Token | air |
Token ID | 1633 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
Jinn | +0.011 |
↑ | +0.011 |
pai | +0.011 |
�� | +0.010 |
� | +0.010 |
Neg logit contributions | |
abol | -0.014 |
theless | -0.014 |
utonium | -0.014 |
akespe | -0.013 |
andre | -0.013 |
Token | loads |
Token ID | 46030 |
Feature activation | -6.63e-01 |
Pos logit contributions | |
Jinn | +0.236 |
↑ | +0.235 |
pai | +0.233 |
�� | +0.218 |
� | +0.216 |
Neg logit contributions | |
abol | -0.370 |
theless | -0.358 |
utonium | -0.350 |
akespe | -0.343 |
andre | -0.334 |
Token | allowing |
Token ID | 5086 |
Feature activation | -9.55e-02 |
Pos logit contributions | |
abol | +0.879 |
theless | +0.851 |
utonium | +0.831 |
akespe | +0.815 |
andre | +0.796 |
Neg logit contributions | |
Jinn | -0.490 |
↑ | -0.486 |
pai | -0.484 |
�� | -0.451 |
� | -0.443 |
Token | the |
Token ID | 262 |
Feature activation | -4.05e-02 |
Pos logit contributions | |
abol | +0.130 |
theless | +0.126 |
utonium | +0.123 |
akespe | +0.121 |
andre | +0.118 |
Neg logit contributions | |
Jinn | -0.067 |
↑ | -0.067 |
pai | -0.066 |
�� | -0.061 |
� | -0.060 |
Token | wing |
Token ID | 8539 |
Feature activation | -4.85e-02 |
Pos logit contributions | |
abol | +0.044 |
theless | +0.043 |
utonium | +0.042 |
akespe | +0.041 |
andre | +0.039 |
Neg logit contributions | |
Jinn | -0.039 |
↑ | -0.039 |
pai | -0.039 |
�� | -0.037 |
� | -0.036 |
Token | tips |
Token ID | 41315 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
abol | +0.059 |
theless | +0.057 |
utonium | +0.055 |
akespe | +0.054 |
andre | +0.053 |
Neg logit contributions | |
Jinn | -0.042 |
↑ | -0.041 |
pai | -0.041 |
�� | -0.039 |
� | -0.038 |
Token | to |
Token ID | 284 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
Jinn | +0.851 |
↑ | +0.846 |
pai | +0.839 |
�� | +0.771 |
� | +0.767 |
Neg logit contributions | |
abol | -1.566 |
theless | -1.519 |
utonium | -1.485 |
akespe | -1.459 |
andre | -1.421 |
Token | almost |
Token ID | 2048 |
Feature activation | -8.50e-02 |
Pos logit contributions | |
abol | +0.019 |
theless | +0.018 |
utonium | +0.018 |
akespe | +0.017 |
andre | +0.017 |
Neg logit contributions | |
Jinn | -0.014 |
↑ | -0.014 |
pai | -0.014 |
�� | -0.013 |
� | -0.013 |
Token | lay |
Token ID | 3830 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
abol | +0.101 |
theless | +0.097 |
utonium | +0.094 |
akespe | +0.092 |
andre | +0.090 |
Neg logit contributions | |
Jinn | -0.075 |
↑ | -0.074 |
pai | -0.074 |
�� | -0.071 |
� | -0.069 |
Token | down |
Token ID | 866 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
Jinn | +0.123 |
↑ | +0.123 |
pai | +0.122 |
�� | +0.114 |
� | +0.114 |
Neg logit contributions | |
abol | -0.146 |
theless | -0.141 |
utonium | -0.138 |
akespe | -0.134 |
andre | -0.130 |
Token | upon |
Token ID | 2402 |
Feature activation | -6.27e-02 |
Pos logit contributions | |
abol | +0.262 |
theless | +0.254 |
utonium | +0.248 |
akespe | +0.243 |
andre | +0.238 |
Neg logit contributions | |
Jinn | -0.144 |
↑ | -0.143 |
pai | -0.142 |
�� | -0.132 |
� | -0.130 |
Token | see |
Token ID | 766 |
Feature activation | -6.28e-02 |
Pos logit contributions | |
abol | +0.033 |
theless | +0.032 |
utonium | +0.031 |
akespe | +0.030 |
andre | +0.029 |
Neg logit contributions | |
Jinn | -0.020 |
↑ | -0.020 |
pai | -0.020 |
�� | -0.018 |
� | -0.018 |
Token | your |
Token ID | 534 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
abol | +0.083 |
theless | +0.081 |
utonium | +0.079 |
akespe | +0.077 |
andre | +0.076 |
Neg logit contributions | |
Jinn | -0.046 |
↑ | -0.046 |
pai | -0.045 |
�� | -0.042 |
� | -0.042 |
Token | city |
Token ID | 1748 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
abol | +0.282 |
theless | +0.273 |
utonium | +0.266 |
akespe | +0.260 |
andre | +0.254 |
Neg logit contributions | |
Jinn | -0.192 |
↑ | -0.191 |
pai | -0.189 |
�� | -0.177 |
� | -0.176 |
Token | � |
Token ID | 14519 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
↑ | +0.094 |
Jinn | +0.094 |
pai | +0.093 |
�� | +0.086 |
� | +0.086 |
Neg logit contributions | |
abol | -0.153 |
theless | -0.148 |
utonium | -0.145 |
akespe | -0.142 |
andre | -0.138 |
Token | � |
Token ID | 244 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
↑ | +0.182 |
Jinn | +0.181 |
pai | +0.180 |
�� | +0.172 |
� | +0.169 |
Neg logit contributions | |
abol | -0.244 |
theless | -0.237 |
utonium | -0.230 |
akespe | -0.225 |
andre | -0.218 |
Token | ️ |
Token ID | 37929 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
abol | +0.183 |
theless | +0.178 |
utonium | +0.174 |
akespe | +0.171 |
andre | +0.167 |
Neg logit contributions | |
↑ | -0.082 |
Jinn | -0.082 |
pai | -0.081 |
�� | -0.074 |
� | -0.074 |
Token | Be |
Token ID | 1355 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
↑ | +0.911 |
Jinn | +0.902 |
pai | +0.894 |
�� | +0.840 |
� | +0.837 |
Neg logit contributions | |
abol | -1.216 |
theless | -1.176 |
utonium | -1.148 |
akespe | -1.124 |
andre | -1.087 |
Token | safe |
Token ID | 3338 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
Jinn | +0.162 |
↑ | +0.162 |
pai | +0.160 |
�� | +0.149 |
� | +0.149 |
Neg logit contributions | |
abol | -0.244 |
theless | -0.236 |
utonium | -0.230 |
akespe | -0.226 |
andre | -0.220 |
Token | pic |
Token ID | 8301 |
Feature activation | -6.14e-02 |
Pos logit contributions | |
abol | +0.397 |
theless | +0.384 |
utonium | +0.374 |
akespe | +0.367 |
andre | +0.359 |
Neg logit contributions | |
Jinn | -0.246 |
↑ | -0.243 |
pai | -0.242 |
�� | -0.226 |
� | -0.224 |
Token | . |
Token ID | 13 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
abol | +0.080 |
theless | +0.078 |
utonium | +0.076 |
akespe | +0.074 |
andre | +0.073 |
Neg logit contributions | |
Jinn | -0.046 |
↑ | -0.046 |
pai | -0.046 |
�� | -0.043 |
� | -0.042 |
Token | twitter |
Token ID | 6956 |
Feature activation | +5.15e-02 |
Pos logit contributions | |
abol | +0.095 |
theless | +0.089 |
utonium | +0.085 |
akespe | +0.082 |
andre | +0.078 |
Neg logit contributions | |
Jinn | -0.184 |
↑ | -0.183 |
pai | -0.182 |
�� | -0.176 |
� | -0.174 |
Token | so |
Token ID | 523 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
↑ | +0.172 |
Jinn | +0.172 |
pai | +0.169 |
�� | +0.158 |
� | +0.157 |
Neg logit contributions | |
abol | -0.269 |
theless | -0.261 |
utonium | -0.255 |
akespe | -0.251 |
andre | -0.243 |
Token | that |
Token ID | 326 |
Feature activation | -5.93e-02 |
Pos logit contributions | |
abol | +0.144 |
theless | +0.140 |
utonium | +0.137 |
akespe | +0.134 |
andre | +0.130 |
Neg logit contributions | |
Jinn | -0.086 |
↑ | -0.086 |
pai | -0.085 |
�� | -0.079 |
� | -0.078 |
Token | if |
Token ID | 611 |
Feature activation | -3.30e-02 |
Pos logit contributions | |
abol | +0.075 |
theless | +0.072 |
utonium | +0.070 |
akespe | +0.069 |
andre | +0.067 |
Neg logit contributions | |
Jinn | -0.047 |
↑ | -0.047 |
pai | -0.047 |
�� | -0.044 |
� | -0.043 |
Token | they |
Token ID | 484 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
abol | +0.042 |
theless | +0.040 |
utonium | +0.039 |
akespe | +0.038 |
andre | +0.037 |
Neg logit contributions | |
Jinn | -0.027 |
↑ | -0.026 |
pai | -0.026 |
�� | -0.025 |
� | -0.024 |
Token | Out |
Token ID | 3806 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
Jinn | +0.010 |
↑ | +0.010 |
pai | +0.010 |
�� | +0.010 |
� | +0.010 |
Neg logit contributions | |
abol | -0.016 |
theless | -0.015 |
utonium | -0.015 |
akespe | -0.014 |
andre | -0.014 |
Token | wit |
Token ID | 39289 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
abol | +0.264 |
theless | +0.258 |
utonium | +0.254 |
akespe | +0.250 |
andre | +0.246 |
Neg logit contributions | |
Jinn | -0.038 |
↑ | -0.038 |
pai | -0.036 |
�� | -0.029 |
� | -0.028 |
Token | his |
Token ID | 465 |
Feature activation | +4.71e-02 |
Pos logit contributions | |
Jinn | +0.762 |
↑ | +0.758 |
pai | +0.748 |
�� | +0.693 |
� | +0.689 |
Neg logit contributions | |
abol | -1.310 |
theless | -1.270 |
utonium | -1.242 |
akespe | -1.218 |
andre | -1.187 |
Token | Master |
Token ID | 5599 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
Jinn | +0.045 |
↑ | +0.045 |
pai | +0.045 |
�� | +0.042 |
� | +0.042 |
Neg logit contributions | |
abol | -0.052 |
theless | -0.050 |
utonium | -0.049 |
akespe | -0.048 |
andre | -0.046 |
Token | mind |
Token ID | 10155 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
Jinn | +0.355 |
↑ | +0.353 |
pai | +0.351 |
�� | +0.333 |
� | +0.332 |
Neg logit contributions | |
abol | -0.285 |
theless | -0.274 |
utonium | -0.265 |
akespe | -0.258 |
andre | -0.248 |
Token | , |
Token ID | 11 |
Feature activation | -3.08e-02 |
Pos logit contributions | |
Jinn | +0.139 |
↑ | +0.139 |
pai | +0.137 |
�� | +0.127 |
� | +0.126 |
Neg logit contributions | |
abol | -0.248 |
theless | -0.240 |
utonium | -0.235 |
akespe | -0.230 |
andre | -0.225 |
Token | he |
Token ID | 339 |
Feature activation | +7.58e-02 |
Pos logit contributions | |
abol | +0.039 |
theless | +0.037 |
utonium | +0.037 |
akespe | +0.036 |
andre | +0.035 |
Neg logit contributions | |
Jinn | -0.025 |
↑ | -0.025 |
pai | -0.025 |
�� | -0.023 |
� | -0.023 |
Token | to |
Token ID | 284 |
Feature activation | +5.77e-02 |
Pos logit contributions | |
abol | +0.132 |
theless | +0.128 |
utonium | +0.125 |
akespe | +0.123 |
andre | +0.120 |
Neg logit contributions | |
Jinn | -0.076 |
↑ | -0.075 |
pai | -0.075 |
�� | -0.069 |
� | -0.069 |
Token | � |
Token ID | 564 |
Feature activation | -2.56e-03 |
Pos logit contributions | |
Jinn | +0.050 |
↑ | +0.049 |
pai | +0.049 |
�� | +0.047 |
� | +0.045 |
Neg logit contributions | |
abol | -0.069 |
theless | -0.067 |
utonium | -0.065 |
akespe | -0.063 |
andre | -0.062 |
Token | � |
Token ID | 246 |
Feature activation | -9.89e-02 |
Pos logit contributions | |
abol | +0.003 |
theless | +0.003 |
utonium | +0.002 |
akespe | +0.002 |
andre | +0.002 |
Neg logit contributions | |
Jinn | -0.003 |
↑ | -0.003 |
pai | -0.003 |
�� | -0.002 |
� | -0.002 |
Token | net |
Token ID | 3262 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
abol | +0.108 |
theless | +0.104 |
utonium | +0.101 |
akespe | +0.098 |
andre | +0.095 |
Neg logit contributions | |
Jinn | -0.097 |
↑ | -0.096 |
pai | -0.095 |
�� | -0.090 |
� | -0.089 |
Token | - |
Token ID | 12 |
Feature activation | +6.33e-02 |
Pos logit contributions | |
Jinn | +0.243 |
↑ | +0.242 |
pai | +0.241 |
�� | +0.225 |
� | +0.224 |
Neg logit contributions | |
abol | -0.340 |
theless | -0.328 |
utonium | -0.321 |
akespe | -0.314 |
andre | -0.305 |
Token | deck |
Token ID | 35875 |
Feature activation | +9.85e-01 |
Pos logit contributions | |
Jinn | +0.065 |
↑ | +0.064 |
pai | +0.064 |
�� | +0.061 |
� | +0.060 |
Neg logit contributions | |
abol | -0.066 |
theless | -0.063 |
utonium | -0.062 |
akespe | -0.060 |
andre | -0.058 |
Token | � |
Token ID | 447 |
Feature activation | +1.69e-02 |
Pos logit contributions | |
Jinn | +0.739 |
↑ | +0.736 |
pai | +0.728 |
�� | +0.673 |
� | +0.669 |
Neg logit contributions | |
abol | -1.296 |
theless | -1.253 |
utonium | -1.229 |
akespe | -1.205 |
andre | -1.172 |
Token | � |
Token ID | 247 |
Feature activation | +6.95e-02 |
Pos logit contributions | |
Jinn | +0.017 |
↑ | +0.017 |
pai | +0.017 |
�� | +0.016 |
� | +0.016 |
Neg logit contributions | |
abol | -0.018 |
theless | -0.017 |
utonium | -0.017 |
akespe | -0.016 |
andre | -0.016 |
Token | ( |
Token ID | 357 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
Jinn | +0.055 |
↑ | +0.055 |
pai | +0.054 |
�� | +0.051 |
� | +0.050 |
Neg logit contributions | |
abol | -0.089 |
theless | -0.086 |
utonium | -0.084 |
akespe | -0.082 |
andre | -0.080 |
Token | cop |
Token ID | 22163 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
Jinn | +0.167 |
↑ | +0.167 |
pai | +0.166 |
�� | +0.157 |
� | +0.156 |
Neg logit contributions | |
abol | -0.168 |
theless | -0.161 |
utonium | -0.157 |
akespe | -0.153 |
andre | -0.148 |
Token | ying |
Token ID | 1112 |
Feature activation | +1.66e-02 |
Pos logit contributions | |
Jinn | +0.341 |
↑ | +0.340 |
pai | +0.338 |
�� | +0.321 |
� | +0.319 |
Neg logit contributions | |
abol | -0.303 |
theless | -0.290 |
utonium | -0.280 |
akespe | -0.273 |
andre | -0.264 |
Token | alongside |
Token ID | 7848 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
Jinn | +0.106 |
↑ | +0.105 |
pai | +0.104 |
�� | +0.096 |
� | +0.094 |
Neg logit contributions | |
abol | -0.229 |
theless | -0.222 |
utonium | -0.218 |
akespe | -0.214 |
andre | -0.209 |
Token | Chelsea |
Token ID | 12147 |
Feature activation | -8.25e-03 |
Pos logit contributions | |
Jinn | +0.213 |
↑ | +0.211 |
pai | +0.209 |
�� | +0.197 |
� | +0.196 |
Neg logit contributions | |
abol | -0.276 |
theless | -0.267 |
utonium | -0.260 |
akespe | -0.254 |
andre | -0.247 |
Token | and |
Token ID | 290 |
Feature activation | +2.39e-02 |
Pos logit contributions | |
abol | +0.011 |
theless | +0.011 |
utonium | +0.011 |
akespe | +0.011 |
andre | +0.010 |
Neg logit contributions | |
Jinn | -0.006 |
↑ | -0.006 |
pai | -0.006 |
�� | -0.005 |
� | -0.005 |
Token | Tottenham |
Token ID | 24272 |
Feature activation | -2.51e-02 |
Pos logit contributions | |
Jinn | +0.023 |
↑ | +0.022 |
pai | +0.022 |
�� | +0.021 |
� | +0.021 |
Neg logit contributions | |
abol | -0.027 |
theless | -0.026 |
utonium | -0.025 |
akespe | -0.025 |
andre | -0.024 |
Token | Hots |
Token ID | 41239 |
Feature activation | +5.61e-01 |
Pos logit contributions | |
abol | +0.035 |
theless | +0.034 |
utonium | +0.034 |
akespe | +0.033 |
andre | +0.032 |
Neg logit contributions | |
Jinn | -0.016 |
↑ | -0.016 |
pai | -0.016 |
�� | -0.015 |
� | -0.015 |
Token | pur |
Token ID | 14225 |
Feature activation | +9.54e-01 |
Pos logit contributions | |
Jinn | +0.449 |
↑ | +0.439 |
pai | +0.435 |
�� | +0.412 |
� | +0.404 |
Neg logit contributions | |
abol | -0.714 |
theless | -0.679 |
utonium | -0.673 |
akespe | -0.660 |
andre | -0.650 |
Token | for |
Token ID | 329 |
Feature activation | +2.36e-02 |
Pos logit contributions | |
Jinn | +0.626 |
↑ | +0.621 |
pai | +0.612 |
�� | +0.563 |
� | +0.555 |
Neg logit contributions | |
abol | -1.347 |
theless | -1.307 |
utonium | -1.279 |
akespe | -1.258 |
andre | -1.228 |
Token | the |
Token ID | 262 |
Feature activation | +6.50e-02 |
Pos logit contributions | |
Jinn | +0.017 |
↑ | +0.017 |
pai | +0.017 |
�� | +0.016 |
� | +0.016 |
Neg logit contributions | |
abol | -0.031 |
theless | -0.030 |
utonium | -0.030 |
akespe | -0.029 |
andre | -0.028 |
Token | Premier |
Token ID | 9952 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
Jinn | +0.057 |
↑ | +0.056 |
pai | +0.056 |
�� | +0.052 |
� | +0.052 |
Neg logit contributions | |
abol | -0.078 |
theless | -0.075 |
utonium | -0.073 |
akespe | -0.071 |
andre | -0.069 |
Token | League |
Token ID | 4041 |
Feature activation | +1.85e-02 |
Pos logit contributions | |
Jinn | +0.217 |
pai | +0.215 |
↑ | +0.213 |
�� | +0.200 |
� | +0.198 |
Neg logit contributions | |
abol | -0.357 |
theless | -0.344 |
utonium | -0.337 |
akespe | -0.329 |
andre | -0.324 |
Token | title |
Token ID | 3670 |
Feature activation | +1.95e-02 |
Pos logit contributions | |
Jinn | +0.015 |
↑ | +0.015 |
pai | +0.015 |
�� | +0.014 |
� | +0.014 |
Neg logit contributions | |
abol | -0.023 |
theless | -0.022 |
utonium | -0.022 |
akespe | -0.021 |
andre | -0.021 |
Token | � |
Token ID | 247 |
Feature activation | +6.78e-02 |
Pos logit contributions | |
abol | +0.041 |
theless | +0.039 |
utonium | +0.038 |
akespe | +0.037 |
andre | +0.037 |
Neg logit contributions | |
Jinn | -0.027 |
↑ | -0.027 |
pai | -0.027 |
�� | -0.025 |
� | -0.025 |
Token | s |
Token ID | 82 |
Feature activation | -3.83e-03 |
Pos logit contributions | |
Jinn | +0.054 |
↑ | +0.054 |
pai | +0.054 |
�� | +0.050 |
� | +0.050 |
Neg logit contributions | |
abol | -0.085 |
theless | -0.082 |
utonium | -0.081 |
akespe | -0.079 |
andre | -0.077 |
Token | � |
Token ID | 564 |
Feature activation | +4.87e-04 |
Pos logit contributions | |
abol | +0.005 |
theless | +0.004 |
utonium | +0.004 |
akespe | +0.004 |
andre | +0.004 |
Neg logit contributions | |
Jinn | -0.003 |
↑ | -0.003 |
pai | -0.003 |
�� | -0.003 |
� | -0.003 |
Token | � |
Token ID | 250 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
Jinn | +0.000 |
↑ | +0.000 |
pai | +0.000 |
�� | +0.000 |
� | +0.000 |
Neg logit contributions | |
abol | -0.001 |
theless | -0.001 |
utonium | -0.001 |
akespe | -0.001 |
andre | -0.001 |
Token | sec |
Token ID | 2363 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
abol | +0.012 |
theless | +0.012 |
utonium | +0.012 |
akespe | +0.011 |
andre | +0.011 |
Neg logit contributions | |
Jinn | -0.012 |
↑ | -0.012 |
pai | -0.012 |
�� | -0.012 |
� | -0.012 |
Token | rets |
Token ID | 8004 |
Feature activation | +9.54e-01 |
Pos logit contributions | |
Jinn | +0.257 |
↑ | +0.256 |
pai | +0.254 |
�� | +0.242 |
� | +0.240 |
Neg logit contributions | |
abol | -0.238 |
theless | -0.228 |
utonium | -0.222 |
akespe | -0.216 |
andre | -0.209 |
Token | � |
Token ID | 447 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
↑ | +0.724 |
Jinn | +0.720 |
pai | +0.711 |
�� | +0.661 |
� | +0.655 |
Neg logit contributions | |
abol | -1.245 |
theless | -1.206 |
utonium | -1.177 |
akespe | -1.157 |
andre | -1.123 |
Token | � |
Token ID | 251 |
Feature activation | +7.04e-02 |
Pos logit contributions | |
Jinn | +0.121 |
↑ | +0.120 |
pai | +0.119 |
�� | +0.112 |
� | +0.110 |
Neg logit contributions | |
abol | -0.196 |
theless | -0.190 |
utonium | -0.185 |
akespe | -0.181 |
andre | -0.177 |
Token | . |
Token ID | 13 |
Feature activation | +7.51e-02 |
Pos logit contributions | |
Jinn | +0.053 |
↑ | +0.053 |
pai | +0.052 |
�� | +0.049 |
� | +0.048 |
Neg logit contributions | |
abol | -0.092 |
theless | -0.089 |
utonium | -0.087 |
akespe | -0.085 |
andre | -0.083 |
Token |
|
Token ID | 198 |
Feature activation | +2.61e-03 |
Pos logit contributions | |
Jinn | +0.061 |
↑ | +0.061 |
pai | +0.060 |
�� | +0.056 |
� | +0.056 |
Neg logit contributions | |
abol | -0.094 |
theless | -0.091 |
utonium | -0.089 |
akespe | -0.087 |
andre | -0.085 |
Token |
|
Token ID | 198 |
Feature activation | +3.69e-02 |
Pos logit contributions | |
Jinn | +0.002 |
↑ | +0.002 |
pai | +0.002 |
�� | +0.002 |
� | +0.002 |
Neg logit contributions | |
abol | -0.003 |
theless | -0.003 |
utonium | -0.003 |
akespe | -0.003 |
andre | -0.003 |
Token | � |
Token ID | 447 |
Feature activation | +5.50e-02 |
Pos logit contributions | |
Jinn | +0.192 |
↑ | +0.191 |
pai | +0.190 |
�� | +0.179 |
� | +0.177 |
Neg logit contributions | |
abol | -0.245 |
theless | -0.235 |
utonium | -0.229 |
akespe | -0.224 |
andre | -0.219 |
Token | � |
Token ID | 247 |
Feature activation | +2.40e-02 |
Pos logit contributions | |
Jinn | +0.056 |
↑ | +0.055 |
pai | +0.055 |
�� | +0.052 |
� | +0.052 |
Neg logit contributions | |
abol | -0.058 |
theless | -0.056 |
utonium | -0.054 |
akespe | -0.053 |
andre | -0.051 |
Token | t |
Token ID | 83 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
Jinn | +0.021 |
↑ | +0.021 |
pai | +0.021 |
�� | +0.019 |
� | +0.019 |
Neg logit contributions | |
abol | -0.029 |
theless | -0.028 |
utonium | -0.027 |
akespe | -0.026 |
andre | -0.026 |
Token | have |
Token ID | 423 |
Feature activation | +6.66e-02 |
Pos logit contributions | |
abol | +0.015 |
theless | +0.015 |
utonium | +0.014 |
akespe | +0.014 |
andre | +0.014 |
Neg logit contributions | |
Jinn | -0.011 |
↑ | -0.011 |
pai | -0.011 |
�� | -0.010 |
� | -0.010 |
Token | Out |
Token ID | 3806 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
Jinn | +0.051 |
↑ | +0.051 |
pai | +0.050 |
�� | +0.047 |
� | +0.046 |
Neg logit contributions | |
abol | -0.086 |
theless | -0.084 |
utonium | -0.082 |
akespe | -0.080 |
andre | -0.078 |
Token | wit |
Token ID | 39289 |
Feature activation | +9.33e-01 |
Pos logit contributions | |
abol | +0.147 |
theless | +0.142 |
utonium | +0.139 |
akespe | +0.136 |
andre | +0.133 |
Neg logit contributions | |
Jinn | -0.084 |
↑ | -0.084 |
pai | -0.083 |
�� | -0.077 |
� | -0.076 |
Token | , |
Token ID | 11 |
Feature activation | +2.26e-02 |
Pos logit contributions | |
Jinn | +0.741 |
↑ | +0.738 |
pai | +0.729 |
�� | +0.680 |
� | +0.674 |
Neg logit contributions | |
abol | -1.186 |
theless | -1.149 |
utonium | -1.122 |
akespe | -1.100 |
andre | -1.071 |
Token | and |
Token ID | 290 |
Feature activation | +4.13e-02 |
Pos logit contributions | |
Jinn | +0.018 |
↑ | +0.018 |
pai | +0.017 |
�� | +0.016 |
� | +0.016 |
Neg logit contributions | |
abol | -0.029 |
theless | -0.028 |
utonium | -0.027 |
akespe | -0.027 |
andre | -0.026 |
Token | his |
Token ID | 465 |
Feature activation | -3.33e-03 |
Pos logit contributions | |
Jinn | +0.033 |
↑ | +0.032 |
pai | +0.032 |
�� | +0.030 |
� | +0.030 |
Neg logit contributions | |
abol | -0.053 |
theless | -0.051 |
utonium | -0.050 |
akespe | -0.049 |
andre | -0.048 |
Token | STOP |
Token ID | 44934 |
Feature activation | +6.55e-02 |
Pos logit contributions | |
abol | +0.004 |
theless | +0.004 |
utonium | +0.004 |
akespe | +0.004 |
andre | +0.004 |
Neg logit contributions | |
Jinn | -0.003 |
↑ | -0.003 |
pai | -0.003 |
�� | -0.003 |
� | -0.003 |
Token | click |
Token ID | 3904 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
Jinn | +0.058 |
↑ | +0.058 |
pai | +0.057 |
�� | +0.054 |
� | +0.053 |
Neg logit contributions | |
abol | -0.077 |
theless | -0.075 |
utonium | -0.073 |
akespe | -0.071 |
andre | -0.069 |
Token | Fire |
Token ID | 3764 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
Jinn | +0.031 |
↑ | +0.031 |
pai | +0.031 |
�� | +0.029 |
� | +0.029 |
Neg logit contributions | |
abol | -0.051 |
theless | -0.050 |
utonium | -0.048 |
akespe | -0.047 |
andre | -0.046 |
Token | j |
Token ID | 73 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
abol | +0.492 |
theless | +0.473 |
utonium | +0.462 |
akespe | +0.450 |
andre | +0.436 |
Neg logit contributions | |
Jinn | -0.433 |
↑ | -0.431 |
pai | -0.424 |
�� | -0.402 |
� | -0.400 |
Token | ail |
Token ID | 603 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
abol | +0.097 |
theless | +0.092 |
utonium | +0.088 |
akespe | +0.085 |
andre | +0.080 |
Neg logit contributions | |
Jinn | -0.175 |
↑ | -0.174 |
pai | -0.173 |
� | -0.165 |
�� | -0.165 |
Token | . |
Token ID | 764 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
abol | +0.267 |
theless | +0.258 |
utonium | +0.252 |
akespe | +0.247 |
andre | +0.241 |
Neg logit contributions | |
Jinn | -0.160 |
↑ | -0.159 |
pai | -0.157 |
�� | -0.146 |
� | -0.145 |
Token | Dist |
Token ID | 4307 |
Feature activation | +3.59e-02 |
Pos logit contributions | |
Jinn | +0.174 |
↑ | +0.173 |
pai | +0.172 |
�� | +0.161 |
� | +0.159 |
Neg logit contributions | |
abol | -0.256 |
theless | -0.247 |
utonium | -0.241 |
akespe | -0.236 |
andre | -0.230 |
Token | ribute |
Token ID | 4163 |
Feature activation | +9.31e-01 |
Pos logit contributions | |
Jinn | +0.024 |
↑ | +0.023 |
pai | +0.023 |
�� | +0.021 |
� | +0.021 |
Neg logit contributions | |
abol | -0.051 |
theless | -0.049 |
utonium | -0.048 |
akespe | -0.047 |
andre | -0.046 |
Token | your |
Token ID | 534 |
Feature activation | -9.69e-02 |
Pos logit contributions | |
Jinn | +0.721 |
↑ | +0.717 |
pai | +0.710 |
�� | +0.662 |
� | +0.656 |
Neg logit contributions | |
abol | -1.201 |
theless | -1.162 |
utonium | -1.134 |
akespe | -1.113 |
andre | -1.086 |
Token | desktop |
Token ID | 11364 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
abol | +0.111 |
theless | +0.107 |
utonium | +0.104 |
akespe | +0.101 |
andre | +0.099 |
Neg logit contributions | |
Jinn | -0.089 |
↑ | -0.089 |
pai | -0.088 |
�� | -0.083 |
� | -0.083 |
Token | Linux |
Token ID | 7020 |
Feature activation | -8.03e-02 |
Pos logit contributions | |
abol | +0.298 |
theless | +0.288 |
utonium | +0.281 |
akespe | +0.275 |
andre | +0.268 |
Neg logit contributions | |
Jinn | -0.194 |
↑ | -0.193 |
pai | -0.191 |
�� | -0.179 |
� | -0.177 |
Token | application |
Token ID | 3586 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
abol | +0.094 |
theless | +0.091 |
utonium | +0.089 |
akespe | +0.087 |
andre | +0.084 |
Neg logit contributions | |
Jinn | -0.071 |
↑ | -0.071 |
pai | -0.070 |
�� | -0.066 |
� | -0.066 |
Token | in |
Token ID | 287 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
abol | +0.174 |
theless | +0.168 |
utonium | +0.164 |
akespe | +0.161 |
andre | +0.158 |
Neg logit contributions | |
Jinn | -0.095 |
↑ | -0.094 |
pai | -0.093 |
�� | -0.086 |
� | -0.086 |
Token | - |
Token ID | 12 |
Feature activation | +8.62e-02 |
Pos logit contributions | |
abol | +0.037 |
theless | +0.036 |
utonium | +0.035 |
akespe | +0.034 |
andre | +0.033 |
Neg logit contributions | |
↑ | -0.032 |
Jinn | -0.032 |
pai | -0.031 |
� | -0.029 |
�� | -0.029 |
Token | |
Token ID | 220 |
Feature activation | +6.15e-01 |
Pos logit contributions | |
Jinn | +0.080 |
↑ | +0.080 |
pai | +0.079 |
�� | +0.075 |
� | +0.074 |
Neg logit contributions | |
abol | -0.097 |
theless | -0.094 |
utonium | -0.092 |
akespe | -0.089 |
andre | -0.087 |
Token | ional |
Token ID | 1538 |
Feature activation | -7.14e-01 |
Pos logit contributions | |
pai | +0.567 |
↑ | +0.566 |
Jinn | +0.562 |
�� | +0.527 |
� | +0.522 |
Neg logit contributions | |
abol | -0.698 |
theless | -0.673 |
utonium | -0.661 |
akespe | -0.639 |
andre | -0.620 |
Token | that |
Token ID | 326 |
Feature activation | -5.10e-02 |
Pos logit contributions | |
abol | +0.858 |
theless | +0.824 |
utonium | +0.799 |
akespe | +0.786 |
andre | +0.771 |
Neg logit contributions | |
Jinn | -0.616 |
↑ | -0.610 |
pai | -0.610 |
�� | -0.574 |
� | -0.567 |
Token | For |
Token ID | 1114 |
Feature activation | -5.68e-02 |
Pos logit contributions | |
abol | +0.068 |
theless | +0.065 |
utonium | +0.064 |
akespe | +0.063 |
andre | +0.061 |
Neg logit contributions | |
Jinn | -0.038 |
↑ | -0.037 |
pai | -0.037 |
�� | -0.034 |
� | -0.034 |
Token | cade |
Token ID | 46395 |
Feature activation | +9.15e-01 |
Pos logit contributions | |
abol | +0.059 |
theless | +0.056 |
utonium | +0.054 |
akespe | +0.053 |
andre | +0.052 |
Neg logit contributions | |
Jinn | -0.059 |
↑ | -0.058 |
pai | -0.058 |
�� | -0.055 |
� | -0.055 |
Token | ll |
Token ID | 297 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
Jinn | +0.903 |
↑ | +0.900 |
pai | +0.893 |
�� | +0.844 |
� | +0.839 |
Neg logit contributions | |
abol | -0.986 |
theless | -0.949 |
utonium | -0.922 |
akespe | -0.900 |
andre | -0.872 |
Token | � |
Token ID | 447 |
Feature activation | +6.13e-02 |
Pos logit contributions | |
Jinn | +0.114 |
↑ | +0.113 |
pai | +0.112 |
�� | +0.103 |
� | +0.103 |
Neg logit contributions | |
abol | -0.205 |
theless | -0.199 |
utonium | -0.194 |
akespe | -0.191 |
andre | -0.186 |
Token | � |
Token ID | 247 |
Feature activation | +9.65e-02 |
Pos logit contributions | |
Jinn | +0.056 |
↑ | +0.056 |
pai | +0.055 |
�� | +0.052 |
� | +0.052 |
Neg logit contributions | |
abol | -0.071 |
theless | -0.068 |
utonium | -0.066 |
akespe | -0.065 |
andre | -0.063 |
Token | s |
Token ID | 82 |
Feature activation | +2.48e-02 |
Pos logit contributions | |
Jinn | +0.080 |
↑ | +0.079 |
pai | +0.079 |
�� | +0.073 |
� | +0.073 |
Neg logit contributions | |
abol | -0.120 |
theless | -0.116 |
utonium | -0.113 |
akespe | -0.111 |
andre | -0.108 |
Token | was |
Token ID | 373 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
Jinn | +0.022 |
↑ | +0.022 |
pai | +0.022 |
�� | +0.021 |
� | +0.021 |
Neg logit contributions | |
abol | -0.029 |
theless | -0.028 |
utonium | -0.027 |
akespe | -0.027 |
andre | -0.026 |
Token | Girls |
Token ID | 12002 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
Jinn | +0.006 |
↑ | +0.006 |
pai | +0.006 |
�� | +0.006 |
� | +0.006 |
Neg logit contributions | |
abol | -0.009 |
theless | -0.009 |
utonium | -0.008 |
akespe | -0.008 |
andre | -0.008 |
Token | at |
Token ID | 379 |
Feature activation | +8.39e-03 |
Pos logit contributions | |
abol | +0.451 |
theless | +0.433 |
utonium | +0.427 |
akespe | +0.417 |
andre | +0.410 |
Neg logit contributions | |
Jinn | -0.235 |
pai | -0.233 |
↑ | -0.233 |
�� | -0.217 |
� | -0.214 |
Token | Risk |
Token ID | 19602 |
Feature activation | +3.21e-02 |
Pos logit contributions | |
Jinn | +0.006 |
↑ | +0.006 |
pai | +0.006 |
�� | +0.006 |
� | +0.006 |
Neg logit contributions | |
abol | -0.011 |
theless | -0.011 |
utonium | -0.011 |
akespe | -0.010 |
andre | -0.010 |
Token | of |
Token ID | 286 |
Feature activation | -2.46e-02 |
Pos logit contributions | |
Jinn | +0.027 |
↑ | +0.027 |
pai | +0.027 |
�� | +0.025 |
� | +0.025 |
Neg logit contributions | |
abol | -0.039 |
theless | -0.038 |
utonium | -0.037 |
akespe | -0.036 |
andre | -0.035 |
Token | Gen |
Token ID | 5215 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
abol | +0.030 |
theless | +0.029 |
utonium | +0.028 |
akespe | +0.027 |
andre | +0.027 |
Neg logit contributions | |
Jinn | -0.021 |
↑ | -0.021 |
pai | -0.021 |
�� | -0.020 |
� | -0.019 |
Token | ital |
Token ID | 1287 |
Feature activation | +9.12e-01 |
Pos logit contributions | |
Jinn | +0.115 |
↑ | +0.114 |
pai | +0.113 |
�� | +0.107 |
� | +0.105 |
Neg logit contributions | |
abol | -0.176 |
theless | -0.168 |
utonium | -0.166 |
akespe | -0.162 |
andre | -0.159 |
Token | Mut |
Token ID | 13859 |
Feature activation | -4.19e-03 |
Pos logit contributions | |
Jinn | +0.639 |
↑ | +0.635 |
pai | +0.626 |
�� | +0.577 |
� | +0.571 |
Neg logit contributions | |
abol | -1.242 |
theless | -1.215 |
utonium | -1.186 |
akespe | -1.168 |
andre | -1.132 |
Token | ilation |
Token ID | 10520 |
Feature activation | -2.25e-02 |
Pos logit contributions | |
abol | +0.004 |
theless | +0.004 |
utonium | +0.004 |
akespe | +0.004 |
andre | +0.004 |
Neg logit contributions | |
Jinn | -0.004 |
↑ | -0.004 |
pai | -0.004 |
�� | -0.004 |
� | -0.004 |
Token | � |
Token ID | 447 |
Feature activation | +6.21e-02 |
Pos logit contributions | |
abol | +0.027 |
theless | +0.027 |
utonium | +0.026 |
akespe | +0.025 |
andre | +0.025 |
Neg logit contributions | |
Jinn | -0.019 |
↑ | -0.019 |
pai | -0.019 |
�� | -0.018 |
� | -0.017 |
Token | � |
Token ID | 251 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
Jinn | +0.052 |
↑ | +0.051 |
pai | +0.051 |
�� | +0.048 |
� | +0.047 |
Neg logit contributions | |
abol | -0.077 |
theless | -0.074 |
utonium | -0.072 |
akespe | -0.071 |
andre | -0.069 |
Token | ? |
Token ID | 30 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
Jinn | +0.093 |
↑ | +0.093 |
pai | +0.092 |
�� | +0.086 |
� | +0.085 |
Neg logit contributions | |
abol | -0.144 |
theless | -0.140 |
utonium | -0.136 |
akespe | -0.134 |
andre | -0.130 |
Token | reacted |
Token ID | 22798 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
abol | +0.265 |
theless | +0.256 |
utonium | +0.249 |
akespe | +0.244 |
andre | +0.239 |
Neg logit contributions | |
Jinn | -0.170 |
↑ | -0.169 |
pai | -0.168 |
�� | -0.157 |
� | -0.155 |
Token | furiously |
Token ID | 44896 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
Jinn | +0.013 |
↑ | +0.013 |
pai | +0.013 |
� | +0.012 |
�� | +0.012 |
Neg logit contributions | |
abol | -0.020 |
theless | -0.019 |
utonium | -0.019 |
akespe | -0.018 |
andre | -0.018 |
Token | to |
Token ID | 284 |
Feature activation | -1.94e-02 |
Pos logit contributions | |
abol | +0.015 |
theless | +0.015 |
utonium | +0.014 |
akespe | +0.014 |
andre | +0.014 |
Neg logit contributions | |
Jinn | -0.008 |
↑ | -0.008 |
pai | -0.008 |
�� | -0.007 |
� | -0.007 |
Token | Chancellor |
Token ID | 19477 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
abol | +0.024 |
theless | +0.024 |
utonium | +0.023 |
akespe | +0.023 |
andre | +0.022 |
Neg logit contributions | |
Jinn | -0.016 |
↑ | -0.015 |
pai | -0.015 |
�� | -0.014 |
� | -0.014 |
Token | Philip |
Token ID | 14576 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
Jinn | +0.110 |
↑ | +0.109 |
pai | +0.108 |
� | +0.102 |
�� | +0.102 |
Neg logit contributions | |
abol | -0.120 |
theless | -0.116 |
utonium | -0.112 |
akespe | -0.110 |
andre | -0.106 |
Token | Hammond |
Token ID | 26649 |
Feature activation | +9.11e-01 |
Pos logit contributions | |
Jinn | +0.063 |
↑ | +0.062 |
pai | +0.061 |
�� | +0.055 |
� | +0.054 |
Neg logit contributions | |
abol | -0.176 |
theless | -0.171 |
utonium | -0.167 |
akespe | -0.165 |
andre | -0.161 |
Token | 's |
Token ID | 338 |
Feature activation | +3.92e-02 |
Pos logit contributions | |
Jinn | +0.689 |
↑ | +0.679 |
pai | +0.674 |
�� | +0.622 |
ki | +0.620 |
Neg logit contributions | |
abol | -1.196 |
theless | -1.158 |
utonium | -1.133 |
akespe | -1.110 |
andre | -1.082 |
Token | budget |
Token ID | 4466 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
Jinn | +0.037 |
↑ | +0.036 |
pai | +0.036 |
�� | +0.034 |
� | +0.034 |
Neg logit contributions | |
abol | -0.044 |
theless | -0.043 |
utonium | -0.042 |
akespe | -0.041 |
andre | -0.039 |
Token | pledge |
Token ID | 13995 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
Jinn | +0.135 |
↑ | +0.134 |
pai | +0.133 |
� | +0.125 |
�� | +0.125 |
Neg logit contributions | |
abol | -0.160 |
theless | -0.155 |
utonium | -0.151 |
akespe | -0.147 |
andre | -0.143 |
Token | to |
Token ID | 284 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
Jinn | +0.230 |
↑ | +0.229 |
pai | +0.226 |
�� | +0.208 |
� | +0.208 |
Neg logit contributions | |
abol | -0.412 |
theless | -0.401 |
utonium | -0.392 |
akespe | -0.384 |
andre | -0.375 |
Token | give |
Token ID | 1577 |
Feature activation | +2.14e-02 |
Pos logit contributions | |
Jinn | +0.143 |
↑ | +0.142 |
pai | +0.141 |
�� | +0.132 |
� | +0.131 |
Neg logit contributions | |
abol | -0.206 |
theless | -0.200 |
utonium | -0.195 |
akespe | -0.191 |
andre | -0.186 |
Token | by |
Token ID | 416 |
Feature activation | -5.56e-02 |
Pos logit contributions | |
abol | +0.031 |
theless | +0.030 |
utonium | +0.029 |
akespe | +0.029 |
andre | +0.028 |
Neg logit contributions | |
Jinn | -0.016 |
↑ | -0.016 |
pai | -0.016 |
�� | -0.015 |
� | -0.014 |
Token | Buddhism |
Token ID | 25932 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
abol | +0.076 |
theless | +0.074 |
utonium | +0.072 |
akespe | +0.071 |
andre | +0.070 |
Neg logit contributions | |
Jinn | -0.038 |
↑ | -0.038 |
pai | -0.038 |
�� | -0.035 |
� | -0.034 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +8.37e-02 |
Pos logit contributions | |
Jinn | +0.097 |
↑ | +0.096 |
pai | +0.096 |
�� | +0.089 |
� | +0.088 |
Neg logit contributions | |
abol | -0.162 |
theless | -0.157 |
utonium | -0.153 |
akespe | -0.150 |
andre | -0.147 |
Token | " |
Token ID | 1 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
↑ | +0.090 |
Jinn | +0.090 |
pai | +0.090 |
�� | +0.085 |
� | +0.085 |
Neg logit contributions | |
abol | -0.082 |
theless | -0.080 |
utonium | -0.077 |
akespe | -0.075 |
andre | -0.072 |
Token | Sec |
Token ID | 6558 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
abol | +0.099 |
theless | +0.095 |
utonium | +0.092 |
akespe | +0.090 |
andre | +0.087 |
Neg logit contributions | |
Jinn | -0.111 |
↑ | -0.111 |
pai | -0.110 |
�� | -0.105 |
� | -0.104 |
Token | rets |
Token ID | 8004 |
Feature activation | +9.10e-01 |
Pos logit contributions | |
Jinn | +0.387 |
↑ | +0.385 |
pai | +0.382 |
�� | +0.361 |
� | +0.358 |
Neg logit contributions | |
abol | -0.451 |
theless | -0.433 |
utonium | -0.422 |
akespe | -0.412 |
andre | -0.401 |
Token | of |
Token ID | 286 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
Jinn | +0.696 |
↑ | +0.695 |
pai | +0.685 |
�� | +0.637 |
� | +0.632 |
Neg logit contributions | |
abol | -1.181 |
theless | -1.147 |
utonium | -1.118 |
akespe | -1.098 |
andre | -1.070 |
Token | Season |
Token ID | 7369 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
Jinn | +0.100 |
↑ | +0.100 |
pai | +0.099 |
�� | +0.092 |
� | +0.091 |
Neg logit contributions | |
abol | -0.167 |
theless | -0.162 |
utonium | -0.158 |
akespe | -0.155 |
andre | -0.151 |
Token | One |
Token ID | 1881 |
Feature activation | +2.44e-02 |
Pos logit contributions | |
↑ | +0.323 |
Jinn | +0.322 |
pai | +0.319 |
�� | +0.296 |
� | +0.292 |
Neg logit contributions | |
abol | -0.506 |
theless | -0.491 |
utonium | -0.478 |
akespe | -0.469 |
andre | -0.456 |
Token | " |
Token ID | 366 |
Feature activation | -8.61e-02 |
Pos logit contributions | |
Jinn | +0.018 |
↑ | +0.018 |
pai | +0.018 |
�� | +0.016 |
� | +0.016 |
Neg logit contributions | |
abol | -0.033 |
theless | -0.032 |
utonium | -0.031 |
akespe | -0.030 |
andre | -0.030 |
Token |
|
Token ID | 198 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
abol | +0.105 |
theless | +0.102 |
utonium | +0.099 |
akespe | +0.097 |
andre | +0.094 |
Neg logit contributions | |
Jinn | -0.073 |
↑ | -0.073 |
pai | -0.072 |
�� | -0.067 |
� | -0.067 |
Token | , |
Token ID | 11 |
Feature activation | +4.78e-03 |
Pos logit contributions | |
Jinn | +0.053 |
↑ | +0.053 |
pai | +0.052 |
�� | +0.049 |
� | +0.048 |
Neg logit contributions | |
abol | -0.097 |
theless | -0.094 |
utonium | -0.092 |
akespe | -0.090 |
andre | -0.088 |
Token | or |
Token ID | 393 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
Jinn | +0.004 |
↑ | +0.004 |
pai | +0.004 |
�� | +0.003 |
� | +0.003 |
Neg logit contributions | |
abol | -0.006 |
theless | -0.006 |
utonium | -0.006 |
akespe | -0.006 |
andre | -0.006 |
Token | grants |
Token ID | 11455 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
abol | +0.014 |
theless | +0.013 |
utonium | +0.013 |
akespe | +0.013 |
andre | +0.012 |
Neg logit contributions | |
Jinn | -0.009 |
↑ | -0.009 |
pai | -0.009 |
�� | -0.008 |
� | -0.008 |
Token | him |
Token ID | 683 |
Feature activation | +6.39e-02 |
Pos logit contributions | |
Jinn | +0.106 |
↑ | +0.105 |
pai | +0.104 |
�� | +0.096 |
� | +0.095 |
Neg logit contributions | |
abol | -0.205 |
theless | -0.199 |
utonium | -0.194 |
akespe | -0.191 |
andre | -0.186 |
Token | Out |
Token ID | 3806 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
Jinn | +0.051 |
↑ | +0.050 |
pai | +0.050 |
�� | +0.047 |
� | +0.046 |
Neg logit contributions | |
abol | -0.081 |
theless | -0.079 |
utonium | -0.077 |
akespe | -0.075 |
andre | -0.073 |
Token | wit |
Token ID | 39289 |
Feature activation | +9.07e-01 |
Pos logit contributions | |
abol | +0.385 |
theless | +0.376 |
utonium | +0.370 |
akespe | +0.365 |
andre | +0.359 |
Neg logit contributions | |
Jinn | -0.060 |
↑ | -0.059 |
pai | -0.057 |
�� | -0.046 |
� | -0.045 |
Token | so |
Token ID | 523 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
↑ | +0.661 |
Jinn | +0.659 |
pai | +0.648 |
�� | +0.599 |
ki | +0.593 |
Neg logit contributions | |
abol | -1.214 |
theless | -1.180 |
utonium | -1.152 |
akespe | -1.135 |
andre | -1.102 |
Token | that |
Token ID | 326 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
abol | +0.223 |
theless | +0.216 |
utonium | +0.210 |
akespe | +0.206 |
andre | +0.201 |
Neg logit contributions | |
Jinn | -0.157 |
↑ | -0.156 |
pai | -0.155 |
�� | -0.145 |
� | -0.144 |
Token | he |
Token ID | 339 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
abol | +0.146 |
theless | +0.141 |
utonium | +0.137 |
akespe | +0.134 |
andre | +0.131 |
Neg logit contributions | |
Jinn | -0.091 |
↑ | -0.091 |
pai | -0.090 |
�� | -0.084 |
� | -0.084 |
Token | can |
Token ID | 460 |
Feature activation | -2.04e-03 |
Pos logit contributions | |
Jinn | +0.014 |
↑ | +0.014 |
pai | +0.013 |
�� | +0.012 |
� | +0.012 |
Neg logit contributions | |
abol | -0.024 |
theless | -0.023 |
utonium | -0.023 |
akespe | -0.022 |
andre | -0.022 |
Token | counter |
Token ID | 3753 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
abol | +0.002 |
theless | +0.002 |
utonium | +0.002 |
akespe | +0.002 |
andre | +0.002 |
Neg logit contributions | |
Jinn | -0.002 |
↑ | -0.002 |
pai | -0.002 |
�� | -0.002 |
� | -0.002 |
Token | present |
Token ID | 1944 |
Feature activation | +6.24e-02 |
Pos logit contributions | |
Jinn | +0.060 |
↑ | +0.060 |
pai | +0.059 |
�� | +0.054 |
� | +0.053 |
Neg logit contributions | |
abol | -0.149 |
theless | -0.145 |
utonium | -0.142 |
akespe | -0.139 |
andre | -0.136 |
Token | . |
Token ID | 13 |
Feature activation | +4.32e-02 |
Pos logit contributions | |
Jinn | +0.046 |
↑ | +0.045 |
pai | +0.045 |
�� | +0.042 |
� | +0.041 |
Neg logit contributions | |
abol | -0.083 |
theless | -0.081 |
utonium | -0.079 |
akespe | -0.077 |
andre | -0.075 |
Token |
|
Token ID | 198 |
Feature activation | +7.56e-02 |
Pos logit contributions | |
Jinn | +0.036 |
↑ | +0.035 |
pai | +0.035 |
�� | +0.033 |
� | +0.032 |
Neg logit contributions | |
abol | -0.054 |
theless | -0.052 |
utonium | -0.050 |
akespe | -0.049 |
andre | -0.048 |
Token |
|
Token ID | 198 |
Feature activation | +7.72e-02 |
Pos logit contributions | |
Jinn | +0.061 |
↑ | +0.060 |
pai | +0.060 |
�� | +0.057 |
� | +0.056 |
Neg logit contributions | |
abol | -0.095 |
theless | -0.091 |
utonium | -0.089 |
akespe | -0.087 |
andre | -0.086 |
Token | For |
Token ID | 1890 |
Feature activation | -8.10e-02 |
Pos logit contributions | |
↑ | +0.081 |
Jinn | +0.081 |
pai | +0.080 |
�� | +0.076 |
� | +0.076 |
Neg logit contributions | |
abol | -0.078 |
theless | -0.076 |
utonium | -0.073 |
akespe | -0.071 |
andre | -0.069 |
Token | cade |
Token ID | 46395 |
Feature activation | +9.02e-01 |
Pos logit contributions | |
abol | +0.084 |
theless | +0.081 |
utonium | +0.078 |
akespe | +0.076 |
andre | +0.074 |
Neg logit contributions | |
Jinn | -0.083 |
↑ | -0.083 |
pai | -0.082 |
�� | -0.078 |
� | -0.077 |
Token | ll |
Token ID | 297 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
Jinn | +0.881 |
↑ | +0.878 |
pai | +0.872 |
�� | +0.822 |
� | +0.819 |
Neg logit contributions | |
abol | -0.979 |
theless | -0.945 |
utonium | -0.918 |
akespe | -0.896 |
andre | -0.866 |
Token | told |
Token ID | 1297 |
Feature activation | -2.01e-02 |
Pos logit contributions | |
Jinn | +0.090 |
↑ | +0.089 |
pai | +0.089 |
�� | +0.082 |
� | +0.082 |
Neg logit contributions | |
abol | -0.153 |
theless | -0.148 |
utonium | -0.145 |
akespe | -0.142 |
andre | -0.138 |
Token | the |
Token ID | 262 |
Feature activation | +7.53e-03 |
Pos logit contributions | |
abol | +0.027 |
theless | +0.026 |
utonium | +0.025 |
akespe | +0.025 |
andre | +0.024 |
Neg logit contributions | |
Jinn | -0.015 |
↑ | -0.015 |
pai | -0.015 |
�� | -0.014 |
� | -0.014 |
Token | judges |
Token ID | 10266 |
Feature activation | +5.19e-02 |
Pos logit contributions | |
Jinn | +0.007 |
↑ | +0.007 |
pai | +0.007 |
�� | +0.006 |
� | +0.006 |
Neg logit contributions | |
abol | -0.009 |
theless | -0.008 |
utonium | -0.008 |
akespe | -0.008 |
andre | -0.008 |
Token | : |
Token ID | 25 |
Feature activation | -3.15e-02 |
Pos logit contributions | |
Jinn | +0.043 |
↑ | +0.043 |
pai | +0.043 |
�� | +0.040 |
� | +0.040 |
Neg logit contributions | |
abol | -0.064 |
theless | -0.062 |
utonium | -0.060 |
akespe | -0.059 |
andre | -0.058 |
Token | 185 |
Token ID | 21652 |
Feature activation | +8.66e-02 |
Pos logit contributions | |
abol | +0.135 |
theless | +0.130 |
utonium | +0.126 |
akespe | +0.124 |
andre | +0.120 |
Neg logit contributions | |
Jinn | -0.110 |
↑ | -0.109 |
pai | -0.108 |
�� | -0.102 |
� | -0.101 |
Token | million |
Token ID | 1510 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
Jinn | +0.070 |
↑ | +0.069 |
pai | +0.069 |
�� | +0.064 |
ki | +0.063 |
Neg logit contributions | |
abol | -0.109 |
theless | -0.106 |
utonium | -0.103 |
akespe | -0.101 |
andre | -0.098 |
Token | in |
Token ID | 287 |
Feature activation | -2.24e-02 |
Pos logit contributions | |
Jinn | +0.160 |
↑ | +0.159 |
pai | +0.157 |
�� | +0.144 |
� | +0.143 |
Neg logit contributions | |
abol | -0.337 |
theless | -0.328 |
utonium | -0.320 |
akespe | -0.315 |
andre | -0.307 |
Token | un |
Token ID | 555 |
Feature activation | -3.68e-01 |
Pos logit contributions | |
abol | +0.027 |
theless | +0.026 |
utonium | +0.025 |
akespe | +0.025 |
andre | +0.024 |
Neg logit contributions | |
Jinn | -0.019 |
↑ | -0.019 |
pai | -0.019 |
�� | -0.018 |
� | -0.018 |
Token | sec |
Token ID | 2363 |
Feature activation | +6.73e-02 |
Pos logit contributions | |
abol | +0.430 |
theless | +0.413 |
utonium | +0.402 |
akespe | +0.393 |
andre | +0.384 |
Neg logit contributions | |
Jinn | -0.331 |
↑ | -0.330 |
pai | -0.327 |
�� | -0.309 |
� | -0.305 |
Token | ured |
Token ID | 1522 |
Feature activation | +8.96e-01 |
Pos logit contributions | |
Jinn | +0.076 |
↑ | +0.075 |
pai | +0.075 |
�� | +0.072 |
� | +0.071 |
Neg logit contributions | |
abol | -0.063 |
theless | -0.060 |
utonium | -0.058 |
akespe | -0.057 |
andre | -0.055 |
Token | loans |
Token ID | 10021 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
Jinn | +0.745 |
↑ | +0.736 |
pai | +0.730 |
�� | +0.679 |
ki | +0.679 |
Neg logit contributions | |
abol | -1.107 |
theless | -1.070 |
utonium | -1.049 |
akespe | -1.026 |
andre | -0.997 |
Token | . |
Token ID | 13 |
Feature activation | +3.66e-02 |
Pos logit contributions | |
Jinn | +0.136 |
↑ | +0.135 |
pai | +0.133 |
�� | +0.124 |
� | +0.122 |
Neg logit contributions | |
abol | -0.250 |
theless | -0.242 |
utonium | -0.237 |
akespe | -0.233 |
andre | -0.227 |
Token | The |
Token ID | 383 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
Jinn | +0.030 |
↑ | +0.030 |
pai | +0.030 |
�� | +0.028 |
� | +0.028 |
Neg logit contributions | |
abol | -0.045 |
theless | -0.044 |
utonium | -0.042 |
akespe | -0.041 |
andre | -0.041 |
Token | three |
Token ID | 1115 |
Feature activation | +6.05e-02 |
Pos logit contributions | |
Jinn | +0.116 |
↑ | +0.115 |
pai | +0.114 |
�� | +0.108 |
� | +0.107 |
Neg logit contributions | |
abol | -0.146 |
theless | -0.141 |
utonium | -0.138 |
akespe | -0.135 |
andre | -0.131 |
Token | men |
Token ID | 1450 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
Jinn | +0.052 |
↑ | +0.052 |
pai | +0.051 |
�� | +0.048 |
� | +0.048 |
Neg logit contributions | |
abol | -0.073 |
theless | -0.070 |
utonium | -0.069 |
akespe | -0.067 |
andre | -0.065 |
Token | government |
Token ID | 1230 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
Jinn | +0.456 |
↑ | +0.454 |
pai | +0.450 |
�� | +0.425 |
� | +0.421 |
Neg logit contributions | |
abol | -0.567 |
theless | -0.546 |
utonium | -0.531 |
akespe | -0.520 |
andre | -0.506 |
Token | . |
Token ID | 13 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
Jinn | +0.210 |
↑ | +0.208 |
pai | +0.207 |
�� | +0.193 |
� | +0.192 |
Neg logit contributions | |
abol | -0.316 |
theless | -0.305 |
utonium | -0.298 |
akespe | -0.292 |
andre | -0.284 |
Token |
|
Token ID | 198 |
Feature activation | -7.45e-03 |
Pos logit contributions | |
Jinn | +0.010 |
↑ | +0.010 |
pai | +0.010 |
�� | +0.009 |
� | +0.009 |
Neg logit contributions | |
abol | -0.015 |
theless | -0.015 |
utonium | -0.014 |
akespe | -0.014 |
andre | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
abol | +0.009 |
theless | +0.009 |
utonium | +0.009 |
akespe | +0.009 |
andre | +0.008 |
Neg logit contributions | |
Jinn | -0.006 |
↑ | -0.006 |
pai | -0.006 |
�� | -0.006 |
� | -0.005 |
Token | For |
Token ID | 1890 |
Feature activation | -7.47e-02 |
Pos logit contributions | |
↑ | +0.012 |
Jinn | +0.012 |
pai | +0.012 |
�� | +0.011 |
� | +0.011 |
Neg logit contributions | |
abol | -0.012 |
theless | -0.011 |
utonium | -0.011 |
akespe | -0.011 |
andre | -0.010 |
Token | cade |
Token ID | 46395 |
Feature activation | +8.92e-01 |
Pos logit contributions | |
abol | +0.088 |
theless | +0.085 |
utonium | +0.082 |
akespe | +0.081 |
andre | +0.079 |
Neg logit contributions | |
Jinn | -0.066 |
↑ | -0.066 |
pai | -0.066 |
�� | -0.062 |
� | -0.061 |
Token | ll |
Token ID | 297 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
Jinn | +0.872 |
↑ | +0.870 |
pai | +0.864 |
�� | +0.815 |
� | +0.811 |
Neg logit contributions | |
abol | -0.967 |
theless | -0.932 |
utonium | -0.905 |
akespe | -0.884 |
andre | -0.854 |
Token | was |
Token ID | 373 |
Feature activation | +9.22e-02 |
Pos logit contributions | |
Jinn | +0.084 |
↑ | +0.084 |
pai | +0.083 |
�� | +0.077 |
� | +0.077 |
Neg logit contributions | |
abol | -0.138 |
theless | -0.133 |
utonium | -0.130 |
akespe | -0.128 |
andre | -0.124 |
Token | called |
Token ID | 1444 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
Jinn | +0.079 |
↑ | +0.079 |
pai | +0.078 |
�� | +0.074 |
� | +0.073 |
Neg logit contributions | |
abol | -0.111 |
theless | -0.107 |
utonium | -0.104 |
akespe | -0.102 |
andre | -0.099 |
Token | to |
Token ID | 284 |
Feature activation | -4.52e-02 |
Pos logit contributions | |
abol | +0.367 |
theless | +0.355 |
utonium | +0.347 |
akespe | +0.341 |
andre | +0.334 |
Neg logit contributions | |
Jinn | -0.201 |
↑ | -0.199 |
pai | -0.198 |
�� | -0.184 |
� | -0.182 |
Token | the |
Token ID | 262 |
Feature activation | +1.72e-02 |
Pos logit contributions | |
abol | +0.057 |
theless | +0.055 |
utonium | +0.054 |
akespe | +0.052 |
andre | +0.051 |
Neg logit contributions | |
Jinn | -0.037 |
↑ | -0.036 |
pai | -0.036 |
�� | -0.034 |
� | -0.033 |
Token | merc |
Token ID | 11991 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
abol | +0.020 |
theless | +0.020 |
utonium | +0.019 |
akespe | +0.019 |
andre | +0.018 |
Neg logit contributions | |
Jinn | -0.012 |
↑ | -0.012 |
pai | -0.012 |
�� | -0.011 |
� | -0.011 |
Token | red |
Token ID | 445 |
Feature activation | +5.94e-02 |
Pos logit contributions | |
Jinn | +0.433 |
↑ | +0.432 |
pai | +0.431 |
�� | +0.407 |
� | +0.405 |
Neg logit contributions | |
abol | -0.354 |
theless | -0.342 |
utonium | -0.328 |
akespe | -0.320 |
andre | -0.306 |
Token | i |
Token ID | 72 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
Jinn | +0.055 |
↑ | +0.055 |
pai | +0.055 |
�� | +0.052 |
� | +0.051 |
Neg logit contributions | |
abol | -0.067 |
theless | -0.065 |
utonium | -0.063 |
akespe | -0.062 |
andre | -0.060 |
Token | 26 |
Token ID | 2608 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
abol | +0.135 |
theless | +0.130 |
utonium | +0.127 |
akespe | +0.125 |
andre | +0.122 |
Neg logit contributions | |
Jinn | -0.087 |
↑ | -0.086 |
pai | -0.086 |
�� | -0.080 |
� | -0.079 |
Token | ju |
Token ID | 7544 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
abol | +0.188 |
theless | +0.182 |
utonium | +0.177 |
akespe | +0.174 |
andre | +0.169 |
Neg logit contributions | |
Jinn | -0.131 |
↑ | -0.130 |
pai | -0.129 |
�� | -0.121 |
� | -0.120 |
Token | illet |
Token ID | 32512 |
Feature activation | +8.89e-01 |
Pos logit contributions | |
Jinn | +0.120 |
↑ | +0.119 |
pai | +0.118 |
�� | +0.111 |
� | +0.110 |
Neg logit contributions | |
abol | -0.172 |
theless | -0.166 |
utonium | -0.161 |
akespe | -0.158 |
andre | -0.154 |
Token | . |
Token ID | 13 |
Feature activation | +5.99e-02 |
Pos logit contributions | |
Jinn | +0.809 |
↑ | +0.808 |
pai | +0.799 |
�� | +0.748 |
� | +0.745 |
Neg logit contributions | |
abol | -1.023 |
theless | -0.990 |
utonium | -0.965 |
akespe | -0.943 |
andre | -0.911 |
Token | pic |
Token ID | 8301 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
Jinn | +0.053 |
↑ | +0.053 |
pai | +0.052 |
�� | +0.049 |
� | +0.049 |
Neg logit contributions | |
abol | -0.071 |
theless | -0.068 |
utonium | -0.067 |
akespe | -0.065 |
andre | -0.063 |
Token | . |
Token ID | 13 |
Feature activation | +3.59e-02 |
Pos logit contributions | |
Jinn | +0.111 |
↑ | +0.110 |
pai | +0.110 |
�� | +0.102 |
� | +0.101 |
Neg logit contributions | |
abol | -0.194 |
theless | -0.187 |
utonium | -0.183 |
akespe | -0.179 |
andre | -0.175 |
Token | twitter |
Token ID | 6956 |
Feature activation | +6.74e-02 |
Pos logit contributions | |
Jinn | +0.049 |
↑ | +0.049 |
pai | +0.049 |
�� | +0.047 |
� | +0.046 |
Neg logit contributions | |
abol | -0.025 |
theless | -0.024 |
utonium | -0.023 |
akespe | -0.022 |
andre | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | -3.64e-02 |
Pos logit contributions | |
Jinn | +0.051 |
↑ | +0.051 |
pai | +0.050 |
�� | +0.047 |
� | +0.046 |
Neg logit contributions | |
abol | -0.088 |
theless | -0.085 |
utonium | -0.083 |
akespe | -0.081 |
andre | -0.080 |
Token | four |
Token ID | 1440 |
Feature activation | +7.88e-02 |
Pos logit contributions | |
abol | +0.012 |
theless | +0.012 |
utonium | +0.011 |
akespe | +0.011 |
andre | +0.011 |
Neg logit contributions | |
Jinn | -0.009 |
↑ | -0.009 |
pai | -0.009 |
�� | -0.008 |
� | -0.008 |
Token | other |
Token ID | 584 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
Jinn | +0.070 |
↑ | +0.069 |
pai | +0.069 |
�� | +0.064 |
� | +0.064 |
Neg logit contributions | |
abol | -0.093 |
theless | -0.090 |
utonium | -0.088 |
akespe | -0.086 |
andre | -0.084 |
Token | � |
Token ID | 564 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
abol | +0.375 |
theless | +0.361 |
utonium | +0.352 |
akespe | +0.345 |
andre | +0.335 |
Neg logit contributions | |
Jinn | -0.287 |
↑ | -0.285 |
pai | -0.283 |
�� | -0.266 |
� | -0.264 |
Token | � |
Token ID | 250 |
Feature activation | -9.02e-02 |
Pos logit contributions | |
abol | +0.131 |
theless | +0.127 |
utonium | +0.124 |
akespe | +0.122 |
andre | +0.118 |
Neg logit contributions | |
Jinn | -0.083 |
↑ | -0.083 |
pai | -0.082 |
�� | -0.077 |
� | -0.076 |
Token | house |
Token ID | 4803 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
abol | +0.080 |
theless | +0.078 |
utonium | +0.075 |
akespe | +0.073 |
andre | +0.070 |
Neg logit contributions | |
↑ | -0.105 |
pai | -0.105 |
Jinn | -0.104 |
�� | -0.099 |
� | -0.099 |
Token | hold |
Token ID | 2946 |
Feature activation | +8.76e-01 |
Pos logit contributions | |
abol | +0.198 |
theless | +0.192 |
utonium | +0.186 |
akespe | +0.182 |
andre | +0.178 |
Neg logit contributions | |
↑ | -0.152 |
Jinn | -0.151 |
pai | -0.151 |
�� | -0.141 |
� | -0.141 |
Token | � |
Token ID | 447 |
Feature activation | -5.54e-02 |
Pos logit contributions | |
↑ | +0.833 |
Jinn | +0.827 |
pai | +0.824 |
� | +0.774 |
�� | +0.774 |
Neg logit contributions | |
abol | -0.974 |
theless | -0.941 |
utonium | -0.913 |
akespe | -0.894 |
andre | -0.867 |
Token | � |
Token ID | 251 |
Feature activation | -2.20e-02 |
Pos logit contributions | |
abol | +0.071 |
theless | +0.069 |
utonium | +0.067 |
akespe | +0.066 |
andre | +0.064 |
Neg logit contributions | |
Jinn | -0.043 |
↑ | -0.043 |
pai | -0.043 |
�� | -0.040 |
� | -0.040 |
Token | members |
Token ID | 1866 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
abol | +0.022 |
theless | +0.021 |
utonium | +0.021 |
akespe | +0.020 |
andre | +0.019 |
Neg logit contributions | |
Jinn | -0.023 |
↑ | -0.023 |
pai | -0.023 |
�� | -0.022 |
� | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | +5.00e-02 |
Pos logit contributions | |
abol | +0.014 |
theless | +0.013 |
utonium | +0.013 |
akespe | +0.013 |
andre | +0.013 |
Neg logit contributions | |
Jinn | -0.008 |
↑ | -0.008 |
pai | -0.008 |
�� | -0.008 |
� | -0.008 |
Token | But |
Token ID | 887 |
Feature activation | -4.34e-02 |
Pos logit contributions | |
Jinn | +0.042 |
↑ | +0.041 |
pai | +0.041 |
�� | +0.039 |
� | +0.038 |
Neg logit contributions | |
abol | -0.061 |
theless | -0.059 |
utonium | -0.058 |
akespe | -0.056 |
andre | -0.055 |
Token | relay |
Token ID | 24248 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
Jinn | +0.063 |
↑ | +0.063 |
pai | +0.062 |
�� | +0.058 |
� | +0.057 |
Neg logit contributions | |
abol | -0.106 |
theless | -0.102 |
utonium | -0.100 |
akespe | -0.098 |
andre | -0.095 |
Token | improvements |
Token ID | 8561 |
Feature activation | -8.02e-03 |
Pos logit contributions | |
Jinn | +0.211 |
↑ | +0.210 |
pai | +0.208 |
�� | +0.196 |
� | +0.194 |
Neg logit contributions | |
abol | -0.282 |
theless | -0.272 |
utonium | -0.265 |
akespe | -0.259 |
andre | -0.253 |
Token | , |
Token ID | 11 |
Feature activation | +4.43e-02 |
Pos logit contributions | |
abol | +0.010 |
theless | +0.010 |
utonium | +0.010 |
akespe | +0.010 |
andre | +0.009 |
Neg logit contributions | |
Jinn | -0.006 |
↑ | -0.006 |
pai | -0.006 |
�� | -0.006 |
� | -0.006 |
Token | se |
Token ID | 384 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
Jinn | +0.034 |
↑ | +0.034 |
pai | +0.034 |
�� | +0.032 |
� | +0.031 |
Neg logit contributions | |
abol | -0.057 |
theless | -0.055 |
utonium | -0.054 |
akespe | -0.053 |
andre | -0.052 |
Token | g |
Token ID | 70 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
Jinn | +0.191 |
↑ | +0.190 |
pai | +0.189 |
�� | +0.181 |
� | +0.180 |
Neg logit contributions | |
abol | -0.129 |
theless | -0.123 |
utonium | -0.118 |
akespe | -0.115 |
andre | -0.110 |
Token | wit |
Token ID | 39289 |
Feature activation | +8.76e-01 |
Pos logit contributions | |
abol | +0.385 |
theless | +0.377 |
utonium | +0.371 |
akespe | +0.365 |
andre | +0.360 |
Neg logit contributions | |
Jinn | -0.046 |
↑ | -0.045 |
pai | -0.044 |
�� | -0.033 |
� | -0.032 |
Token | fraud |
Token ID | 7394 |
Feature activation | -6.78e-02 |
Pos logit contributions | |
Jinn | +0.719 |
↑ | +0.717 |
pai | +0.709 |
�� | +0.662 |
� | +0.657 |
Neg logit contributions | |
abol | -1.089 |
theless | -1.052 |
utonium | -1.028 |
akespe | -1.007 |
andre | -0.981 |
Token | proofs |
Token ID | 39197 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
abol | +0.081 |
theless | +0.078 |
utonium | +0.076 |
akespe | +0.074 |
andre | +0.072 |
Neg logit contributions | |
Jinn | -0.060 |
↑ | -0.059 |
pai | -0.059 |
�� | -0.055 |
� | -0.055 |
Token | , |
Token ID | 11 |
Feature activation | +4.63e-02 |
Pos logit contributions | |
abol | +0.163 |
theless | +0.158 |
utonium | +0.154 |
akespe | +0.151 |
andre | +0.148 |
Neg logit contributions | |
Jinn | -0.093 |
↑ | -0.092 |
pai | -0.092 |
�� | -0.086 |
� | -0.084 |
Token | dynamic |
Token ID | 8925 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
Jinn | +0.037 |
↑ | +0.037 |
pai | +0.037 |
�� | +0.034 |
� | +0.034 |
Neg logit contributions | |
abol | -0.058 |
theless | -0.057 |
utonium | -0.055 |
akespe | -0.054 |
andre | -0.053 |
Token | block |
Token ID | 2512 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
abol | +0.209 |
theless | +0.203 |
utonium | +0.198 |
akespe | +0.194 |
andre | +0.189 |
Neg logit contributions | |
Jinn | -0.129 |
↑ | -0.128 |
pai | -0.127 |
�� | -0.120 |
� | -0.117 |
Token | immediately |
Token ID | 3393 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
abol | +0.197 |
theless | +0.191 |
utonium | +0.187 |
akespe | +0.182 |
andre | +0.179 |
Neg logit contributions | |
Jinn | -0.113 |
↑ | -0.112 |
pai | -0.111 |
�� | -0.104 |
� | -0.103 |
Token | towards |
Token ID | 3371 |
Feature activation | +2.77e-02 |
Pos logit contributions | |
Jinn | +0.126 |
↑ | +0.126 |
pai | +0.124 |
�� | +0.115 |
� | +0.114 |
Neg logit contributions | |
abol | -0.239 |
theless | -0.232 |
utonium | -0.227 |
akespe | -0.222 |
andre | -0.217 |
Token | the |
Token ID | 262 |
Feature activation | +4.82e-02 |
Pos logit contributions | |
Jinn | +0.023 |
↑ | +0.022 |
pai | +0.022 |
�� | +0.021 |
� | +0.021 |
Neg logit contributions | |
abol | -0.035 |
theless | -0.033 |
utonium | -0.033 |
akespe | -0.032 |
andre | -0.031 |
Token | se |
Token ID | 384 |
Feature activation | +5.75e-02 |
Pos logit contributions | |
Jinn | +0.042 |
↑ | +0.042 |
pai | +0.041 |
�� | +0.039 |
� | +0.039 |
Neg logit contributions | |
abol | -0.058 |
theless | -0.055 |
utonium | -0.054 |
akespe | -0.053 |
andre | -0.052 |
Token | g |
Token ID | 70 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
Jinn | +0.071 |
↑ | +0.071 |
pai | +0.070 |
�� | +0.067 |
� | +0.067 |
Neg logit contributions | |
abol | -0.048 |
theless | -0.045 |
utonium | -0.044 |
akespe | -0.042 |
andre | -0.041 |
Token | wit |
Token ID | 39289 |
Feature activation | +8.71e-01 |
Pos logit contributions | |
abol | +0.446 |
theless | +0.435 |
utonium | +0.429 |
akespe | +0.423 |
andre | +0.416 |
Neg logit contributions | |
Jinn | -0.055 |
↑ | -0.054 |
pai | -0.052 |
�� | -0.040 |
� | -0.038 |
Token | 4 |
Token ID | 604 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
Jinn | +0.773 |
↑ | +0.770 |
pai | +0.763 |
�� | +0.715 |
� | +0.711 |
Neg logit contributions | |
abol | -1.026 |
theless | -0.989 |
utonium | -0.965 |
akespe | -0.945 |
andre | -0.919 |
Token | MB |
Token ID | 10744 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
Jinn | +0.079 |
↑ | +0.079 |
pai | +0.078 |
�� | +0.073 |
� | +0.072 |
Neg logit contributions | |
abol | -0.130 |
theless | -0.126 |
utonium | -0.123 |
akespe | -0.121 |
andre | -0.118 |
Token | block |
Token ID | 2512 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
Jinn | +0.267 |
↑ | +0.265 |
pai | +0.263 |
�� | +0.246 |
� | +0.244 |
Neg logit contributions | |
abol | -0.413 |
theless | -0.399 |
utonium | -0.390 |
akespe | -0.382 |
andre | -0.372 |
Token | soft |
Token ID | 2705 |
Feature activation | +9.41e-02 |
Pos logit contributions | |
abol | +0.184 |
theless | +0.178 |
utonium | +0.173 |
akespe | +0.170 |
andre | +0.166 |
Neg logit contributions | |
Jinn | -0.105 |
↑ | -0.104 |
pai | -0.104 |
�� | -0.097 |
� | -0.096 |
Token | - |
Token ID | 12 |
Feature activation | +4.16e-02 |
Pos logit contributions | |
Jinn | +0.082 |
↑ | +0.081 |
pai | +0.080 |
�� | +0.076 |
� | +0.075 |
Neg logit contributions | |
abol | -0.113 |
theless | -0.109 |
utonium | -0.106 |
akespe | -0.104 |
andre | -0.101 |
Token | Feel |
Token ID | 18571 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
abol | +0.185 |
theless | +0.178 |
utonium | +0.173 |
akespe | +0.169 |
andre | +0.165 |
Neg logit contributions | |
Jinn | -0.150 |
↑ | -0.149 |
pai | -0.148 |
�� | -0.140 |
� | -0.139 |
Token | Secure |
Token ID | 26707 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
abol | +0.311 |
theless | +0.299 |
utonium | +0.291 |
akespe | +0.284 |
andre | +0.276 |
Neg logit contributions | |
Jinn | -0.271 |
↑ | -0.270 |
pai | -0.268 |
�� | -0.253 |
� | -0.251 |
Token | In |
Token ID | 554 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
Jinn | +0.156 |
↑ | +0.155 |
pai | +0.153 |
�� | +0.143 |
� | +0.141 |
Neg logit contributions | |
abol | -0.276 |
theless | -0.267 |
utonium | -0.261 |
akespe | -0.256 |
andre | -0.250 |
Token | Your |
Token ID | 3406 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
abol | +0.193 |
theless | +0.186 |
utonium | +0.182 |
akespe | +0.178 |
andre | +0.173 |
Neg logit contributions | |
Jinn | -0.142 |
↑ | -0.141 |
pai | -0.140 |
�� | -0.131 |
� | -0.130 |
Token | Bed |
Token ID | 15585 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
abol | +0.276 |
theless | +0.267 |
utonium | +0.260 |
akespe | +0.255 |
andre | +0.249 |
Neg logit contributions | |
Jinn | -0.181 |
↑ | -0.179 |
pai | -0.178 |
�� | -0.166 |
� | -0.165 |
Token | rooms |
Token ID | 9649 |
Feature activation | -9.74e-01 |
Pos logit contributions | |
abol | +0.411 |
theless | +0.398 |
utonium | +0.388 |
akespe | +0.380 |
andre | +0.371 |
Neg logit contributions | |
Jinn | -0.265 |
↑ | -0.263 |
pai | -0.261 |
�� | -0.244 |
� | -0.241 |
Token | ". |
Token ID | 1911 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
abol | +1.328 |
theless | +1.283 |
utonium | +1.255 |
akespe | +1.229 |
andre | +1.206 |
Neg logit contributions | |
Jinn | -0.681 |
↑ | -0.674 |
pai | -0.671 |
�� | -0.625 |
� | -0.613 |
Token |
|
Token ID | 198 |
Feature activation | -9.99e-02 |
Pos logit contributions | |
Jinn | +0.173 |
↑ | +0.172 |
pai | +0.170 |
�� | +0.158 |
� | +0.158 |
Neg logit contributions | |
abol | -0.272 |
theless | -0.263 |
utonium | -0.257 |
akespe | -0.252 |
andre | -0.245 |
Token |
|
Token ID | 198 |
Feature activation | -8.69e-02 |
Pos logit contributions | |
abol | +0.125 |
theless | +0.120 |
utonium | +0.117 |
akespe | +0.114 |
andre | +0.113 |
Neg logit contributions | |
Jinn | -0.081 |
↑ | -0.080 |
pai | -0.080 |
�� | -0.076 |
� | -0.074 |
Token | On |
Token ID | 2202 |
Feature activation | -7.15e-02 |
Pos logit contributions | |
abol | +0.090 |
theless | +0.087 |
utonium | +0.084 |
akespe | +0.082 |
andre | +0.079 |
Neg logit contributions | |
↑ | -0.089 |
Jinn | -0.089 |
pai | -0.089 |
�� | -0.084 |
� | -0.084 |
Token | the |
Token ID | 262 |
Feature activation | -8.95e-02 |
Pos logit contributions | |
abol | +0.095 |
theless | +0.092 |
utonium | +0.090 |
akespe | +0.088 |
andre | +0.086 |
Neg logit contributions | |
Jinn | -0.053 |
↑ | -0.053 |
pai | -0.052 |
�� | -0.048 |
� | -0.048 |
Token | murdered |
Token ID | 12864 |
Feature activation | -1.09e-03 |
Pos logit contributions | |
abol | +0.069 |
theless | +0.066 |
utonium | +0.065 |
akespe | +0.064 |
andre | +0.062 |
Neg logit contributions | |
Jinn | -0.041 |
↑ | -0.041 |
pai | -0.040 |
�� | -0.038 |
� | -0.037 |
Token | Tang |
Token ID | 18816 |
Feature activation | +4.99e-03 |
Pos logit contributions | |
abol | +0.001 |
theless | +0.001 |
utonium | +0.001 |
akespe | +0.001 |
andre | +0.001 |
Neg logit contributions | |
Jinn | -0.001 |
↑ | -0.001 |
pai | -0.001 |
�� | -0.001 |
� | -0.001 |
Token | Shen |
Token ID | 22323 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
Jinn | +0.004 |
↑ | +0.004 |
pai | +0.004 |
�� | +0.004 |
� | +0.004 |
Neg logit contributions | |
abol | -0.006 |
theless | -0.006 |
utonium | -0.006 |
akespe | -0.006 |
andre | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
Jinn | +0.104 |
↑ | +0.103 |
pai | +0.102 |
�� | +0.094 |
� | +0.093 |
Neg logit contributions | |
abol | -0.196 |
theless | -0.191 |
utonium | -0.186 |
akespe | -0.183 |
andre | -0.178 |
Token | S |
Token ID | 311 |
Feature activation | +1.03e-03 |
Pos logit contributions | |
↑ | +0.009 |
Jinn | +0.009 |
pai | +0.009 |
�� | +0.008 |
� | +0.008 |
Neg logit contributions | |
abol | -0.013 |
theless | -0.012 |
utonium | -0.012 |
akespe | -0.012 |
andre | -0.011 |
Token | aki |
Token ID | 8182 |
Feature activation | -9.56e-01 |
Pos logit contributions | |
Jinn | +0.001 |
↑ | +0.001 |
pai | +0.001 |
�� | +0.001 |
� | +0.001 |
Neg logit contributions | |
abol | -0.001 |
theless | -0.001 |
utonium | -0.001 |
akespe | -0.001 |
andre | -0.001 |
Token | lay |
Token ID | 3830 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
abol | +1.231 |
theless | +1.192 |
utonium | +1.161 |
akespe | +1.136 |
andre | +1.114 |
Neg logit contributions | |
Jinn | -0.738 |
↑ | -0.738 |
pai | -0.733 |
�� | -0.687 |
� | -0.676 |
Token | in |
Token ID | 287 |
Feature activation | -7.40e-02 |
Pos logit contributions | |
Jinn | +0.133 |
↑ | +0.132 |
pai | +0.131 |
�� | +0.122 |
� | +0.120 |
Neg logit contributions | |
abol | -0.237 |
theless | -0.229 |
utonium | -0.224 |
akespe | -0.220 |
andre | -0.215 |
Token | wait |
Token ID | 4043 |
Feature activation | +9.66e-02 |
Pos logit contributions | |
abol | +0.088 |
theless | +0.085 |
utonium | +0.083 |
akespe | +0.081 |
andre | +0.079 |
Neg logit contributions | |
Jinn | -0.065 |
↑ | -0.064 |
pai | -0.064 |
�� | -0.060 |
� | -0.059 |
Token | until |
Token ID | 1566 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
Jinn | +0.066 |
↑ | +0.065 |
pai | +0.064 |
�� | +0.059 |
� | +0.059 |
Neg logit contributions | |
abol | -0.134 |
theless | -0.130 |
utonium | -0.127 |
akespe | -0.125 |
andre | -0.122 |
Token | Yoshi |
Token ID | 38936 |
Feature activation | -9.10e-02 |
Pos logit contributions | |
Jinn | +0.186 |
↑ | +0.185 |
pai | +0.183 |
�� | +0.170 |
� | +0.169 |
Neg logit contributions | |
abol | -0.311 |
theless | -0.301 |
utonium | -0.293 |
akespe | -0.288 |
andre | -0.281 |
Token | like |
Token ID | 588 |
Feature activation | -2.67e-02 |
Pos logit contributions | |
Jinn | +0.093 |
↑ | +0.092 |
pai | +0.092 |
�� | +0.085 |
� | +0.084 |
Neg logit contributions | |
abol | -0.162 |
theless | -0.157 |
utonium | -0.153 |
akespe | -0.150 |
andre | -0.147 |
Token | a |
Token ID | 257 |
Feature activation | -3.33e-02 |
Pos logit contributions | |
abol | +0.035 |
theless | +0.034 |
utonium | +0.033 |
akespe | +0.032 |
andre | +0.031 |
Neg logit contributions | |
Jinn | -0.020 |
↑ | -0.020 |
pai | -0.020 |
�� | -0.019 |
� | -0.018 |
Token | lot |
Token ID | 1256 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
abol | +0.040 |
theless | +0.039 |
utonium | +0.038 |
akespe | +0.037 |
andre | +0.036 |
Neg logit contributions | |
Jinn | -0.028 |
↑ | -0.028 |
pai | -0.028 |
�� | -0.026 |
� | -0.026 |
Token | of |
Token ID | 286 |
Feature activation | +2.91e-03 |
Pos logit contributions | |
Jinn | +0.009 |
↑ | +0.009 |
pai | +0.009 |
�� | +0.008 |
� | +0.008 |
Neg logit contributions | |
abol | -0.014 |
theless | -0.014 |
utonium | -0.014 |
akespe | -0.013 |
andre | -0.013 |
Token | bl |
Token ID | 698 |
Feature activation | -3.04e-02 |
Pos logit contributions | |
Jinn | +0.002 |
↑ | +0.002 |
pai | +0.002 |
�� | +0.002 |
� | +0.002 |
Neg logit contributions | |
abol | -0.004 |
theless | -0.004 |
utonium | -0.003 |
akespe | -0.003 |
andre | -0.003 |
Token | uster |
Token ID | 5819 |
Feature activation | -9.49e-01 |
Pos logit contributions | |
abol | +0.024 |
theless | +0.024 |
utonium | +0.022 |
akespe | +0.021 |
andre | +0.020 |
Neg logit contributions | |
↑ | -0.038 |
Jinn | -0.038 |
pai | -0.038 |
ki | -0.036 |
� | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | -1.64e-02 |
Pos logit contributions | |
abol | +1.239 |
theless | +1.198 |
utonium | +1.167 |
akespe | +1.147 |
andre | +1.123 |
Neg logit contributions | |
Jinn | -0.717 |
↑ | -0.711 |
pai | -0.709 |
�� | -0.660 |
� | -0.651 |
Token | Perhaps |
Token ID | 8673 |
Feature activation | +3.19e-02 |
Pos logit contributions | |
abol | +0.020 |
theless | +0.019 |
utonium | +0.018 |
akespe | +0.018 |
andre | +0.018 |
Neg logit contributions | |
Jinn | -0.014 |
↑ | -0.014 |
pai | -0.014 |
�� | -0.013 |
� | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | -4.88e-02 |
Pos logit contributions | |
Jinn | +0.024 |
↑ | +0.024 |
pai | +0.024 |
�� | +0.022 |
� | +0.022 |
Neg logit contributions | |
abol | -0.041 |
theless | -0.040 |
utonium | -0.039 |
akespe | -0.038 |
andre | -0.037 |
Token | tru |
Token ID | 45768 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
abol | +0.060 |
theless | +0.058 |
utonium | +0.057 |
akespe | +0.056 |
andre | +0.054 |
Neg logit contributions | |
Jinn | -0.040 |
↑ | -0.040 |
pai | -0.040 |
�� | -0.037 |
� | -0.037 |
Token | est |
Token ID | 395 |
Feature activation | +7.78e-02 |
Pos logit contributions | |
abol | +0.299 |
theless | +0.290 |
utonium | +0.283 |
akespe | +0.278 |
andre | +0.271 |
Neg logit contributions | |
Jinn | -0.166 |
↑ | -0.165 |
pai | -0.163 |
�� | -0.152 |
� | -0.150 |
Token | away |
Token ID | 1497 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
Jinn | +0.014 |
↑ | +0.014 |
pai | +0.014 |
�� | +0.013 |
� | +0.013 |
Neg logit contributions | |
abol | -0.023 |
theless | -0.022 |
utonium | -0.022 |
akespe | -0.021 |
andre | -0.021 |
Token | at |
Token ID | 379 |
Feature activation | -4.40e-02 |
Pos logit contributions | |
abol | +0.362 |
theless | +0.348 |
utonium | +0.341 |
akespe | +0.334 |
andre | +0.326 |
Neg logit contributions | |
↑ | -0.203 |
Jinn | -0.202 |
pai | -0.201 |
�� | -0.188 |
� | -0.184 |
Token | work |
Token ID | 670 |
Feature activation | -9.64e-02 |
Pos logit contributions | |
abol | +0.057 |
theless | +0.055 |
utonium | +0.054 |
akespe | +0.053 |
andre | +0.051 |
Neg logit contributions | |
Jinn | -0.034 |
↑ | -0.034 |
pai | -0.034 |
�� | -0.031 |
� | -0.031 |
Token | , |
Token ID | 11 |
Feature activation | +3.20e-02 |
Pos logit contributions | |
abol | +0.127 |
theless | +0.123 |
utonium | +0.120 |
akespe | +0.118 |
andre | +0.115 |
Neg logit contributions | |
Jinn | -0.072 |
↑ | -0.072 |
pai | -0.071 |
�� | -0.066 |
� | -0.065 |
Token | S |
Token ID | 311 |
Feature activation | +1.50e-02 |
Pos logit contributions | |
Jinn | +0.026 |
↑ | +0.026 |
pai | +0.025 |
�� | +0.024 |
� | +0.023 |
Neg logit contributions | |
abol | -0.040 |
theless | -0.039 |
utonium | -0.038 |
akespe | -0.037 |
andre | -0.036 |
Token | aki |
Token ID | 8182 |
Feature activation | -9.46e-01 |
Pos logit contributions | |
Jinn | +0.015 |
↑ | +0.015 |
pai | +0.015 |
�� | +0.014 |
� | +0.014 |
Neg logit contributions | |
abol | -0.016 |
theless | -0.015 |
utonium | -0.015 |
akespe | -0.014 |
andre | -0.014 |
Token | broke |
Token ID | 6265 |
Feature activation | -4.65e-02 |
Pos logit contributions | |
abol | +1.224 |
theless | +1.183 |
utonium | +1.152 |
akespe | +1.127 |
andre | +1.106 |
Neg logit contributions | |
Jinn | -0.727 |
↑ | -0.726 |
pai | -0.721 |
�� | -0.677 |
� | -0.666 |
Token | into |
Token ID | 656 |
Feature activation | +7.68e-02 |
Pos logit contributions | |
abol | +0.062 |
theless | +0.060 |
utonium | +0.059 |
akespe | +0.058 |
andre | +0.056 |
Neg logit contributions | |
↑ | -0.034 |
Jinn | -0.034 |
pai | -0.033 |
�� | -0.031 |
� | -0.031 |
Token | his |
Token ID | 465 |
Feature activation | -4.45e-02 |
Pos logit contributions | |
Jinn | +0.059 |
↑ | +0.058 |
pai | +0.058 |
�� | +0.054 |
� | +0.053 |
Neg logit contributions | |
abol | -0.100 |
theless | -0.097 |
utonium | -0.095 |
akespe | -0.093 |
andre | -0.091 |
Token | apartment |
Token ID | 7962 |
Feature activation | +2.12e-02 |
Pos logit contributions | |
abol | +0.051 |
theless | +0.049 |
utonium | +0.048 |
akespe | +0.047 |
andre | +0.046 |
Neg logit contributions | |
Jinn | -0.041 |
↑ | -0.040 |
pai | -0.040 |
�� | -0.038 |
� | -0.037 |
Token | and |
Token ID | 290 |
Feature activation | -5.31e-02 |
Pos logit contributions | |
Jinn | +0.015 |
↑ | +0.015 |
pai | +0.015 |
�� | +0.014 |
� | +0.014 |
Neg logit contributions | |
abol | -0.028 |
theless | -0.028 |
utonium | -0.027 |
akespe | -0.026 |
andre | -0.026 |
Token | the |
Token ID | 262 |
Feature activation | +5.07e-02 |
Pos logit contributions | |
Jinn | +0.066 |
↑ | +0.066 |
pai | +0.065 |
�� | +0.060 |
� | +0.060 |
Neg logit contributions | |
abol | -0.113 |
theless | -0.109 |
utonium | -0.107 |
akespe | -0.105 |
andre | -0.102 |
Token | " |
Token ID | 366 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
Jinn | +0.042 |
↑ | +0.042 |
pai | +0.042 |
�� | +0.039 |
� | +0.039 |
Neg logit contributions | |
abol | -0.062 |
theless | -0.060 |
utonium | -0.059 |
akespe | -0.057 |
andre | -0.056 |
Token | aber |
Token ID | 27359 |
Feature activation | -9.24e-02 |
Pos logit contributions | |
abol | +0.136 |
theless | +0.131 |
utonium | +0.127 |
akespe | +0.124 |
andre | +0.120 |
Neg logit contributions | |
Jinn | -0.133 |
↑ | -0.133 |
pai | -0.132 |
�� | -0.125 |
� | -0.124 |
Token | rant |
Token ID | 5250 |
Feature activation | -3.21e-02 |
Pos logit contributions | |
abol | +0.072 |
theless | +0.068 |
utonium | +0.065 |
akespe | +0.063 |
andre | +0.060 |
Neg logit contributions | |
Jinn | -0.119 |
↑ | -0.119 |
pai | -0.118 |
�� | -0.113 |
� | -0.113 |
Token | sal |
Token ID | 3664 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
abol | +0.039 |
theless | +0.037 |
utonium | +0.036 |
akespe | +0.036 |
andre | +0.035 |
Neg logit contributions | |
Jinn | -0.028 |
↑ | -0.027 |
pai | -0.027 |
�� | -0.025 |
� | -0.025 |
Token | ience |
Token ID | 1240 |
Feature activation | -9.39e-01 |
Pos logit contributions | |
Jinn | +0.268 |
↑ | +0.267 |
pai | +0.266 |
�� | +0.257 |
� | +0.256 |
Neg logit contributions | |
abol | -0.044 |
theless | -0.039 |
utonium | -0.033 |
akespe | -0.030 |
andre | -0.025 |
Token | " |
Token ID | 1 |
Feature activation | +7.24e-03 |
Pos logit contributions | |
abol | +1.173 |
theless | +1.126 |
utonium | +1.099 |
akespe | +1.075 |
andre | +1.052 |
Neg logit contributions | |
Jinn | -0.768 |
↑ | -0.758 |
pai | -0.754 |
�� | -0.710 |
� | -0.699 |
Token | hypothesis |
Token ID | 14078 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
Jinn | +0.006 |
↑ | +0.006 |
pai | +0.006 |
�� | +0.005 |
� | +0.005 |
Neg logit contributions | |
abol | -0.009 |
theless | -0.009 |
utonium | -0.009 |
akespe | -0.008 |
andre | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | +4.17e-02 |
Pos logit contributions | |
abol | +0.307 |
theless | +0.298 |
utonium | +0.291 |
akespe | +0.285 |
andre | +0.279 |
Neg logit contributions | |
Jinn | -0.173 |
↑ | -0.172 |
pai | -0.171 |
�� | -0.159 |
� | -0.157 |
Token | which |
Token ID | 543 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
Jinn | +0.034 |
↑ | +0.034 |
pai | +0.033 |
�� | +0.031 |
� | +0.031 |
Neg logit contributions | |
abol | -0.052 |
theless | -0.051 |
utonium | -0.050 |
akespe | -0.049 |
andre | -0.047 |
Token | attributes |
Token ID | 12608 |
Feature activation | +3.04e-02 |
Pos logit contributions | |
abol | +0.170 |
theless | +0.164 |
utonium | +0.160 |
akespe | +0.156 |
andre | +0.152 |
Neg logit contributions | |
Jinn | -0.132 |
↑ | -0.132 |
pai | -0.131 |
�� | -0.123 |
� | -0.122 |
Token | of |
Token ID | 286 |
Feature activation | +7.83e-02 |
Pos logit contributions | |
Jinn | +0.199 |
↑ | +0.198 |
pai | +0.195 |
�� | +0.182 |
� | +0.180 |
Neg logit contributions | |
abol | -0.328 |
theless | -0.318 |
utonium | -0.310 |
akespe | -0.303 |
andre | -0.296 |
Token | this |
Token ID | 428 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
Jinn | +0.061 |
↑ | +0.060 |
pai | +0.059 |
�� | +0.055 |
� | +0.055 |
Neg logit contributions | |
abol | -0.101 |
theless | -0.098 |
utonium | -0.096 |
akespe | -0.094 |
andre | -0.092 |
Token | little |
Token ID | 1310 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
Jinn | +0.107 |
↑ | +0.107 |
pai | +0.106 |
�� | +0.100 |
� | +0.099 |
Neg logit contributions | |
abol | -0.145 |
theless | -0.140 |
utonium | -0.136 |
akespe | -0.133 |
andre | -0.130 |
Token | Sh |
Token ID | 911 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
Jinn | +0.103 |
↑ | +0.103 |
pai | +0.102 |
�� | +0.096 |
� | +0.095 |
Neg logit contributions | |
abol | -0.148 |
theless | -0.143 |
utonium | -0.140 |
akespe | -0.137 |
andre | -0.133 |
Token | akespe |
Token ID | 20621 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
pai | +0.364 |
↑ | +0.363 |
Jinn | +0.363 |
ki | +0.345 |
� | +0.344 |
Neg logit contributions | |
abol | -0.271 |
theless | -0.269 |
utonium | -0.253 |
akespe | -0.234 |
andre | -0.233 |
Token | arian |
Token ID | 3699 |
Feature activation | -9.16e-01 |
Pos logit contributions | |
abol | +0.231 |
theless | +0.218 |
utonium | +0.211 |
akespe | +0.205 |
andre | +0.196 |
Neg logit contributions | |
Jinn | -0.342 |
↑ | -0.341 |
pai | -0.339 |
�� | -0.325 |
� | -0.323 |
Token | drama |
Token ID | 10512 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
abol | +1.067 |
theless | +1.028 |
utonium | +1.000 |
akespe | +0.983 |
andre | +0.954 |
Neg logit contributions | |
Jinn | -0.824 |
↑ | -0.819 |
pai | -0.815 |
�� | -0.764 |
� | -0.760 |
Token | : |
Token ID | 25 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
abol | +0.142 |
theless | +0.137 |
utonium | +0.134 |
akespe | +0.132 |
andre | +0.129 |
Neg logit contributions | |
Jinn | -0.083 |
↑ | -0.082 |
pai | -0.082 |
�� | -0.076 |
� | -0.075 |
Token | the |
Token ID | 262 |
Feature activation | +6.49e-02 |
Pos logit contributions | |
Jinn | +0.010 |
↑ | +0.010 |
pai | +0.010 |
�� | +0.009 |
� | +0.009 |
Neg logit contributions | |
abol | -0.016 |
theless | -0.015 |
utonium | -0.015 |
akespe | -0.015 |
andre | -0.014 |
Token | 1950 |
Token ID | 11445 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
Jinn | +0.060 |
↑ | +0.060 |
pai | +0.059 |
�� | +0.056 |
� | +0.055 |
Neg logit contributions | |
abol | -0.074 |
theless | -0.072 |
utonium | -0.070 |
akespe | -0.068 |
andre | -0.066 |
Token | NFL |
Token ID | 5134 |
Feature activation | -8.18e-02 |
Pos logit contributions | |
Jinn | +0.182 |
↑ | +0.182 |
pai | +0.180 |
�� | +0.171 |
� | +0.169 |
Neg logit contributions | |
abol | -0.198 |
theless | -0.191 |
utonium | -0.185 |
akespe | -0.181 |
andre | -0.176 |
Token | he |
Token ID | 339 |
Feature activation | +2.92e-02 |
Pos logit contributions | |
Jinn | +0.025 |
↑ | +0.025 |
pai | +0.025 |
�� | +0.024 |
� | +0.023 |
Neg logit contributions | |
abol | -0.040 |
theless | -0.038 |
utonium | -0.038 |
akespe | -0.037 |
andre | -0.036 |
Token | murdered |
Token ID | 12864 |
Feature activation | +3.00e-02 |
Pos logit contributions | |
Jinn | +0.022 |
↑ | +0.022 |
pai | +0.022 |
�� | +0.020 |
� | +0.020 |
Neg logit contributions | |
abol | -0.038 |
theless | -0.037 |
utonium | -0.036 |
akespe | -0.035 |
andre | -0.035 |
Token | Yoshi |
Token ID | 38936 |
Feature activation | +1.53e-02 |
Pos logit contributions | |
Jinn | +0.023 |
↑ | +0.023 |
pai | +0.023 |
�� | +0.021 |
� | +0.021 |
Neg logit contributions | |
abol | -0.039 |
theless | -0.037 |
utonium | -0.036 |
akespe | -0.036 |
andre | -0.035 |
Token | . |
Token ID | 13 |
Feature activation | -5.03e-03 |
Pos logit contributions | |
Jinn | +0.011 |
↑ | +0.011 |
pai | +0.011 |
�� | +0.010 |
� | +0.010 |
Neg logit contributions | |
abol | -0.020 |
theless | -0.020 |
utonium | -0.019 |
akespe | -0.019 |
andre | -0.018 |
Token | S |
Token ID | 311 |
Feature activation | +2.89e-02 |
Pos logit contributions | |
abol | +0.006 |
theless | +0.006 |
utonium | +0.006 |
akespe | +0.006 |
andre | +0.006 |
Neg logit contributions | |
Jinn | -0.004 |
↑ | -0.004 |
pai | -0.004 |
�� | -0.004 |
� | -0.004 |
Token | aki |
Token ID | 8182 |
Feature activation | -9.13e-01 |
Pos logit contributions | |
Jinn | +0.030 |
↑ | +0.029 |
pai | +0.029 |
�� | +0.028 |
� | +0.028 |
Neg logit contributions | |
abol | -0.030 |
theless | -0.029 |
utonium | -0.028 |
akespe | -0.027 |
andre | -0.026 |
Token | refuses |
Token ID | 17567 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
abol | +0.987 |
theless | +0.949 |
utonium | +0.918 |
akespe | +0.896 |
andre | +0.873 |
Neg logit contributions | |
Jinn | -0.896 |
↑ | -0.895 |
pai | -0.890 |
�� | -0.846 |
� | -0.836 |
Token | and |
Token ID | 290 |
Feature activation | +6.56e-02 |
Pos logit contributions | |
Jinn | +0.083 |
↑ | +0.083 |
pai | +0.082 |
�� | +0.076 |
� | +0.075 |
Neg logit contributions | |
abol | -0.147 |
theless | -0.143 |
utonium | -0.139 |
akespe | -0.136 |
andre | -0.133 |
Token | displays |
Token ID | 11298 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
Jinn | +0.061 |
↑ | +0.060 |
pai | +0.060 |
�� | +0.056 |
� | +0.056 |
Neg logit contributions | |
abol | -0.075 |
theless | -0.072 |
utonium | -0.070 |
akespe | -0.069 |
andre | -0.067 |
Token | a |
Token ID | 257 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
abol | +0.313 |
theless | +0.303 |
utonium | +0.296 |
akespe | +0.290 |
andre | +0.283 |
Neg logit contributions | |
Jinn | -0.192 |
↑ | -0.191 |
pai | -0.190 |
�� | -0.177 |
� | -0.175 |
Token | therm |
Token ID | 21969 |
Feature activation | -6.91e-02 |
Pos logit contributions | |
Jinn | +0.096 |
↑ | +0.096 |
pai | +0.095 |
�� | +0.089 |
� | +0.088 |
Neg logit contributions | |
abol | -0.135 |
theless | -0.130 |
utonium | -0.127 |
akespe | -0.124 |
andre | -0.121 |
Token | deliver |
Token ID | 5203 |
Feature activation | -5.26e-02 |
Pos logit contributions | |
Jinn | +0.057 |
↑ | +0.056 |
pai | +0.056 |
�� | +0.052 |
� | +0.052 |
Neg logit contributions | |
abol | -0.079 |
theless | -0.076 |
utonium | -0.074 |
akespe | -0.073 |
andre | -0.071 |
Token | a |
Token ID | 257 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
abol | +0.068 |
theless | +0.066 |
utonium | +0.065 |
akespe | +0.063 |
andre | +0.062 |
Neg logit contributions | |
Jinn | -0.040 |
↑ | -0.040 |
pai | -0.040 |
�� | -0.037 |
� | -0.036 |
Token | message |
Token ID | 3275 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
Jinn | +0.090 |
↑ | +0.090 |
pai | +0.089 |
�� | +0.084 |
� | +0.083 |
Neg logit contributions | |
abol | -0.116 |
theless | -0.112 |
utonium | -0.109 |
akespe | -0.107 |
andre | -0.104 |
Token | to |
Token ID | 284 |
Feature activation | +2.68e-02 |
Pos logit contributions | |
abol | +0.191 |
theless | +0.185 |
utonium | +0.181 |
akespe | +0.178 |
andre | +0.173 |
Neg logit contributions | |
Jinn | -0.105 |
↑ | -0.104 |
pai | -0.103 |
�� | -0.096 |
� | -0.095 |
Token | S |
Token ID | 311 |
Feature activation | +6.46e-02 |
Pos logit contributions | |
Jinn | +0.020 |
↑ | +0.020 |
pai | +0.020 |
�� | +0.018 |
� | +0.018 |
Neg logit contributions | |
abol | -0.035 |
theless | -0.034 |
utonium | -0.033 |
akespe | -0.033 |
andre | -0.032 |
Token | aki |
Token ID | 8182 |
Feature activation | -9.13e-01 |
Pos logit contributions | |
Jinn | +0.066 |
↑ | +0.066 |
pai | +0.066 |
�� | +0.062 |
� | +0.061 |
Neg logit contributions | |
abol | -0.067 |
theless | -0.065 |
utonium | -0.063 |
akespe | -0.061 |
andre | -0.059 |
Token | ... |
Token ID | 986 |
Feature activation | +1.88e-03 |
Pos logit contributions | |
abol | +1.193 |
theless | +1.151 |
utonium | +1.125 |
akespe | +1.103 |
andre | +1.081 |
Neg logit contributions | |
↑ | -0.685 |
Jinn | -0.682 |
pai | -0.679 |
�� | -0.634 |
� | -0.625 |
Token | which |
Token ID | 543 |
Feature activation | -8.26e-02 |
Pos logit contributions | |
Jinn | +0.001 |
↑ | +0.001 |
pai | +0.001 |
�� | +0.001 |
� | +0.001 |
Neg logit contributions | |
abol | -0.002 |
theless | -0.002 |
utonium | -0.002 |
akespe | -0.002 |
andre | -0.002 |
Token | he |
Token ID | 339 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
abol | +0.104 |
theless | +0.100 |
utonium | +0.098 |
akespe | +0.096 |
andre | +0.094 |
Neg logit contributions | |
Jinn | -0.067 |
↑ | -0.067 |
pai | -0.066 |
�� | -0.062 |
� | -0.061 |
Token | does |
Token ID | 857 |
Feature activation | -4.44e-03 |
Pos logit contributions | |
Jinn | +0.096 |
↑ | +0.095 |
pai | +0.094 |
�� | +0.088 |
� | +0.088 |
Neg logit contributions | |
abol | -0.126 |
theless | -0.121 |
utonium | -0.119 |
akespe | -0.116 |
andre | -0.113 |
Token | in |
Token ID | 287 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
abol | +0.006 |
theless | +0.006 |
utonium | +0.006 |
akespe | +0.006 |
andre | +0.005 |
Neg logit contributions | |
Jinn | -0.003 |
↑ | -0.003 |
pai | -0.003 |
�� | -0.003 |
� | -0.003 |
Token | of |
Token ID | 286 |
Feature activation | +3.52e-02 |
Pos logit contributions | |
Jinn | +0.096 |
↑ | +0.096 |
pai | +0.095 |
�� | +0.089 |
� | +0.088 |
Neg logit contributions | |
abol | -0.147 |
theless | -0.141 |
utonium | -0.138 |
akespe | -0.135 |
andre | -0.132 |
Token | nin |
Token ID | 13462 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
Jinn | +0.027 |
↑ | +0.027 |
pai | +0.026 |
�� | +0.025 |
� | +0.024 |
Neg logit contributions | |
abol | -0.046 |
theless | -0.044 |
utonium | -0.043 |
akespe | -0.042 |
andre | -0.041 |
Token | jas |
Token ID | 28121 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
abol | +0.017 |
theless | +0.016 |
utonium | +0.015 |
akespe | +0.015 |
andre | +0.014 |
Neg logit contributions | |
Jinn | -0.022 |
↑ | -0.022 |
pai | -0.022 |
�� | -0.021 |
� | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | -6.45e-02 |
Pos logit contributions | |
Jinn | +0.016 |
↑ | +0.016 |
pai | +0.016 |
�� | +0.015 |
� | +0.014 |
Neg logit contributions | |
abol | -0.029 |
theless | -0.028 |
utonium | -0.027 |
akespe | -0.027 |
andre | -0.026 |
Token | S |
Token ID | 311 |
Feature activation | -1.74e-02 |
Pos logit contributions | |
abol | +0.079 |
theless | +0.076 |
utonium | +0.074 |
akespe | +0.072 |
andre | +0.071 |
Neg logit contributions | |
Jinn | -0.053 |
↑ | -0.053 |
pai | -0.053 |
�� | -0.050 |
� | -0.049 |
Token | aki |
Token ID | 8182 |
Feature activation | -9.11e-01 |
Pos logit contributions | |
abol | +0.018 |
theless | +0.017 |
utonium | +0.017 |
akespe | +0.016 |
andre | +0.016 |
Neg logit contributions | |
Jinn | -0.018 |
↑ | -0.018 |
pai | -0.018 |
�� | -0.017 |
� | -0.017 |
Token | recognized |
Token ID | 8018 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
abol | +1.181 |
theless | +1.144 |
utonium | +1.112 |
akespe | +1.087 |
andre | +1.069 |
Neg logit contributions | |
↑ | -0.693 |
Jinn | -0.691 |
pai | -0.689 |
�� | -0.649 |
� | -0.637 |
Token | this |
Token ID | 428 |
Feature activation | -9.95e-03 |
Pos logit contributions | |
abol | +0.163 |
theless | +0.157 |
utonium | +0.153 |
akespe | +0.150 |
andre | +0.147 |
Neg logit contributions | |
Jinn | -0.097 |
↑ | -0.097 |
pai | -0.096 |
�� | -0.090 |
� | -0.089 |
Token | as |
Token ID | 355 |
Feature activation | -3.15e-03 |
Pos logit contributions | |
abol | +0.013 |
theless | +0.013 |
utonium | +0.012 |
akespe | +0.012 |
andre | +0.012 |
Neg logit contributions | |
↑ | -0.007 |
pai | -0.007 |
Jinn | -0.007 |
�� | -0.007 |
� | -0.007 |
Token | his |
Token ID | 465 |
Feature activation | -7.27e-02 |
Pos logit contributions | |
abol | +0.004 |
theless | +0.004 |
utonium | +0.004 |
akespe | +0.004 |
andre | +0.004 |
Neg logit contributions | |
↑ | -0.002 |
Jinn | -0.002 |
pai | -0.002 |
�� | -0.002 |
� | -0.002 |
Token | opportunity |
Token ID | 3663 |
Feature activation | -5.00e-02 |
Pos logit contributions | |
abol | +0.087 |
theless | +0.084 |
utonium | +0.082 |
akespe | +0.080 |
andre | +0.078 |
Neg logit contributions | |
↑ | -0.063 |
Jinn | -0.063 |
pai | -0.062 |
�� | -0.059 |
� | -0.058 |
Token | her |
Token ID | 607 |
Feature activation | +4.10e-02 |
Pos logit contributions | |
abol | +0.149 |
theless | +0.144 |
utonium | +0.140 |
akespe | +0.137 |
andre | +0.133 |
Neg logit contributions | |
Jinn | -0.111 |
↑ | -0.110 |
pai | -0.109 |
�� | -0.102 |
� | -0.102 |
Token | murderer |
Token ID | 29262 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
Jinn | +0.038 |
↑ | +0.037 |
pai | +0.037 |
�� | +0.035 |
� | +0.035 |
Neg logit contributions | |
abol | -0.047 |
theless | -0.045 |
utonium | -0.044 |
akespe | -0.043 |
andre | -0.042 |
Token | Oro |
Token ID | 31770 |
Feature activation | +1.59e-02 |
Pos logit contributions | |
abol | +0.134 |
theless | +0.130 |
utonium | +0.126 |
akespe | +0.124 |
andre | +0.121 |
Neg logit contributions | |
Jinn | -0.079 |
↑ | -0.078 |
pai | -0.078 |
�� | -0.072 |
� | -0.072 |
Token | ku |
Token ID | 23063 |
Feature activation | +9.73e-02 |
Pos logit contributions | |
Jinn | +0.014 |
↑ | +0.014 |
pai | +0.014 |
�� | +0.013 |
� | +0.013 |
Neg logit contributions | |
abol | -0.019 |
theless | -0.018 |
utonium | -0.018 |
akespe | -0.018 |
andre | -0.017 |
Token | S |
Token ID | 311 |
Feature activation | +2.09e-02 |
Pos logit contributions | |
Jinn | +0.076 |
↑ | +0.076 |
pai | +0.075 |
�� | +0.070 |
� | +0.070 |
Neg logit contributions | |
abol | -0.124 |
theless | -0.120 |
utonium | -0.117 |
akespe | -0.115 |
andre | -0.112 |
Token | aki |
Token ID | 8182 |
Feature activation | -9.11e-01 |
Pos logit contributions | |
Jinn | +0.021 |
↑ | +0.021 |
pai | +0.021 |
�� | +0.019 |
� | +0.019 |
Neg logit contributions | |
abol | -0.022 |
theless | -0.022 |
utonium | -0.021 |
akespe | -0.020 |
andre | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | -4.22e-02 |
Pos logit contributions | |
abol | +1.166 |
theless | +1.124 |
utonium | +1.096 |
akespe | +1.075 |
andre | +1.054 |
Neg logit contributions | |
Jinn | -0.709 |
↑ | -0.708 |
pai | -0.704 |
�� | -0.659 |
� | -0.651 |
Token | who |
Token ID | 508 |
Feature activation | -7.30e-02 |
Pos logit contributions | |
abol | +0.054 |
theless | +0.052 |
utonium | +0.051 |
akespe | +0.050 |
andre | +0.049 |
Neg logit contributions | |
Jinn | -0.033 |
↑ | -0.033 |
pai | -0.033 |
�� | -0.031 |
� | -0.030 |
Token | proclaimed |
Token ID | 25546 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
abol | +0.099 |
theless | +0.096 |
utonium | +0.093 |
akespe | +0.092 |
andre | +0.090 |
Neg logit contributions | |
Jinn | -0.052 |
↑ | -0.052 |
pai | -0.051 |
�� | -0.047 |
� | -0.047 |
Token | himself |
Token ID | 2241 |
Feature activation | +9.91e-03 |
Pos logit contributions | |
abol | +0.238 |
theless | +0.229 |
utonium | +0.223 |
akespe | +0.218 |
andre | +0.213 |
Neg logit contributions | |
Jinn | -0.178 |
↑ | -0.177 |
pai | -0.176 |
�� | -0.166 |
� | -0.164 |
Token | to |
Token ID | 284 |
Feature activation | -8.02e-03 |
Pos logit contributions | |
↑ | +0.008 |
Jinn | +0.008 |
pai | +0.008 |
�� | +0.007 |
� | +0.007 |
Neg logit contributions | |
abol | -0.013 |
theless | -0.012 |
utonium | -0.012 |
akespe | -0.012 |
andre | -0.012 |
Token | his |
Token ID | 465 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
abol | +0.042 |
theless | +0.041 |
utonium | +0.040 |
akespe | +0.039 |
andre | +0.038 |
Neg logit contributions | |
Jinn | -0.025 |
↑ | -0.025 |
pai | -0.024 |
�� | -0.023 |
� | -0.022 |
Token | bo |
Token ID | 1489 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
Jinn | +0.010 |
↑ | +0.010 |
pai | +0.010 |
�� | +0.009 |
� | +0.009 |
Neg logit contributions | |
abol | -0.012 |
theless | -0.012 |
utonium | -0.011 |
akespe | -0.011 |
andre | -0.011 |
Token | staff |
Token ID | 3085 |
Feature activation | -8.30e-03 |
Pos logit contributions | |
abol | +0.226 |
theless | +0.217 |
utonium | +0.213 |
akespe | +0.209 |
andre | +0.204 |
Neg logit contributions | |
Jinn | -0.139 |
↑ | -0.138 |
pai | -0.137 |
�� | -0.129 |
� | -0.127 |
Token | into |
Token ID | 656 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
abol | +0.011 |
theless | +0.011 |
utonium | +0.011 |
akespe | +0.011 |
andre | +0.010 |
Neg logit contributions | |
Jinn | -0.006 |
↑ | -0.006 |
pai | -0.006 |
�� | -0.005 |
� | -0.005 |
Token | S |
Token ID | 311 |
Feature activation | +4.46e-02 |
Pos logit contributions | |
Jinn | +0.117 |
↑ | +0.117 |
pai | +0.116 |
�� | +0.107 |
� | +0.105 |
Neg logit contributions | |
abol | -0.236 |
theless | -0.228 |
utonium | -0.223 |
akespe | -0.219 |
andre | -0.214 |
Token | aki |
Token ID | 8182 |
Feature activation | -9.07e-01 |
Pos logit contributions | |
Jinn | +0.045 |
↑ | +0.045 |
pai | +0.045 |
�� | +0.042 |
� | +0.042 |
Neg logit contributions | |
abol | -0.046 |
theless | -0.045 |
utonium | -0.043 |
akespe | -0.042 |
andre | -0.041 |
Token | 's |
Token ID | 338 |
Feature activation | +4.56e-02 |
Pos logit contributions | |
abol | +1.148 |
theless | +1.105 |
utonium | +1.079 |
akespe | +1.057 |
andre | +1.038 |
Neg logit contributions | |
↑ | -0.722 |
Jinn | -0.716 |
pai | -0.712 |
�� | -0.672 |
� | -0.660 |
Token | jaw |
Token ID | 19218 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
Jinn | +0.047 |
↑ | +0.047 |
pai | +0.046 |
�� | +0.044 |
� | +0.044 |
Neg logit contributions | |
abol | -0.047 |
theless | -0.045 |
utonium | -0.044 |
akespe | -0.043 |
andre | -0.042 |
Token | , |
Token ID | 11 |
Feature activation | +3.96e-02 |
Pos logit contributions | |
Jinn | +0.150 |
↑ | +0.149 |
pai | +0.148 |
�� | +0.137 |
� | +0.135 |
Neg logit contributions | |
abol | -0.272 |
theless | -0.264 |
utonium | -0.258 |
akespe | -0.253 |
andre | -0.247 |
Token | knocking |
Token ID | 21500 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
Jinn | +0.031 |
↑ | +0.031 |
pai | +0.030 |
�� | +0.028 |
� | +0.028 |
Neg logit contributions | |
abol | -0.051 |
theless | -0.049 |
utonium | -0.048 |
akespe | -0.047 |
andre | -0.046 |
Token | him |
Token ID | 683 |
Feature activation | +9.87e-02 |
Pos logit contributions | |
Jinn | +0.167 |
↑ | +0.167 |
pai | +0.165 |
�� | +0.152 |
� | +0.150 |
Neg logit contributions | |
abol | -0.346 |
theless | -0.336 |
utonium | -0.328 |
akespe | -0.322 |
andre | -0.315 |
Token | him |
Token ID | 683 |
Feature activation | +3.08e-02 |
Pos logit contributions | |
Jinn | +0.316 |
↑ | +0.316 |
pai | +0.313 |
�� | +0.290 |
� | +0.287 |
Neg logit contributions | |
abol | -0.589 |
theless | -0.570 |
utonium | -0.557 |
akespe | -0.547 |
andre | -0.534 |
Token | . |
Token ID | 13 |
Feature activation | -9.73e-02 |
Pos logit contributions | |
Jinn | +0.022 |
↑ | +0.022 |
pai | +0.022 |
�� | +0.020 |
� | +0.020 |
Neg logit contributions | |
abol | -0.041 |
theless | -0.040 |
utonium | -0.039 |
akespe | -0.038 |
andre | -0.037 |
Token |
|
Token ID | 198 |
Feature activation | -4.46e-02 |
Pos logit contributions | |
abol | +0.119 |
theless | +0.115 |
utonium | +0.112 |
akespe | +0.109 |
andre | +0.107 |
Neg logit contributions | |
pai | -0.080 |
↑ | -0.080 |
Jinn | -0.080 |
�� | -0.076 |
� | -0.074 |
Token |
|
Token ID | 198 |
Feature activation | -4.08e-02 |
Pos logit contributions | |
abol | +0.056 |
theless | +0.054 |
utonium | +0.053 |
akespe | +0.051 |
andre | +0.051 |
Neg logit contributions | |
Jinn | -0.036 |
↑ | -0.036 |
pai | -0.036 |
�� | -0.034 |
� | -0.033 |
Token | S |
Token ID | 50 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
abol | +0.041 |
theless | +0.039 |
utonium | +0.038 |
akespe | +0.037 |
andre | +0.036 |
Neg logit contributions | |
Jinn | -0.043 |
↑ | -0.043 |
pai | -0.043 |
�� | -0.041 |
� | -0.040 |
Token | aki |
Token ID | 8182 |
Feature activation | -9.05e-01 |
Pos logit contributions | |
abol | +0.116 |
theless | +0.112 |
utonium | +0.108 |
akespe | +0.106 |
andre | +0.102 |
Neg logit contributions | |
Jinn | -0.114 |
↑ | -0.113 |
pai | -0.113 |
�� | -0.106 |
� | -0.106 |
Token | quickly |
Token ID | 2952 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
abol | +1.167 |
theless | +1.129 |
utonium | +1.098 |
akespe | +1.073 |
andre | +1.055 |
Neg logit contributions | |
↑ | -0.696 |
Jinn | -0.695 |
pai | -0.692 |
�� | -0.651 |
� | -0.640 |
Token | built |
Token ID | 3170 |
Feature activation | -5.16e-02 |
Pos logit contributions | |
abol | +0.566 |
theless | +0.547 |
utonium | +0.534 |
akespe | +0.523 |
andre | +0.511 |
Neg logit contributions | |
Jinn | -0.345 |
↑ | -0.343 |
pai | -0.340 |
�� | -0.317 |
� | -0.314 |
Token | the |
Token ID | 262 |
Feature activation | -7.50e-02 |
Pos logit contributions | |
abol | +0.064 |
theless | +0.061 |
utonium | +0.060 |
akespe | +0.059 |
andre | +0.057 |
Neg logit contributions | |
Jinn | -0.043 |
↑ | -0.043 |
pai | -0.042 |
�� | -0.040 |
� | -0.039 |
Token | New |
Token ID | 968 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
abol | +0.090 |
theless | +0.087 |
utonium | +0.085 |
akespe | +0.084 |
andre | +0.081 |
Neg logit contributions | |
Jinn | -0.065 |
↑ | -0.064 |
pai | -0.064 |
�� | -0.060 |
� | -0.059 |
Token | York |
Token ID | 1971 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
abol | +0.254 |
theless | +0.245 |
utonium | +0.239 |
akespe | +0.233 |
andre | +0.227 |
Neg logit contributions | |
Jinn | -0.198 |
↑ | -0.197 |
pai | -0.196 |
�� | -0.184 |
� | -0.183 |
Token | Big |
Token ID | 4403 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
abol | +0.407 |
theless | +0.391 |
utonium | +0.382 |
akespe | +0.374 |
andre | +0.364 |
Neg logit contributions | |
Jinn | -0.318 |
↑ | -0.316 |
pai | -0.314 |
�� | -0.296 |
� | -0.293 |
Token | Lie |
Token ID | 12060 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
Jinn | +0.140 |
↑ | +0.139 |
pai | +0.138 |
�� | +0.128 |
� | +0.127 |
Neg logit contributions | |
abol | -0.221 |
theless | -0.213 |
utonium | -0.208 |
akespe | -0.204 |
andre | -0.199 |
Token | : |
Token ID | 25 |
Feature activation | -2.14e-02 |
Pos logit contributions | |
abol | +0.523 |
theless | +0.506 |
utonium | +0.494 |
akespe | +0.484 |
andre | +0.473 |
Neg logit contributions | |
Jinn | -0.314 |
↑ | -0.312 |
pai | -0.309 |
�� | -0.288 |
� | -0.285 |
Token | Free |
Token ID | 3232 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
abol | +0.026 |
theless | +0.025 |
utonium | +0.025 |
akespe | +0.024 |
andre | +0.024 |
Neg logit contributions | |
Jinn | -0.018 |
↑ | -0.018 |
pai | -0.018 |
�� | -0.017 |
� | -0.017 |
Token | Tu |
Token ID | 16749 |
Feature activation | -3.11e-02 |
Pos logit contributions | |
abol | +0.312 |
theless | +0.299 |
utonium | +0.294 |
akespe | +0.287 |
andre | +0.279 |
Neg logit contributions | |
Jinn | -0.215 |
↑ | -0.213 |
pai | -0.212 |
�� | -0.199 |
� | -0.196 |
Token | ition |
Token ID | 653 |
Feature activation | -9.05e-01 |
Pos logit contributions | |
abol | +0.025 |
theless | +0.025 |
utonium | +0.023 |
akespe | +0.023 |
andre | +0.021 |
Neg logit contributions | |
Jinn | -0.039 |
↑ | -0.039 |
pai | -0.038 |
�� | -0.037 |
ki | -0.036 |
Token | Increases |
Token ID | 23920 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
abol | +1.152 |
theless | +1.109 |
utonium | +1.086 |
akespe | +1.063 |
andre | +1.041 |
Neg logit contributions | |
Jinn | -0.715 |
↑ | -0.707 |
pai | -0.704 |
�� | -0.658 |
� | -0.649 |
Token | Your |
Token ID | 3406 |
Feature activation | -2.65e-02 |
Pos logit contributions | |
abol | +0.132 |
theless | +0.127 |
utonium | +0.124 |
akespe | +0.122 |
andre | +0.119 |
Neg logit contributions | |
Jinn | -0.084 |
↑ | -0.083 |
pai | -0.083 |
�� | -0.078 |
� | -0.077 |
Token | Career |
Token ID | 32619 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
abol | +0.034 |
theless | +0.032 |
utonium | +0.032 |
akespe | +0.031 |
andre | +0.030 |
Neg logit contributions | |
Jinn | -0.021 |
↑ | -0.021 |
pai | -0.021 |
�� | -0.019 |
� | -0.019 |
Token | Success |
Token ID | 16282 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
abol | +0.230 |
theless | +0.222 |
utonium | +0.217 |
akespe | +0.213 |
andre | +0.207 |
Neg logit contributions | |
Jinn | -0.148 |
↑ | -0.147 |
pai | -0.145 |
�� | -0.136 |
� | -0.135 |
Token |
|
Token ID | 198 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
abol | +0.332 |
theless | +0.321 |
utonium | +0.313 |
akespe | +0.307 |
andre | +0.300 |
Neg logit contributions | |
Jinn | -0.203 |
↑ | -0.201 |
pai | -0.200 |
�� | -0.186 |
� | -0.185 |
Token | The |
Token ID | 383 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
Jinn | +0.051 |
↑ | +0.051 |
pai | +0.050 |
�� | +0.047 |
� | +0.047 |
Neg logit contributions | |
abol | -0.071 |
theless | -0.068 |
utonium | -0.067 |
akespe | -0.065 |
andre | -0.064 |
Token | message |
Token ID | 3275 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
Jinn | +0.157 |
↑ | +0.155 |
pai | +0.154 |
�� | +0.144 |
� | +0.143 |
Neg logit contributions | |
abol | -0.243 |
theless | -0.236 |
utonium | -0.230 |
akespe | -0.225 |
andre | -0.220 |
Token | demands |
Token ID | 8665 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
abol | +0.169 |
theless | +0.163 |
utonium | +0.159 |
akespe | +0.156 |
andre | +0.152 |
Neg logit contributions | |
Jinn | -0.111 |
↑ | -0.109 |
pai | -0.108 |
�� | -0.101 |
� | -0.100 |
Token | that |
Token ID | 326 |
Feature activation | +5.81e-02 |
Pos logit contributions | |
abol | +0.538 |
theless | +0.519 |
utonium | +0.506 |
akespe | +0.495 |
andre | +0.483 |
Neg logit contributions | |
Jinn | -0.370 |
↑ | -0.369 |
pai | -0.366 |
�� | -0.343 |
� | -0.341 |
Token | S |
Token ID | 311 |
Feature activation | +8.93e-02 |
Pos logit contributions | |
Jinn | +0.046 |
↑ | +0.046 |
pai | +0.046 |
�� | +0.043 |
� | +0.043 |
Neg logit contributions | |
abol | -0.073 |
theless | -0.071 |
utonium | -0.069 |
akespe | -0.068 |
andre | -0.066 |
Token | aki |
Token ID | 8182 |
Feature activation | -9.04e-01 |
Pos logit contributions | |
Jinn | +0.091 |
↑ | +0.091 |
pai | +0.091 |
�� | +0.085 |
� | +0.085 |
Neg logit contributions | |
abol | -0.093 |
theless | -0.090 |
utonium | -0.087 |
akespe | -0.085 |
andre | -0.082 |
Token | meet |
Token ID | 1826 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
abol | +1.076 |
theless | +1.034 |
utonium | +1.005 |
akespe | +0.981 |
andre | +0.962 |
Neg logit contributions | |
Jinn | -0.788 |
↑ | -0.787 |
pai | -0.782 |
�� | -0.743 |
� | -0.730 |
Token | the |
Token ID | 262 |
Feature activation | +5.24e-02 |
Pos logit contributions | |
Jinn | +0.279 |
↑ | +0.277 |
pai | +0.274 |
�� | +0.253 |
� | +0.251 |
Neg logit contributions | |
abol | -0.526 |
theless | -0.510 |
utonium | -0.499 |
akespe | -0.490 |
andre | -0.478 |
Token | Turtles |
Token ID | 44356 |
Feature activation | +5.33e-01 |
Pos logit contributions | |
Jinn | +0.044 |
↑ | +0.043 |
pai | +0.043 |
�� | +0.040 |
� | +0.040 |
Neg logit contributions | |
abol | -0.065 |
theless | -0.063 |
utonium | -0.061 |
akespe | -0.060 |
andre | -0.058 |
Token | on |
Token ID | 319 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
Jinn | +0.385 |
↑ | +0.379 |
pai | +0.373 |
�� | +0.345 |
� | +0.342 |
Neg logit contributions | |
abol | -0.716 |
theless | -0.701 |
utonium | -0.682 |
akespe | -0.670 |
andre | -0.651 |
Token | the |
Token ID | 262 |
Feature activation | +3.94e-02 |
Pos logit contributions | |
Jinn | +0.102 |
↑ | +0.100 |
pai | +0.099 |
�� | +0.092 |
ki | +0.091 |
Neg logit contributions | |
abol | -0.177 |
theless | -0.172 |
utonium | -0.168 |
akespe | -0.165 |
andre | -0.161 |
Token | credit |
Token ID | 3884 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
abol | +0.170 |
theless | +0.164 |
utonium | +0.160 |
akespe | +0.157 |
andre | +0.154 |
Neg logit contributions | |
Jinn | -0.093 |
↑ | -0.092 |
pai | -0.091 |
�� | -0.085 |
� | -0.084 |
Token | for |
Token ID | 329 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
↑ | +0.142 |
Jinn | +0.141 |
pai | +0.139 |
�� | +0.128 |
� | +0.127 |
Neg logit contributions | |
abol | -0.272 |
theless | -0.264 |
utonium | -0.258 |
akespe | -0.253 |
andre | -0.246 |
Token | your |
Token ID | 534 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
abol | +0.143 |
theless | +0.139 |
utonium | +0.136 |
akespe | +0.133 |
andre | +0.130 |
Neg logit contributions | |
Jinn | -0.078 |
↑ | -0.078 |
pai | -0.076 |
�� | -0.071 |
� | -0.070 |
Token | aw |
Token ID | 3253 |
Feature activation | -5.69e-02 |
Pos logit contributions | |
abol | +0.377 |
theless | +0.365 |
utonium | +0.356 |
akespe | +0.349 |
andre | +0.340 |
Neg logit contributions | |
Jinn | -0.241 |
↑ | -0.240 |
pai | -0.238 |
�� | -0.222 |
� | -0.220 |
Token | es |
Token ID | 274 |
Feature activation | -4.07e-02 |
Pos logit contributions | |
abol | +0.067 |
theless | +0.065 |
utonium | +0.063 |
akespe | +0.061 |
andre | +0.060 |
Neg logit contributions | |
Jinn | -0.051 |
↑ | -0.050 |
pai | -0.050 |
�� | -0.047 |
� | -0.047 |
Token | omen |
Token ID | 3674 |
Feature activation | -8.95e-01 |
Pos logit contributions | |
abol | +0.037 |
theless | +0.035 |
utonium | +0.034 |
akespe | +0.033 |
andre | +0.032 |
Neg logit contributions | |
Jinn | -0.047 |
↑ | -0.047 |
pai | -0.047 |
�� | -0.045 |
� | -0.045 |
Token | ess |
Token ID | 408 |
Feature activation | -9.68e-02 |
Pos logit contributions | |
abol | +0.688 |
theless | +0.650 |
utonium | +0.624 |
akespe | +0.603 |
andre | +0.577 |
Neg logit contributions | |
Jinn | -1.161 |
↑ | -1.156 |
pai | -1.150 |
�� | -1.104 |
� | -1.097 |
Token | . |
Token ID | 13 |
Feature activation | -4.64e-02 |
Pos logit contributions | |
abol | +0.129 |
theless | +0.125 |
utonium | +0.122 |
akespe | +0.120 |
andre | +0.117 |
Neg logit contributions | |
Jinn | -0.071 |
↑ | -0.071 |
pai | -0.070 |
�� | -0.065 |
� | -0.064 |
Token |
|
Token ID | 198 |
Feature activation | -6.27e-02 |
Pos logit contributions | |
abol | +0.055 |
theless | +0.053 |
utonium | +0.052 |
akespe | +0.051 |
andre | +0.049 |
Neg logit contributions | |
Jinn | -0.041 |
↑ | -0.041 |
pai | -0.040 |
�� | -0.038 |
� | -0.038 |
Token |
|
Token ID | 198 |
Feature activation | -3.62e-02 |
Pos logit contributions | |
abol | +0.079 |
theless | +0.075 |
utonium | +0.074 |
akespe | +0.072 |
andre | +0.071 |
Neg logit contributions | |
Jinn | -0.051 |
↑ | -0.050 |
pai | -0.050 |
�� | -0.047 |
� | -0.046 |
Token | If |
Token ID | 1532 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
abol | +0.034 |
theless | +0.033 |
utonium | +0.032 |
akespe | +0.031 |
andre | +0.029 |
Neg logit contributions | |
↑ | -0.041 |
pai | -0.041 |
Jinn | -0.041 |
� | -0.039 |
�� | -0.038 |
Token | chemical |
Token ID | 5931 |
Feature activation | -5.20e-01 |
Pos logit contributions | |
abol | +0.071 |
theless | +0.067 |
utonium | +0.065 |
akespe | +0.063 |
andre | +0.061 |
Neg logit contributions | |
Jinn | -0.090 |
↑ | -0.090 |
pai | -0.089 |
�� | -0.085 |
� | -0.085 |
Token | weapons |
Token ID | 3777 |
Feature activation | -5.21e-01 |
Pos logit contributions | |
abol | +0.358 |
theless | +0.335 |
utonium | +0.321 |
akespe | +0.310 |
andre | +0.294 |
Neg logit contributions | |
Jinn | -0.718 |
↑ | -0.714 |
pai | -0.710 |
�� | -0.681 |
� | -0.680 |
Token | by |
Token ID | 416 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
abol | +0.722 |
theless | +0.700 |
utonium | +0.685 |
akespe | +0.673 |
andre | +0.657 |
Neg logit contributions | |
Jinn | -0.354 |
↑ | -0.352 |
pai | -0.348 |
�� | -0.321 |
� | -0.317 |
Token | Osama |
Token ID | 29236 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
abol | +0.136 |
theless | +0.131 |
utonium | +0.128 |
akespe | +0.126 |
andre | +0.123 |
Neg logit contributions | |
Jinn | -0.087 |
↑ | -0.087 |
pai | -0.086 |
�� | -0.080 |
� | -0.080 |
Token | bin |
Token ID | 9874 |
Feature activation | -2.10e-04 |
Pos logit contributions | |
abol | +0.494 |
theless | +0.478 |
utonium | +0.470 |
akespe | +0.461 |
andre | +0.452 |
Neg logit contributions | |
↑ | -0.184 |
Jinn | -0.184 |
pai | -0.183 |
�� | -0.167 |
� | -0.163 |
Token | Laden |
Token ID | 19402 |
Feature activation | -8.86e-01 |
Pos logit contributions | |
abol | +0.000 |
theless | +0.000 |
utonium | +0.000 |
akespe | +0.000 |
andre | +0.000 |
Neg logit contributions | |
Jinn | -0.000 |
↑ | -0.000 |
pai | -0.000 |
�� | -0.000 |
� | -0.000 |
Token | and |
Token ID | 290 |
Feature activation | -5.74e-02 |
Pos logit contributions | |
abol | +1.180 |
theless | +1.141 |
utonium | +1.116 |
akespe | +1.094 |
andre | +1.070 |
Neg logit contributions | |
Jinn | -0.649 |
↑ | -0.647 |
pai | -0.641 |
�� | -0.596 |
� | -0.589 |
Token | Saddam |
Token ID | 24277 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
abol | +0.071 |
theless | +0.069 |
utonium | +0.067 |
akespe | +0.066 |
andre | +0.064 |
Neg logit contributions | |
Jinn | -0.048 |
↑ | -0.047 |
pai | -0.047 |
�� | -0.044 |
� | -0.043 |
Token | Hussein |
Token ID | 22983 |
Feature activation | +4.98e-02 |
Pos logit contributions | |
abol | +0.454 |
theless | +0.438 |
utonium | +0.428 |
akespe | +0.419 |
andre | +0.409 |
Neg logit contributions | |
Jinn | -0.289 |
↑ | -0.288 |
pai | -0.286 |
�� | -0.268 |
� | -0.265 |
Token | . |
Token ID | 13 |
Feature activation | -4.61e-02 |
Pos logit contributions | |
Jinn | +0.036 |
↑ | +0.036 |
pai | +0.035 |
�� | +0.032 |
� | +0.032 |
Neg logit contributions | |
abol | -0.067 |
theless | -0.065 |
utonium | -0.063 |
akespe | -0.062 |
andre | -0.061 |
Token |
|
Token ID | 198 |
Feature activation | -5.91e-02 |
Pos logit contributions | |
abol | +0.058 |
theless | +0.056 |
utonium | +0.054 |
akespe | +0.053 |
andre | +0.052 |
Neg logit contributions | |
Jinn | -0.037 |
↑ | -0.037 |
pai | -0.037 |
�� | -0.035 |
� | -0.034 |
Token | among |
Token ID | 1871 |
Feature activation | +6.31e-02 |
Pos logit contributions | |
abol | +0.618 |
theless | +0.602 |
utonium | +0.591 |
akespe | +0.581 |
andre | +0.571 |
Neg logit contributions | |
Jinn | -0.190 |
↑ | -0.187 |
pai | -0.185 |
�� | -0.165 |
� | -0.162 |
Token | all |
Token ID | 477 |
Feature activation | -7.72e-02 |
Pos logit contributions | |
Jinn | +0.059 |
↑ | +0.059 |
pai | +0.058 |
�� | +0.055 |
� | +0.055 |
Neg logit contributions | |
abol | -0.071 |
theless | -0.068 |
utonium | -0.066 |
akespe | -0.065 |
andre | -0.063 |
Token | edge |
Token ID | 5743 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
abol | +0.086 |
theless | +0.083 |
utonium | +0.081 |
akespe | +0.079 |
andre | +0.076 |
Neg logit contributions | |
↑ | -0.074 |
Jinn | -0.073 |
pai | -0.072 |
�� | -0.068 |
� | -0.068 |
Token | r |
Token ID | 374 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
abol | +0.260 |
theless | +0.252 |
utonium | +0.244 |
akespe | +0.238 |
andre | +0.231 |
Neg logit contributions | |
↑ | -0.228 |
Jinn | -0.228 |
pai | -0.226 |
�� | -0.213 |
� | -0.211 |
Token | us |
Token ID | 385 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
abol | +0.446 |
theless | +0.430 |
utonium | +0.417 |
akespe | +0.408 |
andre | +0.395 |
Neg logit contributions | |
Jinn | -0.399 |
↑ | -0.398 |
pai | -0.395 |
�� | -0.373 |
� | -0.370 |
Token | hers |
Token ID | 7084 |
Feature activation | -8.83e-01 |
Pos logit contributions | |
abol | +0.159 |
theless | +0.152 |
utonium | +0.145 |
akespe | +0.140 |
andre | +0.134 |
Neg logit contributions | |
Jinn | -0.270 |
↑ | -0.270 |
pai | -0.268 |
�� | -0.256 |
� | -0.255 |
Token | *) |
Token ID | 28104 |
Feature activation | -5.66e-01 |
Pos logit contributions | |
abol | +0.998 |
theless | +0.962 |
utonium | +0.936 |
akespe | +0.915 |
andre | +0.889 |
Neg logit contributions | |
Jinn | -0.825 |
↑ | -0.821 |
pai | -0.815 |
�� | -0.769 |
� | -0.763 |
Token |
|
Token ID | 198 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
abol | +0.720 |
theless | +0.696 |
utonium | +0.680 |
akespe | +0.666 |
andre | +0.650 |
Neg logit contributions | |
Jinn | -0.448 |
↑ | -0.446 |
pai | -0.442 |
�� | -0.412 |
� | -0.408 |
Token |
|
Token ID | 198 |
Feature activation | -7.93e-02 |
Pos logit contributions | |
abol | +0.160 |
theless | +0.153 |
utonium | +0.150 |
akespe | +0.146 |
andre | +0.144 |
Neg logit contributions | |
Jinn | -0.104 |
↑ | -0.103 |
pai | -0.103 |
�� | -0.097 |
� | -0.095 |
Token | Total |
Token ID | 14957 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
abol | +0.098 |
theless | +0.095 |
utonium | +0.093 |
akespe | +0.091 |
andre | +0.088 |
Neg logit contributions | |
↑ | -0.065 |
Jinn | -0.065 |
pai | -0.065 |
�� | -0.061 |
� | -0.060 |
Token | guaranteed |
Token ID | 11462 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
abol | +0.232 |
theless | +0.226 |
utonium | +0.222 |
akespe | +0.218 |
andre | +0.214 |
Neg logit contributions | |
Jinn | -0.077 |
↑ | -0.077 |
pai | -0.076 |
�� | -0.068 |
� | -0.067 |
Token | among |
Token ID | 1871 |
Feature activation | +6.35e-02 |
Pos logit contributions | |
abol | +0.603 |
theless | +0.588 |
utonium | +0.578 |
akespe | +0.569 |
andre | +0.559 |
Neg logit contributions | |
Jinn | -0.147 |
↑ | -0.145 |
pai | -0.143 |
�� | -0.124 |
� | -0.121 |
Token | all |
Token ID | 477 |
Feature activation | -6.04e-02 |
Pos logit contributions | |
Jinn | +0.054 |
↑ | +0.054 |
pai | +0.053 |
�� | +0.050 |
� | +0.050 |
Neg logit contributions | |
abol | -0.077 |
theless | -0.075 |
utonium | -0.073 |
akespe | -0.071 |
andre | -0.069 |
Token | edge |
Token ID | 5743 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
abol | +0.070 |
theless | +0.068 |
utonium | +0.066 |
akespe | +0.065 |
andre | +0.063 |
Neg logit contributions | |
↑ | -0.055 |
Jinn | -0.054 |
pai | -0.054 |
�� | -0.050 |
� | -0.050 |
Token | r |
Token ID | 374 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
abol | +0.239 |
theless | +0.231 |
utonium | +0.224 |
akespe | +0.219 |
andre | +0.212 |
Neg logit contributions | |
↑ | -0.210 |
Jinn | -0.210 |
pai | -0.208 |
�� | -0.196 |
� | -0.194 |
Token | us |
Token ID | 385 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
abol | +0.455 |
theless | +0.438 |
utonium | +0.425 |
akespe | +0.416 |
andre | +0.403 |
Neg logit contributions | |
Jinn | -0.412 |
↑ | -0.410 |
pai | -0.407 |
�� | -0.385 |
� | -0.382 |
Token | hers |
Token ID | 7084 |
Feature activation | -8.72e-01 |
Pos logit contributions | |
abol | +0.148 |
theless | +0.141 |
utonium | +0.135 |
akespe | +0.130 |
andre | +0.124 |
Neg logit contributions | |
Jinn | -0.251 |
↑ | -0.251 |
pai | -0.249 |
�� | -0.238 |
� | -0.237 |
Token | *) |
Token ID | 28104 |
Feature activation | -5.75e-01 |
Pos logit contributions | |
abol | +0.971 |
theless | +0.934 |
utonium | +0.909 |
akespe | +0.888 |
andre | +0.863 |
Neg logit contributions | |
Jinn | -0.830 |
↑ | -0.825 |
pai | -0.819 |
�� | -0.774 |
� | -0.768 |
Token |
|
Token ID | 198 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
abol | +0.730 |
theless | +0.706 |
utonium | +0.690 |
akespe | +0.676 |
andre | +0.659 |
Neg logit contributions | |
Jinn | -0.456 |
↑ | -0.453 |
pai | -0.450 |
�� | -0.420 |
� | -0.416 |
Token |
|
Token ID | 198 |
Feature activation | -6.30e-02 |
Pos logit contributions | |
abol | +0.142 |
theless | +0.136 |
utonium | +0.133 |
akespe | +0.130 |
andre | +0.128 |
Neg logit contributions | |
Jinn | -0.092 |
↑ | -0.091 |
pai | -0.091 |
�� | -0.086 |
� | -0.084 |
Token | Even |
Token ID | 6104 |
Feature activation | +8.48e-02 |
Pos logit contributions | |
abol | +0.066 |
theless | +0.064 |
utonium | +0.061 |
akespe | +0.060 |
andre | +0.058 |
Neg logit contributions | |
↑ | -0.064 |
Jinn | -0.064 |
pai | -0.064 |
�� | -0.060 |
� | -0.060 |
Token | at |
Token ID | 379 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
Jinn | +0.055 |
↑ | +0.054 |
pai | +0.054 |
�� | +0.049 |
� | +0.049 |
Neg logit contributions | |
abol | -0.120 |
theless | -0.117 |
utonium | -0.114 |
akespe | -0.112 |
andre | -0.110 |
Token | among |
Token ID | 1871 |
Feature activation | +3.81e-02 |
Pos logit contributions | |
abol | +0.707 |
theless | +0.689 |
utonium | +0.677 |
akespe | +0.667 |
andre | +0.655 |
Neg logit contributions | |
Jinn | -0.175 |
↑ | -0.172 |
pai | -0.171 |
�� | -0.148 |
� | -0.145 |
Token | all |
Token ID | 477 |
Feature activation | -8.53e-02 |
Pos logit contributions | |
↑ | +0.043 |
Jinn | +0.043 |
pai | +0.042 |
�� | +0.040 |
� | +0.040 |
Neg logit contributions | |
abol | -0.036 |
theless | -0.034 |
utonium | -0.033 |
akespe | -0.032 |
andre | -0.031 |
Token | edge |
Token ID | 5743 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
abol | +0.084 |
theless | +0.081 |
utonium | +0.078 |
akespe | +0.076 |
andre | +0.073 |
Neg logit contributions | |
↑ | -0.093 |
Jinn | -0.093 |
pai | -0.091 |
�� | -0.087 |
� | -0.087 |
Token | r |
Token ID | 374 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
abol | +0.294 |
theless | +0.288 |
utonium | +0.278 |
akespe | +0.270 |
andre | +0.262 |
Neg logit contributions | |
↑ | -0.239 |
pai | -0.238 |
Jinn | -0.238 |
�� | -0.222 |
� | -0.221 |
Token | us |
Token ID | 385 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
abol | +0.479 |
theless | +0.464 |
utonium | +0.447 |
akespe | +0.439 |
andre | +0.424 |
Neg logit contributions | |
Jinn | -0.418 |
↑ | -0.418 |
pai | -0.413 |
�� | -0.391 |
� | -0.387 |
Token | hers |
Token ID | 7084 |
Feature activation | -8.69e-01 |
Pos logit contributions | |
abol | +0.169 |
theless | +0.162 |
utonium | +0.155 |
akespe | +0.150 |
andre | +0.143 |
Neg logit contributions | |
↑ | -0.283 |
Jinn | -0.282 |
pai | -0.281 |
�� | -0.268 |
� | -0.267 |
Token | *) |
Token ID | 28104 |
Feature activation | -5.45e-01 |
Pos logit contributions | |
abol | +0.984 |
theless | +0.948 |
utonium | +0.922 |
akespe | +0.902 |
andre | +0.876 |
Neg logit contributions | |
Jinn | -0.810 |
↑ | -0.806 |
pai | -0.800 |
�� | -0.755 |
� | -0.749 |
Token |
|
Token ID | 198 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
abol | +0.696 |
theless | +0.673 |
utonium | +0.657 |
akespe | +0.644 |
andre | +0.628 |
Neg logit contributions | |
Jinn | -0.430 |
↑ | -0.428 |
pai | -0.424 |
�� | -0.395 |
� | -0.391 |
Token |
|
Token ID | 198 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
abol | +0.203 |
theless | +0.195 |
utonium | +0.190 |
akespe | +0.186 |
andre | +0.183 |
Neg logit contributions | |
Jinn | -0.132 |
↑ | -0.130 |
pai | -0.130 |
�� | -0.123 |
� | -0.120 |
Token | 2017 |
Token ID | 5539 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
abol | +0.110 |
theless | +0.107 |
utonium | +0.104 |
akespe | +0.102 |
andre | +0.097 |
Neg logit contributions | |
↑ | -0.099 |
Jinn | -0.098 |
pai | -0.098 |
�� | -0.092 |
� | -0.092 |
Token | salary |
Token ID | 9588 |
Feature activation | -5.86e-04 |
Pos logit contributions | |
↑ | +0.223 |
Jinn | +0.222 |
pai | +0.220 |
�� | +0.207 |
� | +0.206 |
Neg logit contributions | |
abol | -0.278 |
theless | -0.268 |
utonium | -0.260 |
akespe | -0.255 |
andre | -0.246 |
Token | EN |
Token ID | 1677 |
Feature activation | +5.08e-02 |
Pos logit contributions | |
abol | +0.236 |
theless | +0.228 |
utonium | +0.222 |
akespe | +0.218 |
andre | +0.212 |
Neg logit contributions | |
Jinn | -0.155 |
↑ | -0.155 |
pai | -0.153 |
�� | -0.143 |
� | -0.142 |
Token | founder |
Token ID | 9119 |
Feature activation | +2.51e-02 |
Pos logit contributions | |
Jinn | +0.039 |
↑ | +0.039 |
pai | +0.038 |
�� | +0.036 |
� | +0.035 |
Neg logit contributions | |
abol | -0.066 |
theless | -0.064 |
utonium | -0.062 |
akespe | -0.061 |
andre | -0.060 |
Token | In |
Token ID | 554 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
Jinn | +0.020 |
↑ | +0.020 |
pai | +0.020 |
�� | +0.018 |
� | +0.018 |
Neg logit contributions | |
abol | -0.032 |
theless | -0.031 |
utonium | -0.030 |
akespe | -0.029 |
andre | -0.029 |
Token | aba |
Token ID | 15498 |
Feature activation | -6.20e-01 |
Pos logit contributions | |
abol | +0.182 |
theless | +0.175 |
utonium | +0.169 |
akespe | +0.165 |
andre | +0.159 |
Neg logit contributions | |
Jinn | -0.197 |
↑ | -0.196 |
pai | -0.195 |
�� | -0.184 |
� | -0.184 |
Token | Hiro |
Token ID | 25940 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
abol | +0.801 |
theless | +0.775 |
utonium | +0.756 |
akespe | +0.741 |
andre | +0.724 |
Neg logit contributions | |
Jinn | -0.476 |
↑ | -0.475 |
pai | -0.470 |
�� | -0.440 |
� | -0.434 |
Token | aki |
Token ID | 8182 |
Feature activation | -8.68e-01 |
Pos logit contributions | |
Jinn | +0.381 |
↑ | +0.379 |
pai | +0.377 |
�� | +0.357 |
� | +0.355 |
Neg logit contributions | |
abol | -0.371 |
theless | -0.357 |
utonium | -0.346 |
akespe | -0.337 |
andre | -0.327 |
Token | and |
Token ID | 290 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
abol | +1.142 |
theless | +1.103 |
utonium | +1.078 |
akespe | +1.056 |
andre | +1.035 |
Neg logit contributions | |
Jinn | -0.643 |
↑ | -0.642 |
pai | -0.634 |
�� | -0.597 |
� | -0.587 |
Token | TOP |
Token ID | 28662 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
abol | +0.140 |
theless | +0.135 |
utonium | +0.132 |
akespe | +0.129 |
andre | +0.126 |
Neg logit contributions | |
Jinn | -0.100 |
↑ | -0.099 |
pai | -0.098 |
�� | -0.092 |
� | -0.092 |
Token | AN |
Token ID | 1565 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
abol | +0.184 |
theless | +0.176 |
utonium | +0.171 |
akespe | +0.167 |
andre | +0.162 |
Neg logit contributions | |
Jinn | -0.169 |
↑ | -0.168 |
pai | -0.167 |
�� | -0.158 |
� | -0.157 |
Token | GA |
Token ID | 9273 |
Feature activation | -6.81e-02 |
Pos logit contributions | |
abol | +0.319 |
theless | +0.308 |
utonium | +0.299 |
akespe | +0.292 |
andre | +0.283 |
Neg logit contributions | |
Jinn | -0.298 |
↑ | -0.297 |
pai | -0.295 |
�� | -0.278 |
� | -0.277 |
Token | World |
Token ID | 2159 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
abol | +0.076 |
theless | +0.073 |
utonium | +0.071 |
akespe | +0.069 |
andre | +0.068 |
Neg logit contributions | |
Jinn | -0.065 |
↑ | -0.064 |
pai | -0.064 |
�� | -0.060 |
� | -0.060 |
Token | so |
Token ID | 523 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
↑ | +0.172 |
Jinn | +0.172 |
pai | +0.169 |
�� | +0.158 |
� | +0.157 |
Neg logit contributions | |
abol | -0.269 |
theless | -0.261 |
utonium | -0.255 |
akespe | -0.251 |
andre | -0.243 |
Token | that |
Token ID | 326 |
Feature activation | -5.93e-02 |
Pos logit contributions | |
abol | +0.144 |
theless | +0.140 |
utonium | +0.137 |
akespe | +0.134 |
andre | +0.130 |
Neg logit contributions | |
Jinn | -0.086 |
↑ | -0.086 |
pai | -0.085 |
�� | -0.079 |
� | -0.078 |
Token | if |
Token ID | 611 |
Feature activation | -3.30e-02 |
Pos logit contributions | |
abol | +0.075 |
theless | +0.072 |
utonium | +0.070 |
akespe | +0.069 |
andre | +0.067 |
Neg logit contributions | |
Jinn | -0.047 |
↑ | -0.047 |
pai | -0.047 |
�� | -0.044 |
� | -0.043 |
Token | they |
Token ID | 484 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
abol | +0.042 |
theless | +0.040 |
utonium | +0.039 |
akespe | +0.038 |
andre | +0.037 |
Neg logit contributions | |
Jinn | -0.027 |
↑ | -0.026 |
pai | -0.026 |
�� | -0.025 |
� | -0.024 |
Token | Out |
Token ID | 3806 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
Jinn | +0.010 |
↑ | +0.010 |
pai | +0.010 |
�� | +0.010 |
� | +0.010 |
Neg logit contributions | |
abol | -0.016 |
theless | -0.015 |
utonium | -0.015 |
akespe | -0.014 |
andre | -0.014 |
Token | wit |
Token ID | 39289 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
abol | +0.264 |
theless | +0.258 |
utonium | +0.254 |
akespe | +0.250 |
andre | +0.246 |
Neg logit contributions | |
Jinn | -0.038 |
↑ | -0.038 |
pai | -0.036 |
�� | -0.029 |
� | -0.028 |
Token | his |
Token ID | 465 |
Feature activation | +4.71e-02 |
Pos logit contributions | |
Jinn | +0.762 |
↑ | +0.758 |
pai | +0.748 |
�� | +0.693 |
� | +0.689 |
Neg logit contributions | |
abol | -1.310 |
theless | -1.270 |
utonium | -1.242 |
akespe | -1.218 |
andre | -1.187 |
Token | Master |
Token ID | 5599 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
Jinn | +0.045 |
↑ | +0.045 |
pai | +0.045 |
�� | +0.042 |
� | +0.042 |
Neg logit contributions | |
abol | -0.052 |
theless | -0.050 |
utonium | -0.049 |
akespe | -0.048 |
andre | -0.046 |
Token | mind |
Token ID | 10155 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
Jinn | +0.355 |
↑ | +0.353 |
pai | +0.351 |
�� | +0.333 |
� | +0.332 |
Neg logit contributions | |
abol | -0.285 |
theless | -0.274 |
utonium | -0.265 |
akespe | -0.258 |
andre | -0.248 |
Token | , |
Token ID | 11 |
Feature activation | -3.08e-02 |
Pos logit contributions | |
Jinn | +0.139 |
↑ | +0.139 |
pai | +0.137 |
�� | +0.127 |
� | +0.126 |
Neg logit contributions | |
abol | -0.248 |
theless | -0.240 |
utonium | -0.235 |
akespe | -0.230 |
andre | -0.225 |
Token | he |
Token ID | 339 |
Feature activation | +7.58e-02 |
Pos logit contributions | |
abol | +0.039 |
theless | +0.037 |
utonium | +0.037 |
akespe | +0.036 |
andre | +0.035 |
Neg logit contributions | |
Jinn | -0.025 |
↑ | -0.025 |
pai | -0.025 |
�� | -0.023 |
� | -0.023 |
Token | older |
Token ID | 4697 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
Jinn | +0.017 |
↑ | +0.017 |
pai | +0.017 |
�� | +0.016 |
� | +0.016 |
Neg logit contributions | |
abol | -0.026 |
theless | -0.025 |
utonium | -0.024 |
akespe | -0.024 |
andre | -0.023 |
Token | adults |
Token ID | 6490 |
Feature activation | +3.16e-01 |
Pos logit contributions | |
Jinn | +0.089 |
↑ | +0.089 |
pai | +0.088 |
�� | +0.082 |
� | +0.082 |
Neg logit contributions | |
abol | -0.131 |
theless | -0.127 |
utonium | -0.124 |
akespe | -0.122 |
andre | -0.118 |
Token | . |
Token ID | 13 |
Feature activation | -2.29e-02 |
Pos logit contributions | |
Jinn | +0.232 |
↑ | +0.231 |
pai | +0.229 |
�� | +0.212 |
� | +0.210 |
Neg logit contributions | |
abol | -0.421 |
theless | -0.408 |
utonium | -0.399 |
akespe | -0.391 |
andre | -0.382 |
Token | 2 |
Token ID | 362 |
Feature activation | +1.34e-03 |
Pos logit contributions | |
abol | +0.024 |
theless | +0.023 |
utonium | +0.022 |
akespe | +0.022 |
andre | +0.021 |
Neg logit contributions | |
Jinn | -0.023 |
↑ | -0.023 |
pai | -0.023 |
�� | -0.022 |
� | -0.022 |
Token | nd |
Token ID | 358 |
Feature activation | +7.88e-02 |
Pos logit contributions | |
Jinn | +0.001 |
↑ | +0.001 |
pai | +0.001 |
�� | +0.001 |
� | +0.001 |
Neg logit contributions | |
abol | -0.002 |
theless | -0.002 |
utonium | -0.002 |
akespe | -0.001 |
andre | -0.001 |
Token | ed |
Token ID | 1225 |
Feature activation | +6.52e-01 |
Pos logit contributions | |
Jinn | +0.032 |
↑ | +0.032 |
pai | +0.032 |
�� | +0.027 |
� | +0.027 |
Neg logit contributions | |
abol | -0.130 |
theless | -0.127 |
utonium | -0.124 |
akespe | -0.123 |
andre | -0.120 |
Token | . |
Token ID | 13 |
Feature activation | +4.91e-02 |
Pos logit contributions | |
Jinn | +0.504 |
↑ | +0.499 |
pai | +0.496 |
�� | +0.463 |
� | +0.458 |
Neg logit contributions | |
abol | -0.842 |
theless | -0.814 |
utonium | -0.797 |
akespe | -0.780 |
andre | -0.763 |
Token | 2010 |
Token ID | 3050 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
Jinn | +0.050 |
↑ | +0.050 |
pai | +0.049 |
�� | +0.047 |
� | +0.047 |
Neg logit contributions | |
abol | -0.051 |
theless | -0.049 |
utonium | -0.048 |
akespe | -0.047 |
andre | -0.045 |
Token | . |
Token ID | 13 |
Feature activation | +6.88e-02 |
Pos logit contributions | |
abol | +0.240 |
theless | +0.232 |
utonium | +0.227 |
akespe | +0.222 |
andre | +0.217 |
Neg logit contributions | |
Jinn | -0.139 |
↑ | -0.137 |
pai | -0.137 |
�� | -0.128 |
� | -0.126 |
Token | Atlanta |
Token ID | 9371 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
Jinn | +0.065 |
↑ | +0.065 |
pai | +0.064 |
�� | +0.061 |
� | +0.060 |
Neg logit contributions | |
abol | -0.077 |
theless | -0.074 |
utonium | -0.072 |
akespe | -0.070 |
andre | -0.068 |
Token | , |
Token ID | 11 |
Feature activation | -3.98e-03 |
Pos logit contributions | |
abol | +0.480 |
theless | +0.465 |
utonium | +0.455 |
akespe | +0.446 |
andre | +0.436 |
Neg logit contributions | |
Jinn | -0.256 |
↑ | -0.255 |
pai | -0.252 |
�� | -0.234 |
� | -0.231 |
Token | to |
Token ID | 284 |
Feature activation | +2.95e-02 |
Pos logit contributions | |
abol | +0.073 |
theless | +0.071 |
utonium | +0.069 |
akespe | +0.067 |
andre | +0.066 |
Neg logit contributions | |
Jinn | -0.049 |
↑ | -0.049 |
pai | -0.048 |
�� | -0.045 |
� | -0.045 |
Token | 44 |
Token ID | 5846 |
Feature activation | +6.03e-02 |
Pos logit contributions | |
Jinn | +0.031 |
pai | +0.031 |
↑ | +0.031 |
�� | +0.030 |
� | +0.029 |
Neg logit contributions | |
abol | -0.029 |
theless | -0.028 |
utonium | -0.027 |
akespe | -0.027 |
andre | -0.026 |
Token | year |
Token ID | 614 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
Jinn | +0.057 |
↑ | +0.057 |
pai | +0.057 |
�� | +0.054 |
� | +0.053 |
Neg logit contributions | |
abol | -0.067 |
theless | -0.065 |
utonium | -0.063 |
akespe | -0.061 |
andre | -0.060 |
Token | old |
Token ID | 1468 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
abol | +0.244 |
theless | +0.235 |
utonium | +0.228 |
akespe | +0.223 |
andre | +0.217 |
Neg logit contributions | |
Jinn | -0.205 |
↑ | -0.204 |
pai | -0.202 |
�� | -0.191 |
� | -0.189 |
Token | age |
Token ID | 2479 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
Jinn | +0.257 |
↑ | +0.255 |
pai | +0.253 |
�� | +0.238 |
� | +0.236 |
Neg logit contributions | |
abol | -0.333 |
theless | -0.321 |
utonium | -0.312 |
akespe | -0.306 |
andre | -0.297 |
Token | bracket |
Token ID | 19096 |
Feature activation | +6.64e-01 |
Pos logit contributions | |
Jinn | +0.298 |
↑ | +0.297 |
pai | +0.293 |
�� | +0.269 |
� | +0.266 |
Neg logit contributions | |
abol | -0.671 |
theless | -0.652 |
utonium | -0.638 |
akespe | -0.627 |
andre | -0.613 |
Token | . |
Token ID | 13 |
Feature activation | +2.61e-02 |
Pos logit contributions | |
Jinn | +0.493 |
↑ | +0.491 |
pai | +0.485 |
�� | +0.451 |
� | +0.446 |
Neg logit contributions | |
abol | -0.878 |
theless | -0.851 |
utonium | -0.831 |
akespe | -0.816 |
andre | -0.796 |
Token |
|
Token ID | 198 |
Feature activation | +3.94e-03 |
Pos logit contributions | |
Jinn | +0.022 |
↑ | +0.022 |
pai | +0.021 |
�� | +0.020 |
� | +0.020 |
Neg logit contributions | |
abol | -0.032 |
theless | -0.031 |
utonium | -0.031 |
akespe | -0.030 |
andre | -0.029 |
Token |
|
Token ID | 198 |
Feature activation | +5.53e-03 |
Pos logit contributions | |
Jinn | +0.003 |
↑ | +0.003 |
pai | +0.003 |
�� | +0.003 |
� | +0.003 |
Neg logit contributions | |
abol | -0.005 |
theless | -0.005 |
utonium | -0.005 |
akespe | -0.005 |
andre | -0.004 |
Token | The |
Token ID | 464 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
↑ | +0.006 |
Jinn | +0.006 |
pai | +0.006 |
�� | +0.006 |
� | +0.006 |
Neg logit contributions | |
abol | -0.006 |
theless | -0.005 |
utonium | -0.005 |
akespe | -0.005 |
andre | -0.005 |
Token | cities |
Token ID | 4736 |
Feature activation | -5.16e-02 |
Pos logit contributions | |
Jinn | +0.105 |
↑ | +0.104 |
pai | +0.102 |
�� | +0.096 |
� | +0.096 |
Neg logit contributions | |
abol | -0.148 |
theless | -0.143 |
utonium | -0.140 |
akespe | -0.137 |
andre | -0.133 |
Token | GL |
Token ID | 10188 |
Feature activation | +3.31e-03 |
Pos logit contributions | |
Jinn | +0.001 |
↑ | +0.001 |
pai | +0.001 |
�� | +0.000 |
� | +0.000 |
Neg logit contributions | |
abol | -0.001 |
theless | -0.001 |
utonium | -0.001 |
akespe | -0.001 |
andre | -0.001 |
Token | a |
Token ID | 64 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
Jinn | +0.004 |
↑ | +0.004 |
pai | +0.003 |
�� | +0.003 |
� | +0.003 |
Neg logit contributions | |
abol | -0.003 |
theless | -0.003 |
utonium | -0.003 |
akespe | -0.003 |
andre | -0.003 |
Token | DOS |
Token ID | 35178 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
Jinn | +0.156 |
↑ | +0.156 |
pai | +0.155 |
�� | +0.148 |
� | +0.148 |
Neg logit contributions | |
abol | -0.092 |
theless | -0.087 |
utonium | -0.083 |
akespe | -0.080 |
andre | -0.076 |
Token | ' |
Token ID | 6 |
Feature activation | +8.94e-02 |
Pos logit contributions | |
abol | +0.135 |
theless | +0.131 |
utonium | +0.128 |
akespe | +0.125 |
andre | +0.122 |
Neg logit contributions | |
Jinn | -0.080 |
↑ | -0.080 |
pai | -0.079 |
�� | -0.073 |
� | -0.073 |
Token | escape |
Token ID | 6654 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
Jinn | +0.077 |
↑ | +0.077 |
pai | +0.076 |
�� | +0.071 |
� | +0.071 |
Neg logit contributions | |
abol | -0.107 |
theless | -0.104 |
utonium | -0.101 |
akespe | -0.099 |
andre | -0.096 |
Token | advice |
Token ID | 5608 |
Feature activation | +6.68e-01 |
Pos logit contributions | |
Jinn | +0.164 |
↑ | +0.163 |
pai | +0.161 |
�� | +0.149 |
� | +0.148 |
Neg logit contributions | |
abol | -0.306 |
theless | -0.296 |
utonium | -0.290 |
akespe | -0.284 |
andre | -0.278 |
Token | ( |
Token ID | 357 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
Jinn | +0.482 |
↑ | +0.480 |
pai | +0.473 |
�� | +0.437 |
� | +0.434 |
Neg logit contributions | |
abol | -0.899 |
theless | -0.872 |
utonium | -0.852 |
akespe | -0.836 |
andre | -0.815 |
Token | 28 |
Token ID | 2078 |
Feature activation | -3.06e-02 |
Pos logit contributions | |
↑ | +0.223 |
Jinn | +0.223 |
pai | +0.221 |
� | +0.208 |
�� | +0.208 |
Neg logit contributions | |
abol | -0.252 |
theless | -0.243 |
utonium | -0.236 |
akespe | -0.231 |
andre | -0.223 |
Token | ) |
Token ID | 8 |
Feature activation | +9.25e-02 |
Pos logit contributions | |
abol | +0.035 |
theless | +0.034 |
utonium | +0.033 |
akespe | +0.032 |
andre | +0.031 |
Neg logit contributions | |
Jinn | -0.028 |
↑ | -0.028 |
pai | -0.028 |
�� | -0.026 |
� | -0.026 |
Token |
|
Token ID | 198 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
Jinn | +0.073 |
↑ | +0.073 |
pai | +0.072 |
�� | +0.067 |
� | +0.066 |
Neg logit contributions | |
abol | -0.118 |
theless | -0.115 |
utonium | -0.112 |
akespe | -0.110 |
andre | -0.107 |
Token |
|
Token ID | 198 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
Jinn | +0.117 |
↑ | +0.116 |
pai | +0.116 |
�� | +0.109 |
� | +0.107 |
Neg logit contributions | |
abol | -0.185 |
theless | -0.178 |
utonium | -0.174 |
akespe | -0.170 |
andre | -0.167 |
Token | fried |
Token ID | 25520 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
Jinn | +0.067 |
↑ | +0.067 |
pai | +0.066 |
�� | +0.063 |
� | +0.063 |
Neg logit contributions | |
abol | -0.070 |
theless | -0.067 |
utonium | -0.065 |
akespe | -0.063 |
andre | -0.062 |
Token | - |
Token ID | 12 |
Feature activation | +7.58e-02 |
Pos logit contributions | |
Jinn | +0.127 |
↑ | +0.126 |
pai | +0.126 |
�� | +0.117 |
� | +0.116 |
Neg logit contributions | |
abol | -0.225 |
theless | -0.218 |
utonium | -0.213 |
akespe | -0.209 |
andre | -0.204 |
Token | rice |
Token ID | 20970 |
Feature activation | +7.00e-02 |
Pos logit contributions | |
Jinn | +0.076 |
↑ | +0.076 |
pai | +0.075 |
�� | +0.072 |
� | +0.071 |
Neg logit contributions | |
abol | -0.080 |
theless | -0.077 |
utonium | -0.075 |
akespe | -0.073 |
andre | -0.071 |
Token | dish |
Token ID | 9433 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
Jinn | +0.052 |
↑ | +0.052 |
pai | +0.052 |
�� | +0.048 |
� | +0.048 |
Neg logit contributions | |
abol | -0.092 |
theless | -0.089 |
utonium | -0.087 |
akespe | -0.085 |
andre | -0.083 |
Token | with |
Token ID | 351 |
Feature activation | +9.15e-02 |
Pos logit contributions | |
Jinn | +0.100 |
↑ | +0.099 |
pai | +0.098 |
�� | +0.091 |
� | +0.090 |
Neg logit contributions | |
abol | -0.181 |
theless | -0.175 |
utonium | -0.171 |
akespe | -0.168 |
andre | -0.164 |
Token | esc |
Token ID | 3671 |
Feature activation | +7.65e-01 |
Pos logit contributions | |
Jinn | +0.065 |
↑ | +0.065 |
pai | +0.064 |
�� | +0.060 |
� | +0.059 |
Neg logit contributions | |
abol | -0.123 |
theless | -0.120 |
utonium | -0.117 |
akespe | -0.115 |
andre | -0.112 |
Token | olar |
Token ID | 6192 |
Feature activation | -5.40e-03 |
Pos logit contributions | |
Jinn | +0.884 |
↑ | +0.880 |
pai | +0.875 |
�� | +0.834 |
� | +0.830 |
Neg logit contributions | |
abol | -0.694 |
theless | -0.663 |
utonium | -0.640 |
akespe | -0.622 |
andre | -0.600 |
Token | and |
Token ID | 290 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
abol | +0.007 |
theless | +0.007 |
utonium | +0.007 |
akespe | +0.007 |
andre | +0.006 |
Neg logit contributions | |
Jinn | -0.004 |
↑ | -0.004 |
pai | -0.004 |
�� | -0.004 |
� | -0.004 |
Token | Chinese |
Token ID | 3999 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
Jinn | +0.008 |
↑ | +0.008 |
pai | +0.007 |
�� | +0.007 |
� | +0.007 |
Neg logit contributions | |
abol | -0.014 |
theless | -0.014 |
utonium | -0.014 |
akespe | -0.013 |
andre | -0.013 |
Token | sausage |
Token ID | 31889 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
Jinn | +0.254 |
↑ | +0.253 |
pai | +0.250 |
�� | +0.232 |
� | +0.229 |
Neg logit contributions | |
abol | -0.475 |
theless | -0.460 |
utonium | -0.449 |
akespe | -0.441 |
andre | -0.431 |
Token | that |
Token ID | 326 |
Feature activation | +2.28e-02 |
Pos logit contributions | |
abol | +0.436 |
theless | +0.422 |
utonium | +0.412 |
akespe | +0.404 |
andre | +0.396 |
Neg logit contributions | |
Jinn | -0.248 |
↑ | -0.247 |
pai | -0.246 |
�� | -0.229 |
� | -0.226 |
Token | be |
Token ID | 307 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
Jinn | +0.028 |
↑ | +0.028 |
pai | +0.028 |
�� | +0.027 |
� | +0.026 |
Neg logit contributions | |
abol | -0.041 |
theless | -0.040 |
utonium | -0.039 |
akespe | -0.038 |
andre | -0.037 |
Token | mit |
Token ID | 10255 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
Jinn | +0.015 |
↑ | +0.015 |
pai | +0.015 |
�� | +0.014 |
� | +0.013 |
Neg logit contributions | |
abol | -0.026 |
theless | -0.025 |
utonium | -0.024 |
akespe | -0.024 |
andre | -0.024 |
Token | igated |
Token ID | 26963 |
Feature activation | -4.48e-01 |
Pos logit contributions | |
Jinn | +0.305 |
↑ | +0.304 |
pai | +0.302 |
�� | +0.279 |
� | +0.277 |
Neg logit contributions | |
abol | -0.477 |
theless | -0.465 |
utonium | -0.452 |
akespe | -0.443 |
andre | -0.431 |
Token | to |
Token ID | 284 |
Feature activation | +5.73e-02 |
Pos logit contributions | |
abol | +0.617 |
theless | +0.599 |
utonium | +0.585 |
akespe | +0.575 |
andre | +0.562 |
Neg logit contributions | |
Jinn | -0.309 |
↑ | -0.307 |
pai | -0.303 |
�� | -0.281 |
� | -0.277 |
Token | an |
Token ID | 281 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
Jinn | +0.042 |
↑ | +0.042 |
pai | +0.041 |
�� | +0.038 |
� | +0.038 |
Neg logit contributions | |
abol | -0.077 |
theless | -0.074 |
utonium | -0.073 |
akespe | -0.071 |
andre | -0.070 |
Token | extent |
Token ID | 6287 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
Jinn | +0.117 |
↑ | +0.117 |
pai | +0.115 |
�� | +0.108 |
� | +0.107 |
Neg logit contributions | |
abol | -0.184 |
theless | -0.179 |
utonium | -0.176 |
akespe | -0.171 |
andre | -0.167 |
Token | , |
Token ID | 11 |
Feature activation | +9.17e-02 |
Pos logit contributions | |
Jinn | +0.171 |
↑ | +0.170 |
pai | +0.168 |
�� | +0.156 |
� | +0.154 |
Neg logit contributions | |
abol | -0.337 |
theless | -0.326 |
utonium | -0.319 |
akespe | -0.313 |
andre | -0.306 |
Token | especially |
Token ID | 2592 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
Jinn | +0.062 |
↑ | +0.062 |
pai | +0.061 |
�� | +0.057 |
� | +0.056 |
Neg logit contributions | |
abol | -0.127 |
theless | -0.123 |
utonium | -0.120 |
akespe | -0.118 |
andre | -0.116 |
Token | if |
Token ID | 611 |
Feature activation | +1.74e-02 |
Pos logit contributions | |
Jinn | +0.131 |
↑ | +0.129 |
pai | +0.129 |
�� | +0.120 |
� | +0.118 |
Neg logit contributions | |
abol | -0.268 |
theless | -0.260 |
utonium | -0.253 |
akespe | -0.249 |
andre | -0.244 |
Token | you |
Token ID | 345 |
Feature activation | +8.15e-02 |
Pos logit contributions | |
Jinn | +0.014 |
↑ | +0.014 |
pai | +0.014 |
�� | +0.013 |
� | +0.013 |
Neg logit contributions | |
abol | -0.021 |
theless | -0.021 |
utonium | -0.020 |
akespe | -0.020 |
andre | -0.019 |
Token | take |
Token ID | 1011 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
Jinn | +0.068 |
↑ | +0.067 |
pai | +0.067 |
�� | +0.064 |
� | +0.062 |
Neg logit contributions | |
abol | -0.101 |
theless | -0.097 |
utonium | -0.094 |
akespe | -0.091 |
andre | -0.090 |
Token | ." |
Token ID | 526 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
abol | +0.108 |
theless | +0.104 |
utonium | +0.102 |
akespe | +0.100 |
andre | +0.098 |
Neg logit contributions | |
Jinn | -0.048 |
↑ | -0.048 |
pai | -0.047 |
�� | -0.044 |
� | -0.043 |
Token |
|
Token ID | 198 |
Feature activation | +5.91e-02 |
Pos logit contributions | |
Jinn | +0.306 |
↑ | +0.304 |
pai | +0.301 |
�� | +0.279 |
� | +0.278 |
Neg logit contributions | |
abol | -0.493 |
theless | -0.477 |
utonium | -0.464 |
akespe | -0.457 |
andre | -0.443 |
Token |
|
Token ID | 198 |
Feature activation | +6.65e-02 |
Pos logit contributions | |
Jinn | +0.048 |
↑ | +0.047 |
pai | +0.047 |
�� | +0.044 |
� | +0.043 |
Neg logit contributions | |
abol | -0.074 |
theless | -0.072 |
utonium | -0.070 |
akespe | -0.068 |
andre | -0.067 |
Token | Others |
Token ID | 25599 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
Jinn | +0.071 |
↑ | +0.071 |
pai | +0.070 |
� | +0.067 |
�� | +0.066 |
Neg logit contributions | |
abol | -0.066 |
theless | -0.064 |
utonium | -0.062 |
akespe | -0.061 |
andre | -0.058 |
Token | sit |
Token ID | 1650 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
abol | +0.286 |
theless | +0.276 |
utonium | +0.268 |
akespe | +0.263 |
andre | +0.257 |
Neg logit contributions | |
Jinn | -0.196 |
↑ | -0.195 |
pai | -0.194 |
�� | -0.182 |
� | -0.180 |
Token | in |
Token ID | 287 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
Jinn | +0.145 |
↑ | +0.144 |
pai | +0.143 |
� | +0.132 |
�� | +0.131 |
Neg logit contributions | |
abol | -0.254 |
theless | -0.247 |
utonium | -0.241 |
akespe | -0.236 |
andre | -0.230 |
Token | a |
Token ID | 257 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
Jinn | +0.172 |
↑ | +0.171 |
pai | +0.170 |
�� | +0.159 |
� | +0.158 |
Neg logit contributions | |
abol | -0.245 |
theless | -0.237 |
utonium | -0.231 |
akespe | -0.226 |
andre | -0.221 |
Token | circle |
Token ID | 9197 |
Feature activation | -4.90e-02 |
Pos logit contributions | |
Jinn | +0.135 |
↑ | +0.135 |
pai | +0.134 |
�� | +0.125 |
� | +0.124 |
Neg logit contributions | |
abol | -0.187 |
theless | -0.180 |
utonium | -0.176 |
akespe | -0.172 |
andre | -0.168 |
Token | on |
Token ID | 319 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
abol | +0.065 |
theless | +0.063 |
utonium | +0.061 |
akespe | +0.060 |
andre | +0.059 |
Neg logit contributions | |
Jinn | -0.037 |
↑ | -0.036 |
pai | -0.036 |
�� | -0.033 |
� | -0.033 |
Token | a |
Token ID | 257 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
Jinn | +0.130 |
↑ | +0.128 |
pai | +0.127 |
�� | +0.118 |
� | +0.117 |
Neg logit contributions | |
abol | -0.227 |
theless | -0.220 |
utonium | -0.214 |
akespe | -0.210 |
andre | -0.206 |
Token | grass |
Token ID | 8701 |
Feature activation | -6.36e-02 |
Pos logit contributions | |
Jinn | +0.134 |
↑ | +0.133 |
pai | +0.132 |
�� | +0.124 |
� | +0.123 |
Neg logit contributions | |
abol | -0.182 |
theless | -0.176 |
utonium | -0.171 |
akespe | -0.168 |
andre | -0.163 |
Token |
|
Token ID | 198 |
Feature activation | +1.78e-02 |
Pos logit contributions | |
Jinn | +0.025 |
↑ | +0.025 |
pai | +0.025 |
�� | +0.023 |
� | +0.023 |
Neg logit contributions | |
abol | -0.036 |
theless | -0.035 |
utonium | -0.034 |
akespe | -0.034 |
andre | -0.033 |
Token |
|
Token ID | 198 |
Feature activation | +4.14e-02 |
Pos logit contributions | |
Jinn | +0.014 |
↑ | +0.014 |
pai | +0.014 |
�� | +0.013 |
� | +0.013 |
Neg logit contributions | |
abol | -0.022 |
theless | -0.022 |
utonium | -0.021 |
akespe | -0.021 |
andre | -0.020 |
Token | Click |
Token ID | 8164 |
Feature activation | +3.44e-01 |
Pos logit contributions | |
↑ | +0.046 |
Jinn | +0.046 |
pai | +0.046 |
� | +0.043 |
�� | +0.043 |
Neg logit contributions | |
abol | -0.039 |
theless | -0.038 |
utonium | -0.037 |
akespe | -0.036 |
andre | -0.034 |
Token | here |
Token ID | 994 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
Jinn | +0.211 |
↑ | +0.209 |
pai | +0.207 |
�� | +0.189 |
� | +0.186 |
Neg logit contributions | |
abol | -0.501 |
theless | -0.486 |
utonium | -0.476 |
akespe | -0.468 |
andre | -0.458 |
Token | to |
Token ID | 284 |
Feature activation | +8.60e-03 |
Pos logit contributions | |
Jinn | +0.203 |
↑ | +0.202 |
pai | +0.200 |
�� | +0.185 |
� | +0.183 |
Neg logit contributions | |
abol | -0.373 |
theless | -0.362 |
utonium | -0.354 |
akespe | -0.347 |
andre | -0.339 |
Token | subscribe |
Token ID | 12383 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
Jinn | +0.007 |
↑ | +0.007 |
pai | +0.007 |
�� | +0.007 |
� | +0.007 |
Neg logit contributions | |
abol | -0.011 |
theless | -0.010 |
utonium | -0.010 |
akespe | -0.010 |
andre | -0.009 |
Token | via |
Token ID | 2884 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
↑ | +0.140 |
Jinn | +0.140 |
pai | +0.138 |
�� | +0.127 |
� | +0.126 |
Neg logit contributions | |
abol | -0.263 |
theless | -0.256 |
utonium | -0.250 |
akespe | -0.245 |
andre | -0.239 |
Token | iTunes |
Token ID | 4830 |
Feature activation | +8.50e-02 |
Pos logit contributions | |
Jinn | +0.170 |
↑ | +0.170 |
pai | +0.167 |
�� | +0.157 |
� | +0.157 |
Neg logit contributions | |
abol | -0.234 |
theless | -0.226 |
utonium | -0.220 |
akespe | -0.216 |
andre | -0.210 |
Token |
|
Token ID | 198 |
Feature activation | -5.11e-03 |
Pos logit contributions | |
↑ | +0.063 |
Jinn | +0.063 |
pai | +0.062 |
�� | +0.058 |
� | +0.058 |
Neg logit contributions | |
abol | -0.112 |
theless | -0.109 |
utonium | -0.106 |
akespe | -0.104 |
andre | -0.102 |
Token |
|
Token ID | 198 |
Feature activation | +1.94e-02 |
Pos logit contributions | |
abol | +0.006 |
theless | +0.006 |
utonium | +0.006 |
akespe | +0.006 |
andre | +0.006 |
Neg logit contributions | |
Jinn | -0.004 |
↑ | -0.004 |
pai | -0.004 |
�� | -0.004 |
� | -0.004 |
Token | Click |
Token ID | 8164 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
↑ | +0.021 |
Jinn | +0.021 |
pai | +0.021 |
� | +0.020 |
�� | +0.020 |
Neg logit contributions | |
abol | -0.019 |
theless | -0.018 |
utonium | -0.018 |
akespe | -0.017 |
andre | -0.016 |
Token | d |
Token ID | 67 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
Jinn | +0.046 |
↑ | +0.046 |
pai | +0.046 |
�� | +0.044 |
� | +0.043 |
Neg logit contributions | |
abol | -0.042 |
theless | -0.040 |
utonium | -0.039 |
akespe | -0.038 |
andre | -0.036 |
Token | aughters |
Token ID | 13441 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
↑ | +0.241 |
Jinn | +0.240 |
pai | +0.240 |
ki | +0.223 |
�� | +0.222 |
Neg logit contributions | |
abol | -0.271 |
theless | -0.265 |
utonium | -0.255 |
akespe | -0.248 |
andre | -0.242 |
Token | died |
Token ID | 3724 |
Feature activation | +6.32e-02 |
Pos logit contributions | |
Jinn | +0.252 |
↑ | +0.250 |
pai | +0.248 |
�� | +0.231 |
� | +0.229 |
Neg logit contributions | |
abol | -0.432 |
theless | -0.418 |
utonium | -0.409 |
akespe | -0.400 |
andre | -0.392 |
Token | at |
Token ID | 379 |
Feature activation | -6.60e-02 |
Pos logit contributions | |
Jinn | +0.043 |
↑ | +0.043 |
pai | +0.043 |
�� | +0.039 |
� | +0.039 |
Neg logit contributions | |
abol | -0.087 |
theless | -0.085 |
utonium | -0.083 |
akespe | -0.081 |
andre | -0.079 |
Token | the |
Token ID | 262 |
Feature activation | +7.86e-02 |
Pos logit contributions | |
abol | +0.082 |
theless | +0.080 |
utonium | +0.078 |
akespe | +0.076 |
andre | +0.074 |
Neg logit contributions | |
Jinn | -0.054 |
↑ | -0.054 |
pai | -0.053 |
�� | -0.050 |
� | -0.049 |
Token | ages |
Token ID | 9337 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
Jinn | +0.077 |
↑ | +0.076 |
pai | +0.075 |
�� | +0.071 |
� | +0.071 |
Neg logit contributions | |
abol | -0.086 |
theless | -0.083 |
utonium | -0.080 |
akespe | -0.078 |
andre | -0.076 |
Token | of |
Token ID | 286 |
Feature activation | +1.96e-02 |
Pos logit contributions | |
Jinn | +0.201 |
↑ | +0.200 |
pai | +0.197 |
�� | +0.184 |
� | +0.182 |
Neg logit contributions | |
abol | -0.322 |
theless | -0.312 |
utonium | -0.304 |
akespe | -0.299 |
andre | -0.291 |
Token | 12 |
Token ID | 1105 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
Jinn | +0.019 |
↑ | +0.019 |
pai | +0.019 |
�� | +0.018 |
� | +0.018 |
Neg logit contributions | |
abol | -0.021 |
theless | -0.021 |
utonium | -0.020 |
akespe | -0.020 |
andre | -0.019 |
Token | and |
Token ID | 290 |
Feature activation | +6.21e-02 |
Pos logit contributions | |
Jinn | +0.105 |
↑ | +0.104 |
pai | +0.104 |
�� | +0.096 |
� | +0.095 |
Neg logit contributions | |
abol | -0.193 |
theless | -0.187 |
utonium | -0.183 |
akespe | -0.179 |
andre | -0.175 |
Token | 18 |
Token ID | 1248 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
Jinn | +0.062 |
↑ | +0.061 |
pai | +0.061 |
�� | +0.058 |
� | +0.057 |
Neg logit contributions | |
abol | -0.067 |
theless | -0.064 |
utonium | -0.062 |
akespe | -0.061 |
andre | -0.059 |
Token | , |
Token ID | 11 |
Feature activation | +8.30e-02 |
Pos logit contributions | |
Jinn | +0.126 |
↑ | +0.125 |
pai | +0.124 |
�� | +0.115 |
� | +0.113 |
Neg logit contributions | |
abol | -0.245 |
theless | -0.238 |
utonium | -0.232 |
akespe | -0.228 |
andre | -0.223 |
Token | Enter |
Token ID | 17469 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
↑ | +0.171 |
Jinn | +0.171 |
pai | +0.170 |
� | +0.161 |
�� | +0.161 |
Neg logit contributions | |
abol | -0.150 |
theless | -0.145 |
utonium | -0.141 |
akespe | -0.137 |
andre | -0.131 |
Token | 4 |
Token ID | 604 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
Jinn | +0.285 |
↑ | +0.284 |
pai | +0.281 |
�� | +0.260 |
� | +0.258 |
Neg logit contributions | |
abol | -0.505 |
theless | -0.489 |
utonium | -0.478 |
akespe | -0.470 |
andre | -0.458 |
Token | different |
Token ID | 1180 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
Jinn | +0.102 |
↑ | +0.102 |
pai | +0.101 |
�� | +0.094 |
� | +0.094 |
Neg logit contributions | |
abol | -0.147 |
theless | -0.142 |
utonium | -0.138 |
akespe | -0.136 |
andre | -0.132 |
Token | portals |
Token ID | 42604 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
Jinn | +0.146 |
↑ | +0.145 |
pai | +0.144 |
�� | +0.135 |
� | +0.134 |
Neg logit contributions | |
abol | -0.184 |
theless | -0.177 |
utonium | -0.173 |
akespe | -0.169 |
andre | -0.164 |
Token | without |
Token ID | 1231 |
Feature activation | +9.31e-02 |
Pos logit contributions | |
Jinn | +0.145 |
↑ | +0.144 |
pai | +0.141 |
�� | +0.129 |
� | +0.128 |
Neg logit contributions | |
abol | -0.320 |
theless | -0.310 |
utonium | -0.304 |
akespe | -0.299 |
andre | -0.292 |
Token | touching |
Token ID | 15241 |
Feature activation | +4.15e-01 |
Pos logit contributions | |
Jinn | +0.064 |
↑ | +0.064 |
pai | +0.063 |
�� | +0.058 |
� | +0.058 |
Neg logit contributions | |
abol | -0.128 |
theless | -0.124 |
utonium | -0.122 |
akespe | -0.120 |
andre | -0.117 |
Token | the |
Token ID | 262 |
Feature activation | +2.56e-02 |
Pos logit contributions | |
Jinn | +0.281 |
↑ | +0.279 |
pai | +0.275 |
�� | +0.252 |
� | +0.251 |
Neg logit contributions | |
abol | -0.577 |
theless | -0.560 |
utonium | -0.548 |
akespe | -0.539 |
andre | -0.526 |
Token | ground |
Token ID | 2323 |
Feature activation | -7.70e-03 |
Pos logit contributions | |
Jinn | +0.020 |
↑ | +0.020 |
pai | +0.019 |
�� | +0.018 |
� | +0.018 |
Neg logit contributions | |
abol | -0.033 |
theless | -0.032 |
utonium | -0.031 |
akespe | -0.031 |
andre | -0.030 |
Token | in |
Token ID | 287 |
Feature activation | +4.99e-02 |
Pos logit contributions | |
abol | +0.011 |
theless | +0.010 |
utonium | +0.010 |
akespe | +0.010 |
andre | +0.010 |
Neg logit contributions | |
Jinn | -0.005 |
↑ | -0.005 |
pai | -0.005 |
�� | -0.005 |
� | -0.005 |
Token | co |
Token ID | 763 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
Jinn | +0.042 |
↑ | +0.042 |
pai | +0.042 |
�� | +0.039 |
� | +0.039 |
Neg logit contributions | |
abol | -0.061 |
theless | -0.059 |
utonium | -0.057 |
akespe | -0.056 |
andre | -0.055 |
Token | - |
Token ID | 12 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
abol | +0.153 |
theless | +0.146 |
utonium | +0.143 |
akespe | +0.140 |
andre | +0.137 |
Neg logit contributions | |
Jinn | -0.109 |
↑ | -0.107 |
pai | -0.107 |
�� | -0.101 |
� | -0.100 |
Token | bus |
Token ID | 1323 |
Feature activation | +2.92e-02 |
Pos logit contributions | |
Jinn | +0.039 |
↑ | +0.038 |
pai | +0.038 |
�� | +0.036 |
� | +0.035 |
Neg logit contributions | |
abol | -0.055 |
theless | -0.054 |
utonium | -0.052 |
akespe | -0.051 |
andre | -0.050 |
Token | pass |
Token ID | 1208 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
Jinn | +0.026 |
↑ | +0.026 |
pai | +0.026 |
�� | +0.024 |
� | +0.024 |
Neg logit contributions | |
abol | -0.034 |
theless | -0.033 |
utonium | -0.032 |
akespe | -0.032 |
andre | -0.031 |
Token | with |
Token ID | 351 |
Feature activation | +5.09e-02 |
Pos logit contributions | |
Jinn | +0.089 |
↑ | +0.089 |
pai | +0.088 |
�� | +0.082 |
� | +0.081 |
Neg logit contributions | |
abol | -0.160 |
theless | -0.155 |
utonium | -0.151 |
akespe | -0.149 |
andre | -0.145 |
Token | my |
Token ID | 616 |
Feature activation | +6.32e-02 |
Pos logit contributions | |
Jinn | +0.039 |
↑ | +0.039 |
pai | +0.038 |
�� | +0.036 |
� | +0.036 |
Neg logit contributions | |
abol | -0.066 |
theless | -0.064 |
utonium | -0.062 |
akespe | -0.061 |
andre | -0.060 |
Token | picture |
Token ID | 4286 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
Jinn | +0.051 |
↑ | +0.051 |
pai | +0.051 |
�� | +0.047 |
� | +0.047 |
Neg logit contributions | |
abol | -0.079 |
theless | -0.077 |
utonium | -0.075 |
akespe | -0.073 |
andre | -0.071 |
Token | on |
Token ID | 319 |
Feature activation | +5.12e-02 |
Pos logit contributions | |
↑ | +0.252 |
Jinn | +0.252 |
pai | +0.248 |
�� | +0.229 |
� | +0.228 |
Neg logit contributions | |
abol | -0.462 |
theless | -0.450 |
utonium | -0.439 |
akespe | -0.430 |
andre | -0.419 |
Token | it |
Token ID | 340 |
Feature activation | -5.47e-02 |
Pos logit contributions | |
Jinn | +0.037 |
↑ | +0.036 |
pai | +0.036 |
�� | +0.033 |
� | +0.033 |
Neg logit contributions | |
abol | -0.069 |
theless | -0.067 |
utonium | -0.066 |
akespe | -0.064 |
andre | -0.063 |
Token | , |
Token ID | 11 |
Feature activation | -7.40e-03 |
Pos logit contributions | |
abol | +0.073 |
theless | +0.070 |
utonium | +0.069 |
akespe | +0.067 |
andre | +0.066 |
Neg logit contributions | |
Jinn | -0.040 |
↑ | -0.040 |
pai | -0.040 |
�� | -0.037 |
� | -0.037 |
Token | � |
Token ID | 447 |
Feature activation | -5.81e-02 |
Pos logit contributions | |
abol | +0.010 |
theless | +0.009 |
utonium | +0.009 |
akespe | +0.009 |
andre | +0.009 |
Neg logit contributions | |
Jinn | -0.006 |
↑ | -0.006 |
pai | -0.006 |
�� | -0.005 |
� | -0.005 |
Token | � |
Token ID | 251 |
Feature activation | +3.96e-03 |
Pos logit contributions | |
abol | +0.070 |
theless | +0.067 |
utonium | +0.065 |
akespe | +0.064 |
andre | +0.062 |
Neg logit contributions | |
Jinn | -0.051 |
↑ | -0.050 |
pai | -0.050 |
�� | -0.047 |
� | -0.046 |
Token | Warren |
Token ID | 11328 |
Feature activation | -6.77e-02 |
Pos logit contributions | |
Jinn | +0.003 |
↑ | +0.003 |
pai | +0.003 |
�� | +0.003 |
� | +0.003 |
Neg logit contributions | |
abol | -0.005 |
theless | -0.005 |
utonium | -0.004 |
akespe | -0.004 |
andre | -0.004 |
Token | of |
Token ID | 286 |
Feature activation | +6.18e-02 |
Pos logit contributions | |
Jinn | +0.083 |
↑ | +0.082 |
pai | +0.082 |
�� | +0.076 |
� | +0.076 |
Neg logit contributions | |
abol | -0.141 |
theless | -0.136 |
utonium | -0.133 |
akespe | -0.130 |
andre | -0.127 |
Token | an |
Token ID | 281 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
Jinn | +0.046 |
↑ | +0.045 |
pai | +0.045 |
�� | +0.042 |
� | +0.041 |
Neg logit contributions | |
abol | -0.082 |
theless | -0.080 |
utonium | -0.078 |
akespe | -0.076 |
andre | -0.074 |
Token | original |
Token ID | 2656 |
Feature activation | +3.05e-02 |
Pos logit contributions | |
Jinn | +0.068 |
↑ | +0.068 |
pai | +0.067 |
�� | +0.062 |
� | +0.061 |
Neg logit contributions | |
abol | -0.141 |
theless | -0.137 |
utonium | -0.134 |
akespe | -0.131 |
andre | -0.128 |
Token | image |
Token ID | 2939 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
Jinn | +0.020 |
↑ | +0.020 |
pai | +0.020 |
�� | +0.018 |
� | +0.018 |
Neg logit contributions | |
abol | -0.043 |
theless | -0.041 |
utonium | -0.041 |
akespe | -0.040 |
andre | -0.039 |
Token | below |
Token ID | 2174 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
Jinn | +0.169 |
↑ | +0.167 |
pai | +0.166 |
�� | +0.153 |
� | +0.152 |
Neg logit contributions | |
abol | -0.335 |
theless | -0.325 |
utonium | -0.318 |
akespe | -0.312 |
andre | -0.305 |
Token | : |
Token ID | 25 |
Feature activation | -5.23e-02 |
Pos logit contributions | |
Jinn | +0.193 |
↑ | +0.192 |
pai | +0.190 |
�� | +0.176 |
� | +0.174 |
Neg logit contributions | |
abol | -0.371 |
theless | -0.360 |
utonium | -0.352 |
akespe | -0.346 |
andre | -0.338 |
Token |
|
Token ID | 198 |
Feature activation | -3.95e-02 |
Pos logit contributions | |
abol | +0.066 |
theless | +0.064 |
utonium | +0.062 |
akespe | +0.061 |
andre | +0.060 |
Neg logit contributions | |
Jinn | -0.042 |
↑ | -0.042 |
pai | -0.041 |
�� | -0.039 |
� | -0.038 |
Token |
|
Token ID | 198 |
Feature activation | -4.30e-02 |
Pos logit contributions | |
abol | +0.050 |
theless | +0.048 |
utonium | +0.047 |
akespe | +0.046 |
andre | +0.045 |
Neg logit contributions | |
Jinn | -0.032 |
↑ | -0.031 |
pai | -0.031 |
�� | -0.030 |
� | -0.029 |
Token | Ga |
Token ID | 35389 |
Feature activation | +8.85e-02 |
Pos logit contributions | |
abol | +0.042 |
theless | +0.041 |
utonium | +0.039 |
akespe | +0.038 |
andre | +0.037 |
Neg logit contributions | |
↑ | -0.046 |
Jinn | -0.046 |
pai | -0.046 |
�� | -0.044 |
� | -0.044 |
Token | ussian |
Token ID | 31562 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
Jinn | +0.106 |
↑ | +0.106 |
pai | +0.105 |
�� | +0.100 |
� | +0.100 |
Neg logit contributions | |
abol | -0.077 |
theless | -0.073 |
utonium | -0.071 |
akespe | -0.068 |
andre | -0.066 |
Token | bl |
Token ID | 698 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
abol | +0.397 |
theless | +0.382 |
utonium | +0.372 |
akespe | +0.364 |
andre | +0.355 |
Neg logit contributions | |
Jinn | -0.299 |
↑ | -0.297 |
pai | -0.296 |
�� | -0.278 |
� | -0.275 |
Token | . |
Token ID | 13 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
abol | +0.041 |
theless | +0.040 |
utonium | +0.039 |
akespe | +0.038 |
andre | +0.037 |
Neg logit contributions | |
Jinn | -0.023 |
↑ | -0.023 |
pai | -0.023 |
�� | -0.021 |
� | -0.021 |
Token | Hide |
Token ID | 10415 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
abol | +0.161 |
theless | +0.156 |
utonium | +0.153 |
akespe | +0.149 |
andre | +0.146 |
Neg logit contributions | |
Jinn | -0.086 |
↑ | -0.085 |
pai | -0.084 |
�� | -0.078 |
� | -0.077 |
Token | Caption |
Token ID | 11260 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
Jinn | +0.130 |
pai | +0.129 |
↑ | +0.129 |
�� | +0.118 |
� | +0.115 |
Neg logit contributions | |
abol | -0.335 |
theless | -0.323 |
utonium | -0.318 |
akespe | -0.312 |
andre | -0.307 |
Token | 15 |
Token ID | 1315 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
abol | +0.366 |
theless | +0.347 |
utonium | +0.338 |
akespe | +0.327 |
andre | +0.326 |
Neg logit contributions | |
Jinn | -0.330 |
pai | -0.326 |
↑ | -0.325 |
�� | -0.313 |
� | -0.304 |
Token | of |
Token ID | 286 |
Feature activation | -5.99e-03 |
Pos logit contributions | |
abol | +0.152 |
theless | +0.146 |
utonium | +0.143 |
akespe | +0.140 |
andre | +0.137 |
Neg logit contributions | |
Jinn | -0.101 |
↑ | -0.100 |
pai | -0.099 |
�� | -0.094 |
� | -0.092 |
Token | 15 |
Token ID | 1315 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
abol | +0.007 |
theless | +0.006 |
utonium | +0.006 |
akespe | +0.006 |
andre | +0.006 |
Neg logit contributions | |
Jinn | -0.006 |
pai | -0.006 |
↑ | -0.006 |
�� | -0.005 |
� | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
abol | +0.144 |
theless | +0.138 |
utonium | +0.136 |
akespe | +0.132 |
andre | +0.131 |
Neg logit contributions | |
Jinn | -0.095 |
pai | -0.093 |
↑ | -0.093 |
�� | -0.088 |
� | -0.087 |
Token |
|
Token ID | 198 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
Jinn | +0.014 |
↑ | +0.014 |
pai | +0.014 |
�� | +0.013 |
� | +0.013 |
Neg logit contributions | |
abol | -0.021 |
theless | -0.020 |
utonium | -0.020 |
akespe | -0.019 |
andre | -0.019 |
Token | Earlier |
Token ID | 13689 |
Feature activation | +3.97e-02 |
Pos logit contributions | |
Jinn | +0.013 |
↑ | +0.013 |
pai | +0.013 |
�� | +0.013 |
� | +0.012 |
Neg logit contributions | |
abol | -0.012 |
theless | -0.012 |
utonium | -0.012 |
akespe | -0.011 |
andre | -0.011 |
Token | Thursday |
Token ID | 3635 |
Feature activation | -3.50e-02 |
Pos logit contributions | |
Jinn | +0.030 |
↑ | +0.030 |
pai | +0.029 |
�� | +0.027 |
� | +0.027 |
Neg logit contributions | |
abol | -0.052 |
theless | -0.050 |
utonium | -0.049 |
akespe | -0.048 |
andre | -0.047 |
Token | , |
Token ID | 11 |
Feature activation | +7.75e-02 |
Pos logit contributions | |
abol | +0.046 |
theless | +0.044 |
utonium | +0.043 |
akespe | +0.042 |
andre | +0.041 |
Neg logit contributions | |
Jinn | -0.027 |
↑ | -0.027 |
pai | -0.026 |
�� | -0.025 |
� | -0.024 |
Token | going |
Token ID | 1016 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
Jinn | +0.203 |
↑ | +0.201 |
pai | +0.199 |
�� | +0.179 |
� | +0.178 |
Neg logit contributions | |
abol | -0.509 |
theless | -0.495 |
utonium | -0.485 |
akespe | -0.475 |
andre | -0.466 |
Token | on |
Token ID | 319 |
Feature activation | +4.23e-02 |
Pos logit contributions | |
Jinn | +0.093 |
↑ | +0.092 |
pai | +0.091 |
�� | +0.084 |
� | +0.084 |
Neg logit contributions | |
abol | -0.167 |
theless | -0.162 |
utonium | -0.159 |
akespe | -0.155 |
andre | -0.152 |
Token | , |
Token ID | 11 |
Feature activation | +3.34e-03 |
Pos logit contributions | |
Jinn | +0.031 |
↑ | +0.031 |
pai | +0.030 |
�� | +0.028 |
� | +0.028 |
Neg logit contributions | |
abol | -0.057 |
theless | -0.055 |
utonium | -0.054 |
akespe | -0.052 |
andre | -0.051 |
Token | but |
Token ID | 475 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
Jinn | +0.002 |
↑ | +0.002 |
pai | +0.002 |
�� | +0.002 |
� | +0.002 |
Neg logit contributions | |
abol | -0.004 |
theless | -0.004 |
utonium | -0.004 |
akespe | -0.004 |
andre | -0.004 |
Token | who |
Token ID | 508 |
Feature activation | +1.86e-02 |
Pos logit contributions | |
abol | +0.169 |
theless | +0.164 |
utonium | +0.160 |
akespe | +0.157 |
andre | +0.153 |
Neg logit contributions | |
Jinn | -0.100 |
↑ | -0.099 |
pai | -0.099 |
�� | -0.092 |
� | -0.091 |
Token | can |
Token ID | 460 |
Feature activation | +2.60e-02 |
Pos logit contributions | |
Jinn | +0.015 |
↑ | +0.015 |
pai | +0.015 |
�� | +0.014 |
� | +0.014 |
Neg logit contributions | |
abol | -0.023 |
theless | -0.022 |
utonium | -0.022 |
akespe | -0.022 |
andre | -0.021 |
Token | deny |
Token ID | 10129 |
Feature activation | +2.34e-02 |
Pos logit contributions | |
Jinn | +0.022 |
↑ | +0.022 |
pai | +0.022 |
�� | +0.021 |
� | +0.020 |
Neg logit contributions | |
abol | -0.032 |
theless | -0.030 |
utonium | -0.030 |
akespe | -0.029 |
andre | -0.028 |
Token | that |
Token ID | 326 |
Feature activation | -2.56e-03 |
Pos logit contributions | |
Jinn | +0.020 |
↑ | +0.020 |
pai | +0.020 |
�� | +0.019 |
� | +0.018 |
Neg logit contributions | |
abol | -0.028 |
theless | -0.027 |
utonium | -0.026 |
akespe | -0.026 |
andre | -0.025 |
Token | she |
Token ID | 673 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
abol | +0.003 |
theless | +0.003 |
utonium | +0.003 |
akespe | +0.003 |
andre | +0.003 |
Neg logit contributions | |
Jinn | -0.002 |
↑ | -0.002 |
pai | -0.002 |
�� | -0.002 |
� | -0.002 |
Token | loves |
Token ID | 10408 |
Feature activation | -2.68e-02 |
Pos logit contributions | |
Jinn | +0.013 |
↑ | +0.013 |
pai | +0.013 |
�� | +0.012 |
� | +0.012 |
Neg logit contributions | |
abol | -0.020 |
theless | -0.020 |
utonium | -0.019 |
akespe | -0.019 |
andre | -0.018 |
Token | Jen |
Token ID | 13364 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
abol | +0.034 |
theless | +0.033 |
utonium | +0.032 |
akespe | +0.031 |
andre | +0.031 |
Neg logit contributions | |
Jinn | -0.021 |
↑ | -0.021 |
pai | -0.021 |
�� | -0.020 |
� | -0.020 |
Token | how |
Token ID | 703 |
Feature activation | -5.33e-02 |
Pos logit contributions | |
Jinn | +0.017 |
↑ | +0.016 |
pai | +0.016 |
�� | +0.015 |
� | +0.015 |
Neg logit contributions | |
abol | -0.030 |
theless | -0.029 |
utonium | -0.029 |
akespe | -0.028 |
andre | -0.028 |
Token | they |
Token ID | 484 |
Feature activation | +8.05e-03 |
Pos logit contributions | |
abol | +0.070 |
theless | +0.068 |
utonium | +0.066 |
akespe | +0.065 |
andre | +0.064 |
Neg logit contributions | |
Jinn | -0.040 |
↑ | -0.040 |
pai | -0.039 |
�� | -0.037 |
� | -0.036 |
Token | were |
Token ID | 547 |
Feature activation | +1.51e-02 |
Pos logit contributions | |
Jinn | +0.006 |
↑ | +0.006 |
pai | +0.006 |
�� | +0.006 |
� | +0.006 |
Neg logit contributions | |
abol | -0.011 |
theless | -0.010 |
utonium | -0.010 |
akespe | -0.010 |
andre | -0.010 |
Token | really |
Token ID | 1107 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
Jinn | +0.011 |
↑ | +0.011 |
pai | +0.011 |
�� | +0.010 |
� | +0.010 |
Neg logit contributions | |
abol | -0.020 |
theless | -0.019 |
utonium | -0.019 |
akespe | -0.019 |
andre | -0.018 |
Token | tricky |
Token ID | 17198 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
Jinn | +0.210 |
↑ | +0.208 |
pai | +0.208 |
�� | +0.194 |
� | +0.192 |
Neg logit contributions | |
abol | -0.339 |
theless | -0.327 |
utonium | -0.319 |
akespe | -0.313 |
andre | -0.306 |
Token | . |
Token ID | 13 |
Feature activation | +6.74e-02 |
Pos logit contributions | |
Jinn | +0.074 |
↑ | +0.074 |
pai | +0.073 |
�� | +0.068 |
� | +0.067 |
Neg logit contributions | |
abol | -0.140 |
theless | -0.136 |
utonium | -0.133 |
akespe | -0.130 |
andre | -0.127 |
Token | If |
Token ID | 1002 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
Jinn | +0.057 |
↑ | +0.057 |
pai | +0.056 |
�� | +0.053 |
� | +0.052 |
Neg logit contributions | |
abol | -0.082 |
theless | -0.079 |
utonium | -0.077 |
akespe | -0.075 |
andre | -0.074 |
Token | you |
Token ID | 345 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
Jinn | +0.082 |
↑ | +0.082 |
pai | +0.081 |
�� | +0.075 |
� | +0.075 |
Neg logit contributions | |
abol | -0.137 |
theless | -0.132 |
utonium | -0.129 |
akespe | -0.127 |
andre | -0.123 |
Token | go |
Token ID | 467 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
Jinn | +0.009 |
↑ | +0.009 |
pai | +0.009 |
�� | +0.009 |
� | +0.008 |
Neg logit contributions | |
abol | -0.015 |
theless | -0.014 |
utonium | -0.014 |
akespe | -0.014 |
andre | -0.013 |
Token | back |
Token ID | 736 |
Feature activation | -7.67e-02 |
Pos logit contributions | |
Jinn | +0.097 |
↑ | +0.097 |
pai | +0.096 |
�� | +0.089 |
� | +0.089 |
Neg logit contributions | |
abol | -0.161 |
theless | -0.156 |
utonium | -0.153 |
akespe | -0.149 |
andre | -0.146 |
Token | and |
Token ID | 290 |
Feature activation | +3.55e-02 |
Pos logit contributions | |
abol | +0.103 |
theless | +0.100 |
utonium | +0.098 |
akespe | +0.096 |
andre | +0.094 |
Neg logit contributions | |
↑ | -0.055 |
Jinn | -0.055 |
pai | -0.054 |
�� | -0.050 |
� | -0.050 |
Token | as |
Token ID | 355 |
Feature activation | +3.44e-02 |
Pos logit contributions | |
abol | +0.085 |
theless | +0.082 |
utonium | +0.080 |
akespe | +0.079 |
andre | +0.077 |
Neg logit contributions | |
Jinn | -0.050 |
↑ | -0.049 |
pai | -0.049 |
�� | -0.046 |
� | -0.045 |
Token | " |
Token ID | 366 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
Jinn | +0.026 |
↑ | +0.026 |
pai | +0.025 |
�� | +0.023 |
� | +0.023 |
Neg logit contributions | |
abol | -0.045 |
theless | -0.044 |
utonium | -0.043 |
akespe | -0.042 |
andre | -0.041 |
Token | client |
Token ID | 16366 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
abol | +0.257 |
theless | +0.247 |
utonium | +0.240 |
akespe | +0.234 |
andre | +0.226 |
Neg logit contributions | |
Jinn | -0.250 |
↑ | -0.249 |
pai | -0.247 |
�� | -0.234 |
� | -0.233 |
Token | based |
Token ID | 1912 |
Feature activation | -2.64e-02 |
Pos logit contributions | |
abol | +0.158 |
theless | +0.153 |
utonium | +0.149 |
akespe | +0.146 |
andre | +0.142 |
Neg logit contributions | |
Jinn | -0.107 |
↑ | -0.106 |
pai | -0.105 |
�� | -0.099 |
� | -0.098 |
Token | mission |
Token ID | 4365 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
abol | +0.033 |
theless | +0.032 |
utonium | +0.031 |
akespe | +0.030 |
andre | +0.030 |
Neg logit contributions | |
Jinn | -0.022 |
pai | -0.021 |
↑ | -0.021 |
�� | -0.020 |
� | -0.020 |
Token | structures |
Token ID | 8573 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
abol | +0.176 |
theless | +0.169 |
utonium | +0.165 |
akespe | +0.161 |
andre | +0.158 |
Neg logit contributions | |
Jinn | -0.134 |
pai | -0.132 |
↑ | -0.132 |
�� | -0.125 |
� | -0.124 |
Token | with |
Token ID | 351 |
Feature activation | -2.43e-04 |
Pos logit contributions | |
abol | +0.600 |
theless | +0.579 |
utonium | +0.566 |
akespe | +0.555 |
andre | +0.545 |
Neg logit contributions | |
Jinn | -0.330 |
pai | -0.325 |
↑ | -0.324 |
�� | -0.303 |
� | -0.299 |
Token | persistent |
Token ID | 16218 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
abol | +0.000 |
theless | +0.000 |
utonium | +0.000 |
akespe | +0.000 |
andre | +0.000 |
Neg logit contributions | |
Jinn | -0.000 |
↑ | -0.000 |
pai | -0.000 |
�� | -0.000 |
� | -0.000 |
Token | elements |
Token ID | 4847 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
Jinn | +0.149 |
↑ | +0.148 |
pai | +0.147 |
�� | +0.138 |
� | +0.137 |
Neg logit contributions | |
abol | -0.209 |
theless | -0.201 |
utonium | -0.196 |
akespe | -0.192 |
andre | -0.187 |
Token | ." |
Token ID | 526 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
abol | +0.671 |
theless | +0.648 |
utonium | +0.631 |
akespe | +0.620 |
andre | +0.606 |
Neg logit contributions | |
Jinn | -0.368 |
pai | -0.364 |
↑ | -0.363 |
�� | -0.339 |
� | -0.333 |
Token | The |
Token ID | 383 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
Jinn | +0.264 |
↑ | +0.263 |
pai | +0.260 |
�� | +0.244 |
� | +0.242 |
Neg logit contributions | |
abol | -0.366 |
theless | -0.353 |
utonium | -0.345 |
akespe | -0.338 |
andre | -0.328 |
Token | m |
Token ID | 285 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
↑ | +0.058 |
Jinn | +0.058 |
pai | +0.058 |
�� | +0.055 |
� | +0.054 |
Neg logit contributions | |
abol | -0.066 |
theless | -0.064 |
utonium | -0.062 |
akespe | -0.060 |
andre | -0.058 |
Token | ics |
Token ID | 873 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
abol | +0.232 |
theless | +0.227 |
utonium | +0.219 |
akespe | +0.214 |
andre | +0.209 |
Neg logit contributions | |
Jinn | -0.164 |
↑ | -0.163 |
pai | -0.163 |
�� | -0.151 |
� | -0.150 |
Token | were |
Token ID | 547 |
Feature activation | -5.27e-02 |
Pos logit contributions | |
abol | +0.192 |
theless | +0.186 |
utonium | +0.181 |
akespe | +0.178 |
andre | +0.174 |
Neg logit contributions | |
Jinn | -0.105 |
↑ | -0.104 |
pai | -0.103 |
�� | -0.096 |
� | -0.095 |
Token | off |
Token ID | 572 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
abol | +0.069 |
theless | +0.066 |
utonium | +0.065 |
akespe | +0.063 |
andre | +0.062 |
Neg logit contributions | |
Jinn | -0.040 |
↑ | -0.040 |
pai | -0.040 |
�� | -0.037 |
� | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | -4.84e-02 |
Pos logit contributions | |
abol | +0.199 |
theless | +0.193 |
utonium | +0.189 |
akespe | +0.185 |
andre | +0.181 |
Neg logit contributions | |
Jinn | -0.107 |
↑ | -0.106 |
pai | -0.105 |
�� | -0.098 |
� | -0.096 |
Token | Cecil |
Token ID | 32234 |
Feature activation | -5.84e-01 |
Pos logit contributions | |
abol | +0.059 |
theless | +0.057 |
utonium | +0.056 |
akespe | +0.055 |
andre | +0.054 |
Neg logit contributions | |
Jinn | -0.040 |
↑ | -0.040 |
pai | -0.040 |
�� | -0.037 |
� | -0.037 |
Token | knew |
Token ID | 2993 |
Feature activation | -1.62e-04 |
Pos logit contributions | |
abol | +0.810 |
theless | +0.786 |
utonium | +0.768 |
akespe | +0.754 |
andre | +0.738 |
Neg logit contributions | |
Jinn | -0.396 |
↑ | -0.393 |
pai | -0.391 |
�� | -0.362 |
� | -0.355 |
Token | the |
Token ID | 262 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
abol | +0.000 |
theless | +0.000 |
utonium | +0.000 |
akespe | +0.000 |
andre | +0.000 |
Neg logit contributions | |
Jinn | -0.000 |
↑ | -0.000 |
pai | -0.000 |
�� | -0.000 |
� | -0.000 |
Token | studio |
Token ID | 8034 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
abol | +0.141 |
theless | +0.137 |
utonium | +0.133 |
akespe | +0.130 |
andre | +0.126 |
Neg logit contributions | |
Jinn | -0.109 |
↑ | -0.109 |
pai | -0.107 |
�� | -0.101 |
� | -0.101 |
Token | so |
Token ID | 523 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
abol | +0.278 |
theless | +0.268 |
utonium | +0.262 |
akespe | +0.256 |
andre | +0.250 |
Neg logit contributions | |
Jinn | -0.183 |
↑ | -0.182 |
pai | -0.181 |
�� | -0.170 |
� | -0.168 |
Token | well |
Token ID | 880 |
Feature activation | -3.16e-02 |
Pos logit contributions | |
abol | +0.189 |
theless | +0.183 |
utonium | +0.179 |
akespe | +0.176 |
andre | +0.172 |
Neg logit contributions | |
Jinn | -0.093 |
↑ | -0.093 |
pai | -0.091 |
�� | -0.084 |
� | -0.083 |
Token | metal |
Token ID | 6147 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
Jinn | +0.184 |
↑ | +0.183 |
pai | +0.181 |
�� | +0.170 |
� | +0.169 |
Neg logit contributions | |
abol | -0.252 |
theless | -0.243 |
utonium | -0.237 |
akespe | -0.232 |
andre | -0.226 |
Token | container |
Token ID | 9290 |
Feature activation | +1.18e-02 |
Pos logit contributions | |
Jinn | +0.158 |
↑ | +0.157 |
pai | +0.155 |
�� | +0.146 |
� | +0.145 |
Neg logit contributions | |
abol | -0.222 |
theless | -0.215 |
utonium | -0.209 |
akespe | -0.205 |
andre | -0.200 |
Token | held |
Token ID | 2714 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
Jinn | +0.010 |
↑ | +0.009 |
pai | +0.009 |
�� | +0.009 |
� | +0.009 |
Neg logit contributions | |
abol | -0.015 |
theless | -0.014 |
utonium | -0.014 |
akespe | -0.014 |
andre | -0.013 |
Token | some |
Token ID | 617 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
Jinn | +0.093 |
↑ | +0.093 |
pai | +0.092 |
�� | +0.086 |
� | +0.085 |
Neg logit contributions | |
abol | -0.157 |
theless | -0.152 |
utonium | -0.148 |
akespe | -0.145 |
andre | -0.142 |
Token | strange |
Token ID | 6283 |
Feature activation | +8.00e-02 |
Pos logit contributions | |
Jinn | +0.140 |
↑ | +0.139 |
pai | +0.138 |
�� | +0.129 |
� | +0.128 |
Neg logit contributions | |
abol | -0.212 |
theless | -0.205 |
utonium | -0.200 |
akespe | -0.196 |
andre | -0.191 |
Token | chemical |
Token ID | 5931 |
Feature activation | -4.74e-01 |
Pos logit contributions | |
Jinn | +0.070 |
↑ | +0.069 |
pai | +0.069 |
�� | +0.065 |
� | +0.064 |
Neg logit contributions | |
abol | -0.096 |
theless | -0.092 |
utonium | -0.090 |
akespe | -0.088 |
andre | -0.086 |
Token | , |
Token ID | 11 |
Feature activation | +1.00e-02 |
Pos logit contributions | |
abol | +0.554 |
theless | +0.535 |
utonium | +0.521 |
akespe | +0.511 |
andre | +0.496 |
Neg logit contributions | |
Jinn | -0.425 |
↑ | -0.422 |
pai | -0.419 |
�� | -0.394 |
� | -0.391 |
Token | and |
Token ID | 290 |
Feature activation | +1.86e-02 |
Pos logit contributions | |
Jinn | +0.008 |
↑ | +0.007 |
pai | +0.007 |
�� | +0.007 |
� | +0.007 |
Neg logit contributions | |
abol | -0.013 |
theless | -0.013 |
utonium | -0.012 |
akespe | -0.012 |
andre | -0.012 |
Token | when |
Token ID | 618 |
Feature activation | +9.47e-02 |
Pos logit contributions | |
Jinn | +0.014 |
↑ | +0.014 |
pai | +0.014 |
�� | +0.013 |
� | +0.013 |
Neg logit contributions | |
abol | -0.024 |
theless | -0.023 |
utonium | -0.023 |
akespe | -0.022 |
andre | -0.022 |
Token | it |
Token ID | 340 |
Feature activation | -2.79e-02 |
Pos logit contributions | |
Jinn | +0.072 |
↑ | +0.071 |
pai | +0.071 |
�� | +0.066 |
� | +0.065 |
Neg logit contributions | |
abol | -0.124 |
theless | -0.120 |
utonium | -0.117 |
akespe | -0.115 |
andre | -0.112 |
Token | hit |
Token ID | 2277 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
abol | +0.035 |
theless | +0.034 |
utonium | +0.034 |
akespe | +0.033 |
andre | +0.032 |
Neg logit contributions | |
Jinn | -0.022 |
↑ | -0.022 |
pai | -0.022 |
�� | -0.020 |
� | -0.020 |
Token | will |
Token ID | 481 |
Feature activation | -4.22e-02 |
Pos logit contributions | |
Jinn | +0.020 |
↑ | +0.020 |
pai | +0.020 |
�� | +0.019 |
� | +0.019 |
Neg logit contributions | |
abol | -0.027 |
theless | -0.026 |
utonium | -0.025 |
akespe | -0.025 |
andre | -0.024 |
Token | receive |
Token ID | 3328 |
Feature activation | -1.73e-02 |
Pos logit contributions | |
abol | +0.049 |
theless | +0.048 |
utonium | +0.047 |
akespe | +0.046 |
andre | +0.044 |
Neg logit contributions | |
↑ | -0.038 |
Jinn | -0.037 |
pai | -0.037 |
�� | -0.035 |
� | -0.035 |
Token | emails |
Token ID | 7237 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
abol | +0.020 |
theless | +0.020 |
utonium | +0.019 |
akespe | +0.019 |
andre | +0.018 |
Neg logit contributions | |
↑ | -0.015 |
Jinn | -0.015 |
pai | -0.015 |
�� | -0.014 |
� | -0.014 |
Token | containing |
Token ID | 7268 |
Feature activation | -3.98e-01 |
Pos logit contributions | |
↑ | +0.259 |
Jinn | +0.255 |
pai | +0.252 |
ki | +0.239 |
� | +0.239 |
Neg logit contributions | |
abol | -0.272 |
theless | -0.263 |
utonium | -0.255 |
akespe | -0.249 |
andre | -0.241 |
Token | news |
Token ID | 1705 |
Feature activation | +7.54e-02 |
Pos logit contributions | |
abol | +0.458 |
theless | +0.442 |
utonium | +0.431 |
akespe | +0.422 |
andre | +0.407 |
Neg logit contributions | |
Jinn | -0.366 |
↑ | -0.364 |
pai | -0.359 |
�� | -0.338 |
� | -0.337 |
Token | content |
Token ID | 2695 |
Feature activation | -4.60e-01 |
Pos logit contributions | |
↑ | +0.072 |
Jinn | +0.071 |
pai | +0.071 |
� | +0.067 |
�� | +0.066 |
Neg logit contributions | |
abol | -0.083 |
theless | -0.081 |
utonium | -0.079 |
akespe | -0.078 |
andre | -0.074 |
Token | , |
Token ID | 837 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
abol | +0.666 |
theless | +0.646 |
utonium | +0.633 |
akespe | +0.620 |
andre | +0.610 |
Neg logit contributions | |
Jinn | -0.284 |
pai | -0.278 |
↑ | -0.278 |
�� | -0.258 |
� | -0.251 |
Token | updates |
Token ID | 5992 |
Feature activation | -8.81e-02 |
Pos logit contributions | |
Jinn | +0.402 |
↑ | +0.402 |
pai | +0.398 |
�� | +0.378 |
� | +0.375 |
Neg logit contributions | |
abol | -0.376 |
theless | -0.362 |
utonium | -0.349 |
akespe | -0.342 |
andre | -0.328 |
Token | and |
Token ID | 290 |
Feature activation | +6.43e-02 |
Pos logit contributions | |
abol | +0.118 |
theless | +0.115 |
utonium | +0.112 |
akespe | +0.110 |
andre | +0.107 |
Neg logit contributions | |
Jinn | -0.064 |
↑ | -0.063 |
pai | -0.063 |
�� | -0.058 |
� | -0.058 |
Token | promotions |
Token ID | 20699 |
Feature activation | -4.74e-02 |
Pos logit contributions | |
Jinn | +0.056 |
↑ | +0.056 |
pai | +0.055 |
�� | +0.052 |
� | +0.051 |
Neg logit contributions | |
abol | -0.077 |
theless | -0.074 |
utonium | -0.072 |
akespe | -0.071 |
andre | -0.069 |
Token | from |
Token ID | 422 |
Feature activation | +8.90e-02 |
Pos logit contributions | |
abol | +0.073 |
theless | +0.071 |
utonium | +0.070 |
akespe | +0.069 |
andre | +0.067 |
Neg logit contributions | |
Jinn | -0.025 |
↑ | -0.024 |
pai | -0.024 |
�� | -0.022 |
� | -0.021 |
Token | to |
Token ID | 284 |
Feature activation | -6.79e-02 |
Pos logit contributions | |
abol | +0.358 |
theless | +0.347 |
utonium | +0.339 |
akespe | +0.332 |
andre | +0.325 |
Neg logit contributions | |
Jinn | -0.203 |
↑ | -0.202 |
pai | -0.200 |
�� | -0.186 |
� | -0.184 |
Token | Amazon |
Token ID | 6186 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
abol | +0.088 |
theless | +0.086 |
utonium | +0.083 |
akespe | +0.082 |
andre | +0.080 |
Neg logit contributions | |
Jinn | -0.052 |
↑ | -0.051 |
pai | -0.051 |
�� | -0.048 |
� | -0.047 |
Token | � |
Token ID | 447 |
Feature activation | -4.73e-02 |
Pos logit contributions | |
Jinn | +0.085 |
↑ | +0.085 |
pai | +0.084 |
�� | +0.079 |
� | +0.078 |
Neg logit contributions | |
abol | -0.137 |
theless | -0.133 |
utonium | -0.130 |
akespe | -0.127 |
andre | -0.124 |
Token | � |
Token ID | 247 |
Feature activation | -6.70e-02 |
Pos logit contributions | |
abol | +0.049 |
theless | +0.047 |
utonium | +0.046 |
akespe | +0.044 |
andre | +0.043 |
Neg logit contributions | |
Jinn | -0.049 |
↑ | -0.049 |
pai | -0.048 |
�� | -0.046 |
� | -0.045 |
Token | s |
Token ID | 82 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
abol | +0.082 |
theless | +0.080 |
utonium | +0.078 |
akespe | +0.076 |
andre | +0.074 |
Neg logit contributions | |
Jinn | -0.056 |
↑ | -0.056 |
pai | -0.055 |
�� | -0.052 |
� | -0.051 |
Token | DRM |
Token ID | 31400 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
Jinn | +0.013 |
↑ | +0.013 |
pai | +0.013 |
�� | +0.012 |
� | +0.012 |
Neg logit contributions | |
abol | -0.017 |
theless | -0.017 |
utonium | -0.016 |
akespe | -0.016 |
andre | -0.015 |
Token | implementation |
Token ID | 7822 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
abol | +0.559 |
theless | +0.537 |
utonium | +0.524 |
akespe | +0.513 |
andre | +0.501 |
Neg logit contributions | |
Jinn | -0.402 |
↑ | -0.398 |
pai | -0.395 |
�� | -0.373 |
� | -0.367 |
Token | , |
Token ID | 11 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
abol | +0.313 |
theless | +0.303 |
utonium | +0.295 |
akespe | +0.290 |
andre | +0.284 |
Neg logit contributions | |
Jinn | -0.182 |
↑ | -0.179 |
pai | -0.178 |
�� | -0.167 |
� | -0.164 |
Token | any |
Token ID | 597 |
Feature activation | +1.90e-02 |
Pos logit contributions | |
Jinn | +0.080 |
↑ | +0.080 |
pai | +0.079 |
�� | +0.074 |
� | +0.073 |
Neg logit contributions | |
abol | -0.131 |
theless | -0.127 |
utonium | -0.124 |
akespe | -0.122 |
andre | -0.119 |
Token | backup |
Token ID | 11559 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
Jinn | +0.016 |
↑ | +0.016 |
pai | +0.016 |
�� | +0.015 |
� | +0.015 |
Neg logit contributions | |
abol | -0.023 |
theless | -0.022 |
utonium | -0.021 |
akespe | -0.021 |
andre | -0.020 |
Token | copy |
Token ID | 4866 |
Feature activation | +4.64e-03 |
Pos logit contributions | |
abol | +0.311 |
theless | +0.301 |
utonium | +0.293 |
akespe | +0.287 |
andre | +0.280 |
Neg logit contributions | |
Jinn | -0.210 |
↑ | -0.209 |
pai | -0.207 |
�� | -0.194 |
� | -0.192 |