | -0.098 |
Merit | -0.096 |
Bank | -0.095 |
Token | . |
Token ID | 13 |
Feature activation | +3.33e-02 |
Pos logit contributions | |
TIT | +0.023 |
\\\\\\\\ | +0.023 |
OTAL | +0.019 |
Merit | +0.019 |
Sessions | +0.019 |
Neg logit contributions | |
opoly | -0.023 |
ration | -0.023 |
abled | -0.023 |
Jacqu | -0.022 |
marginalized | -0.022 |
Token | � |
Token ID | 447 |
Feature activation | +3.02e-02 |
Pos logit contributions | |
ration | +0.023 |
opoly | +0.023 |
abled | +0.022 |
Jacqu | +0.022 |
marginalized | +0.021 |
Neg logit contributions | |
TIT | -0.027 |
\\\\\\\\ | -0.027 |
OTAL | -0.023 |
Merit | -0.022 |
Sessions | -0.022 |
Token | � |
Token ID | 251 |
Feature activation | +9.16e-02 |
Pos logit contributions | |
ration | +0.024 |
opoly | +0.024 |
abled | +0.023 |
Jacqu | +0.023 |
marginalized | +0.022 |
Neg logit contributions | |
TIT | -0.021 |
\\\\\\\\ | -0.021 |
OTAL | -0.017 |
Merit | -0.017 |
Bank | -0.017 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -9.47e-02 |
Pos logit contributions | |
ration | +0.058 |
opoly | +0.058 |
abled | +0.056 |
Jacqu | +0.055 |
marginalized | +0.054 |
Neg logit contributions | |
TIT | -0.079 |
\\\\\\\\ | -0.078 |
OTAL | -0.067 |
Merit | -0.066 |
Sessions | -0.065 |
Token | S |
Token ID | 50 |
Feature activation | -8.86e-02 |
Pos logit contributions | |
TIT | +0.069 |
\\\\\\\\ | +0.068 |
OTAL | +0.057 |
Merit | +0.056 |
Bank | +0.055 |
Neg logit contributions | |
ration | -0.073 |
opoly | -0.072 |
abled | -0.070 |
Jacqu | -0.070 |
marginalized | -0.068 |
Token | print |
Token ID | 4798 |
Feature activation | +5.96e-01 |
Pos logit contributions | |
TIT | +0.069 |
\\\\\\\\ | +0.068 |
OTAL | +0.057 |
Merit | +0.056 |
Bank | +0.056 |
Neg logit contributions | |
ration | -0.064 |
opoly | -0.063 |
abled | -0.061 |
Jacqu | -0.061 |
marginalized | -0.059 |
Token | � |
Token ID | 447 |
Feature activation | +8.34e-02 |
Pos logit contributions | |
opoly | +0.381 |
ration | +0.379 |
abled | +0.370 |
Jacqu | +0.362 |
marginalized | +0.351 |
Neg logit contributions | |
TIT | -0.505 |
\\\\\\\\ | -0.497 |
OTAL | -0.429 |
Merit | -0.424 |
Bank | -0.422 |
Token | � |
Token ID | 247 |
Feature activation | +6.94e-02 |
Pos logit contributions | |
ration | +0.076 |
opoly | +0.076 |
abled | +0.074 |
Jacqu | +0.074 |
marginalized | +0.072 |
Neg logit contributions | |
TIT | -0.048 |
\\\\\\\\ | -0.047 |
OTAL | -0.037 |
Merit | -0.036 |
Bank | -0.036 |
Token | s |
Token ID | 82 |
Feature activation | +3.54e-02 |
Pos logit contributions | |
ration | +0.047 |
opoly | +0.047 |
abled | +0.045 |
Jacqu | +0.045 |
marginalized | +0.044 |
Neg logit contributions | |
TIT | -0.057 |
\\\\\\\\ | -0.056 |
OTAL | -0.048 |
Merit | -0.047 |
Bank | -0.047 |
Token | ability |
Token ID | 2694 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
ration | +0.023 |
opoly | +0.023 |
abled | +0.023 |
Jacqu | +0.022 |
marginalized | +0.022 |
Neg logit contributions | |
TIT | -0.029 |
\\\\\\\\ | -0.029 |
OTAL | -0.025 |
Merit | -0.024 |
Bank | -0.024 |
Token | to |
Token ID | 284 |
Feature activation | -5.02e-02 |
Pos logit contributions | |
ration | +0.120 |
opoly | +0.119 |
abled | +0.115 |
Jacqu | +0.114 |
marginalized | +0.110 |
Neg logit contributions | |
TIT | -0.170 |
\\\\\\\\ | -0.168 |
OTAL | -0.146 |
Merit | -0.143 |
Bank | -0.141 |
Token | his |
Token ID | 465 |
Feature activation | +2.89e-02 |
Pos logit contributions | |
opoly | +0.033 |
ration | +0.032 |
abled | +0.031 |
Jacqu | +0.030 |
marginalized | +0.029 |
Neg logit contributions | |
TIT | -0.062 |
\\\\\\\\ | -0.061 |
OTAL | -0.054 |
Sessions | -0.053 |
Merit | -0.053 |
Token | support |
Token ID | 1104 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
opoly | +0.024 |
ration | +0.024 |
abled | +0.023 |
Jacqu | +0.023 |
raq | +0.022 |
Neg logit contributions | |
TIT | -0.019 |
\\\\\\\\ | -0.018 |
OTAL | -0.015 |
Sessions | -0.015 |
Merit | -0.015 |
Token | last |
Token ID | 938 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
TIT | +0.288 |
\\\\\\\\ | +0.286 |
OTAL | +0.247 |
Merit | +0.244 |
Sessions | +0.243 |
Neg logit contributions | |
ration | -0.205 |
opoly | -0.204 |
abled | -0.197 |
Jacqu | -0.195 |
marginalized | -0.188 |
Token | month |
Token ID | 1227 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
TIT | +0.105 |
\\\\\\\\ | +0.104 |
OTAL | +0.087 |
Merit | +0.085 |
Sessions | +0.085 |
Neg logit contributions | |
opoly | -0.113 |
ration | -0.113 |
abled | -0.109 |
Jacqu | -0.108 |
marginalized | -0.105 |
Token | . |
Token ID | 13 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
TIT | +0.138 |
\\\\\\\\ | +0.136 |
OTAL | +0.116 |
Merit | +0.114 |
Sessions | +0.113 |
Neg logit contributions | |
ration | -0.119 |
opoly | -0.119 |
abled | -0.115 |
Jacqu | -0.114 |
marginalized | -0.111 |
Token | Sessions |
Token ID | 15184 |
Feature activation | -8.04e-01 |
Pos logit contributions | |
TIT | +0.097 |
\\\\\\\\ | +0.095 |
OTAL | +0.082 |
Merit | +0.081 |
Sessions | +0.080 |
Neg logit contributions | |
ration | -0.076 |
opoly | -0.076 |
abled | -0.073 |
Jacqu | -0.072 |
marginalized | -0.070 |
Token | is |
Token ID | 318 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
TIT | +0.666 |
\\\\\\\\ | +0.658 |
Sessions | +0.562 |
Merit | +0.561 |
OTAL | +0.561 |
Neg logit contributions | |
opoly | -0.524 |
ration | -0.523 |
abled | -0.505 |
Jacqu | -0.499 |
raq | -0.478 |
Token | one |
Token ID | 530 |
Feature activation | +4.37e-02 |
Pos logit contributions | |
TIT | +0.112 |
\\\\\\\\ | +0.110 |
Sessions | +0.095 |
OTAL | +0.095 |
Merit | +0.094 |
Neg logit contributions | |
opoly | -0.082 |
ration | -0.082 |
abled | -0.079 |
Jacqu | -0.078 |
rift | -0.075 |
Token | of |
Token ID | 286 |
Feature activation | -6.75e-02 |
Pos logit contributions | |
ration | +0.028 |
opoly | +0.028 |
abled | +0.027 |
Jacqu | +0.026 |
marginalized | +0.026 |
Neg logit contributions | |
TIT | -0.037 |
\\\\\\\\ | -0.037 |
OTAL | -0.032 |
Merit | -0.031 |
Tuc | -0.031 |
Token | the |
Token ID | 262 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
TIT | +0.061 |
\\\\\\\\ | +0.060 |
OTAL | +0.052 |
Merit | +0.051 |
Sessions | +0.051 |
Neg logit contributions | |
ration | -0.040 |
opoly | -0.040 |
abled | -0.038 |
Jacqu | -0.038 |
marginalized | -0.036 |
Token | st |
Token ID | 336 |
Feature activation | -2.02e-02 |
Pos logit contributions | |
TIT | +0.100 |
\\\\\\\\ | +0.098 |
OTAL | +0.084 |
Sessions | +0.084 |
Merit | +0.083 |
Neg logit contributions | |
opoly | -0.078 |
ration | -0.078 |
abled | -0.075 |
Jacqu | -0.074 |
marginalized | -0.071 |
Token | must |
Token ID | 1276 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
opoly | +0.050 |
ration | +0.050 |
abled | +0.049 |
Jacqu | +0.047 |
boarded | +0.046 |
Neg logit contributions | |
TIT | -0.063 |
\\\\\\\\ | -0.062 |
OTAL | -0.053 |
Sessions | -0.053 |
Merit | -0.053 |
Token | not |
Token ID | 407 |
Feature activation | -7.38e-02 |
Pos logit contributions | |
TIT | +0.123 |
\\\\\\\\ | +0.121 |
OTAL | +0.106 |
Merit | +0.104 |
Sessions | +0.104 |
Neg logit contributions | |
opoly | -0.078 |
ration | -0.077 |
abled | -0.074 |
Jacqu | -0.074 |
boarded | -0.070 |
Token | fade |
Token ID | 22100 |
Feature activation | +4.32e-02 |
Pos logit contributions | |
TIT | +0.066 |
\\\\\\\\ | +0.065 |
Merit | +0.056 |
Sessions | +0.056 |
OTAL | +0.056 |
Neg logit contributions | |
opoly | -0.043 |
ration | -0.042 |
abled | -0.041 |
Jacqu | -0.041 |
raq | -0.039 |
Token | away |
Token ID | 1497 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
opoly | +0.030 |
ration | +0.030 |
abled | +0.029 |
Jacqu | +0.029 |
marginalized | +0.028 |
Neg logit contributions | |
TIT | -0.034 |
\\\\\\\\ | -0.034 |
OTAL | -0.028 |
Merit | -0.028 |
Sessions | -0.028 |
Token | ," |
Token ID | 553 |
Feature activation | +5.80e-02 |
Pos logit contributions | |
TIT | +0.122 |
\\\\\\\\ | +0.120 |
OTAL | +0.102 |
Merit | +0.101 |
Sessions | +0.100 |
Neg logit contributions | |
opoly | -0.102 |
ration | -0.102 |
abled | -0.099 |
Jacqu | -0.097 |
marginalized | -0.094 |
Token | Sessions |
Token ID | 15184 |
Feature activation | -7.91e-01 |
Pos logit contributions | |
ration | +0.061 |
opoly | +0.061 |
abled | +0.060 |
Jacqu | +0.059 |
marginalized | +0.058 |
Neg logit contributions | |
TIT | -0.025 |
\\\\\\\\ | -0.025 |
OTAL | -0.018 |
Merit | -0.017 |
Bank | -0.017 |
Token | said |
Token ID | 531 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
TIT | +0.641 |
\\\\\\\\ | +0.633 |
OTAL | +0.539 |
Merit | +0.534 |
Sessions | +0.534 |
Neg logit contributions | |
ration | -0.535 |
opoly | -0.534 |
abled | -0.516 |
Jacqu | -0.509 |
marginalized | -0.493 |
Token | during |
Token ID | 1141 |
Feature activation | -6.06e-02 |
Pos logit contributions | |
TIT | +0.102 |
\\\\\\\\ | +0.101 |
OTAL | +0.086 |
Merit | +0.085 |
Sessions | +0.084 |
Neg logit contributions | |
ration | -0.083 |
opoly | -0.083 |
abled | -0.080 |
Jacqu | -0.079 |
marginalized | -0.077 |
Token | the |
Token ID | 262 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
TIT | +0.054 |
\\\\\\\\ | +0.054 |
OTAL | +0.047 |
Merit | +0.046 |
Sessions | +0.046 |
Neg logit contributions | |
opoly | -0.036 |
ration | -0.036 |
abled | -0.034 |
Jacqu | -0.034 |
marginalized | -0.033 |
Token | Alabama |
Token ID | 9266 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
TIT | +0.083 |
\\\\\\\\ | +0.082 |
OTAL | +0.069 |
Sessions | +0.068 |
Merit | +0.068 |
Neg logit contributions | |
opoly | -0.081 |
ration | -0.081 |
abled | -0.078 |
Jacqu | -0.077 |
marginalized | -0.075 |
Token | rally |
Token ID | 7903 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
TIT | +0.196 |
\\\\\\\\ | +0.193 |
OTAL | +0.161 |
Merit | +0.161 |
Sessions | +0.161 |
Neg logit contributions | |
opoly | -0.204 |
ration | -0.203 |
abled | -0.199 |
Jacqu | -0.195 |
marginalized | -0.190 |
Token | President |
Token ID | 1992 |
Feature activation | +2.48e-02 |
Pos logit contributions | |
ration | +0.014 |
opoly | +0.014 |
abled | +0.013 |
Jacqu | +0.013 |
marginalized | +0.013 |
Neg logit contributions | |
TIT | -0.017 |
\\\\\\\\ | -0.016 |
OTAL | -0.014 |
Merit | -0.014 |
Sessions | -0.014 |
Token | Mike |
Token ID | 4995 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
ration | +0.015 |
opoly | +0.015 |
abled | +0.015 |
Jacqu | +0.015 |
marginalized | +0.014 |
Neg logit contributions | |
TIT | -0.022 |
\\\\\\\\ | -0.021 |
OTAL | -0.018 |
Merit | -0.018 |
Bank | -0.018 |
Token | Pence |
Token ID | 17339 |
Feature activation | -9.08e-02 |
Pos logit contributions | |
ration | +0.099 |
opoly | +0.098 |
abled | +0.096 |
Jacqu | +0.095 |
marginalized | +0.092 |
Neg logit contributions | |
TIT | -0.097 |
\\\\\\\\ | -0.095 |
OTAL | -0.080 |
Merit | -0.079 |
Sessions | -0.078 |
Token | cited |
Token ID | 9181 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
TIT | +0.075 |
\\\\\\\\ | +0.074 |
OTAL | +0.064 |
Sessions | +0.063 |
Merit | +0.062 |
Neg logit contributions | |
opoly | -0.060 |
ration | -0.059 |
abled | -0.058 |
Jacqu | -0.057 |
marginalized | -0.055 |
Token | the |
Token ID | 262 |
Feature activation | -3.83e-02 |
Pos logit contributions | |
TIT | +0.117 |
\\\\\\\\ | +0.116 |
OTAL | +0.099 |
Sessions | +0.098 |
Merit | +0.097 |
Neg logit contributions | |
opoly | -0.092 |
ration | -0.092 |
abled | -0.089 |
Jacqu | -0.088 |
marginalized | -0.085 |
Token | Sessions |
Token ID | 15184 |
Feature activation | -7.60e-01 |
Pos logit contributions | |
TIT | +0.031 |
\\\\\\\\ | +0.031 |
OTAL | +0.026 |
Sessions | +0.026 |
Merit | +0.026 |
Neg logit contributions | |
opoly | -0.026 |
ration | -0.026 |
abled | -0.025 |
Jacqu | -0.025 |
marginalized | -0.024 |
Token | - |
Token ID | 12 |
Feature activation | -7.15e-02 |
Pos logit contributions | |
TIT | +0.643 |
\\\\\\\\ | +0.637 |
OTAL | +0.545 |
Sessions | +0.543 |
Merit | +0.540 |
Neg logit contributions | |
opoly | -0.485 |
ration | -0.484 |
abled | -0.470 |
Jacqu | -0.463 |
marginalized | -0.447 |
Token | R |
Token ID | 49 |
Feature activation | -8.71e-02 |
Pos logit contributions | |
TIT | +0.057 |
\\\\\\\\ | +0.056 |
OTAL | +0.048 |
Merit | +0.047 |
Bank | +0.046 |
Neg logit contributions | |
ration | -0.050 |
opoly | -0.050 |
abled | -0.048 |
Jacqu | -0.048 |
marginalized | -0.046 |
Token | osen |
Token ID | 5233 |
Feature activation | +7.40e-02 |
Pos logit contributions | |
TIT | +0.089 |
\\\\\\\\ | +0.088 |
OTAL | +0.078 |
Merit | +0.077 |
Tuc | +0.076 |
Neg logit contributions | |
ration | -0.041 |
opoly | -0.041 |
abled | -0.039 |
Jacqu | -0.038 |
marginalized | -0.037 |
Token | stein |
Token ID | 5714 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
ration | +0.071 |
opoly | +0.071 |
abled | +0.070 |
Jacqu | +0.069 |
marginalized | +0.068 |
Neg logit contributions | |
TIT | -0.039 |
\\\\\\\\ | -0.038 |
OTAL | -0.029 |
Merit | -0.029 |
Sessions | -0.028 |
Token | recommendation |
Token ID | 15602 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
TIT | +0.082 |
\\\\\\\\ | +0.081 |
OTAL | +0.069 |
Sessions | +0.069 |
Merit | +0.068 |
Neg logit contributions | |
opoly | -0.072 |
ration | -0.071 |
abled | -0.070 |
Jacqu | -0.069 |
marginalized | -0.067 |
Token | Jeff |
Token ID | 5502 |
Feature activation | -3.28e-02 |
Pos logit contributions | |
TIT | +0.128 |
\\\\\\\\ | +0.126 |
OTAL | +0.108 |
Merit | +0.106 |
Sessions | +0.106 |
Neg logit contributions | |
ration | -0.115 |
opoly | -0.115 |
abled | -0.112 |
Jacqu | -0.107 |
marginalized | -0.106 |
Token | Sessions |
Token ID | 15184 |
Feature activation | -6.79e-01 |
Pos logit contributions | |
TIT | +0.012 |
\\\\\\\\ | +0.012 |
OTAL | +0.008 |
Merit | +0.008 |
Bank | +0.008 |
Neg logit contributions | |
ration | -0.036 |
opoly | -0.036 |
abled | -0.036 |
Jacqu | -0.036 |
marginalized | -0.035 |
Token | Sen |
Token ID | 2311 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
TIT | +0.472 |
\\\\\\\\ | +0.465 |
OTAL | +0.386 |
Merit | +0.379 |
Sessions | +0.375 |
Neg logit contributions | |
ration | -0.539 |
opoly | -0.538 |
abled | -0.524 |
Jacqu | -0.518 |
marginalized | -0.505 |
Token | . |
Token ID | 13 |
Feature activation | -5.99e-03 |
Pos logit contributions | |
TIT | +0.209 |
\\\\\\\\ | +0.206 |
OTAL | +0.176 |
Sessions | +0.174 |
Merit | +0.173 |
Neg logit contributions | |
ration | -0.194 |
opoly | -0.193 |
abled | -0.186 |
Jacqu | -0.184 |
marginalized | -0.180 |
Token | Jeff |
Token ID | 5502 |
Feature activation | -3.85e-02 |
Pos logit contributions | |
TIT | +0.005 |
\\\\\\\\ | +0.005 |
OTAL | +0.004 |
Merit | +0.004 |
Sessions | +0.004 |
Neg logit contributions | |
ration | -0.004 |
opoly | -0.004 |
abled | -0.004 |
Jacqu | -0.004 |
marginalized | -0.004 |
Token | Sessions |
Token ID | 15184 |
Feature activation | -7.24e-01 |
Pos logit contributions | |
TIT | +0.007 |
\\\\\\\\ | +0.006 |
OTAL | +0.002 |
Merit | +0.001 |
Bank | +0.001 |
Neg logit contributions | |
ration | -0.051 |
opoly | -0.051 |
abled | -0.050 |
Jacqu | -0.050 |
marginalized | -0.049 |
Token | of |
Token ID | 286 |
Feature activation | -7.95e-02 |
Pos logit contributions | |
TIT | +0.622 |
\\\\\\\\ | +0.615 |
OTAL | +0.530 |
Merit | +0.522 |
Sessions | +0.517 |
Neg logit contributions | |
ration | -0.457 |
opoly | -0.455 |
abled | -0.440 |
Jacqu | -0.434 |
marginalized | -0.420 |
Token | Alabama |
Token ID | 9266 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
TIT | +0.054 |
\\\\\\\\ | +0.053 |
OTAL | +0.044 |
Merit | +0.043 |
Bank | +0.042 |
Neg logit contributions | |
ration | -0.065 |
opoly | -0.065 |
abled | -0.063 |
Jacqu | -0.063 |
marginalized | -0.061 |
Token | is |
Token ID | 318 |
Feature activation | -9.22e-02 |
Pos logit contributions | |
TIT | +0.240 |
\\\\\\\\ | +0.237 |
OTAL | +0.202 |
Merit | +0.201 |
Sessions | +0.201 |
Neg logit contributions | |
opoly | -0.193 |
ration | -0.193 |
abled | -0.187 |
Jacqu | -0.183 |
marginalized | -0.177 |
Token | the |
Token ID | 262 |
Feature activation | -9.10e-02 |
Pos logit contributions | |
TIT | +0.080 |
\\\\\\\\ | +0.078 |
Sessions | +0.068 |
OTAL | +0.068 |
Merit | +0.068 |
Neg logit contributions | |
opoly | -0.057 |
ration | -0.057 |
abled | -0.055 |
Jacqu | -0.054 |
marginalized | -0.052 |
Token | only |
Token ID | 691 |
Feature activation | -5.39e-02 |
Pos logit contributions | |
TIT | +0.070 |
\\\\\\\\ | +0.069 |
OTAL | +0.058 |
Sessions | +0.058 |
Merit | +0.058 |
Neg logit contributions | |
opoly | -0.065 |
ration | -0.065 |
abled | -0.063 |
Jacqu | -0.062 |
marginalized | -0.060 |
Token | / |
Token ID | 14 |
Feature activation | -3.25e-02 |
Pos logit contributions | |
TIT | +0.145 |
\\\\\\\\ | +0.142 |
OTAL | +0.123 |
Merit | +0.120 |
Bank | +0.119 |
Neg logit contributions | |
ration | -0.107 |
opoly | -0.107 |
Jacqu | -0.103 |
abled | -0.102 |
marginalized | -0.098 |
Token | Getty |
Token ID | 6633 |
Feature activation | +4.93e-02 |
Pos logit contributions | |
TIT | +0.026 |
\\\\\\\\ | +0.025 |
OTAL | +0.022 |
Merit | +0.021 |
Bank | +0.021 |
Neg logit contributions | |
ration | -0.023 |
opoly | -0.023 |
abled | -0.022 |
Jacqu | -0.022 |
marginalized | -0.021 |
Token | Images |
Token ID | 5382 |
Feature activation | +6.60e-02 |
Pos logit contributions | |
ration | +0.034 |
opoly | +0.034 |
Jacqu | +0.033 |
abled | +0.033 |
marginalized | +0.032 |
Neg logit contributions | |
TIT | -0.039 |
\\\\\\\\ | -0.039 |
OTAL | -0.033 |
Merit | -0.032 |
Tuc | -0.032 |
Token | ) |
Token ID | 8 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
ration | +0.059 |
opoly | +0.058 |
Jacqu | +0.057 |
abled | +0.056 |
marginalized | +0.055 |
Neg logit contributions | |
TIT | -0.040 |
\\\\\\\\ | -0.040 |
OTAL | -0.032 |
Merit | -0.031 |
Bank | -0.030 |
Token | Jeff |
Token ID | 5502 |
Feature activation | -3.28e-02 |
Pos logit contributions | |
TIT | +0.128 |
\\\\\\\\ | +0.126 |
OTAL | +0.108 |
Merit | +0.106 |
Sessions | +0.106 |
Neg logit contributions | |
ration | -0.115 |
opoly | -0.115 |
abled | -0.112 |
Jacqu | -0.107 |
marginalized | -0.106 |
Token | Sessions |
Token ID | 15184 |
Feature activation | -6.79e-01 |
Pos logit contributions | |
TIT | +0.012 |
\\\\\\\\ | +0.012 |
OTAL | +0.008 |
Merit | +0.008 |
Bank | +0.008 |
Neg logit contributions | |
ration | -0.036 |
opoly | -0.036 |
abled | -0.036 |
Jacqu | -0.036 |
marginalized | -0.035 |
Token | Sen |
Token ID | 2311 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
TIT | +0.472 |
\\\\\\\\ | +0.465 |
OTAL | +0.386 |
Merit | +0.379 |
Sessions | +0.375 |
Neg logit contributions | |
ration | -0.539 |
opoly | -0.538 |
abled | -0.524 |
Jacqu | -0.518 |
marginalized | -0.505 |
Token | . |
Token ID | 13 |
Feature activation | -5.99e-03 |
Pos logit contributions | |
TIT | +0.209 |
\\\\\\\\ | +0.206 |
OTAL | +0.176 |
Sessions | +0.174 |
Merit | +0.173 |
Neg logit contributions | |
ration | -0.194 |
opoly | -0.193 |
abled | -0.186 |
Jacqu | -0.184 |
marginalized | -0.180 |
Token | Jeff |
Token ID | 5502 |
Feature activation | -3.85e-02 |
Pos logit contributions | |
TIT | +0.005 |
\\\\\\\\ | +0.005 |
OTAL | +0.004 |
Merit | +0.004 |
Sessions | +0.004 |
Neg logit contributions | |
ration | -0.004 |
opoly | -0.004 |
abled | -0.004 |
Jacqu | -0.004 |
marginalized | -0.004 |
Token | Sessions |
Token ID | 15184 |
Feature activation | -7.24e-01 |
Pos logit contributions | |
TIT | +0.007 |
\\\\\\\\ | +0.006 |
OTAL | +0.002 |
Merit | +0.001 |
Bank | +0.001 |
Neg logit contributions | |
ration | -0.051 |
opoly | -0.051 |
abled | -0.050 |
Jacqu | -0.050 |
marginalized | -0.049 |
Token | of |
Token ID | 286 |
Feature activation | -7.95e-02 |
Pos logit contributions | |
TIT | +0.622 |
\\\\\\\\ | +0.615 |
OTAL | +0.530 |
Merit | +0.522 |
Sessions | +0.517 |
Neg logit contributions | |
ration | -0.457 |
opoly | -0.455 |
abled | -0.440 |
Jacqu | -0.434 |
marginalized | -0.420 |
Token | Comey |
Token ID | 12388 |
Feature activation | -4.67e-03 |
Pos logit contributions | |
TIT | +0.052 |
\\\\\\\\ | +0.052 |
OTAL | +0.044 |
Merit | +0.043 |
Sessions | +0.043 |
Neg logit contributions | |
opoly | -0.047 |
ration | -0.047 |
abled | -0.046 |
Jacqu | -0.045 |
marginalized | -0.044 |
Token | before |
Token ID | 878 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
TIT | +0.004 |
\\\\\\\\ | +0.004 |
Sessions | +0.003 |
OTAL | +0.003 |
Merit | +0.003 |
Neg logit contributions | |
opoly | -0.003 |
ration | -0.003 |
abled | -0.003 |
Jacqu | -0.003 |
marginalized | -0.003 |
Token | Attorney |
Token ID | 8123 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
TIT | +0.011 |
\\\\\\\\ | +0.011 |
OTAL | +0.010 |
Sessions | +0.010 |
Merit | +0.009 |
Neg logit contributions | |
opoly | -0.008 |
ration | -0.008 |
abled | -0.008 |
Jacqu | -0.008 |
marginalized | -0.008 |
Token | General |
Token ID | 3611 |
Feature activation | +7.34e-02 |
Pos logit contributions | |
TIT | +0.159 |
\\\\\\\\ | +0.157 |
OTAL | +0.135 |
Merit | +0.132 |
Sessions | +0.132 |
Neg logit contributions | |
ration | -0.146 |
opoly | -0.145 |
abled | -0.141 |
Jacqu | -0.138 |
marginalized | -0.135 |
Token | Jeff |
Token ID | 5502 |
Feature activation | +3.00e-02 |
Pos logit contributions | |
ration | +0.050 |
opoly | +0.050 |
abled | +0.049 |
Jacqu | +0.049 |
marginalized | +0.047 |
Neg logit contributions | |
TIT | -0.059 |
\\\\\\\\ | -0.058 |
OTAL | -0.050 |
Merit | -0.049 |
Bank | -0.048 |
Token | Sessions |
Token ID | 15184 |
Feature activation | -6.50e-01 |
Pos logit contributions | |
ration | +0.040 |
opoly | +0.039 |
Jacqu | +0.039 |
abled | +0.039 |
marginalized | +0.038 |
Neg logit contributions | |
TIT | -0.005 |
\\\\\\\\ | -0.005 |
OTAL | -0.001 |
Merit | -0.001 |
Bank | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | +2.60e-02 |
Pos logit contributions | |
TIT | +0.543 |
\\\\\\\\ | +0.537 |
OTAL | +0.462 |
Sessions | +0.456 |
Merit | +0.456 |
Neg logit contributions | |
opoly | -0.424 |
ration | -0.422 |
abled | -0.408 |
Jacqu | -0.402 |
marginalized | -0.390 |
Token | his |
Token ID | 465 |
Feature activation | +6.72e-02 |
Pos logit contributions | |
opoly | +0.018 |
ration | +0.018 |
abled | +0.017 |
Jacqu | +0.017 |
marginalized | +0.017 |
Neg logit contributions | |
TIT | -0.021 |
\\\\\\\\ | -0.020 |
Sessions | -0.017 |
OTAL | -0.017 |
Merit | -0.017 |
Token | deputy |
Token ID | 10636 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
opoly | +0.048 |
ration | +0.048 |
abled | +0.046 |
Jacqu | +0.045 |
marginalized | +0.044 |
Neg logit contributions | |
TIT | -0.052 |
\\\\\\\\ | -0.051 |
OTAL | -0.044 |
Merit | -0.043 |
Sessions | -0.043 |
Token | , |
Token ID | 11 |
Feature activation | -4.77e-02 |
Pos logit contributions | |
TIT | +0.102 |
\\\\\\\\ | +0.101 |
OTAL | +0.086 |
Merit | +0.084 |
Sessions | +0.084 |
Neg logit contributions | |
ration | -0.090 |
opoly | -0.090 |
abled | -0.087 |
Jacqu | -0.086 |
marginalized | -0.084 |
Token | Rod |
Token ID | 6882 |
Feature activation | -6.92e-02 |
Pos logit contributions | |
TIT | +0.038 |
\\\\\\\\ | +0.037 |
Sessions | +0.032 |
OTAL | +0.032 |
Merit | +0.032 |
Neg logit contributions | |
ration | -0.033 |
opoly | -0.033 |
abled | -0.032 |
Jacqu | -0.031 |
marginalized | -0.030 |
Token |
|
Token ID | 198 |
Feature activation | +2.23e-02 |
Pos logit contributions | |
TIT | +0.019 |
\\\\\\\\ | +0.019 |
OTAL | +0.016 |
Sessions | +0.016 |
Bank | +0.016 |
Neg logit contributions | |
opoly | -0.016 |
ration | -0.016 |
abled | -0.016 |
Jacqu | -0.016 |
marginalized | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | +2.95e-02 |
Pos logit contributions | |
opoly | +0.015 |
ration | +0.015 |
abled | +0.014 |
boarded | +0.014 |
Jacqu | +0.014 |
Neg logit contributions | |
TIT | -0.019 |
\\\\\\\\ | -0.018 |
OTAL | -0.016 |
Merit | -0.016 |
Bank | -0.016 |
Token | YOU |
Token ID | 36981 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
ration | +0.020 |
opoly | +0.020 |
Jacqu | +0.020 |
abled | +0.020 |
marginalized | +0.019 |
Neg logit contributions | |
TIT | -0.024 |
\\\\\\\\ | -0.023 |
OTAL | -0.020 |
Bank | -0.020 |
Merit | -0.020 |
Token | HAVE |
Token ID | 21515 |
Feature activation | -6.46e-02 |
Pos logit contributions | |
TIT | +0.188 |
\\\\\\\\ | +0.184 |
OTAL | +0.154 |
Merit | +0.150 |
Bank | +0.148 |
Neg logit contributions | |
opoly | -0.210 |
ration | -0.210 |
abled | -0.205 |
Jacqu | -0.202 |
marginalized | -0.198 |
Token | A |
Token ID | 317 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
TIT | +0.045 |
\\\\\\\\ | +0.044 |
OTAL | +0.037 |
Merit | +0.036 |
Sessions | +0.036 |
Neg logit contributions | |
opoly | -0.051 |
ration | -0.051 |
abled | -0.050 |
Jacqu | -0.049 |
marginalized | -0.048 |
Token | BAT |
Token ID | 37421 |
Feature activation | -6.16e-01 |
Pos logit contributions | |
TIT | +0.135 |
\\\\\\\\ | +0.133 |
OTAL | +0.112 |
Merit | +0.108 |
Sessions | +0.107 |
Neg logit contributions | |
opoly | -0.151 |
ration | -0.151 |
abled | -0.148 |
Jacqu | -0.145 |
marginalized | -0.142 |
Token | TER |
Token ID | 5781 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
TIT | +0.333 |
\\\\\\\\ | +0.326 |
OTAL | +0.255 |
Merit | +0.246 |
Bank | +0.242 |
Neg logit contributions | |
ration | -0.586 |
opoly | -0.585 |
abled | -0.572 |
Jacqu | -0.567 |
marginalized | -0.556 |
Token | Y |
Token ID | 56 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
TIT | +0.202 |
\\\\\\\\ | +0.199 |
OTAL | +0.154 |
Merit | +0.150 |
Bank | +0.146 |
Neg logit contributions | |
ration | -0.363 |
opoly | -0.361 |
abled | -0.353 |
Jacqu | -0.351 |
marginalized | -0.344 |
Token | BACK |
Token ID | 28767 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
TIT | +0.241 |
\\\\\\\\ | +0.236 |
OTAL | +0.201 |
Merit | +0.196 |
Sessions | +0.194 |
Neg logit contributions | |
opoly | -0.226 |
ration | -0.226 |
abled | -0.221 |
Jacqu | -0.216 |
marginalized | -0.211 |
Token | ED |
Token ID | 1961 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
TIT | +0.112 |
\\\\\\\\ | +0.110 |
OTAL | +0.090 |
Merit | +0.088 |
Bank | +0.086 |
Neg logit contributions | |
ration | -0.151 |
opoly | -0.151 |
abled | -0.147 |
Jacqu | -0.146 |
marginalized | -0.143 |
Token | D |
Token ID | 360 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
TIT | +0.008 |
\\\\\\\\ | +0.008 |
OTAL | +0.007 |
Merit | +0.006 |
Tuc | +0.006 |
Neg logit contributions | |
ration | -0.009 |
opoly | -0.009 |
Jacqu | -0.008 |
abled | -0.008 |
marginalized | -0.008 |
Token | * |
Token ID | 9 |
Feature activation | -7.51e-02 |
Pos logit contributions | |
TIT | +0.013 |
\\\\\\\\ | +0.013 |
OTAL | +0.011 |
Merit | +0.011 |
Bank | +0.011 |
Neg logit contributions | |
ration | -0.012 |
opoly | -0.012 |
abled | -0.012 |
Jacqu | -0.012 |
marginalized | -0.011 |
Token | IF |
Token ID | 5064 |
Feature activation | +7.47e-02 |
Pos logit contributions | |
TIT | +0.055 |
\\\\\\\\ | +0.054 |
OTAL | +0.045 |
Merit | +0.044 |
Bank | +0.044 |
Neg logit contributions | |
ration | -0.058 |
opoly | -0.057 |
abled | -0.056 |
Jacqu | -0.055 |
marginalized | -0.054 |
Token | , |
Token ID | 11 |
Feature activation | -9.66e-02 |
Pos logit contributions | |
ration | +0.063 |
opoly | +0.063 |
abled | +0.061 |
Jacqu | +0.061 |
marginalized | +0.059 |
Neg logit contributions | |
TIT | -0.048 |
\\\\\\\\ | -0.048 |
OTAL | -0.039 |
Merit | -0.038 |
Bank | -0.038 |
Token | WITH |
Token ID | 13315 |
Feature activation | +7.19e-02 |
Pos logit contributions | |
TIT | +0.069 |
\\\\\\\\ | +0.068 |
OTAL | +0.057 |
Merit | +0.055 |
Sessions | +0.055 |
Neg logit contributions | |
ration | -0.075 |
opoly | -0.075 |
abled | -0.073 |
Jacqu | -0.072 |
marginalized | -0.071 |
Token | THE |
Token ID | 3336 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
ration | +0.057 |
opoly | +0.056 |
abled | +0.055 |
Jacqu | +0.055 |
marginalized | +0.053 |
Neg logit contributions | |
TIT | -0.050 |
\\\\\\\\ | -0.050 |
OTAL | -0.041 |
Merit | -0.041 |
Bank | -0.040 |
Token | BAT |
Token ID | 37421 |
Feature activation | -6.05e-01 |
Pos logit contributions | |
TIT | +0.098 |
\\\\\\\\ | +0.097 |
OTAL | +0.079 |
Merit | +0.077 |
Bank | +0.076 |
Neg logit contributions | |
ration | -0.122 |
opoly | -0.122 |
abled | -0.119 |
Jacqu | -0.118 |
marginalized | -0.115 |
Token | TER |
Token ID | 5781 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
TIT | +0.324 |
\\\\\\\\ | +0.321 |
OTAL | +0.250 |
Merit | +0.243 |
Tuc | +0.237 |
Neg logit contributions | |
ration | -0.575 |
opoly | -0.572 |
abled | -0.560 |
Jacqu | -0.557 |
marginalized | -0.544 |
Token | Y |
Token ID | 56 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
TIT | +0.196 |
\\\\\\\\ | +0.191 |
OTAL | +0.147 |
Merit | +0.143 |
Bank | +0.140 |
Neg logit contributions | |
ration | -0.373 |
opoly | -0.372 |
abled | -0.364 |
Jacqu | -0.360 |
marginalized | -0.354 |
Token | BACK |
Token ID | 28767 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
TIT | +0.210 |
\\\\\\\\ | +0.207 |
OTAL | +0.173 |
Merit | +0.170 |
Bank | +0.167 |
Neg logit contributions | |
ration | -0.223 |
opoly | -0.223 |
abled | -0.216 |
Jacqu | -0.215 |
marginalized | -0.209 |
Token | ED |
Token ID | 1961 |
Feature activation | +4.39e-04 |
Pos logit contributions | |
TIT | +0.126 |
\\\\\\\\ | +0.125 |
OTAL | +0.107 |
Merit | +0.105 |
Tuc | +0.104 |
Neg logit contributions | |
ration | -0.104 |
opoly | -0.103 |
abled | -0.100 |
Jacqu | -0.099 |
marginalized | -0.096 |
Token | D |
Token ID | 360 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
ration | +0.000 |
opoly | +0.000 |
Jacqu | +0.000 |
abled | +0.000 |
boarded | +0.000 |
Neg logit contributions | |
TIT | -0.000 |
\\\\\\\\ | -0.000 |
OTAL | -0.000 |
Tuc | -0.000 |
Merit | -0.000 |
Token | amounts |
Token ID | 6867 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
TIT | +0.156 |
\\\\\\\\ | +0.153 |
OTAL | +0.128 |
Merit | +0.127 |
Sessions | +0.126 |
Neg logit contributions | |
opoly | -0.156 |
ration | -0.154 |
abled | -0.152 |
Jacqu | -0.148 |
boarded | -0.144 |
Token | of |
Token ID | 286 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
TIT | +0.236 |
\\\\\\\\ | +0.233 |
OTAL | +0.200 |
Merit | +0.197 |
Sessions | +0.195 |
Neg logit contributions | |
opoly | -0.192 |
ration | -0.192 |
abled | -0.185 |
Jacqu | -0.183 |
marginalized | -0.177 |
Token | criticism |
Token ID | 7734 |
Feature activation | -4.14e-02 |
Pos logit contributions | |
TIT | +0.198 |
\\\\\\\\ | +0.194 |
OTAL | +0.165 |
Merit | +0.163 |
Sessions | +0.163 |
Neg logit contributions | |
opoly | -0.176 |
ration | -0.174 |
abled | -0.170 |
Jacqu | -0.167 |
boarded | -0.162 |
Token | for |
Token ID | 329 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
TIT | +0.035 |
\\\\\\\\ | +0.035 |
OTAL | +0.030 |
Merit | +0.030 |
Sessions | +0.030 |
Neg logit contributions | |
opoly | -0.026 |
ration | -0.026 |
abled | -0.025 |
Jacqu | -0.025 |
boarded | -0.024 |
Token | esp |
Token ID | 15024 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
TIT | +0.089 |
\\\\\\\\ | +0.087 |
Sessions | +0.075 |
Merit | +0.075 |
OTAL | +0.075 |
Neg logit contributions | |
opoly | -0.065 |
ration | -0.063 |
abled | -0.062 |
Jacqu | -0.060 |
raq | -0.059 |
Token | ousing |
Token ID | 12752 |
Feature activation | -5.97e-01 |
Pos logit contributions | |
TIT | +0.103 |
\\\\\\\\ | +0.100 |
OTAL | +0.072 |
Merit | +0.069 |
Bank | +0.067 |
Neg logit contributions | |
opoly | -0.270 |
ration | -0.270 |
abled | -0.264 |
Jacqu | -0.263 |
marginalized | -0.259 |
Token | ideas |
Token ID | 4213 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
TIT | +0.491 |
\\\\\\\\ | +0.484 |
Sessions | +0.414 |
Merit | +0.413 |
OTAL | +0.412 |
Neg logit contributions | |
opoly | -0.395 |
ration | -0.390 |
abled | -0.381 |
Jacqu | -0.374 |
boarded | -0.360 |
Token | that |
Token ID | 326 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
TIT | +0.225 |
\\\\\\\\ | +0.222 |
OTAL | +0.194 |
Sessions | +0.193 |
Merit | +0.192 |
Neg logit contributions | |
opoly | -0.143 |
ration | -0.141 |
abled | -0.137 |
Jacqu | -0.134 |
boarded | -0.128 |
Token | are |
Token ID | 389 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
TIT | +0.123 |
\\\\\\\\ | +0.121 |
OTAL | +0.103 |
Sessions | +0.102 |
Merit | +0.102 |
Neg logit contributions | |
opoly | -0.105 |
ration | -0.104 |
abled | -0.102 |
Jacqu | -0.100 |
boarded | -0.096 |
Token | seen |
Token ID | 1775 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
TIT | +0.249 |
\\\\\\\\ | +0.244 |
OTAL | +0.208 |
Merit | +0.206 |
Sessions | +0.205 |
Neg logit contributions | |
opoly | -0.215 |
ration | -0.213 |
abled | -0.208 |
Jacqu | -0.206 |
boarded | -0.197 |
Token | as |
Token ID | 355 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
TIT | +0.120 |
\\\\\\\\ | +0.118 |
OTAL | +0.099 |
Merit | +0.097 |
Bank | +0.096 |
Neg logit contributions | |
ration | -0.123 |
opoly | -0.122 |
abled | -0.118 |
Jacqu | -0.118 |
marginalized | -0.115 |
Token | detailing |
Token ID | 22976 |
Feature activation | -9.56e-02 |
Pos logit contributions | |
ration | +0.012 |
opoly | +0.012 |
abled | +0.012 |
Jacqu | +0.012 |
marginalized | +0.011 |
Neg logit contributions | |
TIT | -0.018 |
\\\\\\\\ | -0.018 |
OTAL | -0.016 |
Merit | -0.016 |
Sessions | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
TIT | +0.084 |
\\\\\\\\ | +0.083 |
OTAL | +0.071 |
Sessions | +0.071 |
Merit | +0.070 |
Neg logit contributions | |
opoly | -0.058 |
ration | -0.058 |
abled | -0.056 |
Jacqu | -0.055 |
marginalized | -0.053 |
Token | genre |
Token ID | 12121 |
Feature activation | +4.71e-02 |
Pos logit contributions | |
TIT | +0.094 |
\\\\\\\\ | +0.092 |
OTAL | +0.079 |
Merit | +0.078 |
Sessions | +0.078 |
Neg logit contributions | |
opoly | -0.070 |
ration | -0.070 |
abled | -0.068 |
Jacqu | -0.067 |
marginalized | -0.065 |
Token | as |
Token ID | 355 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
ration | +0.030 |
opoly | +0.030 |
abled | +0.029 |
Jacqu | +0.029 |
marginalized | +0.028 |
Neg logit contributions | |
TIT | -0.040 |
\\\\\\\\ | -0.039 |
OTAL | -0.034 |
Merit | -0.033 |
Sessions | -0.033 |
Token | " |
Token ID | 366 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
TIT | +0.165 |
\\\\\\\\ | +0.164 |
OTAL | +0.141 |
Merit | +0.139 |
Bank | +0.138 |
Neg logit contributions | |
ration | -0.116 |
opoly | -0.115 |
abled | -0.111 |
Jacqu | -0.110 |
marginalized | -0.106 |
Token | client |
Token ID | 16366 |
Feature activation | -5.92e-01 |
Pos logit contributions | |
TIT | +0.130 |
\\\\\\\\ | +0.128 |
OTAL | +0.110 |
Merit | +0.109 |
Bank | +0.107 |
Neg logit contributions | |
ration | -0.103 |
opoly | -0.102 |
abled | -0.098 |
Jacqu | -0.098 |
marginalized | -0.095 |
Token | based |
Token ID | 1912 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
TIT | +0.484 |
\\\\\\\\ | +0.479 |
OTAL | +0.408 |
Merit | +0.403 |
Bank | +0.398 |
Neg logit contributions | |
ration | -0.397 |
opoly | -0.395 |
abled | -0.383 |
Jacqu | -0.380 |
marginalized | -0.367 |
Token | mission |
Token ID | 4365 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
TIT | +0.172 |
\\\\\\\\ | +0.170 |
OTAL | +0.144 |
Merit | +0.143 |
Sessions | +0.141 |
Neg logit contributions | |
ration | -0.144 |
opoly | -0.143 |
abled | -0.141 |
Jacqu | -0.139 |
marginalized | -0.134 |
Token | structures |
Token ID | 8573 |
Feature activation | -9.66e-04 |
Pos logit contributions | |
TIT | +0.130 |
\\\\\\\\ | +0.128 |
OTAL | +0.109 |
Merit | +0.108 |
Sessions | +0.106 |
Neg logit contributions | |
ration | -0.109 |
opoly | -0.109 |
abled | -0.106 |
Jacqu | -0.104 |
marginalized | -0.101 |
Token | with |
Token ID | 351 |
Feature activation | +5.80e-02 |
Pos logit contributions | |
TIT | +0.001 |
\\\\\\\\ | +0.001 |
OTAL | +0.001 |
Merit | +0.001 |
Sessions | +0.001 |
Neg logit contributions | |
ration | -0.001 |
opoly | -0.001 |
abled | -0.001 |
Jacqu | -0.001 |
marginalized | -0.001 |
Token | persistent |
Token ID | 16218 |
Feature activation | -4.12e-02 |
Pos logit contributions | |
ration | +0.035 |
opoly | +0.035 |
abled | +0.034 |
Jacqu | +0.033 |
marginalized | +0.032 |
Neg logit contributions | |
TIT | -0.051 |
\\\\\\\\ | -0.051 |
OTAL | -0.044 |
Merit | -0.043 |
Sessions | -0.043 |
Token | . |
Token ID | 13 |
Feature activation | +4.04e-02 |
Pos logit contributions | |
opoly | +0.105 |
ration | +0.105 |
abled | +0.102 |
Jacqu | +0.101 |
marginalized | +0.097 |
Neg logit contributions | |
TIT | -0.122 |
\\\\\\\\ | -0.121 |
OTAL | -0.103 |
Merit | -0.101 |
Sessions | -0.100 |
Token | Unfortunately |
Token ID | 8989 |
Feature activation | -3.15e-02 |
Pos logit contributions | |
ration | +0.029 |
opoly | +0.029 |
abled | +0.028 |
Jacqu | +0.027 |
boarded | +0.027 |
Neg logit contributions | |
TIT | -0.031 |
\\\\\\\\ | -0.031 |
OTAL | -0.026 |
Sessions | -0.026 |
Merit | -0.026 |
Token | , |
Token ID | 11 |
Feature activation | -3.02e-02 |
Pos logit contributions | |
TIT | +0.024 |
\\\\\\\\ | +0.024 |
OTAL | +0.020 |
Merit | +0.020 |
Bank | +0.020 |
Neg logit contributions | |
ration | -0.023 |
opoly | -0.022 |
abled | -0.022 |
Jacqu | -0.022 |
marginalized | -0.021 |
Token | people |
Token ID | 661 |
Feature activation | -4.65e-02 |
Pos logit contributions | |
TIT | +0.026 |
\\\\\\\\ | +0.025 |
OTAL | +0.022 |
Sessions | +0.022 |
Tuc | +0.022 |
Neg logit contributions | |
opoly | -0.019 |
ration | -0.019 |
abled | -0.019 |
Jacqu | -0.018 |
boarded | -0.018 |
Token | like |
Token ID | 588 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
TIT | +0.038 |
\\\\\\\\ | +0.038 |
OTAL | +0.033 |
Sessions | +0.032 |
Tuc | +0.032 |
Neg logit contributions | |
opoly | -0.030 |
ration | -0.030 |
abled | -0.029 |
Jacqu | -0.029 |
rift | -0.027 |
Token | Bac |
Token ID | 35583 |
Feature activation | -5.87e-01 |
Pos logit contributions | |
TIT | +0.156 |
\\\\\\\\ | +0.154 |
OTAL | +0.134 |
Sessions | +0.132 |
Merit | +0.132 |
Neg logit contributions | |
ration | -0.107 |
opoly | -0.107 |
abled | -0.103 |
Jacqu | -0.101 |
boarded | -0.098 |
Token | ile |
Token ID | 576 |
Feature activation | -7.66e-02 |
Pos logit contributions | |
TIT | +0.393 |
\\\\\\\\ | +0.387 |
OTAL | +0.325 |
Merit | +0.315 |
Bank | +0.312 |
Neg logit contributions | |
ration | -0.478 |
opoly | -0.472 |
abled | -0.461 |
Jacqu | -0.461 |
marginalized | -0.449 |
Token | and |
Token ID | 290 |
Feature activation | +2.86e-02 |
Pos logit contributions | |
TIT | +0.060 |
\\\\\\\\ | +0.060 |
OTAL | +0.051 |
Sessions | +0.050 |
Merit | +0.050 |
Neg logit contributions | |
opoly | -0.053 |
ration | -0.053 |
abled | -0.051 |
Jacqu | -0.051 |
marginalized | -0.048 |
Token | Terry |
Token ID | 14286 |
Feature activation | +4.16e-02 |
Pos logit contributions | |
ration | +0.017 |
opoly | +0.017 |
abled | +0.016 |
Jacqu | +0.016 |
boarded | +0.015 |
Neg logit contributions | |
TIT | -0.026 |
\\\\\\\\ | -0.025 |
OTAL | -0.022 |
Merit | -0.022 |
Sessions | -0.022 |
Token | Jones |
Token ID | 5437 |
Feature activation | +9.73e-02 |
Pos logit contributions | |
ration | +0.027 |
opoly | +0.027 |
abled | +0.026 |
Jacqu | +0.026 |
marginalized | +0.025 |
Neg logit contributions | |
TIT | -0.035 |
\\\\\\\\ | -0.034 |
OTAL | -0.030 |
Merit | -0.029 |
Bank | -0.029 |
Token | , |
Token ID | 11 |
Feature activation | -4.58e-02 |
Pos logit contributions | |
opoly | +0.068 |
ration | +0.068 |
abled | +0.066 |
Jacqu | +0.065 |
marginalized | +0.063 |
Neg logit contributions | |
TIT | -0.076 |
\\\\\\\\ | -0.075 |
OTAL | -0.064 |
Merit | -0.063 |
Sessions | -0.063 |
Token | faulty |
Token ID | 30954 |
Feature activation | +6.45e-02 |
Pos logit contributions | |
TIT | +0.034 |
\\\\\\\\ | +0.033 |
OTAL | +0.029 |
Merit | +0.028 |
Bank | +0.028 |
Neg logit contributions | |
ration | -0.026 |
opoly | -0.026 |
abled | -0.026 |
Jacqu | -0.025 |
marginalized | -0.024 |
Token | foreclosure |
Token ID | 41400 |
Feature activation | +9.61e-02 |
Pos logit contributions | |
opoly | +0.045 |
ration | +0.045 |
abled | +0.044 |
Jacqu | +0.043 |
marginalized | +0.042 |
Neg logit contributions | |
TIT | -0.051 |
\\\\\\\\ | -0.050 |
OTAL | -0.043 |
Bank | -0.042 |
Merit | -0.042 |
Token | documents |
Token ID | 4963 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
ration | +0.067 |
opoly | +0.067 |
abled | +0.065 |
Jacqu | +0.064 |
marginalized | +0.062 |
Neg logit contributions | |
TIT | -0.076 |
\\\\\\\\ | -0.076 |
OTAL | -0.064 |
Merit | -0.063 |
Bank | -0.062 |
Token | . |
Token ID | 13 |
Feature activation | -6.37e-02 |
Pos logit contributions | |
ration | +0.067 |
opoly | +0.067 |
abled | +0.065 |
Jacqu | +0.064 |
marginalized | +0.062 |
Neg logit contributions | |
TIT | -0.084 |
\\\\\\\\ | -0.083 |
OTAL | -0.071 |
Merit | -0.070 |
Bank | -0.069 |
Token | ( |
Token ID | 357 |
Feature activation | +4.64e-02 |
Pos logit contributions | |
TIT | +0.050 |
\\\\\\\\ | +0.049 |
OTAL | +0.042 |
Bank | +0.042 |
Merit | +0.042 |
Neg logit contributions | |
ration | -0.045 |
opoly | -0.044 |
abled | -0.044 |
Jacqu | -0.042 |
marginalized | -0.042 |
Token | Bank |
Token ID | 28650 |
Feature activation | -5.80e-01 |
Pos logit contributions | |
ration | +0.037 |
opoly | +0.037 |
abled | +0.036 |
Jacqu | +0.036 |
marginalized | +0.035 |
Neg logit contributions | |
TIT | -0.032 |
\\\\\\\\ | -0.032 |
OTAL | -0.026 |
Bank | -0.026 |
Merit | -0.026 |
Token | of |
Token ID | 286 |
Feature activation | +3.81e-03 |
Pos logit contributions | |
TIT | +0.496 |
\\\\\\\\ | +0.492 |
OTAL | +0.422 |
Merit | +0.417 |
Sessions | +0.409 |
Neg logit contributions | |
opoly | -0.370 |
ration | -0.369 |
abled | -0.355 |
Jacqu | -0.352 |
boarded | -0.338 |
Token | America |
Token ID | 2253 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
ration | +0.002 |
opoly | +0.002 |
abled | +0.002 |
Jacqu | +0.002 |
marginalized | +0.002 |
Neg logit contributions | |
TIT | -0.004 |
\\\\\\\\ | -0.003 |
OTAL | -0.003 |
Merit | -0.003 |
Bank | -0.003 |
Token | recently |
Token ID | 2904 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
ration | +0.133 |
opoly | +0.133 |
abled | +0.129 |
Jacqu | +0.127 |
marginalized | +0.123 |
Neg logit contributions | |
TIT | -0.172 |
\\\\\\\\ | -0.170 |
OTAL | -0.146 |
Merit | -0.144 |
Bank | -0.143 |
Token | agreed |
Token ID | 4987 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
opoly | +0.095 |
ration | +0.094 |
abled | +0.092 |
Jacqu | +0.091 |
rift | +0.087 |
Neg logit contributions | |
TIT | -0.122 |
\\\\\\\\ | -0.120 |
OTAL | -0.104 |
Sessions | -0.102 |
Bank | -0.102 |
Token | to |
Token ID | 284 |
Feature activation | -5.29e-02 |
Pos logit contributions | |
TIT | +0.273 |
\\\\\\\\ | +0.270 |
OTAL | +0.233 |
Merit | +0.229 |
Bank | +0.226 |
Neg logit contributions | |
ration | -0.196 |
opoly | -0.195 |
abled | -0.188 |
Jacqu | -0.186 |
marginalized | -0.180 |
Token | bandwidth |
Token ID | 19484 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
TIT | +0.061 |
\\\\\\\\ | +0.060 |
OTAL | +0.051 |
Merit | +0.050 |
Bank | +0.049 |
Neg logit contributions | |
ration | -0.060 |
opoly | -0.060 |
abled | -0.058 |
Jacqu | -0.057 |
marginalized | -0.056 |
Token | than |
Token ID | 621 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
TIT | +0.229 |
\\\\\\\\ | +0.227 |
OTAL | +0.193 |
Merit | +0.189 |
Sessions | +0.187 |
Neg logit contributions | |
opoly | -0.201 |
ration | -0.200 |
abled | -0.194 |
Jacqu | -0.193 |
marginalized | -0.187 |
Token | the |
Token ID | 262 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
TIT | +0.210 |
\\\\\\\\ | +0.207 |
OTAL | +0.174 |
Merit | +0.169 |
Bank | +0.168 |
Neg logit contributions | |
ration | -0.213 |
opoly | -0.213 |
abled | -0.207 |
Jacqu | -0.204 |
marginalized | -0.199 |
Token | GTX |
Token ID | 12646 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
TIT | +0.104 |
\\\\\\\\ | +0.103 |
OTAL | +0.086 |
Merit | +0.084 |
Bank | +0.083 |
Neg logit contributions | |
opoly | -0.109 |
ration | -0.108 |
abled | -0.106 |
Jacqu | -0.104 |
marginalized | -0.102 |
Token | 980 |
Token ID | 40022 |
Feature activation | -3.92e-02 |
Pos logit contributions | |
TIT | +0.123 |
\\\\\\\\ | +0.122 |
OTAL | +0.106 |
Merit | +0.104 |
Sessions | +0.103 |
Neg logit contributions | |
opoly | -0.076 |
ration | -0.075 |
abled | -0.073 |
Jacqu | -0.072 |
marginalized | -0.070 |
Token | GPU |
Token ID | 11362 |
Feature activation | -5.78e-01 |
Pos logit contributions | |
TIT | +0.030 |
\\\\\\\\ | +0.030 |
OTAL | +0.025 |
Merit | +0.024 |
Bank | +0.024 |
Neg logit contributions | |
opoly | -0.028 |
ration | -0.028 |
abled | -0.028 |
Jacqu | -0.027 |
marginalized | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
TIT | +0.465 |
\\\\\\\\ | +0.461 |
OTAL | +0.393 |
Merit | +0.384 |
Bank | +0.382 |
Neg logit contributions | |
opoly | -0.394 |
ration | -0.391 |
abled | -0.381 |
Jacqu | -0.376 |
marginalized | -0.367 |
Token |
|
Token ID | 198 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
TIT | +0.179 |
\\\\\\\\ | +0.176 |
OTAL | +0.151 |
Merit | +0.148 |
Bank | +0.147 |
Neg logit contributions | |
ration | -0.149 |
opoly | -0.148 |
abled | -0.144 |
Jacqu | -0.140 |
marginalized | -0.138 |
Token |
|
Token ID | 198 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
TIT | +0.105 |
\\\\\\\\ | +0.102 |
OTAL | +0.089 |
Merit | +0.088 |
Bank | +0.087 |
Neg logit contributions | |
ration | -0.082 |
opoly | -0.082 |
abled | -0.079 |
boarded | -0.077 |
Jacqu | -0.077 |
Token | The |
Token ID | 464 |
Feature activation | -9.52e-02 |
Pos logit contributions | |
TIT | +0.075 |
\\\\\\\\ | +0.073 |
OTAL | +0.061 |
Merit | +0.060 |
Bank | +0.059 |
Neg logit contributions | |
ration | -0.081 |
opoly | -0.081 |
abled | -0.078 |
Jacqu | -0.078 |
marginalized | -0.076 |
Token | MSI |
Token ID | 30781 |
Feature activation | -5.10e-02 |
Pos logit contributions | |
TIT | +0.072 |
\\\\\\\\ | +0.071 |
OTAL | +0.060 |
Merit | +0.059 |
Bank | +0.058 |
Neg logit contributions | |
opoly | -0.070 |
ration | -0.069 |
abled | -0.068 |
Jacqu | -0.067 |
marginalized | -0.065 |
Token |
|
Token ID | 198 |
Feature activation | +5.39e-02 |
Pos logit contributions | |
TIT | +0.018 |
\\\\\\\\ | +0.017 |
OTAL | +0.015 |
Merit | +0.015 |
Sessions | +0.015 |
Neg logit contributions | |
ration | -0.014 |
opoly | -0.014 |
abled | -0.013 |
boarded | -0.013 |
Jacqu | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | +6.83e-02 |
Pos logit contributions | |
ration | +0.036 |
opoly | +0.035 |
abled | +0.034 |
boarded | +0.033 |
Jacqu | +0.033 |
Neg logit contributions | |
TIT | -0.045 |
\\\\\\\\ | -0.044 |
OTAL | -0.038 |
Merit | -0.038 |
Sessions | -0.038 |
Token | Google |
Token ID | 11708 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
ration | +0.050 |
opoly | +0.050 |
abled | +0.048 |
Jacqu | +0.048 |
marginalized | +0.047 |
Neg logit contributions | |
TIT | -0.052 |
\\\\\\\\ | -0.051 |
OTAL | -0.043 |
Merit | -0.043 |
Bank | -0.042 |
Token | Scholar |
Token ID | 11713 |
Feature activation | +4.51e-02 |
Pos logit contributions | |
TIT | +0.074 |
\\\\\\\\ | +0.072 |
OTAL | +0.058 |
Merit | +0.057 |
Sessions | +0.057 |
Neg logit contributions | |
ration | -0.110 |
opoly | -0.110 |
abled | -0.108 |
Jacqu | -0.106 |
boarded | -0.104 |
Token | S |
Token ID | 311 |
Feature activation | -6.90e-02 |
Pos logit contributions | |
ration | +0.026 |
opoly | +0.025 |
abled | +0.025 |
Jacqu | +0.024 |
marginalized | +0.023 |
Neg logit contributions | |
TIT | -0.041 |
\\\\\\\\ | -0.041 |
OTAL | -0.036 |
Merit | -0.035 |
Bank | -0.035 |
Token | AGE |
Token ID | 11879 |
Feature activation | -5.74e-01 |
Pos logit contributions | |
TIT | +0.017 |
\\\\\\\\ | +0.017 |
OTAL | +0.009 |
Merit | +0.008 |
Bank | +0.007 |
Neg logit contributions | |
ration | -0.085 |
opoly | -0.085 |
abled | -0.084 |
Jacqu | -0.083 |
marginalized | -0.082 |
Token | Journals |
Token ID | 48608 |
Feature activation | +7.93e-02 |
Pos logit contributions | |
TIT | +0.413 |
\\\\\\\\ | +0.402 |
OTAL | +0.339 |
Sessions | +0.331 |
Bank | +0.329 |
Neg logit contributions | |
opoly | -0.444 |
ration | -0.442 |
abled | -0.430 |
Jacqu | -0.424 |
marginalized | -0.416 |
Token | | |
Token ID | 930 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
ration | +0.054 |
opoly | +0.054 |
abled | +0.052 |
Jacqu | +0.052 |
marginalized | +0.050 |
Neg logit contributions | |
TIT | -0.064 |
\\\\\\\\ | -0.064 |
OTAL | -0.054 |
Merit | -0.053 |
Bank | -0.052 |
Token | ISI |
Token ID | 22048 |
Feature activation | +5.86e-02 |
Pos logit contributions | |
TIT | +0.093 |
\\\\\\\\ | +0.091 |
OTAL | +0.077 |
Merit | +0.075 |
Sessions | +0.074 |
Neg logit contributions | |
opoly | -0.101 |
ration | -0.101 |
abled | -0.098 |
Jacqu | -0.096 |
marginalized | -0.094 |
Token |
|
Token ID | 198 |
Feature activation | +4.46e-02 |
Pos logit contributions | |
ration | +0.034 |
opoly | +0.034 |
abled | +0.033 |
Jacqu | +0.032 |
marginalized | +0.031 |
Neg logit contributions | |
TIT | -0.053 |
\\\\\\\\ | -0.053 |
OTAL | -0.046 |
Merit | -0.045 |
Bank | -0.045 |
Token |
|
Token ID | 198 |
Feature activation | +5.49e-02 |
Pos logit contributions | |
opoly | +0.029 |
ration | +0.029 |
abled | +0.028 |
boarded | +0.027 |
Jacqu | +0.027 |
Neg logit contributions | |
TIT | -0.038 |
\\\\\\\\ | -0.037 |
OTAL | -0.032 |
Merit | -0.032 |
Sessions | -0.031 |
Token | onomy |
Token ID | 30565 |
Feature activation | +9.84e-02 |
Pos logit contributions | |
ration | +0.089 |
opoly | +0.089 |
abled | +0.085 |
Jacqu | +0.084 |
marginalized | +0.081 |
Neg logit contributions | |
TIT | -0.142 |
\\\\\\\\ | -0.141 |
OTAL | -0.123 |
Merit | -0.121 |
Bank | -0.120 |
Token | of |
Token ID | 286 |
Feature activation | +7.08e-02 |
Pos logit contributions | |
ration | +0.061 |
opoly | +0.061 |
abled | +0.058 |
Jacqu | +0.058 |
marginalized | +0.056 |
Neg logit contributions | |
TIT | -0.086 |
\\\\\\\\ | -0.086 |
OTAL | -0.074 |
Merit | -0.072 |
Tuc | -0.071 |
Token | rock |
Token ID | 3881 |
Feature activation | +3.87e-02 |
Pos logit contributions | |
ration | +0.047 |
opoly | +0.046 |
abled | +0.045 |
Jacqu | +0.044 |
marginalized | +0.043 |
Neg logit contributions | |
TIT | -0.059 |
\\\\\\\\ | -0.058 |
OTAL | -0.050 |
Merit | -0.049 |
Tuc | -0.049 |
Token | - |
Token ID | 12 |
Feature activation | +3.72e-02 |
Pos logit contributions | |
ration | +0.025 |
opoly | +0.025 |
abled | +0.025 |
Jacqu | +0.024 |
marginalized | +0.024 |
Neg logit contributions | |
TIT | -0.032 |
\\\\\\\\ | -0.032 |
OTAL | -0.028 |
Merit | -0.027 |
Bank | -0.027 |
Token | wall |
Token ID | 11930 |
Feature activation | -5.58e-02 |
Pos logit contributions | |
ration | +0.029 |
opoly | +0.029 |
Jacqu | +0.028 |
abled | +0.028 |
marginalized | +0.027 |
Neg logit contributions | |
TIT | -0.027 |
\\\\\\\\ | -0.026 |
OTAL | -0.022 |
Merit | -0.021 |
Bank | -0.021 |
Token | abies |
Token ID | 43256 |
Feature activation | -5.71e-01 |
Pos logit contributions | |
TIT | +0.034 |
\\\\\\\\ | +0.034 |
OTAL | +0.027 |
Merit | +0.027 |
Bank | +0.026 |
Neg logit contributions | |
ration | -0.049 |
opoly | -0.049 |
abled | -0.047 |
Jacqu | -0.047 |
marginalized | -0.046 |
Token | , |
Token ID | 11 |
Feature activation | +2.22e-02 |
Pos logit contributions | |
TIT | +0.467 |
\\\\\\\\ | +0.457 |
OTAL | +0.394 |
Merit | +0.387 |
Tuc | +0.386 |
Neg logit contributions | |
ration | -0.381 |
opoly | -0.380 |
abled | -0.371 |
Jacqu | -0.362 |
marginalized | -0.352 |
Token | Pet |
Token ID | 4767 |
Feature activation | -5.65e-03 |
Pos logit contributions | |
ration | +0.016 |
opoly | +0.016 |
abled | +0.015 |
Jacqu | +0.015 |
marginalized | +0.014 |
Neg logit contributions | |
TIT | -0.017 |
\\\\\\\\ | -0.017 |
OTAL | -0.015 |
Merit | -0.014 |
Tuc | -0.014 |
Token | rog |
Token ID | 3828 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
TIT | +0.006 |
\\\\\\\\ | +0.006 |
OTAL | +0.005 |
Bank | +0.005 |
Merit | +0.005 |
Neg logit contributions | |
ration | -0.002 |
opoly | -0.002 |
Jacqu | -0.002 |
abled | -0.002 |
marginalized | -0.002 |
Token | ale |
Token ID | 1000 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
ration | +0.196 |
opoly | +0.193 |
Jacqu | +0.187 |
abled | +0.185 |
marginalized | +0.182 |
Neg logit contributions | |
TIT | -0.271 |
\\\\\\\\ | -0.268 |
OTAL | -0.236 |
Bank | -0.230 |
Merit | -0.229 |
Token | ( |
Token ID | 357 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
ration | +0.069 |
opoly | +0.069 |
abled | +0.067 |
Jacqu | +0.066 |
marginalized | +0.064 |
Neg logit contributions | |
TIT | -0.100 |
\\\\\\\\ | -0.099 |
OTAL | -0.086 |
Merit | -0.084 |
Bank | -0.083 |
Token | Min |
Token ID | 1855 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
ration | +0.034 |
opoly | +0.034 |
abled | +0.032 |
Jacqu | +0.032 |
marginalized | +0.031 |
Neg logit contributions | |
TIT | -0.043 |
\\\\\\\\ | -0.042 |
OTAL | -0.036 |
Merit | -0.036 |
Sessions | -0.035 |
Token | ova |
Token ID | 10071 |
Feature activation | -6.66e-02 |
Pos logit contributions | |
TIT | +0.064 |
\\\\\\\\ | +0.063 |
OTAL | +0.051 |
Merit | +0.049 |
Bank | +0.049 |
Neg logit contributions | |
ration | -0.102 |
opoly | -0.101 |
Jacqu | -0.099 |
abled | -0.099 |
marginalized | -0.097 |
Token | � |
Token ID | 564 |
Feature activation | +3.85e-02 |
Pos logit contributions | |
TIT | +0.056 |
\\\\\\\\ | +0.055 |
OTAL | +0.047 |
Merit | +0.046 |
Bank | +0.046 |
Neg logit contributions | |
ration | -0.044 |
opoly | -0.043 |
abled | -0.042 |
Jacqu | -0.042 |
marginalized | -0.040 |
Token | � |
Token ID | 250 |
Feature activation | -2.51e-02 |
Pos logit contributions | |
opoly | +0.035 |
ration | +0.035 |
abled | +0.034 |
Jacqu | +0.034 |
boarded | +0.033 |
Neg logit contributions | |
TIT | -0.022 |
\\\\\\\\ | -0.022 |
OTAL | -0.017 |
Merit | -0.017 |
Sessions | -0.016 |
Token | ir |
Token ID | 343 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
TIT | +0.021 |
\\\\\\\\ | +0.021 |
OTAL | +0.018 |
Merit | +0.018 |
Bank | +0.018 |
Neg logit contributions | |
ration | -0.016 |
opoly | -0.016 |
abled | -0.015 |
Jacqu | -0.015 |
marginalized | -0.015 |
Token | respective |
Token ID | 36990 |
Feature activation | -5.66e-01 |
Pos logit contributions | |
ration | +0.213 |
opoly | +0.212 |
abled | +0.208 |
Jacqu | +0.207 |
marginalized | +0.204 |
Neg logit contributions | |
TIT | -0.063 |
\\\\\\\\ | -0.061 |
OTAL | -0.039 |
Merit | -0.037 |
Sessions | -0.036 |
Token | of |
Token ID | 286 |
Feature activation | -8.92e-02 |
Pos logit contributions | |
TIT | +0.484 |
\\\\\\\\ | +0.479 |
OTAL | +0.412 |
Merit | +0.406 |
Bank | +0.401 |
Neg logit contributions | |
ration | -0.361 |
opoly | -0.359 |
abled | -0.347 |
Jacqu | -0.342 |
marginalized | -0.333 |
Token | which |
Token ID | 543 |
Feature activation | +5.12e-03 |
Pos logit contributions | |
TIT | +0.083 |
\\\\\\\\ | +0.082 |
OTAL | +0.072 |
Sessions | +0.071 |
Merit | +0.071 |
Neg logit contributions | |
opoly | -0.050 |
ration | -0.049 |
abled | -0.047 |
Jacqu | -0.047 |
boarded | -0.044 |
Token | unit |
Token ID | 4326 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
opoly | +0.003 |
ration | +0.003 |
abled | +0.003 |
Jacqu | +0.003 |
marginalized | +0.003 |
Neg logit contributions | |
TIT | -0.004 |
\\\\\\\\ | -0.004 |
OTAL | -0.004 |
Merit | -0.004 |
Tuc | -0.004 |
Token | is |
Token ID | 318 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
ration | +0.155 |
opoly | +0.154 |
abled | +0.149 |
Jacqu | +0.148 |
marginalized | +0.143 |
Neg logit contributions | |
TIT | -0.179 |
\\\\\\\\ | -0.177 |
OTAL | -0.151 |
Merit | -0.148 |
Sessions | -0.147 |
Token | accused |
Token ID | 5371 |
Feature activation | -3.78e-02 |
Pos logit contributions | |
TIT | +0.091 |
\\\\\\\\ | +0.089 |
OTAL | +0.077 |
Tuc | +0.076 |
Sessions | +0.075 |
Neg logit contributions | |
opoly | -0.080 |
ration | -0.078 |
abled | -0.076 |
Jacqu | -0.075 |
rift | -0.072 |
Token | be |
Token ID | 307 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
TIT | +0.029 |
\\\\\\\\ | +0.028 |
OTAL | +0.025 |
Merit | +0.025 |
Sessions | +0.024 |
Neg logit contributions | |
opoly | -0.017 |
ration | -0.017 |
abled | -0.016 |
Jacqu | -0.016 |
marginalized | -0.015 |
Token | affected |
Token ID | 5676 |
Feature activation | +3.58e-02 |
Pos logit contributions | |
opoly | +0.124 |
ration | +0.124 |
abled | +0.120 |
Jacqu | +0.119 |
marginalized | +0.115 |
Neg logit contributions | |
TIT | -0.140 |
\\\\\\\\ | -0.138 |
OTAL | -0.117 |
Merit | -0.115 |
Bank | -0.114 |
Token | . |
Token ID | 13 |
Feature activation | -4.56e-02 |
Pos logit contributions | |
ration | +0.025 |
opoly | +0.025 |
abled | +0.024 |
Jacqu | +0.024 |
marginalized | +0.023 |
Neg logit contributions | |
TIT | -0.028 |
\\\\\\\\ | -0.028 |
OTAL | -0.024 |
Merit | -0.023 |
Bank | -0.023 |
Token |
|
Token ID | 198 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
TIT | +0.038 |
\\\\\\\\ | +0.038 |
OTAL | +0.033 |
Merit | +0.032 |
Sessions | +0.032 |
Neg logit contributions | |
ration | -0.030 |
opoly | -0.030 |
abled | -0.029 |
Jacqu | -0.028 |
marginalized | -0.027 |
Token |
|
Token ID | 198 |
Feature activation | +1.14e-03 |
Pos logit contributions | |
ration | +0.007 |
opoly | +0.007 |
abled | +0.007 |
boarded | +0.007 |
Jacqu | +0.007 |
Neg logit contributions | |
TIT | -0.009 |
\\\\\\\\ | -0.009 |
OTAL | -0.008 |
Merit | -0.008 |
Bank | -0.008 |
Token | Par |
Token ID | 10044 |
Feature activation | -5.57e-01 |
Pos logit contributions | |
ration | +0.001 |
opoly | +0.001 |
abled | +0.001 |
Jacqu | +0.001 |
marginalized | +0.001 |
Neg logit contributions | |
TIT | -0.001 |
\\\\\\\\ | -0.001 |
OTAL | -0.001 |
Merit | -0.001 |
Bank | -0.001 |
Token | liament |
Token ID | 5130 |
Feature activation | +8.40e-02 |
Pos logit contributions | |
TIT | +0.424 |
\\\\\\\\ | +0.417 |
OTAL | +0.354 |
Bank | +0.345 |
Sessions | +0.344 |
Neg logit contributions | |
ration | -0.403 |
opoly | -0.401 |
abled | -0.387 |
Jacqu | -0.385 |
marginalized | -0.375 |
Token | ary |
Token ID | 560 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
ration | +0.057 |
opoly | +0.057 |
Jacqu | +0.054 |
abled | +0.054 |
marginalized | +0.053 |
Neg logit contributions | |
TIT | -0.068 |
\\\\\\\\ | -0.067 |
OTAL | -0.057 |
Merit | -0.056 |
Bank | -0.056 |
Token | officers |
Token ID | 3790 |
Feature activation | -6.77e-03 |
Pos logit contributions | |
TIT | +0.225 |
\\\\\\\\ | +0.221 |
OTAL | +0.189 |
Sessions | +0.187 |
Merit | +0.186 |
Neg logit contributions | |
opoly | -0.199 |
ration | -0.197 |
abled | -0.191 |
Jacqu | -0.188 |
marginalized | -0.183 |
Token | have |
Token ID | 423 |
Feature activation | +2.02e-02 |
Pos logit contributions | |
TIT | +0.006 |
\\\\\\\\ | +0.006 |
OTAL | +0.005 |
Merit | +0.005 |
Sessions | +0.005 |
Neg logit contributions | |
opoly | -0.004 |
ration | -0.004 |
abled | -0.004 |
Jacqu | -0.004 |
marginalized | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | -3.73e-02 |
Pos logit contributions | |
opoly | +0.013 |
ration | +0.013 |
abled | +0.013 |
Jacqu | +0.012 |
marginalized | +0.012 |
Neg logit contributions | |
TIT | -0.017 |
\\\\\\\\ | -0.017 |
OTAL | -0.014 |
Merit | -0.014 |
Sessions | -0.014 |
Token | ships |
Token ID | 7937 |
Feature activation | +1.91e-02 |
Pos logit contributions | |
TIT | +0.169 |
\\\\\\\\ | +0.166 |
OTAL | +0.142 |
Sessions | +0.138 |
Bank | +0.138 |
Neg logit contributions | |
opoly | -0.145 |
ration | -0.145 |
abled | -0.141 |
Jacqu | -0.139 |
marginalized | -0.135 |
Token | with |
Token ID | 351 |
Feature activation | -2.15e-02 |
Pos logit contributions | |
opoly | +0.008 |
ration | +0.008 |
abled | +0.008 |
Jacqu | +0.008 |
marginalized | +0.007 |
Neg logit contributions | |
TIT | -0.020 |
\\\\\\\\ | -0.020 |
OTAL | -0.017 |
Tuc | -0.017 |
Sessions | -0.017 |
Token | 25 |
Token ID | 1679 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
TIT | +0.019 |
\\\\\\\\ | +0.018 |
OTAL | +0.016 |
Merit | +0.015 |
Sessions | +0.015 |
Neg logit contributions | |
opoly | -0.014 |
ration | -0.013 |
abled | -0.013 |
Jacqu | -0.013 |
marginalized | -0.012 |
Token | 60 |
Token ID | 1899 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
TIT | +0.238 |
\\\\\\\\ | +0.235 |
OTAL | +0.201 |
Merit | +0.198 |
Bank | +0.196 |
Neg logit contributions | |
ration | -0.190 |
opoly | -0.189 |
abled | -0.183 |
Jacqu | -0.181 |
marginalized | -0.176 |
Token | CU |
Token ID | 29369 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
TIT | +0.162 |
\\\\\\\\ | +0.160 |
OTAL | +0.134 |
Merit | +0.131 |
Bank | +0.130 |
Neg logit contributions | |
ration | -0.171 |
opoly | -0.170 |
abled | -0.165 |
Jacqu | -0.164 |
marginalized | -0.160 |
Token | DA |
Token ID | 5631 |
Feature activation | -5.55e-01 |
Pos logit contributions | |
TIT | +0.202 |
\\\\\\\\ | +0.199 |
OTAL | +0.147 |
Merit | +0.143 |
Bank | +0.138 |
Neg logit contributions | |
ration | -0.451 |
opoly | -0.449 |
abled | -0.439 |
Jacqu | -0.437 |
marginalized | -0.428 |
Token | cores |
Token ID | 21758 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
TIT | +0.367 |
\\\\\\\\ | +0.365 |
OTAL | +0.297 |
Merit | +0.295 |
Bank | +0.284 |
Neg logit contributions | |
ration | -0.460 |
opoly | -0.458 |
abled | -0.447 |
Jacqu | -0.446 |
marginalized | -0.433 |
Token | and |
Token ID | 290 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
TIT | +0.236 |
\\\\\\\\ | +0.234 |
OTAL | +0.201 |
Merit | +0.195 |
Bank | +0.195 |
Neg logit contributions | |
opoly | -0.183 |
ration | -0.181 |
abled | -0.175 |
Jacqu | -0.174 |
marginalized | -0.168 |
Token | 20 |
Token ID | 1160 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
TIT | +0.115 |
\\\\\\\\ | +0.113 |
OTAL | +0.097 |
Merit | +0.095 |
Sessions | +0.094 |
Neg logit contributions | |
opoly | -0.099 |
ration | -0.098 |
abled | -0.095 |
Jacqu | -0.094 |
marginalized | -0.091 |
Token | SM |
Token ID | 9447 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
TIT | +0.162 |
\\\\\\\\ | +0.161 |
OTAL | +0.136 |
Merit | +0.133 |
Bank | +0.131 |
Neg logit contributions | |
ration | -0.152 |
opoly | -0.151 |
abled | -0.147 |
Jacqu | -0.146 |
marginalized | -0.142 |
Token | units |
Token ID | 4991 |
Feature activation | -7.94e-02 |
Pos logit contributions | |
TIT | +0.228 |
\\\\\\\\ | +0.225 |
OTAL | +0.186 |
Merit | +0.182 |
Bank | +0.180 |
Neg logit contributions | |
ration | -0.260 |
opoly | -0.259 |
abled | -0.252 |
Jacqu | -0.250 |
marginalized | -0.244 |
Token | in |
Token ID | 259 |
Feature activation | +4.39e-03 |
Pos logit contributions | |
ration | +0.264 |
opoly | +0.260 |
abled | +0.250 |
Jacqu | +0.249 |
marginalized | +0.243 |
Neg logit contributions | |
TIT | -0.369 |
\\\\\\\\ | -0.361 |
OTAL | -0.311 |
Merit | -0.309 |
Bank | -0.307 |
Token | the |
Token ID | 262 |
Feature activation | -2.67e-02 |
Pos logit contributions | |
ration | +0.003 |
opoly | +0.002 |
abled | +0.002 |
Jacqu | +0.002 |
marginalized | +0.002 |
Neg logit contributions | |
TIT | -0.004 |
\\\\\\\\ | -0.004 |
OTAL | -0.003 |
Merit | -0.003 |
Tuc | -0.003 |
Token | night |
Token ID | 1755 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
TIT | +0.022 |
\\\\\\\\ | +0.022 |
OTAL | +0.019 |
Merit | +0.019 |
Sessions | +0.019 |
Neg logit contributions | |
opoly | -0.017 |
ration | -0.017 |
abled | -0.017 |
Jacqu | -0.016 |
marginalized | -0.016 |
Token | 's |
Token ID | 338 |
Feature activation | +6.38e-03 |
Pos logit contributions | |
TIT | +0.148 |
\\\\\\\\ | +0.148 |
OTAL | +0.127 |
Sessions | +0.125 |
Merit | +0.125 |
Neg logit contributions | |
ration | -0.108 |
opoly | -0.108 |
abled | -0.105 |
Jacqu | -0.103 |
marginalized | -0.100 |
Token | only |
Token ID | 691 |
Feature activation | -7.19e-02 |
Pos logit contributions | |
opoly | +0.004 |
ration | +0.004 |
abled | +0.004 |
Jacqu | +0.004 |
marginalized | +0.004 |
Neg logit contributions | |
TIT | -0.005 |
\\\\\\\\ | -0.005 |
OTAL | -0.004 |
Merit | -0.004 |
Sessions | -0.004 |
Token | repeat |
Token ID | 9585 |
Feature activation | -5.52e-01 |
Pos logit contributions | |
TIT | +0.061 |
\\\\\\\\ | +0.060 |
OTAL | +0.052 |
Sessions | +0.051 |
Merit | +0.051 |
Neg logit contributions | |
opoly | -0.046 |
ration | -0.045 |
abled | -0.044 |
Jacqu | -0.043 |
rift | -0.042 |
Token | category |
Token ID | 6536 |
Feature activation | +6.45e-02 |
Pos logit contributions | |
TIT | +0.465 |
\\\\\\\\ | +0.459 |
OTAL | +0.398 |
Merit | +0.389 |
Sessions | +0.387 |
Neg logit contributions | |
ration | -0.354 |
opoly | -0.353 |
abled | -0.341 |
Jacqu | -0.337 |
marginalized | -0.327 |
Token | win |
Token ID | 1592 |
Feature activation | -6.97e-02 |
Pos logit contributions | |
ration | +0.023 |
opoly | +0.023 |
abled | +0.022 |
Jacqu | +0.021 |
marginalized | +0.020 |
Neg logit contributions | |
TIT | -0.073 |
\\\\\\\\ | -0.072 |
OTAL | -0.065 |
Merit | -0.064 |
Sessions | -0.063 |
Token | from |
Token ID | 422 |
Feature activation | +9.67e-03 |
Pos logit contributions | |
TIT | +0.078 |
\\\\\\\\ | +0.077 |
OTAL | +0.069 |
Merit | +0.069 |
Sessions | +0.068 |
Neg logit contributions | |
ration | -0.026 |
opoly | -0.025 |
abled | -0.024 |
Jacqu | -0.023 |
marginalized | -0.022 |
Token | 2013 |
Token ID | 2211 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
opoly | +0.007 |
ration | +0.007 |
abled | +0.006 |
Jacqu | +0.006 |
marginalized | +0.006 |
Neg logit contributions | |
TIT | -0.008 |
\\\\\\\\ | -0.008 |
OTAL | -0.007 |
Merit | -0.006 |
Sessions | -0.006 |
Token | — |
Token ID | 960 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
TIT | +0.126 |
\\\\\\\\ | +0.125 |
OTAL | +0.113 |
Merit | +0.112 |
Bank | +0.111 |
Neg logit contributions | |
ration | -0.029 |
opoly | -0.029 |
abled | -0.027 |
Jacqu | -0.026 |
marginalized | -0.024 |
Token | overcl |
Token ID | 40397 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
TIT | +0.395 |
\\\\\\\\ | +0.390 |
OTAL | +0.332 |
Merit | +0.326 |
Bank | +0.324 |
Neg logit contributions | |
opoly | -0.362 |
ration | -0.358 |
abled | -0.351 |
Jacqu | -0.346 |
marginalized | -0.336 |
Token | ocking |
Token ID | 8629 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
TIT | +0.122 |
\\\\\\\\ | +0.121 |
OTAL | +0.098 |
Merit | +0.094 |
Bank | +0.093 |
Neg logit contributions | |
ration | -0.178 |
opoly | -0.178 |
abled | -0.173 |
Jacqu | -0.173 |
marginalized | -0.169 |
Token | stability |
Token ID | 10159 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
TIT | +0.307 |
\\\\\\\\ | +0.303 |
OTAL | +0.256 |
Merit | +0.253 |
Sessions | +0.252 |
Neg logit contributions | |
opoly | -0.300 |
ration | -0.293 |
abled | -0.289 |
Jacqu | -0.285 |
boarded | -0.277 |
Token | . |
Token ID | 13 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
TIT | +0.142 |
\\\\\\\\ | +0.140 |
OTAL | +0.120 |
Merit | +0.118 |
Bank | +0.116 |
Neg logit contributions | |
ration | -0.119 |
opoly | -0.119 |
abled | -0.115 |
Jacqu | -0.114 |
marginalized | -0.111 |
Token | MSI |
Token ID | 30781 |
Feature activation | -3.79e-02 |
Pos logit contributions | |
TIT | +0.108 |
\\\\\\\\ | +0.106 |
OTAL | +0.091 |
Merit | +0.089 |
Bank | +0.088 |
Neg logit contributions | |
ration | -0.094 |
opoly | -0.093 |
abled | -0.091 |
Jacqu | -0.089 |
marginalized | -0.087 |
Token | GPU |
Token ID | 11362 |
Feature activation | -5.50e-01 |
Pos logit contributions | |
TIT | +0.031 |
\\\\\\\\ | +0.031 |
OTAL | +0.026 |
Merit | +0.026 |
Sessions | +0.026 |
Neg logit contributions | |
opoly | -0.025 |
ration | -0.025 |
abled | -0.024 |
Jacqu | -0.024 |
marginalized | -0.023 |
Token | Re |
Token ID | 797 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
TIT | +0.387 |
\\\\\\\\ | +0.381 |
OTAL | +0.318 |
Merit | +0.310 |
Bank | +0.308 |
Neg logit contributions | |
opoly | -0.430 |
ration | -0.429 |
abled | -0.418 |
Jacqu | -0.414 |
marginalized | -0.404 |
Token | actor |
Token ID | 11218 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
TIT | +0.174 |
\\\\\\\\ | +0.172 |
OTAL | +0.145 |
Merit | +0.142 |
Bank | +0.140 |
Neg logit contributions | |
ration | -0.170 |
opoly | -0.169 |
abled | -0.164 |
Jacqu | -0.163 |
marginalized | -0.158 |
Token | is |
Token ID | 318 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
TIT | +0.219 |
\\\\\\\\ | +0.216 |
OTAL | +0.188 |
Merit | +0.185 |
Sessions | +0.185 |
Neg logit contributions | |
opoly | -0.154 |
ration | -0.152 |
abled | -0.147 |
Jacqu | -0.145 |
marginalized | -0.141 |
Token | easy |
Token ID | 2562 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
TIT | +0.109 |
\\\\\\\\ | +0.108 |
OTAL | +0.093 |
Merit | +0.092 |
Sessions | +0.091 |
Neg logit contributions | |
opoly | -0.079 |
ration | -0.079 |
abled | -0.076 |
Jacqu | -0.075 |
marginalized | -0.073 |
Token | to |
Token ID | 284 |
Feature activation | -9.48e-02 |
Pos logit contributions | |
TIT | +0.178 |
\\\\\\\\ | +0.176 |
OTAL | +0.152 |
Merit | +0.150 |
Bank | +0.148 |
Neg logit contributions | |
ration | -0.130 |
opoly | -0.129 |
abled | -0.125 |
Jacqu | -0.123 |
marginalized | -0.119 |
Token | Road |
Token ID | 5567 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
TIT | +0.015 |
\\\\\\\\ | +0.015 |
OTAL | +0.013 |
Merit | +0.013 |
Sessions | +0.013 |
Neg logit contributions | |
ration | -0.013 |
opoly | -0.013 |
abled | -0.013 |
Jacqu | -0.013 |
marginalized | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | +5.15e-02 |
Pos logit contributions | |
TIT | +0.146 |
\\\\\\\\ | +0.144 |
OTAL | +0.123 |
Merit | +0.122 |
Sessions | +0.122 |
Neg logit contributions | |
opoly | -0.117 |
ration | -0.116 |
abled | -0.113 |
Jacqu | -0.112 |
marginalized | -0.108 |
Token | The |
Token ID | 383 |
Feature activation | +8.40e-02 |
Pos logit contributions | |
ration | +0.033 |
opoly | +0.033 |
abled | +0.032 |
Jacqu | +0.031 |
marginalized | +0.031 |
Neg logit contributions | |
TIT | -0.044 |
\\\\\\\\ | -0.043 |
OTAL | -0.037 |
Merit | -0.037 |
Bank | -0.036 |
Token | Director |
Token ID | 5890 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
opoly | +0.055 |
ration | +0.054 |
abled | +0.053 |
Jacqu | +0.052 |
marginalized | +0.051 |
Neg logit contributions | |
TIT | -0.070 |
\\\\\\\\ | -0.069 |
OTAL | -0.059 |
Merit | -0.059 |
Sessions | -0.059 |
Token | of |
Token ID | 286 |
Feature activation | +9.37e-02 |
Pos logit contributions | |
ration | +0.093 |
opoly | +0.092 |
abled | +0.090 |
Jacqu | +0.089 |
marginalized | +0.086 |
Neg logit contributions | |
TIT | -0.110 |
\\\\\\\\ | -0.109 |
OTAL | -0.093 |
Merit | -0.091 |
Bank | -0.090 |
Token | Seven |
Token ID | 13723 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
ration | +0.065 |
opoly | +0.065 |
abled | +0.063 |
Jacqu | +0.062 |
marginalized | +0.060 |
Neg logit contributions | |
TIT | -0.075 |
\\\\\\\\ | -0.074 |
OTAL | -0.063 |
Merit | -0.062 |
Sessions | -0.061 |
Token | Eleven |
Token ID | 37339 |
Feature activation | +5.28e-01 |
Pos logit contributions | |
ration | +0.260 |
opoly | +0.259 |
abled | +0.252 |
Jacqu | +0.249 |
marginalized | +0.243 |
Neg logit contributions | |
TIT | -0.274 |
\\\\\\\\ | -0.271 |
OTAL | -0.228 |
Merit | -0.225 |
Bank | -0.222 |
Token | Construction |
Token ID | 20395 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
ration | +0.374 |
opoly | +0.373 |
abled | +0.361 |
Jacqu | +0.357 |
marginalized | +0.348 |
Neg logit contributions | |
TIT | -0.412 |
\\\\\\\\ | -0.407 |
OTAL | -0.345 |
Merit | -0.340 |
Sessions | -0.336 |
Token | company |
Token ID | 1664 |
Feature activation | -5.94e-02 |
Pos logit contributions | |
ration | +0.180 |
opoly | +0.179 |
abled | +0.173 |
Jacqu | +0.171 |
marginalized | +0.166 |
Neg logit contributions | |
TIT | -0.222 |
\\\\\\\\ | -0.220 |
OTAL | -0.188 |
Merit | -0.186 |
Sessions | -0.185 |
Token | Vin |
Token ID | 11820 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
TIT | +0.048 |
\\\\\\\\ | +0.047 |
OTAL | +0.041 |
Merit | +0.040 |
Sessions | +0.040 |
Neg logit contributions | |
opoly | -0.040 |
ration | -0.040 |
abled | -0.039 |
Jacqu | -0.038 |
marginalized | -0.037 |
Token | od |
Token ID | 375 |
Feature activation | -6.35e-02 |
Pos logit contributions | |
TIT | +0.117 |
\\\\\\\\ | +0.115 |
OTAL | +0.094 |
Merit | +0.091 |
Bank | +0.090 |
Neg logit contributions | |
ration | -0.154 |
opoly | -0.153 |
abled | -0.149 |
Jacqu | -0.148 |
marginalized | -0.145 |
Token | Then |
Token ID | 3244 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
TIT | +0.049 |
\\\\\\\\ | +0.048 |
OTAL | +0.041 |
Merit | +0.041 |
Sessions | +0.040 |
Neg logit contributions | |
ration | -0.038 |
opoly | -0.037 |
abled | -0.036 |
Jacqu | -0.035 |
marginalized | -0.035 |
Token | he |
Token ID | 339 |
Feature activation | +5.40e-02 |
Pos logit contributions | |
TIT | +0.139 |
\\\\\\\\ | +0.137 |
OTAL | +0.118 |
Merit | +0.116 |
Sessions | +0.115 |
Neg logit contributions | |
opoly | -0.108 |
ration | -0.108 |
abled | -0.104 |
Jacqu | -0.103 |
marginalized | -0.100 |
Token | projected |
Token ID | 13301 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
opoly | +0.035 |
ration | +0.034 |
abled | +0.033 |
Jacqu | +0.033 |
raq | +0.032 |
Neg logit contributions | |
TIT | -0.045 |
\\\\\\\\ | -0.044 |
Sessions | -0.038 |
OTAL | -0.038 |
Tuc | -0.038 |
Token | a |
Token ID | 257 |
Feature activation | -3.55e-02 |
Pos logit contributions | |
TIT | +0.108 |
\\\\\\\\ | +0.105 |
OTAL | +0.091 |
Sessions | +0.091 |
Tuc | +0.090 |
Neg logit contributions | |
opoly | -0.074 |
ration | -0.073 |
abled | -0.071 |
Jacqu | -0.069 |
marginalized | -0.067 |
Token | movie |
Token ID | 3807 |
Feature activation | -9.09e-02 |
Pos logit contributions | |
TIT | +0.030 |
\\\\\\\\ | +0.030 |
OTAL | +0.026 |
Tuc | +0.025 |
Sessions | +0.025 |
Neg logit contributions | |
opoly | -0.023 |
ration | -0.022 |
abled | -0.022 |
Jacqu | -0.021 |
marginalized | -0.021 |
Token | onto |
Token ID | 4291 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
TIT | +0.078 |
\\\\\\\\ | +0.077 |
OTAL | +0.065 |
Sessions | +0.065 |
Tuc | +0.065 |
Neg logit contributions | |
opoly | -0.057 |
ration | -0.057 |
abled | -0.055 |
Jacqu | -0.054 |
marginalized | -0.053 |
Token | it |
Token ID | 340 |
Feature activation | -5.10e-02 |
Pos logit contributions | |
ration | +0.208 |
opoly | +0.207 |
abled | +0.200 |
Jacqu | +0.197 |
marginalized | +0.192 |
Neg logit contributions | |
TIT | -0.305 |
\\\\\\\\ | -0.300 |
OTAL | -0.260 |
Merit | -0.256 |
Sessions | -0.256 |
Token | . |
Token ID | 13 |
Feature activation | +2.65e-02 |
Pos logit contributions | |
TIT | +0.041 |
\\\\\\\\ | +0.041 |
OTAL | +0.035 |
Sessions | +0.034 |
Merit | +0.034 |
Neg logit contributions | |
opoly | -0.034 |
ration | -0.034 |
abled | -0.033 |
Jacqu | -0.033 |
marginalized | -0.032 |
Token |
|
Token ID | 198 |
Feature activation | +2.77e-02 |
Pos logit contributions | |
ration | +0.017 |
opoly | +0.017 |
abled | +0.017 |
Jacqu | +0.016 |
marginalized | +0.016 |
Neg logit contributions | |
TIT | -0.022 |
\\\\\\\\ | -0.022 |
OTAL | -0.019 |
Merit | -0.019 |
Sessions | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | +2.65e-02 |
Pos logit contributions | |
ration | +0.018 |
opoly | +0.018 |
abled | +0.017 |
Jacqu | +0.017 |
boarded | +0.017 |
Neg logit contributions | |
TIT | -0.023 |
\\\\\\\\ | -0.023 |
OTAL | -0.020 |
Merit | -0.020 |
Bank | -0.020 |
Token | Then |
Token ID | 6423 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
ration | +0.020 |
opoly | +0.020 |
abled | +0.020 |
Jacqu | +0.020 |
marginalized | +0.019 |
Neg logit contributions | |
TIT | -0.019 |
\\\\\\\\ | -0.019 |
OTAL | -0.016 |
Merit | -0.016 |
Bank | -0.016 |
Token | mark |
Token ID | 4102 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
ration | +0.104 |
opoly | +0.104 |
abled | +0.100 |
Jacqu | +0.100 |
marginalized | +0.097 |
Neg logit contributions | |
TIT | -0.148 |
\\\\\\\\ | -0.145 |
OTAL | -0.126 |
Merit | -0.124 |
Bank | -0.123 |
Token | ) |
Token ID | 8 |
Feature activation | -5.54e-02 |
Pos logit contributions | |
ration | +0.214 |
opoly | +0.214 |
abled | +0.207 |
Jacqu | +0.206 |
marginalized | +0.200 |
Neg logit contributions | |
TIT | -0.235 |
\\\\\\\\ | -0.232 |
OTAL | -0.197 |
Merit | -0.193 |
Bank | -0.191 |
Token | in |
Token ID | 287 |
Feature activation | +7.75e-02 |
Pos logit contributions | |
TIT | +0.047 |
\\\\\\\\ | +0.046 |
OTAL | +0.040 |
Bank | +0.039 |
Tuc | +0.039 |
Neg logit contributions | |
opoly | -0.035 |
ration | -0.035 |
abled | -0.034 |
Jacqu | -0.034 |
marginalized | -0.033 |
Token | … |
Token ID | 3926 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
opoly | +0.050 |
ration | +0.050 |
abled | +0.049 |
Jacqu | +0.048 |
marginalized | +0.046 |
Neg logit contributions | |
TIT | -0.065 |
\\\\\\\\ | -0.064 |
OTAL | -0.055 |
Merit | -0.054 |
Bank | -0.054 |
Token | E |
Token ID | 412 |
Feature activation | +6.22e-02 |
Pos logit contributions | |
ration | +0.102 |
opoly | +0.102 |
abled | +0.099 |
Jacqu | +0.098 |
marginalized | +0.095 |
Neg logit contributions | |
TIT | -0.133 |
\\\\\\\\ | -0.131 |
OTAL | -0.113 |
Merit | -0.110 |
Bank | -0.110 |
Token | – |
Token ID | 1906 |
Feature activation | +4.42e-01 |
Pos logit contributions | |
ration | +0.042 |
opoly | +0.042 |
abled | +0.041 |
Jacqu | +0.040 |
marginalized | +0.039 |
Neg logit contributions | |
TIT | -0.051 |
\\\\\\\\ | -0.050 |
OTAL | -0.043 |
Merit | -0.042 |
Bank | -0.041 |
Token | MA |
Token ID | 5673 |
Feature activation | -4.72e-02 |
Pos logit contributions | |
ration | +0.309 |
opoly | +0.308 |
abled | +0.299 |
Jacqu | +0.296 |
marginalized | +0.288 |
Neg logit contributions | |
TIT | -0.351 |
\\\\\\\\ | -0.346 |
OTAL | -0.294 |
Merit | -0.288 |
Bank | -0.287 |
Token | IL |
Token ID | 4146 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
TIT | +0.038 |
\\\\\\\\ | +0.038 |
OTAL | +0.033 |
Bank | +0.032 |
Merit | +0.031 |
Neg logit contributions | |
opoly | -0.032 |
ration | -0.032 |
abled | -0.031 |
Jacqu | -0.030 |
marginalized | -0.030 |
Token | ? |
Token ID | 30 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
opoly | +0.202 |
ration | +0.202 |
abled | +0.196 |
Jacqu | +0.193 |
marginalized | +0.188 |
Neg logit contributions | |
TIT | -0.243 |
\\\\\\\\ | -0.238 |
OTAL | -0.205 |
Merit | -0.200 |
Bank | -0.199 |
Token | No |
Token ID | 1400 |
Feature activation | -7.87e-02 |
Pos logit contributions | |
opoly | +0.185 |
ration | +0.185 |
abled | +0.180 |
Jacqu | +0.176 |
marginalized | +0.172 |
Neg logit contributions | |
TIT | -0.197 |
\\\\\\\\ | -0.193 |
OTAL | -0.164 |
Merit | -0.160 |
Tuc | -0.160 |
Token | , |
Token ID | 11 |
Feature activation | +9.19e-02 |
Pos logit contributions | |
TIT | +0.064 |
\\\\\\\\ | +0.063 |
OTAL | +0.054 |
Merit | +0.053 |
Bank | +0.053 |
Neg logit contributions | |
opoly | -0.053 |
ration | -0.053 |
abled | -0.051 |
Jacqu | -0.051 |
marginalized | -0.049 |
Token | ." |
Token ID | 526 |
Feature activation | +8.31e-02 |
Pos logit contributions | |
TIT | +0.194 |
\\\\\\\\ | +0.192 |
OTAL | +0.163 |
Merit | +0.160 |
Bank | +0.159 |
Neg logit contributions | |
ration | -0.169 |
opoly | -0.169 |
abled | -0.164 |
Jacqu | -0.162 |
marginalized | -0.157 |
Token | 1998 |
Token ID | 7795 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
ration | +0.054 |
opoly | +0.053 |
abled | +0.052 |
Jacqu | +0.050 |
marginalized | +0.049 |
Neg logit contributions | |
TIT | -0.070 |
\\\\\\\\ | -0.069 |
OTAL | -0.060 |
Merit | -0.059 |
Sessions | -0.059 |
Token | annual |
Token ID | 5079 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
TIT | +0.249 |
\\\\\\\\ | +0.246 |
OTAL | +0.210 |
Merit | +0.206 |
Bank | +0.204 |
Neg logit contributions | |
ration | -0.214 |
opoly | -0.214 |
abled | -0.207 |
Jacqu | -0.205 |
marginalized | -0.199 |
Token | report |
Token ID | 989 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
TIT | +0.130 |
\\\\\\\\ | +0.128 |
OTAL | +0.112 |
Sessions | +0.111 |
Merit | +0.111 |
Neg logit contributions | |
opoly | -0.088 |
ration | -0.086 |
abled | -0.084 |
Jacqu | -0.081 |
marginalized | -0.080 |
Token | , |
Token ID | 11 |
Feature activation | +1.87e-02 |
Pos logit contributions | |
ration | +0.089 |
opoly | +0.089 |
abled | +0.086 |
Jacqu | +0.085 |
marginalized | +0.083 |
Neg logit contributions | |
TIT | -0.106 |
\\\\\\\\ | -0.105 |
OTAL | -0.090 |
Merit | -0.088 |
Bank | -0.087 |
Token | Joyce |
Token ID | 25936 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
opoly | +0.013 |
ration | +0.013 |
abled | +0.012 |
Jacqu | +0.012 |
marginalized | +0.012 |
Neg logit contributions | |
TIT | -0.015 |
\\\\\\\\ | -0.015 |
OTAL | -0.013 |
Merit | -0.013 |
Sessions | -0.013 |
Token | Foundation |
Token ID | 5693 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
ration | +0.357 |
opoly | +0.355 |
abled | +0.344 |
Jacqu | +0.340 |
marginalized | +0.331 |
Neg logit contributions | |
TIT | -0.429 |
\\\\\\\\ | -0.424 |
OTAL | -0.362 |
Merit | -0.356 |
Bank | -0.353 |
Token | , |
Token ID | 11 |
Feature activation | +2.79e-02 |
Pos logit contributions | |
ration | +0.154 |
opoly | +0.153 |
abled | +0.149 |
Jacqu | +0.147 |
marginalized | +0.143 |
Neg logit contributions | |
TIT | -0.166 |
\\\\\\\\ | -0.164 |
OTAL | -0.139 |
Merit | -0.136 |
Bank | -0.135 |
Token | p |
Token ID | 279 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
ration | +0.019 |
opoly | +0.019 |
abled | +0.018 |
Jacqu | +0.018 |
marginalized | +0.017 |
Neg logit contributions | |
TIT | -0.023 |
\\\\\\\\ | -0.022 |
OTAL | -0.019 |
Merit | -0.019 |
Sessions | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +4.85e-02 |
Pos logit contributions | |
opoly | +0.099 |
ration | +0.099 |
abled | +0.096 |
Jacqu | +0.095 |
marginalized | +0.092 |
Neg logit contributions | |
TIT | -0.121 |
\\\\\\\\ | -0.120 |
OTAL | -0.102 |
Merit | -0.100 |
Tuc | -0.099 |
Token | 21 |
Token ID | 2310 |
Feature activation | -6.54e-03 |
Pos logit contributions | |
ration | +0.036 |
opoly | +0.035 |
abled | +0.035 |
Jacqu | +0.034 |
marginalized | +0.033 |
Neg logit contributions | |
TIT | -0.037 |
\\\\\\\\ | -0.036 |
OTAL | -0.031 |
Merit | -0.030 |
Bank | -0.030 |
Token | o |
Token ID | 267 |
Feature activation | +4.11e-02 |
Pos logit contributions | |
opoly | +0.102 |
ration | +0.101 |
abled | +0.099 |
Jacqu | +0.097 |
marginalized | +0.094 |
Neg logit contributions | |
TIT | -0.132 |
\\\\\\\\ | -0.130 |
OTAL | -0.112 |
Merit | -0.110 |
Tuc | -0.110 |
Token | K |
Token ID | 509 |
Feature activation | -3.48e-02 |
Pos logit contributions | |
opoly | +0.023 |
ration | +0.023 |
abled | +0.023 |
Jacqu | +0.022 |
marginalized | +0.022 |
Neg logit contributions | |
TIT | -0.038 |
\\\\\\\\ | -0.037 |
OTAL | -0.032 |
Bank | -0.032 |
Merit | -0.032 |
Token | ā |
Token ID | 10235 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
TIT | +0.029 |
\\\\\\\\ | +0.029 |
OTAL | +0.025 |
Bank | +0.024 |
Merit | +0.024 |
Neg logit contributions | |
ration | -0.023 |
opoly | -0.023 |
abled | -0.022 |
Jacqu | -0.022 |
marginalized | -0.021 |
Token | n |
Token ID | 77 |
Feature activation | +8.54e-02 |
Pos logit contributions | |
ration | +0.075 |
opoly | +0.074 |
abled | +0.072 |
Jacqu | +0.071 |
marginalized | +0.069 |
Neg logit contributions | |
TIT | -0.107 |
\\\\\\\\ | -0.106 |
OTAL | -0.092 |
Merit | -0.090 |
Bank | -0.090 |
Token | ep |
Token ID | 538 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
ration | +0.073 |
opoly | +0.072 |
abled | +0.070 |
Jacqu | +0.070 |
marginalized | +0.069 |
Neg logit contributions | |
TIT | -0.054 |
\\\\\\\\ | -0.054 |
OTAL | -0.044 |
Merit | -0.043 |
Bank | -0.042 |
Token | ō |
Token ID | 13090 |
Feature activation | +4.45e-01 |
Pos logit contributions | |
TIT | +0.121 |
\\\\\\\\ | +0.120 |
OTAL | +0.108 |
Merit | +0.107 |
Bank | +0.106 |
Neg logit contributions | |
ration | -0.032 |
opoly | -0.031 |
abled | -0.029 |
Jacqu | -0.029 |
marginalized | -0.027 |
Token | iki |
Token ID | 5580 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
ration | +0.274 |
opoly | +0.273 |
abled | +0.263 |
Jacqu | +0.260 |
marginalized | +0.252 |
Neg logit contributions | |
TIT | -0.390 |
\\\\\\\\ | -0.386 |
OTAL | -0.334 |
Merit | -0.328 |
Bank | -0.325 |
Token | , |
Token ID | 11 |
Feature activation | -2.42e-02 |
Pos logit contributions | |
opoly | +0.112 |
ration | +0.111 |
abled | +0.108 |
Jacqu | +0.106 |
marginalized | +0.104 |
Neg logit contributions | |
TIT | -0.130 |
\\\\\\\\ | -0.129 |
OTAL | -0.110 |
Merit | -0.107 |
Bank | -0.107 |
Token | k |
Token ID | 479 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
TIT | +0.021 |
\\\\\\\\ | +0.021 |
OTAL | +0.018 |
Merit | +0.018 |
Tuc | +0.018 |
Neg logit contributions | |
opoly | -0.015 |
ration | -0.015 |
abled | -0.014 |
Jacqu | -0.014 |
marginalized | -0.014 |
Token | ona |
Token ID | 4450 |
Feature activation | +4.61e-03 |
Pos logit contributions | |
ration | +0.125 |
opoly | +0.123 |
abled | +0.119 |
Jacqu | +0.119 |
marginalized | +0.117 |
Neg logit contributions | |
TIT | -0.153 |
\\\\\\\\ | -0.150 |
OTAL | -0.130 |
Bank | -0.127 |
Merit | -0.126 |
Token | m |
Token ID | 285 |
Feature activation | -5.76e-02 |
Pos logit contributions | |
opoly | +0.003 |
ration | +0.003 |
abled | +0.003 |
Jacqu | +0.003 |
marginalized | +0.003 |
Neg logit contributions | |
TIT | -0.004 |
\\\\\\\\ | -0.004 |
OTAL | -0.003 |
Merit | -0.003 |
Tuc | -0.003 |
Token | was |
Token ID | 373 |
Feature activation | -4.95e-02 |
Pos logit contributions | |
TIT | +0.022 |
\\\\\\\\ | +0.022 |
OTAL | +0.019 |
Merit | +0.018 |
Sessions | +0.018 |
Neg logit contributions | |
opoly | -0.020 |
ration | -0.020 |
abled | -0.020 |
Jacqu | -0.019 |
marginalized | -0.019 |
Token | medicine |
Token ID | 9007 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
TIT | +0.042 |
\\\\\\\\ | +0.041 |
OTAL | +0.036 |
Merit | +0.035 |
Sessions | +0.035 |
Neg logit contributions | |
opoly | -0.032 |
ration | -0.032 |
abled | -0.031 |
Jacqu | -0.030 |
marginalized | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | -7.49e-03 |
Pos logit contributions | |
opoly | +0.109 |
ration | +0.108 |
abled | +0.105 |
Jacqu | +0.104 |
marginalized | +0.100 |
Neg logit contributions | |
TIT | -0.145 |
\\\\\\\\ | -0.143 |
OTAL | -0.123 |
Merit | -0.121 |
Sessions | -0.120 |
Token | I |
Token ID | 314 |
Feature activation | +9.44e-02 |
Pos logit contributions | |
TIT | +0.006 |
\\\\\\\\ | +0.006 |
OTAL | +0.005 |
Merit | +0.005 |
Sessions | +0.005 |
Neg logit contributions | |
ration | -0.005 |
opoly | -0.005 |
abled | -0.005 |
boarded | -0.005 |
marginalized | -0.005 |
Token | saw |
Token ID | 2497 |
Feature activation | -6.32e-02 |
Pos logit contributions | |
opoly | +0.065 |
ration | +0.064 |
abled | +0.063 |
Jacqu | +0.062 |
marginalized | +0.060 |
Neg logit contributions | |
TIT | -0.075 |
\\\\\\\\ | -0.074 |
OTAL | -0.064 |
Merit | -0.062 |
Bank | -0.062 |
Token | how |
Token ID | 703 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
TIT | +0.056 |
\\\\\\\\ | +0.056 |
OTAL | +0.049 |
Sessions | +0.048 |
Merit | +0.048 |
Neg logit contributions | |
opoly | -0.037 |
ration | -0.036 |
abled | -0.036 |
Jacqu | -0.035 |
rift | -0.034 |
Token | it |
Token ID | 340 |
Feature activation | -1.42e-03 |
Pos logit contributions | |
opoly | +0.130 |
ration | +0.128 |
abled | +0.126 |
Jacqu | +0.123 |
rift | +0.119 |
Neg logit contributions | |
TIT | -0.161 |
\\\\\\\\ | -0.159 |
OTAL | -0.137 |
Merit | -0.135 |
Sessions | -0.134 |
Token | not |
Token ID | 407 |
Feature activation | +7.10e-03 |
Pos logit contributions | |
TIT | +0.001 |
\\\\\\\\ | +0.001 |
OTAL | +0.001 |
Sessions | +0.001 |
Merit | +0.001 |
Neg logit contributions | |
opoly | -0.001 |
ration | -0.001 |
abled | -0.001 |
Jacqu | -0.001 |
rift | -0.001 |
Token | only |
Token ID | 691 |
Feature activation | -3.72e-02 |
Pos logit contributions | |
opoly | +0.005 |
ration | +0.005 |
abled | +0.005 |
Jacqu | +0.005 |
rift | +0.004 |
Neg logit contributions | |
TIT | -0.006 |
\\\\\\\\ | -0.006 |
OTAL | -0.005 |
Merit | -0.005 |
Bank | -0.005 |
Token | truly |
Token ID | 4988 |
Feature activation | +3.35e-02 |
Pos logit contributions | |
TIT | +0.030 |
\\\\\\\\ | +0.029 |
OTAL | +0.025 |
Sessions | +0.025 |
Merit | +0.025 |
Neg logit contributions | |
opoly | -0.025 |
ration | -0.025 |
abled | -0.024 |
Jacqu | -0.024 |
rift | -0.023 |
Token | helped |
Token ID | 4193 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
opoly | +0.023 |
ration | +0.022 |
abled | +0.022 |
Jacqu | +0.022 |
rift | +0.021 |
Neg logit contributions | |
TIT | -0.027 |
\\\\\\\\ | -0.027 |
OTAL | -0.023 |
Merit | -0.023 |
Sessions | -0.022 |
Token | - |
Token ID | 12 |
Feature activation | +2.82e-02 |
Pos logit contributions | |
ration | +0.096 |
opoly | +0.096 |
abled | +0.093 |
Jacqu | +0.092 |
marginalized | +0.089 |
Neg logit contributions | |
TIT | -0.127 |
\\\\\\\\ | -0.126 |
OTAL | -0.108 |
Merit | -0.107 |
Sessions | -0.106 |
Token | Kar |
Token ID | 37753 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
ration | +0.022 |
opoly | +0.022 |
abled | +0.021 |
Jacqu | +0.021 |
marginalized | +0.021 |
Neg logit contributions | |
TIT | -0.020 |
\\\\\\\\ | -0.020 |
OTAL | -0.016 |
Merit | -0.016 |
Bank | -0.016 |
Token | ur |
Token ID | 333 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
ration | +0.178 |
opoly | +0.177 |
abled | +0.171 |
Jacqu | +0.171 |
marginalized | +0.167 |
Neg logit contributions | |
TIT | -0.189 |
\\\\\\\\ | -0.186 |
OTAL | -0.158 |
Merit | -0.154 |
Bank | -0.153 |
Token | National |
Token ID | 2351 |
Feature activation | +3.01e-02 |
Pos logit contributions | |
ration | +0.097 |
opoly | +0.096 |
abled | +0.093 |
Jacqu | +0.092 |
marginalized | +0.090 |
Neg logit contributions | |
TIT | -0.127 |
\\\\\\\\ | -0.125 |
OTAL | -0.108 |
Merit | -0.107 |
Bank | -0.105 |
Token | Highway |
Token ID | 14914 |
Feature activation | +2.82e-02 |
Pos logit contributions | |
ration | +0.022 |
opoly | +0.022 |
abled | +0.021 |
Jacqu | +0.021 |
marginalized | +0.021 |
Neg logit contributions | |
TIT | -0.023 |
\\\\\\\\ | -0.022 |
OTAL | -0.019 |
Merit | -0.018 |
Bank | -0.018 |
Token | ( |
Token ID | 7 |
Feature activation | +1.91e-02 |
Pos logit contributions | |
ration | +0.020 |
opoly | +0.020 |
abled | +0.019 |
Jacqu | +0.019 |
marginalized | +0.018 |
Neg logit contributions | |
TIT | -0.022 |
\\\\\\\\ | -0.022 |
OTAL | -0.019 |
Merit | -0.019 |
Bank | -0.018 |
Token | NH |
Token ID | 33863 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
ration | +0.014 |
opoly | +0.014 |
abled | +0.014 |
Jacqu | +0.014 |
marginalized | +0.013 |
Neg logit contributions | |
TIT | -0.014 |
\\\\\\\\ | -0.014 |
OTAL | -0.012 |
Merit | -0.012 |
Bank | -0.012 |
Token | 7 |
Token ID | 22 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
TIT | +0.180 |
\\\\\\\\ | +0.177 |
OTAL | +0.147 |
Merit | +0.144 |
Bank | +0.142 |
Neg logit contributions | |
ration | -0.197 |
opoly | -0.196 |
abled | -0.191 |
Jacqu | -0.189 |
marginalized | -0.185 |
Token | ) |
Token ID | 8 |
Feature activation | -9.21e-02 |
Pos logit contributions | |
ration | +0.122 |
opoly | +0.122 |
abled | +0.118 |
Jacqu | +0.118 |
marginalized | +0.115 |
Neg logit contributions | |
TIT | -0.107 |
\\\\\\\\ | -0.106 |
OTAL | -0.088 |
Merit | -0.086 |
Bank | -0.084 |
Token | is |
Token ID | 318 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
TIT | +0.078 |
\\\\\\\\ | +0.076 |
OTAL | +0.066 |
Merit | +0.065 |
Bank | +0.064 |
Neg logit contributions | |
opoly | -0.060 |
ration | -0.060 |
abled | -0.058 |
Jacqu | -0.057 |
marginalized | -0.055 |
Token | the |
Token ID | 262 |
Feature activation | +5.39e-02 |
Pos logit contributions | |
ration | +0.009 |
opoly | +0.009 |
abled | +0.009 |
Jacqu | +0.009 |
marginalized | +0.008 |
Neg logit contributions | |
TIT | -0.012 |
\\\\\\\\ | -0.012 |
OTAL | -0.010 |
Merit | -0.010 |
Bank | -0.010 |
Token | of |
Token ID | 286 |
Feature activation | +3.47e-02 |
Pos logit contributions | |
ration | +0.095 |
opoly | +0.094 |
abled | +0.091 |
Jacqu | +0.090 |
marginalized | +0.088 |
Neg logit contributions | |
TIT | -0.126 |
\\\\\\\\ | -0.124 |
OTAL | -0.107 |
Merit | -0.105 |
Bank | -0.104 |
Token | a |
Token ID | 257 |
Feature activation | +2.77e-02 |
Pos logit contributions | |
opoly | +0.023 |
ration | +0.023 |
abled | +0.022 |
Jacqu | +0.022 |
rift | +0.021 |
Neg logit contributions | |
TIT | -0.029 |
\\\\\\\\ | -0.028 |
OTAL | -0.024 |
Sessions | -0.024 |
Merit | -0.024 |
Token | redesign |
Token ID | 27135 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
opoly | +0.019 |
ration | +0.018 |
abled | +0.018 |
Jacqu | +0.018 |
rift | +0.017 |
Neg logit contributions | |
TIT | -0.023 |
\\\\\\\\ | -0.022 |
OTAL | -0.019 |
Sessions | -0.019 |
Merit | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | -3.02e-03 |
Pos logit contributions | |
opoly | +0.073 |
ration | +0.072 |
abled | +0.069 |
Jacqu | +0.069 |
marginalized | +0.067 |
Neg logit contributions | |
TIT | -0.085 |
\\\\\\\\ | -0.084 |
OTAL | -0.072 |
Merit | -0.070 |
Sessions | -0.070 |
Token |
|
Token ID | 198 |
Feature activation | +2.85e-02 |
Pos logit contributions | |
TIT | +0.002 |
\\\\\\\\ | +0.002 |
OTAL | +0.002 |
Sessions | +0.002 |
Merit | +0.002 |
Neg logit contributions | |
ration | -0.002 |
opoly | -0.002 |
abled | -0.002 |
Jacqu | -0.002 |
marginalized | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +4.08e-02 |
Pos logit contributions | |
ration | +0.019 |
opoly | +0.019 |
abled | +0.018 |
boarded | +0.018 |
Jacqu | +0.018 |
Neg logit contributions | |
TIT | -0.024 |
\\\\\\\\ | -0.023 |
OTAL | -0.020 |
Merit | -0.020 |
Bank | -0.020 |
Token | R |
Token ID | 49 |
Feature activation | -2.26e-02 |
Pos logit contributions | |
ration | +0.031 |
opoly | +0.031 |
Jacqu | +0.030 |
abled | +0.030 |
marginalized | +0.029 |
Neg logit contributions | |
TIT | -0.030 |
\\\\\\\\ | -0.029 |
OTAL | -0.025 |
Merit | -0.025 |
Bank | -0.024 |
Token | end |
Token ID | 437 |
Feature activation | -3.68e-02 |
Pos logit contributions | |
TIT | +0.016 |
\\\\\\\\ | +0.016 |
OTAL | +0.013 |
Merit | +0.013 |
Bank | +0.013 |
Neg logit contributions | |
ration | -0.017 |
opoly | -0.017 |
abled | -0.017 |
Jacqu | -0.017 |
marginalized | -0.016 |
Token | ering |
Token ID | 1586 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
TIT | +0.031 |
\\\\\\\\ | +0.031 |
OTAL | +0.027 |
Merit | +0.026 |
Sessions | +0.026 |
Neg logit contributions | |
ration | -0.024 |
opoly | -0.023 |
Jacqu | -0.022 |
abled | -0.022 |
marginalized | -0.022 |
Token | of |
Token ID | 286 |
Feature activation | +3.97e-02 |
Pos logit contributions | |
ration | +0.089 |
opoly | +0.088 |
abled | +0.086 |
Jacqu | +0.085 |
marginalized | +0.082 |
Neg logit contributions | |
TIT | -0.118 |
\\\\\\\\ | -0.116 |
OTAL | -0.100 |
Merit | -0.098 |
Bank | -0.097 |
Token | the |
Token ID | 262 |
Feature activation | +6.27e-02 |
Pos logit contributions | |
opoly | +0.027 |
ration | +0.027 |
abled | +0.026 |
Jacqu | +0.026 |
marginalized | +0.025 |
Neg logit contributions | |
TIT | -0.032 |
\\\\\\\\ | -0.032 |
OTAL | -0.027 |
Merit | -0.027 |
Bank | -0.027 |
Token | s |
Token ID | 82 |
Feature activation | -3.02e-02 |
Pos logit contributions | |
TIT | +0.020 |
\\\\\\\\ | +0.019 |
OTAL | +0.016 |
Merit | +0.016 |
Bank | +0.016 |
Neg logit contributions | |
ration | -0.017 |
opoly | -0.017 |
abled | -0.016 |
Jacqu | -0.016 |
marginalized | -0.016 |
Token | cept |
Token ID | 984 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
TIT | +0.030 |
\\\\\\\\ | +0.029 |
OTAL | +0.026 |
Merit | +0.025 |
Bank | +0.025 |
Neg logit contributions | |
ration | -0.015 |
opoly | -0.015 |
abled | -0.014 |
Jacqu | -0.014 |
marginalized | -0.014 |
Token | ics |
Token ID | 873 |
Feature activation | +8.15e-05 |
Pos logit contributions | |
ration | +0.114 |
opoly | +0.114 |
abled | +0.111 |
Jacqu | +0.110 |
marginalized | +0.107 |
Neg logit contributions | |
TIT | -0.097 |
\\\\\\\\ | -0.096 |
OTAL | -0.079 |
Merit | -0.078 |
Bank | -0.077 |
Token | who |
Token ID | 508 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
opoly | +0.000 |
ration | +0.000 |
abled | +0.000 |
Jacqu | +0.000 |
marginalized | +0.000 |
Neg logit contributions | |
TIT | -0.000 |
\\\\\\\\ | -0.000 |
OTAL | -0.000 |
Merit | -0.000 |
Tuc | -0.000 |
Token | claim |
Token ID | 1624 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
opoly | +0.169 |
ration | +0.168 |
abled | +0.164 |
Jacqu | +0.162 |
marginalized | +0.156 |
Neg logit contributions | |
TIT | -0.201 |
\\\\\\\\ | -0.198 |
OTAL | -0.169 |
Merit | -0.167 |
Sessions | -0.166 |
Token | the |
Token ID | 262 |
Feature activation | -3.97e-03 |
Pos logit contributions | |
ration | +0.076 |
opoly | +0.075 |
abled | +0.072 |
Jacqu | +0.072 |
marginalized | +0.069 |
Neg logit contributions | |
TIT | -0.119 |
\\\\\\\\ | -0.118 |
OTAL | -0.103 |
Merit | -0.101 |
Bank | -0.100 |
Token | lifetime |
Token ID | 10869 |
Feature activation | -8.39e-02 |
Pos logit contributions | |
TIT | +0.003 |
\\\\\\\\ | +0.003 |
OTAL | +0.003 |
Merit | +0.003 |
Sessions | +0.002 |
Neg logit contributions | |
opoly | -0.003 |
ration | -0.003 |
abled | -0.003 |
Jacqu | -0.003 |
marginalized | -0.003 |
Token | of |
Token ID | 286 |
Feature activation | -3.09e-02 |
Pos logit contributions | |
TIT | +0.070 |
\\\\\\\\ | +0.069 |
OTAL | +0.059 |
Merit | +0.058 |
Bank | +0.058 |
Neg logit contributions | |
ration | -0.055 |
opoly | -0.055 |
abled | -0.053 |
Jacqu | -0.053 |
marginalized | -0.051 |
Token | CO |
Token ID | 7375 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
TIT | +0.018 |
\\\\\\\\ | +0.018 |
OTAL | +0.014 |
Merit | +0.014 |
Bank | +0.014 |
Neg logit contributions | |
ration | -0.028 |
opoly | -0.028 |
abled | -0.027 |
Jacqu | -0.027 |
marginalized | -0.026 |
Token | 2 |
Token ID | 362 |
Feature activation | -9.24e-02 |
Pos logit contributions | |
\\\\\\\\ | +0.291 |
TIT | +0.291 |
Merit | +0.246 |
OTAL | +0.244 |
Bank | +0.239 |
Neg logit contributions | |
ration | -0.248 |
opoly | -0.245 |
abled | -0.236 |
Jacqu | -0.231 |
marginalized | -0.227 |
Token | in |
Token ID | 287 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
TIT | +0.077 |
\\\\\\\\ | +0.076 |
OTAL | +0.065 |
Merit | +0.064 |
Bank | +0.063 |
Neg logit contributions | |
ration | -0.061 |
opoly | -0.061 |
abled | -0.059 |
Jacqu | -0.059 |
marginalized | -0.057 |
Token | the |
Token ID | 262 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
TIT | +0.172 |
\\\\\\\\ | +0.169 |
OTAL | +0.146 |
Merit | +0.144 |
Sessions | +0.143 |
Neg logit contributions | |
ration | -0.130 |
opoly | -0.129 |
abled | -0.125 |
Jacqu | -0.122 |
boarded | -0.118 |
Token | brilliant |
Token ID | 10457 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
TIT | +0.083 |
\\\\\\\\ | +0.082 |
OTAL | +0.068 |
Merit | +0.067 |
Bank | +0.066 |
Neg logit contributions | |
ration | -0.092 |
opoly | -0.092 |
abled | -0.089 |
Jacqu | -0.088 |
marginalized | -0.086 |
Token | recording |
Token ID | 8296 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
TIT | +0.152 |
\\\\\\\\ | +0.150 |
OTAL | +0.129 |
Merit | +0.127 |
Sessions | +0.126 |
Neg logit contributions | |
ration | -0.118 |
opoly | -0.118 |
abled | -0.114 |
Jacqu | -0.111 |
marginalized | -0.108 |
Token | engineer |
Token ID | 11949 |
Feature activation | +6.15e-02 |
Pos logit contributions | |
TIT | +0.216 |
\\\\\\\\ | +0.213 |
OTAL | +0.182 |
Merit | +0.179 |
Sessions | +0.178 |
Neg logit contributions | |
opoly | -0.172 |
ration | -0.172 |
abled | -0.166 |
Jacqu | -0.164 |
marginalized | -0.159 |
Token | Cecil |
Token ID | 32234 |
Feature activation | +7.51e-02 |
Pos logit contributions | |
ration | +0.039 |
opoly | +0.039 |
abled | +0.038 |
Jacqu | +0.037 |
marginalized | +0.036 |
Neg logit contributions | |
TIT | -0.052 |
\\\\\\\\ | -0.052 |
OTAL | -0.045 |
Merit | -0.044 |
Sessions | -0.044 |
Token | English |
Token ID | 3594 |
Feature activation | -3.41e-02 |
Pos logit contributions | |
ration | +0.055 |
opoly | +0.055 |
abled | +0.054 |
Jacqu | +0.053 |
marginalized | +0.052 |
Neg logit contributions | |
TIT | -0.056 |
\\\\\\\\ | -0.056 |
OTAL | -0.047 |
Merit | -0.046 |
Sessions | -0.046 |
Token | . |
Token ID | 13 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
TIT | +0.030 |
\\\\\\\\ | +0.029 |
OTAL | +0.025 |
Merit | +0.025 |
Sessions | +0.025 |
Neg logit contributions | |
ration | -0.021 |
opoly | -0.021 |
abled | -0.020 |
Jacqu | -0.020 |
marginalized | -0.020 |
Token | I |
Token ID | 314 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
TIT | +0.101 |
\\\\\\\\ | +0.100 |
OTAL | +0.085 |
Sessions | +0.084 |
Tuc | +0.083 |
Neg logit contributions | |
ration | -0.089 |
opoly | -0.088 |
abled | -0.086 |
boarded | -0.082 |
marginalized | -0.082 |
Token | came |
Token ID | 1625 |
Feature activation | -4.14e-02 |
Pos logit contributions | |
TIT | +0.086 |
\\\\\\\\ | +0.085 |
OTAL | +0.072 |
Bank | +0.070 |
Merit | +0.070 |
Neg logit contributions | |
opoly | -0.079 |
ration | -0.079 |
abled | -0.077 |
Jacqu | -0.075 |
marginalized | -0.073 |
Token | in |
Token ID | 287 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
TIT | +0.031 |
\\\\\\\\ | +0.031 |
OTAL | +0.026 |
Merit | +0.025 |
Bank | +0.025 |
Neg logit contributions | |
ration | -0.031 |
opoly | -0.031 |
abled | -0.030 |
Jacqu | -0.029 |
marginalized | -0.029 |
Token | on |
Token ID | 319 |
Feature activation | +3.23e-02 |
Pos logit contributions | |
TIT | +0.090 |
\\\\\\\\ | +0.089 |
OTAL | +0.077 |
Sessions | +0.076 |
Merit | +0.075 |
Neg logit contributions | |
ration | -0.062 |
opoly | -0.062 |
abled | -0.060 |
Jacqu | -0.059 |
marginalized | -0.057 |
Token | of |
Token ID | 286 |
Feature activation | -2.82e-02 |
Pos logit contributions | |
TIT | +0.021 |
\\\\\\\\ | +0.021 |
OTAL | +0.018 |
Merit | +0.018 |
Bank | +0.018 |
Neg logit contributions | |
ration | -0.016 |
opoly | -0.016 |
abled | -0.015 |
Jacqu | -0.015 |
marginalized | -0.015 |
Token | Columbia |
Token ID | 9309 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
TIT | +0.025 |
\\\\\\\\ | +0.025 |
OTAL | +0.022 |
Sessions | +0.021 |
Merit | +0.021 |
Neg logit contributions | |
opoly | -0.017 |
ration | -0.017 |
abled | -0.016 |
Jacqu | -0.016 |
marginalized | -0.015 |
Token | Pictures |
Token ID | 20051 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
ration | +0.172 |
opoly | +0.172 |
abled | +0.168 |
Jacqu | +0.167 |
marginalized | +0.163 |
Neg logit contributions | |
TIT | -0.087 |
\\\\\\\\ | -0.086 |
OTAL | -0.065 |
Merit | -0.063 |
Bank | -0.061 |
Token | The |
Token ID | 383 |
Feature activation | -5.51e-02 |
Pos logit contributions | |
TIT | +0.300 |
\\\\\\\\ | +0.295 |
OTAL | +0.252 |
Merit | +0.248 |
Sessions | +0.247 |
Neg logit contributions | |
ration | -0.257 |
opoly | -0.257 |
abled | -0.250 |
Jacqu | -0.243 |
marginalized | -0.239 |
Token | iconic |
Token ID | 14133 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
TIT | +0.054 |
\\\\\\\\ | +0.054 |
OTAL | +0.047 |
Merit | +0.047 |
Bank | +0.046 |
Neg logit contributions | |
ration | -0.028 |
opoly | -0.028 |
abled | -0.026 |
Jacqu | -0.026 |
marginalized | -0.025 |
Token | old |
Token ID | 1468 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
ration | +0.137 |
opoly | +0.137 |
abled | +0.133 |
Jacqu | +0.132 |
marginalized | +0.128 |
Neg logit contributions | |
TIT | -0.141 |
\\\\\\\\ | -0.139 |
OTAL | -0.117 |
Merit | -0.115 |
Bank | -0.113 |
Token | headquarters |
Token ID | 10043 |
Feature activation | +5.02e-02 |
Pos logit contributions | |
TIT | +0.159 |
\\\\\\\\ | +0.158 |
OTAL | +0.134 |
Merit | +0.132 |
Bank | +0.131 |
Neg logit contributions | |
ration | -0.140 |
opoly | -0.139 |
abled | -0.134 |
Jacqu | -0.133 |
marginalized | -0.130 |
Token | of |
Token ID | 286 |
Feature activation | -3.29e-02 |
Pos logit contributions | |
ration | +0.034 |
opoly | +0.034 |
abled | +0.033 |
Jacqu | +0.032 |
marginalized | +0.032 |
Neg logit contributions | |
TIT | -0.041 |
\\\\\\\\ | -0.040 |
OTAL | -0.035 |
Merit | -0.034 |
Bank | -0.034 |
Token | the |
Token ID | 262 |
Feature activation | -3.35e-02 |
Pos logit contributions | |
TIT | +0.028 |
\\\\\\\\ | +0.028 |
OTAL | +0.024 |
Merit | +0.024 |
Bank | +0.023 |
Neg logit contributions | |
ration | -0.021 |
opoly | -0.021 |
abled | -0.020 |
Jacqu | -0.020 |
marginalized | -0.019 |
Token | first |
Token ID | 717 |
Feature activation | -4.80e-02 |
Pos logit contributions | |
TIT | +0.025 |
\\\\\\\\ | +0.025 |
OTAL | +0.021 |
Merit | +0.021 |
Bank | +0.020 |
Neg logit contributions | |
opoly | -0.025 |
ration | -0.025 |
abled | -0.024 |
Jacqu | -0.024 |
marginalized | -0.023 |
Token | Ghostbusters |
Token ID | 50037 |
Feature activation | +4.92e-02 |
Pos logit contributions | |
TIT | +0.038 |
\\\\\\\\ | +0.038 |
OTAL | +0.032 |
Merit | +0.032 |
Bank | +0.031 |
Neg logit contributions | |
ration | -0.033 |
opoly | -0.033 |
abled | -0.032 |
Jacqu | -0.032 |
marginalized | -0.031 |
Token | 41 |
Token ID | 6073 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
opoly | +0.015 |
ration | +0.015 |
abled | +0.015 |
Jacqu | +0.015 |
marginalized | +0.014 |
Neg logit contributions | |
TIT | -0.016 |
\\\\\\\\ | -0.016 |
OTAL | -0.014 |
Merit | -0.013 |
Sessions | -0.013 |
Token | - |
Token ID | 12 |
Feature activation | +5.41e-02 |
Pos logit contributions | |
TIT | +0.103 |
\\\\\\\\ | +0.101 |
OTAL | +0.087 |
Merit | +0.085 |
Bank | +0.084 |
Neg logit contributions | |
ration | -0.081 |
opoly | -0.080 |
abled | -0.079 |
Jacqu | -0.078 |
boarded | -0.076 |
Token | year |
Token ID | 1941 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
ration | +0.049 |
opoly | +0.049 |
abled | +0.048 |
Jacqu | +0.047 |
boarded | +0.046 |
Neg logit contributions | |
TIT | -0.032 |
\\\\\\\\ | -0.031 |
OTAL | -0.025 |
Merit | -0.024 |
Sessions | -0.023 |
Token | - |
Token ID | 12 |
Feature activation | +8.75e-02 |
Pos logit contributions | |
TIT | +0.209 |
\\\\\\\\ | +0.206 |
OTAL | +0.176 |
Merit | +0.172 |
Bank | +0.172 |
Neg logit contributions | |
ration | -0.158 |
opoly | -0.157 |
abled | -0.152 |
Jacqu | -0.151 |
marginalized | -0.146 |
Token | old |
Token ID | 727 |
Feature activation | +6.50e-02 |
Pos logit contributions | |
ration | +0.054 |
opoly | +0.054 |
Jacqu | +0.052 |
abled | +0.051 |
marginalized | +0.050 |
Neg logit contributions | |
TIT | -0.076 |
\\\\\\\\ | -0.075 |
OTAL | -0.065 |
Merit | -0.065 |
Bank | -0.064 |
Token | 9 |
Token ID | 860 |
Feature activation | -7.55e-02 |
Pos logit contributions | |
opoly | +0.044 |
ration | +0.044 |
abled | +0.042 |
Jacqu | +0.042 |
marginalized | +0.040 |
Neg logit contributions | |
TIT | -0.053 |
\\\\\\\\ | -0.052 |
OTAL | -0.045 |
Merit | -0.044 |
Sessions | -0.044 |
Token | 02 |
Token ID | 2999 |
Feature activation | +5.35e-02 |
Pos logit contributions | |
TIT | +0.063 |
\\\\\\\\ | +0.062 |
OTAL | +0.053 |
Merit | +0.052 |
Tuc | +0.051 |
Neg logit contributions | |
ration | -0.050 |
opoly | -0.049 |
abled | -0.048 |
Jacqu | -0.048 |
marginalized | -0.046 |
Token | 10 |
Token ID | 940 |
Feature activation | +9.63e-02 |
Pos logit contributions | |
ration | +0.033 |
opoly | +0.033 |
abled | +0.032 |
Jacqu | +0.032 |
marginalized | +0.031 |
Neg logit contributions | |
TIT | -0.047 |
\\\\\\\\ | -0.046 |
OTAL | -0.040 |
Merit | -0.039 |
Sessions | -0.039 |
Token | star |
Token ID | 3491 |
Feature activation | -2.43e-02 |
Pos logit contributions | |
ration | +0.066 |
opoly | +0.066 |
abled | +0.064 |
Jacqu | +0.063 |
marginalized | +0.061 |
Neg logit contributions | |
TIT | -0.078 |
\\\\\\\\ | -0.077 |
OTAL | -0.066 |
Merit | -0.064 |
Bank | -0.064 |
Token | has |
Token ID | 468 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
TIT | +0.020 |
\\\\\\\\ | +0.020 |
OTAL | +0.017 |
Merit | +0.017 |
Sessions | +0.017 |
Neg logit contributions | |
ration | -0.016 |
opoly | -0.016 |
abled | -0.015 |
Jacqu | -0.015 |
marginalized | -0.015 |
Token | had |
Token ID | 550 |
Feature activation | +5.80e-02 |
Pos logit contributions | |
opoly | +0.094 |
ration | +0.092 |
abled | +0.090 |
Jacqu | +0.088 |
rift | +0.086 |
Neg logit contributions | |
TIT | -0.126 |
\\\\\\\\ | -0.124 |
Merit | -0.107 |
OTAL | -0.106 |
Sessions | -0.106 |
Token | It |
Token ID | 632 |
Feature activation | -3.37e-03 |
Pos logit contributions | |
TIT | +0.130 |
\\\\\\\\ | +0.128 |
OTAL | +0.111 |
Merit | +0.108 |
Sessions | +0.108 |
Neg logit contributions | |
ration | -0.100 |
opoly | -0.100 |
abled | -0.097 |
Jacqu | -0.095 |
marginalized | -0.092 |
Token | � |
Token ID | 447 |
Feature activation | +9.60e-03 |
Pos logit contributions | |
TIT | +0.003 |
\\\\\\\\ | +0.003 |
OTAL | +0.002 |
Merit | +0.002 |
Bank | +0.002 |
Neg logit contributions | |
ration | -0.002 |
opoly | -0.002 |
abled | -0.002 |
Jacqu | -0.002 |
marginalized | -0.002 |
Token | � |
Token ID | 247 |
Feature activation | -4.37e-02 |
Pos logit contributions | |
opoly | +0.009 |
ration | +0.009 |
abled | +0.008 |
Jacqu | +0.008 |
boarded | +0.008 |
Neg logit contributions | |
TIT | -0.006 |
\\\\\\\\ | -0.005 |
OTAL | -0.004 |
Merit | -0.004 |
Bank | -0.004 |
Token | s |
Token ID | 82 |
Feature activation | +7.40e-02 |
Pos logit contributions | |
TIT | +0.042 |
\\\\\\\\ | +0.042 |
OTAL | +0.036 |
Merit | +0.036 |
Sessions | +0.036 |
Neg logit contributions | |
ration | -0.023 |
opoly | -0.023 |
abled | -0.022 |
Jacqu | -0.022 |
marginalized | -0.021 |
Token | amazing |
Token ID | 4998 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
opoly | +0.049 |
ration | +0.049 |
abled | +0.047 |
Jacqu | +0.046 |
marginalized | +0.045 |
Neg logit contributions | |
TIT | -0.061 |
\\\\\\\\ | -0.061 |
OTAL | -0.052 |
Merit | -0.051 |
Sessions | -0.051 |
Token | ! |
Token ID | 5145 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
TIT | +0.130 |
\\\\\\\\ | +0.128 |
OTAL | +0.110 |
Merit | +0.108 |
Bank | +0.106 |
Neg logit contributions | |
ration | -0.105 |
opoly | -0.105 |
abled | -0.102 |
Jacqu | -0.100 |
marginalized | -0.097 |
Token | � |
Token ID | 447 |
Feature activation | +3.17e-03 |
Pos logit contributions | |
TIT | +0.105 |
\\\\\\\\ | +0.104 |
OTAL | +0.090 |
Merit | +0.087 |
Bank | +0.087 |
Neg logit contributions | |
ration | -0.082 |
opoly | -0.081 |
abled | -0.079 |
Jacqu | -0.077 |
marginalized | -0.076 |
Token | � |
Token ID | 251 |
Feature activation | +3.50e-02 |
Pos logit contributions | |
opoly | +0.003 |
ration | +0.003 |
abled | +0.003 |
Jacqu | +0.003 |
boarded | +0.003 |
Neg logit contributions | |
TIT | -0.002 |
\\\\\\\\ | -0.002 |
OTAL | -0.001 |
Merit | -0.001 |
Bank | -0.001 |
Token | Like |
Token ID | 4525 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
ration | +0.023 |
opoly | +0.023 |
abled | +0.022 |
Jacqu | +0.022 |
marginalized | +0.022 |
Neg logit contributions | |
TIT | -0.029 |
\\\\\\\\ | -0.029 |
OTAL | -0.025 |
Merit | -0.024 |
Sessions | -0.024 |
Token | looking |
Token ID | 2045 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
TIT | +0.126 |
\\\\\\\\ | +0.125 |
OTAL | +0.106 |
Merit | +0.104 |
Bank | +0.103 |
Neg logit contributions | |
ration | -0.111 |
opoly | -0.111 |
abled | -0.107 |
Jacqu | -0.106 |
marginalized | -0.103 |
Token | at |
Token ID | 379 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
TIT | +0.074 |
\\\\\\\\ | +0.073 |
OTAL | +0.061 |
Merit | +0.060 |
Bank | +0.059 |
Neg logit contributions | |
ration | -0.081 |
opoly | -0.081 |
abled | -0.079 |
Jacqu | -0.078 |
marginalized | -0.076 |
Token | interesting |
Token ID | 3499 |
Feature activation | -9.19e-02 |
Pos logit contributions | |
TIT | +0.164 |
\\\\\\\\ | +0.160 |
OTAL | +0.137 |
Merit | +0.135 |
Tuc | +0.135 |
Neg logit contributions | |
opoly | -0.135 |
ration | -0.132 |
abled | -0.130 |
Jacqu | -0.127 |
marginalized | -0.123 |
Token | ." |
Token ID | 526 |
Feature activation | -5.88e-03 |
Pos logit contributions | |
TIT | +0.078 |
\\\\\\\\ | +0.077 |
OTAL | +0.067 |
Sessions | +0.066 |
Merit | +0.066 |
Neg logit contributions | |
opoly | -0.059 |
ration | -0.057 |
abled | -0.056 |
Jacqu | -0.055 |
marginalized | -0.053 |
Token |
|
Token ID | 198 |
Feature activation | -2.36e-02 |
Pos logit contributions | |
TIT | +0.005 |
\\\\\\\\ | +0.005 |
OTAL | +0.004 |
Merit | +0.004 |
Bank | +0.004 |
Neg logit contributions | |
opoly | -0.004 |
ration | -0.004 |
abled | -0.004 |
Jacqu | -0.004 |
marginalized | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -1.86e-02 |
Pos logit contributions | |
TIT | +0.020 |
\\\\\\\\ | +0.019 |
OTAL | +0.017 |
Merit | +0.017 |
Sessions | +0.016 |
Neg logit contributions | |
ration | -0.016 |
opoly | -0.016 |
abled | -0.015 |
boarded | -0.015 |
marginalized | -0.015 |
Token | Don |
Token ID | 3987 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
TIT | +0.014 |
\\\\\\\\ | +0.014 |
OTAL | +0.011 |
Merit | +0.011 |
Bank | +0.011 |
Neg logit contributions | |
ration | -0.014 |
opoly | -0.014 |
abled | -0.014 |
Jacqu | -0.014 |
marginalized | -0.013 |
Token | � |
Token ID | 447 |
Feature activation | -7.11e-02 |
Pos logit contributions | |
TIT | +0.093 |
\\\\\\\\ | +0.092 |
OTAL | +0.078 |
Merit | +0.076 |
Bank | +0.075 |
Neg logit contributions | |
ration | -0.086 |
opoly | -0.086 |
abled | -0.084 |
Jacqu | -0.083 |
marginalized | -0.080 |
Token | � |
Token ID | 247 |
Feature activation | -1.92e-02 |
Pos logit contributions | |
TIT | +0.033 |
\\\\\\\\ | +0.032 |
OTAL | +0.024 |
Merit | +0.024 |
Bank | +0.023 |
Neg logit contributions | |
opoly | -0.073 |
ration | -0.073 |
abled | -0.071 |
Jacqu | -0.071 |
marginalized | -0.069 |
Token | t |
Token ID | 83 |
Feature activation | -6.87e-02 |
Pos logit contributions | |
TIT | +0.016 |
\\\\\\\\ | +0.015 |
OTAL | +0.013 |
Merit | +0.013 |
Bank | +0.013 |
Neg logit contributions | |
ration | -0.013 |
opoly | -0.013 |
abled | -0.012 |
Jacqu | -0.012 |
marginalized | -0.012 |
Token | miss |
Token ID | 2051 |
Feature activation | +3.70e-02 |
Pos logit contributions | |
TIT | +0.056 |
\\\\\\\\ | +0.056 |
OTAL | +0.047 |
Merit | +0.046 |
Tuc | +0.046 |
Neg logit contributions | |
opoly | -0.046 |
ration | -0.046 |
abled | -0.045 |
Jacqu | -0.044 |
marginalized | -0.043 |
Token | our |
Token ID | 674 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
ration | +0.024 |
opoly | +0.024 |
abled | +0.023 |
Jacqu | +0.023 |
marginalized | +0.022 |
Neg logit contributions | |
TIT | -0.031 |
\\\\\\\\ | -0.031 |
OTAL | -0.027 |
Merit | -0.026 |
Sessions | -0.026 |
Token | Japanese |
Token ID | 4960 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
opoly | +0.163 |
ration | +0.163 |
abled | +0.158 |
Jacqu | +0.154 |
marginalized | +0.151 |
Neg logit contributions | |
TIT | -0.211 |
\\\\\\\\ | -0.207 |
OTAL | -0.178 |
Merit | -0.176 |
Sessions | -0.175 |
Token | in |
Token ID | 287 |
Feature activation | -3.04e-02 |
Pos logit contributions | |
TIT | +0.234 |
\\\\\\\\ | +0.231 |
OTAL | +0.198 |
Merit | +0.195 |
Sessions | +0.194 |
Neg logit contributions | |
ration | -0.190 |
opoly | -0.189 |
abled | -0.184 |
Jacqu | -0.181 |
marginalized | -0.175 |
Token | the |
Token ID | 262 |
Feature activation | +1.44e-02 |
Pos logit contributions | |
TIT | +0.026 |
\\\\\\\\ | +0.026 |
OTAL | +0.022 |
Merit | +0.022 |
Sessions | +0.021 |
Neg logit contributions | |
ration | -0.019 |
opoly | -0.019 |
abled | -0.019 |
Jacqu | -0.018 |
marginalized | -0.018 |
Token | NFL |
Token ID | 5134 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
opoly | +0.011 |
ration | +0.011 |
abled | +0.011 |
Jacqu | +0.011 |
marginalized | +0.011 |
Neg logit contributions | |
TIT | -0.010 |
\\\\\\\\ | -0.010 |
OTAL | -0.008 |
Merit | -0.008 |
Tuc | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | -1.44e-02 |
Pos logit contributions | |
TIT | +0.084 |
\\\\\\\\ | +0.083 |
OTAL | +0.071 |
Merit | +0.070 |
Sessions | +0.069 |
Neg logit contributions | |
opoly | -0.071 |
ration | -0.071 |
abled | -0.068 |
Jacqu | -0.067 |
marginalized | -0.065 |
Token | and |
Token ID | 290 |
Feature activation | +6.96e-02 |
Pos logit contributions | |
TIT | +0.012 |
\\\\\\\\ | +0.012 |
OTAL | +0.011 |
Sessions | +0.010 |
Merit | +0.010 |
Neg logit contributions | |
opoly | -0.009 |
ration | -0.009 |
abled | -0.009 |
Jacqu | -0.008 |
marginalized | -0.008 |
Token | statistically |
Token ID | 19941 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
opoly | +0.048 |
ration | +0.048 |
abled | +0.047 |
Jacqu | +0.045 |
marginalized | +0.044 |
Neg logit contributions | |
TIT | -0.056 |
\\\\\\\\ | -0.055 |
OTAL | -0.047 |
Merit | -0.046 |
Sessions | -0.046 |
Token | they |
Token ID | 484 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
TIT | +0.162 |
\\\\\\\\ | +0.160 |
OTAL | +0.135 |
Merit | +0.133 |
Sessions | +0.132 |
Neg logit contributions | |
opoly | -0.150 |
ration | -0.150 |
abled | -0.146 |
Jacqu | -0.144 |
marginalized | -0.140 |
Token | have |
Token ID | 423 |
Feature activation | +7.02e-02 |
Pos logit contributions | |
TIT | +0.117 |
\\\\\\\\ | +0.114 |
OTAL | +0.098 |
Sessions | +0.096 |
Merit | +0.096 |
Neg logit contributions | |
opoly | -0.107 |
ration | -0.105 |
abled | -0.104 |
Jacqu | -0.102 |
marginalized | -0.098 |
Token | allowed |
Token ID | 3142 |
Feature activation | +7.82e-02 |
Pos logit contributions | |
opoly | +0.045 |
ration | +0.044 |
abled | +0.043 |
Jacqu | +0.042 |
rift | +0.040 |
Neg logit contributions | |
TIT | -0.060 |
\\\\\\\\ | -0.059 |
OTAL | -0.051 |
Merit | -0.050 |
Sessions | -0.050 |
Token | the |
Token ID | 262 |
Feature activation | -2.07e-02 |
Pos logit contributions | |
opoly | +0.049 |
ration | +0.049 |
abled | +0.048 |
Jacqu | +0.047 |
marginalized | +0.045 |
Neg logit contributions | |
TIT | -0.067 |
\\\\\\\\ | -0.066 |
OTAL | -0.057 |
Merit | -0.056 |
Sessions | -0.056 |
Token | few |
Token ID | 1178 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
TIT | +0.017 |
\\\\\\\\ | +0.016 |
OTAL | +0.014 |
Merit | +0.014 |
Sessions | +0.014 |
Neg logit contributions | |
opoly | -0.014 |
ration | -0.014 |
abled | -0.014 |
Jacqu | -0.014 |
marginalized | -0.013 |
Token | ations |
Token ID | 602 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
ration | +0.208 |
opoly | +0.207 |
abled | +0.201 |
Jacqu | +0.199 |
marginalized | +0.194 |
Neg logit contributions | |
TIT | -0.221 |
\\\\\\\\ | -0.218 |
OTAL | -0.184 |
Merit | -0.181 |
Bank | -0.178 |
Token | of |
Token ID | 286 |
Feature activation | -8.02e-03 |
Pos logit contributions | |
opoly | +0.125 |
ration | +0.125 |
abled | +0.122 |
Jacqu | +0.119 |
marginalized | +0.115 |
Neg logit contributions | |
TIT | -0.161 |
\\\\\\\\ | -0.159 |
OTAL | -0.137 |
Sessions | -0.136 |
Merit | -0.136 |
Token | racism |
Token ID | 10713 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
TIT | +0.007 |
\\\\\\\\ | +0.007 |
OTAL | +0.006 |
Sessions | +0.006 |
Merit | +0.006 |
Neg logit contributions | |
opoly | -0.005 |
ration | -0.005 |
abled | -0.005 |
Jacqu | -0.005 |
raq | -0.005 |
Token | infect |
Token ID | 7580 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
opoly | +0.079 |
ration | +0.078 |
abled | +0.076 |
Jacqu | +0.075 |
marginalized | +0.072 |
Neg logit contributions | |
TIT | -0.105 |
\\\\\\\\ | -0.104 |
OTAL | -0.090 |
Merit | -0.089 |
Sessions | -0.089 |
Token | New |
Token ID | 968 |
Feature activation | -8.27e-02 |
Pos logit contributions | |
ration | +0.145 |
opoly | +0.145 |
abled | +0.140 |
Jacqu | +0.138 |
marginalized | +0.134 |
Neg logit contributions | |
\\\\\\\\ | -0.175 |
TIT | -0.174 |
OTAL | -0.149 |
Merit | -0.147 |
Sessions | -0.147 |
Token | Castle |
Token ID | 11312 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
TIT | +0.041 |
\\\\\\\\ | +0.040 |
OTAL | +0.031 |
Merit | +0.030 |
Bank | +0.029 |
Neg logit contributions | |
opoly | -0.082 |
ration | -0.082 |
abled | -0.080 |
Jacqu | -0.080 |
marginalized | -0.078 |
Token | city |
Token ID | 1748 |
Feature activation | +6.73e-02 |
Pos logit contributions | |
TIT | +0.358 |
\\\\\\\\ | +0.355 |
OTAL | +0.305 |
Merit | +0.304 |
Sessions | +0.303 |
Neg logit contributions | |
opoly | -0.287 |
ration | -0.286 |
abled | -0.279 |
Jacqu | -0.274 |
raq | -0.264 |
Token | politics |
Token ID | 4819 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
ration | +0.043 |
opoly | +0.043 |
abled | +0.042 |
Jacqu | +0.041 |
marginalized | +0.040 |
Neg logit contributions | |
TIT | -0.056 |
\\\\\\\\ | -0.056 |
OTAL | -0.048 |
Merit | -0.048 |
Sessions | -0.047 |
Token |
|
Token ID | 198 |
Feature activation | -3.46e-02 |
Pos logit contributions | |
ration | +0.170 |
opoly | +0.170 |
abled | +0.163 |
Jacqu | +0.162 |
marginalized | +0.156 |
Neg logit contributions | |
TIT | -0.262 |
\\\\\\\\ | -0.259 |
OTAL | -0.225 |
Merit | -0.221 |
Bank | -0.219 |
Token |
|
Token ID | 198 |
Feature activation | -3.23e-02 |
Pos logit contributions | |
TIT | +0.029 |
\\\\\\\\ | +0.028 |
OTAL | +0.025 |
Merit | +0.025 |
Bank | +0.024 |
Neg logit contributions | |
ration | -0.023 |
opoly | -0.023 |
abled | -0.022 |
Jacqu | -0.021 |
boarded | -0.021 |
Token | In |
Token ID | 818 |
Feature activation | +3.43e-02 |
Pos logit contributions | |
TIT | +0.023 |
\\\\\\\\ | +0.023 |
OTAL | +0.019 |
Merit | +0.019 |
Bank | +0.018 |
Neg logit contributions | |
ration | -0.026 |
opoly | -0.025 |
abled | -0.025 |
Jacqu | -0.024 |
marginalized | -0.024 |
Token | 45 |
Token ID | 4153 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
TIT | +0.038 |
\\\\\\\\ | +0.038 |
OTAL | +0.032 |
Merit | +0.032 |
Sessions | +0.031 |
Neg logit contributions | |
opoly | -0.036 |
ration | -0.036 |
abled | -0.035 |
Jacqu | -0.035 |
marginalized | -0.034 |
Token | minutes |
Token ID | 2431 |
Feature activation | +2.50e-02 |
Pos logit contributions | |
TIT | +0.131 |
\\\\\\\\ | +0.129 |
OTAL | +0.111 |
Merit | +0.109 |
Bank | +0.108 |
Neg logit contributions | |
ration | -0.099 |
opoly | -0.099 |
abled | -0.096 |
Jacqu | -0.095 |
marginalized | -0.092 |
Token | – |
Token ID | 1906 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
opoly | +0.018 |
ration | +0.018 |
abled | +0.017 |
Jacqu | +0.017 |
marginalized | +0.016 |
Neg logit contributions | |
TIT | -0.019 |
\\\\\\\\ | -0.019 |
OTAL | -0.016 |
Merit | -0.016 |
Sessions | -0.016 |
Token | a |
Token ID | 64 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
opoly | +0.159 |
ration | +0.159 |
abled | +0.153 |
Jacqu | +0.151 |
marginalized | +0.147 |
Neg logit contributions | |
TIT | -0.208 |
\\\\\\\\ | -0.205 |
OTAL | -0.178 |
Merit | -0.175 |
Sessions | -0.173 |
Token | long |
Token ID | 890 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
TIT | +0.144 |
\\\\\\\\ | +0.142 |
OTAL | +0.122 |
Merit | +0.120 |
Sessions | +0.119 |
Neg logit contributions | |
opoly | -0.112 |
ration | -0.112 |
abled | -0.109 |
Jacqu | -0.107 |
marginalized | -0.104 |
Token | time |
Token ID | 640 |
Feature activation | -4.35e-01 |
Pos logit contributions | |
TIT | +0.079 |
\\\\\\\\ | +0.077 |
OTAL | +0.063 |
Merit | +0.062 |
Sessions | +0.061 |
Neg logit contributions | |
opoly | -0.103 |
ration | -0.103 |
abled | -0.100 |
Jacqu | -0.099 |
marginalized | -0.097 |
Token | . |
Token ID | 13 |
Feature activation | -9.36e-02 |
Pos logit contributions | |
TIT | +0.368 |
\\\\\\\\ | +0.364 |
OTAL | +0.315 |
Merit | +0.308 |
Sessions | +0.307 |
Neg logit contributions | |
opoly | -0.278 |
ration | -0.278 |
abled | -0.268 |
Jacqu | -0.264 |
marginalized | -0.256 |
Token | Then |
Token ID | 3244 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
TIT | +0.075 |
\\\\\\\\ | +0.074 |
OTAL | +0.064 |
Sessions | +0.063 |
Merit | +0.063 |
Neg logit contributions | |
ration | -0.065 |
opoly | -0.064 |
abled | -0.063 |
marginalized | -0.060 |
boarded | -0.060 |
Token | Fred |
Token ID | 8559 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
TIT | +0.140 |
\\\\\\\\ | +0.138 |
OTAL | +0.122 |
Sessions | +0.120 |
Tuc | +0.119 |
Neg logit contributions | |
opoly | -0.104 |
ration | -0.103 |
abled | -0.101 |
Jacqu | -0.096 |
rift | -0.095 |
Token | gave |
Token ID | 2921 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
opoly | +0.180 |
ration | +0.177 |
abled | +0.173 |
Jacqu | +0.167 |
rift | +0.164 |
Neg logit contributions | |
TIT | -0.228 |
\\\\\\\\ | -0.226 |
Sessions | -0.194 |
OTAL | -0.194 |
Tuc | -0.192 |
Token | me |
Token ID | 502 |
Feature activation | +5.37e-02 |
Pos logit contributions | |
opoly | +0.054 |
ration | +0.054 |
abled | +0.052 |
Jacqu | +0.050 |
marginalized | +0.048 |
Neg logit contributions | |
TIT | -0.103 |
\\\\\\\\ | -0.102 |
OTAL | -0.090 |
Merit | -0.089 |
Sessions | -0.088 |
Token | tried |
Token ID | 3088 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
TIT | +0.021 |
\\\\\\\\ | +0.020 |
OTAL | +0.017 |
Sessions | +0.017 |
Merit | +0.017 |
Neg logit contributions | |
opoly | -0.019 |
ration | -0.018 |
abled | -0.018 |
Jacqu | -0.018 |
rift | -0.017 |
Token | to |
Token ID | 284 |
Feature activation | -8.74e-02 |
Pos logit contributions | |
TIT | +0.132 |
\\\\\\\\ | +0.130 |
OTAL | +0.112 |
Merit | +0.111 |
Sessions | +0.110 |
Neg logit contributions | |
opoly | -0.099 |
ration | -0.098 |
abled | -0.095 |
Jacqu | -0.093 |
marginalized | -0.090 |
Token | do |
Token ID | 466 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
TIT | +0.074 |
\\\\\\\\ | +0.072 |
OTAL | +0.063 |
Sessions | +0.062 |
Merit | +0.062 |
Neg logit contributions | |
opoly | -0.056 |
ration | -0.054 |
abled | -0.053 |
Jacqu | -0.052 |
raq | -0.051 |
Token | a |
Token ID | 257 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
TIT | +0.265 |
\\\\\\\\ | +0.262 |
OTAL | +0.228 |
Merit | +0.224 |
Sessions | +0.223 |
Neg logit contributions | |
opoly | -0.173 |
ration | -0.172 |
abled | -0.166 |
Jacqu | -0.162 |
marginalized | -0.157 |
Token | decent |
Token ID | 7709 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
TIT | +0.095 |
\\\\\\\\ | +0.094 |
OTAL | +0.081 |
Merit | +0.079 |
Sessions | +0.079 |
Neg logit contributions | |
opoly | -0.076 |
ration | -0.076 |
abled | -0.074 |
Jacqu | -0.072 |
marginalized | -0.070 |
Token | job |
Token ID | 1693 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
TIT | +0.206 |
\\\\\\\\ | +0.203 |
OTAL | +0.164 |
Merit | +0.160 |
Sessions | +0.158 |
Neg logit contributions | |
opoly | -0.287 |
ration | -0.287 |
abled | -0.280 |
Jacqu | -0.277 |
marginalized | -0.271 |
Token | acting |
Token ID | 7205 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
TIT | +0.365 |
\\\\\\\\ | +0.361 |
OTAL | +0.310 |
Merit | +0.305 |
Sessions | +0.302 |
Neg logit contributions | |
opoly | -0.292 |
ration | -0.290 |
abled | -0.281 |
Jacqu | -0.277 |
marginalized | -0.268 |
Token | for |
Token ID | 329 |
Feature activation | -9.10e-02 |
Pos logit contributions | |
TIT | +0.117 |
\\\\\\\\ | +0.115 |
OTAL | +0.097 |
Merit | +0.096 |
Sessions | +0.095 |
Neg logit contributions | |
opoly | -0.111 |
ration | -0.110 |
abled | -0.107 |
Jacqu | -0.105 |
marginalized | -0.102 |
Token | the |
Token ID | 262 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
TIT | +0.083 |
\\\\\\\\ | +0.082 |
OTAL | +0.072 |
Merit | +0.071 |
Sessions | +0.070 |
Neg logit contributions | |
opoly | -0.052 |
ration | -0.052 |
abled | -0.050 |
Jacqu | -0.049 |
boarded | -0.047 |
Token | camera |
Token ID | 4676 |
Feature activation | -7.11e-03 |
Pos logit contributions | |
TIT | +0.115 |
\\\\\\\\ | +0.113 |
OTAL | +0.097 |
Merit | +0.096 |
Sessions | +0.095 |
Neg logit contributions | |
opoly | -0.092 |
ration | -0.092 |
abled | -0.089 |
Jacqu | -0.088 |
marginalized | -0.085 |
Token | , |
Token ID | 11 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
TIT | +0.006 |
\\\\\\\\ | +0.006 |
OTAL | +0.005 |
Merit | +0.005 |
Sessions | +0.005 |
Neg logit contributions | |
opoly | -0.005 |
ration | -0.005 |
abled | -0.005 |
Jacqu | -0.005 |
marginalized | -0.004 |
Token | faulty |
Token ID | 30954 |
Feature activation | +6.45e-02 |
Pos logit contributions | |
TIT | +0.034 |
\\\\\\\\ | +0.033 |
OTAL | +0.029 |
Merit | +0.028 |
Bank | +0.028 |
Neg logit contributions | |
ration | -0.026 |
opoly | -0.026 |
abled | -0.026 |
Jacqu | -0.025 |
marginalized | -0.024 |
Token | foreclosure |
Token ID | 41400 |
Feature activation | +9.61e-02 |
Pos logit contributions | |
opoly | +0.045 |
ration | +0.045 |
abled | +0.044 |
Jacqu | +0.043 |
marginalized | +0.042 |
Neg logit contributions | |
TIT | -0.051 |
\\\\\\\\ | -0.050 |
OTAL | -0.043 |
Bank | -0.042 |
Merit | -0.042 |
Token | documents |
Token ID | 4963 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
ration | +0.067 |
opoly | +0.067 |
abled | +0.065 |
Jacqu | +0.064 |
marginalized | +0.062 |
Neg logit contributions | |
TIT | -0.076 |
\\\\\\\\ | -0.076 |
OTAL | -0.064 |
Merit | -0.063 |
Bank | -0.062 |
Token | . |
Token ID | 13 |
Feature activation | -6.37e-02 |
Pos logit contributions | |
ration | +0.067 |
opoly | +0.067 |
abled | +0.065 |
Jacqu | +0.064 |
marginalized | +0.062 |
Neg logit contributions | |
TIT | -0.084 |
\\\\\\\\ | -0.083 |
OTAL | -0.071 |
Merit | -0.070 |
Bank | -0.069 |
Token | ( |
Token ID | 357 |
Feature activation | +4.64e-02 |
Pos logit contributions | |
TIT | +0.050 |
\\\\\\\\ | +0.049 |
OTAL | +0.042 |
Bank | +0.042 |
Merit | +0.042 |
Neg logit contributions | |
ration | -0.045 |
opoly | -0.044 |
abled | -0.044 |
Jacqu | -0.042 |
marginalized | -0.042 |
Token | Bank |
Token ID | 28650 |
Feature activation | -5.80e-01 |
Pos logit contributions | |
ration | +0.037 |
opoly | +0.037 |
abled | +0.036 |
Jacqu | +0.036 |
marginalized | +0.035 |
Neg logit contributions | |
TIT | -0.032 |
\\\\\\\\ | -0.032 |
OTAL | -0.026 |
Bank | -0.026 |
Merit | -0.026 |
Token | of |
Token ID | 286 |
Feature activation | +3.81e-03 |
Pos logit contributions | |
TIT | +0.496 |
\\\\\\\\ | +0.492 |
OTAL | +0.422 |
Merit | +0.417 |
Sessions | +0.409 |
Neg logit contributions | |
opoly | -0.370 |
ration | -0.369 |
abled | -0.355 |
Jacqu | -0.352 |
boarded | -0.338 |
Token | America |
Token ID | 2253 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
ration | +0.002 |
opoly | +0.002 |
abled | +0.002 |
Jacqu | +0.002 |
marginalized | +0.002 |
Neg logit contributions | |
TIT | -0.004 |
\\\\\\\\ | -0.003 |
OTAL | -0.003 |
Merit | -0.003 |
Bank | -0.003 |
Token | recently |
Token ID | 2904 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
ration | +0.133 |
opoly | +0.133 |
abled | +0.129 |
Jacqu | +0.127 |
marginalized | +0.123 |
Neg logit contributions | |
TIT | -0.172 |
\\\\\\\\ | -0.170 |
OTAL | -0.146 |
Merit | -0.144 |
Bank | -0.143 |
Token | agreed |
Token ID | 4987 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
opoly | +0.095 |
ration | +0.094 |
abled | +0.092 |
Jacqu | +0.091 |
rift | +0.087 |
Neg logit contributions | |
TIT | -0.122 |
\\\\\\\\ | -0.120 |
OTAL | -0.104 |
Sessions | -0.102 |
Bank | -0.102 |
Token | to |
Token ID | 284 |
Feature activation | -5.29e-02 |
Pos logit contributions | |
TIT | +0.273 |
\\\\\\\\ | +0.270 |
OTAL | +0.233 |
Merit | +0.229 |
Bank | +0.226 |
Neg logit contributions | |
ration | -0.196 |
opoly | -0.195 |
abled | -0.188 |
Jacqu | -0.186 |
marginalized | -0.180 |
Token | ( |
Token ID | 7 |
Feature activation | -3.54e-02 |
Pos logit contributions | |
TIT | +0.018 |
\\\\\\\\ | +0.017 |
OTAL | +0.015 |
Merit | +0.015 |
Bank | +0.014 |
Neg logit contributions | |
ration | -0.015 |
opoly | -0.015 |
abled | -0.015 |
Jacqu | -0.015 |
marginalized | -0.014 |
Token | count |
Token ID | 9127 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
TIT | +0.030 |
\\\\\\\\ | +0.030 |
OTAL | +0.026 |
Merit | +0.025 |
Bank | +0.025 |
Neg logit contributions | |
ration | -0.023 |
opoly | -0.023 |
abled | -0.022 |
Jacqu | -0.022 |
marginalized | -0.021 |
Token | )); |
Token ID | 18125 |
Feature activation | -3.60e-02 |
Pos logit contributions | |
TIT | +0.082 |
\\\\\\\\ | +0.081 |
OTAL | +0.068 |
Merit | +0.067 |
Bank | +0.066 |
Neg logit contributions | |
ration | -0.076 |
opoly | -0.076 |
abled | -0.074 |
Jacqu | -0.073 |
marginalized | -0.071 |
Token | RAW |
Token ID | 33782 |
Feature activation | +4.16e-02 |
Pos logit contributions | |
TIT | +0.029 |
\\\\\\\\ | +0.028 |
OTAL | +0.024 |
Merit | +0.024 |
Bank | +0.023 |
Neg logit contributions | |
ration | -0.025 |
opoly | -0.025 |
abled | -0.024 |
Jacqu | -0.024 |
marginalized | -0.023 |
Token | _ |
Token ID | 62 |
Feature activation | -6.25e-03 |
Pos logit contributions | |
ration | +0.032 |
opoly | +0.032 |
abled | +0.031 |
Jacqu | +0.031 |
boarded | +0.030 |
Neg logit contributions | |
TIT | -0.031 |
\\\\\\\\ | -0.030 |
OTAL | -0.025 |
Merit | -0.025 |
Bank | -0.025 |
Token | ASS |
Token ID | 10705 |
Feature activation | -4.91e-01 |
Pos logit contributions | |
\\\\\\\\ | +0.002 |
TIT | +0.002 |
OTAL | +0.001 |
Tuc | +0.001 |
Merit | +0.001 |
Neg logit contributions | |
opoly | -0.007 |
ration | -0.007 |
abled | -0.007 |
Jacqu | -0.007 |
marginalized | -0.007 |
Token | ERT |
Token ID | 17395 |
Feature activation | -7.71e-02 |
Pos logit contributions | |
TIT | +0.290 |
\\\\\\\\ | +0.280 |
OTAL | +0.227 |
Merit | +0.220 |
Bank | +0.216 |
Neg logit contributions | |
ration | -0.448 |
opoly | -0.447 |
abled | -0.436 |
Jacqu | -0.432 |
marginalized | -0.426 |
Token | ( |
Token ID | 7 |
Feature activation | -3.78e-02 |
Pos logit contributions | |
TIT | +0.062 |
\\\\\\\\ | +0.062 |
OTAL | +0.053 |
Merit | +0.052 |
Tuc | +0.052 |
Neg logit contributions | |
ration | -0.052 |
opoly | -0.052 |
abled | -0.050 |
Jacqu | -0.050 |
marginalized | -0.048 |
Token | it |
Token ID | 270 |
Feature activation | -9.24e-02 |
Pos logit contributions | |
TIT | +0.030 |
\\\\\\\\ | +0.030 |
OTAL | +0.026 |
Merit | +0.025 |
Tuc | +0.025 |
Neg logit contributions | |
ration | -0.026 |
opoly | -0.026 |
abled | -0.025 |
Jacqu | -0.025 |
marginalized | -0.024 |
Token | -> |
Token ID | 3784 |
Feature activation | -5.57e-03 |
Pos logit contributions | |
TIT | +0.070 |
\\\\\\\\ | +0.068 |
OTAL | +0.058 |
Merit | +0.057 |
Bank | +0.057 |
Neg logit contributions | |
ration | -0.069 |
opoly | -0.069 |
abled | -0.066 |
Jacqu | -0.066 |
marginalized | -0.065 |
Token | i |
Token ID | 72 |
Feature activation | +2.49e-02 |
Pos logit contributions | |
TIT | +0.005 |
\\\\\\\\ | +0.005 |
OTAL | +0.005 |
Merit | +0.005 |
Bank | +0.005 |
Neg logit contributions | |
ration | -0.003 |
opoly | -0.003 |
abled | -0.003 |
Jacqu | -0.003 |
marginalized | -0.003 |