Token |
|
Token ID | 198 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
between | +0.390 |
Gaw | +0.361 |
undertaking | +0.328 |
pty | +0.311 |
abus | +0.306 |
Neg logit contributions | |
united | -0.477 |
CTV | -0.439 |
additive | -0.368 |
iod | -0.361 |
SHARE | -0.330 |
Token |
|
Token ID | 198 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
between | +0.084 |
Gaw | +0.078 |
undertaking | +0.071 |
pty | +0.067 |
abus | +0.066 |
Neg logit contributions | |
united | -0.103 |
CTV | -0.094 |
additive | -0.079 |
iod | -0.077 |
SHARE | -0.071 |
Token | Power |
Token ID | 13434 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
between | +0.085 |
Gaw | +0.082 |
undertaking | +0.074 |
pty | +0.070 |
wagen | +0.069 |
Neg logit contributions | |
united | -0.104 |
CTV | -0.096 |
additive | -0.079 |
iod | -0.076 |
SHARE | -0.073 |
Token | Point |
Token ID | 12727 |
Feature activation | -9.69e-03 |
Pos logit contributions | |
between | +0.360 |
Gaw | +0.341 |
undertaking | +0.317 |
pty | +0.304 |
devices | +0.304 |
Neg logit contributions | |
united | -0.274 |
CTV | -0.247 |
iod | -0.194 |
additive | -0.193 |
SHARE | -0.168 |
Token | slide |
Token ID | 10649 |
Feature activation | +5.24e-01 |
Pos logit contributions | |
united | +0.010 |
CTV | +0.009 |
additive | +0.008 |
iod | +0.008 |
Bravo | +0.007 |
Neg logit contributions | |
between | -0.006 |
Gaw | -0.006 |
undertaking | -0.005 |
pty | -0.005 |
abus | -0.005 |
Token | PNG |
Token ID | 36182 |
Feature activation | +7.68e-01 |
Pos logit contributions | |
between | +0.195 |
Gaw | +0.169 |
undertaking | +0.134 |
pty | +0.116 |
abus | +0.111 |
Neg logit contributions | |
united | -0.677 |
CTV | -0.641 |
additive | -0.567 |
iod | -0.561 |
SHARE | -0.530 |
Token | larger |
Token ID | 4025 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
between | +0.550 |
Gaw | +0.501 |
undertaking | +0.457 |
pty | +0.429 |
abus | +0.425 |
Neg logit contributions | |
united | -0.733 |
CTV | -0.678 |
additive | -0.572 |
iod | -0.565 |
SHARE | -0.514 |
Token | image |
Token ID | 2939 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
between | +0.208 |
Gaw | +0.190 |
undertaking | +0.167 |
pty | +0.158 |
abus | +0.155 |
Neg logit contributions | |
united | -0.328 |
CTV | -0.304 |
additive | -0.260 |
iod | -0.257 |
SHARE | -0.236 |
Token |
|
Token ID | 198 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
between | +0.152 |
Gaw | +0.139 |
undertaking | +0.125 |
pty | +0.119 |
abus | +0.117 |
Neg logit contributions | |
united | -0.197 |
CTV | -0.181 |
additive | -0.153 |
iod | -0.151 |
SHARE | -0.137 |
Token |
|
Token ID | 198 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
between | +0.113 |
Gaw | +0.105 |
undertaking | +0.095 |
pty | +0.090 |
abus | +0.089 |
Neg logit contributions | |
united | -0.137 |
CTV | -0.126 |
additive | -0.105 |
iod | -0.103 |
SHARE | -0.094 |
Token | larg |
Token ID | 15521 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
between | +0.083 |
Gaw | +0.082 |
undertaking | +0.072 |
pty | +0.067 |
wagen | +0.067 |
Neg logit contributions | |
united | -0.123 |
CTV | -0.114 |
additive | -0.093 |
iod | -0.091 |
SHARE | -0.087 |
Token | one |
Token ID | 530 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
between | +0.017 |
Gaw | +0.016 |
undertaking | +0.014 |
pty | +0.013 |
abus | +0.013 |
Neg logit contributions | |
united | -0.024 |
CTV | -0.023 |
additive | -0.019 |
iod | -0.019 |
SHARE | -0.017 |
Token | a |
Token ID | 257 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
between | +0.075 |
Gaw | +0.070 |
undertaking | +0.063 |
pty | +0.060 |
abus | +0.060 |
Neg logit contributions | |
united | -0.093 |
CTV | -0.086 |
additive | -0.072 |
iod | -0.071 |
Bravo | -0.065 |
Token | babys |
Token ID | 46711 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
between | +0.100 |
Gaw | +0.092 |
undertaking | +0.084 |
pty | +0.080 |
abus | +0.079 |
Neg logit contributions | |
united | -0.107 |
CTV | -0.097 |
additive | -0.080 |
iod | -0.079 |
SHARE | -0.071 |
Token | itter |
Token ID | 1967 |
Feature activation | +7.76e-02 |
Pos logit contributions | |
united | +0.178 |
CTV | +0.161 |
additive | +0.131 |
iod | +0.128 |
SHARE | +0.114 |
Neg logit contributions | |
between | -0.193 |
Gaw | -0.182 |
undertaking | -0.167 |
pty | -0.159 |
abus | -0.157 |
Token | — |
Token ID | 960 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
between | +0.062 |
Gaw | +0.057 |
undertaking | +0.052 |
pty | +0.049 |
abus | +0.048 |
Neg logit contributions | |
united | -0.068 |
CTV | -0.062 |
additive | -0.052 |
iod | -0.051 |
SHARE | -0.046 |
Token | between |
Token ID | 23395 |
Feature activation | +7.61e-01 |
Pos logit contributions | |
between | +0.137 |
Gaw | +0.126 |
undertaking | +0.113 |
pty | +0.107 |
abus | +0.105 |
Neg logit contributions | |
united | -0.196 |
CTV | -0.181 |
additive | -0.153 |
iod | -0.151 |
SHARE | -0.139 |
Token | 2002 |
Token ID | 6244 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
between | +0.524 |
Gaw | +0.479 |
undertaking | +0.428 |
pty | +0.401 |
devices | +0.393 |
Neg logit contributions | |
united | -0.752 |
CTV | -0.695 |
additive | -0.588 |
iod | -0.582 |
SHARE | -0.534 |
Token | and |
Token ID | 290 |
Feature activation | +2.12e-02 |
Pos logit contributions | |
between | +0.188 |
Gaw | +0.174 |
undertaking | +0.158 |
pty | +0.150 |
abus | +0.148 |
Neg logit contributions | |
united | -0.210 |
CTV | -0.192 |
additive | -0.159 |
iod | -0.157 |
SHARE | -0.141 |
Token | 2003 |
Token ID | 5816 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
between | +0.012 |
Gaw | +0.011 |
undertaking | +0.010 |
pty | +0.009 |
abus | +0.009 |
Neg logit contributions | |
united | -0.023 |
CTV | -0.021 |
additive | -0.019 |
iod | -0.018 |
SHARE | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | -3.30e-03 |
Pos logit contributions | |
between | +0.102 |
Gaw | +0.094 |
undertaking | +0.085 |
pty | +0.081 |
abus | +0.079 |
Neg logit contributions | |
united | -0.123 |
CTV | -0.113 |
additive | -0.095 |
iod | -0.094 |
SHARE | -0.085 |
Token | Jim |
Token ID | 5395 |
Feature activation | +2.44e-02 |
Pos logit contributions | |
united | +0.003 |
CTV | +0.003 |
additive | +0.002 |
iod | +0.002 |
SHARE | +0.002 |
Neg logit contributions | |
between | -0.003 |
Gaw | -0.002 |
undertaking | -0.002 |
pty | -0.002 |
abus | -0.002 |
Token | 2010 |
Token ID | 3050 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
between | +0.011 |
Gaw | +0.010 |
undertaking | +0.009 |
pty | +0.008 |
abus | +0.008 |
Neg logit contributions | |
united | -0.019 |
CTV | -0.018 |
additive | -0.016 |
iod | -0.015 |
SHARE | -0.014 |
Token | boys |
Token ID | 13202 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
between | +0.174 |
Gaw | +0.167 |
undertaking | +0.156 |
pty | +0.148 |
wagen | +0.145 |
Neg logit contributions | |
united | -0.126 |
CTV | -0.112 |
additive | -0.084 |
iod | -0.084 |
SHARE | -0.074 |
Token | beware |
Token ID | 40600 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
united | +0.349 |
CTV | +0.324 |
additive | +0.282 |
iod | +0.279 |
Bravo | +0.258 |
Neg logit contributions | |
between | -0.172 |
Gaw | -0.156 |
undertaking | -0.132 |
pty | -0.127 |
devices | -0.122 |
Token |
|
Token ID | 198 |
Feature activation | +6.46e-02 |
Pos logit contributions | |
between | +0.142 |
Gaw | +0.131 |
undertaking | +0.118 |
pty | +0.112 |
abus | +0.110 |
Neg logit contributions | |
united | -0.178 |
CTV | -0.164 |
additive | -0.138 |
iod | -0.136 |
SHARE | -0.124 |
Token |
|
Token ID | 198 |
Feature activation | +4.54e-02 |
Pos logit contributions | |
between | +0.049 |
Gaw | +0.045 |
undertaking | +0.041 |
pty | +0.039 |
abus | +0.038 |
Neg logit contributions | |
united | -0.059 |
CTV | -0.054 |
additive | -0.046 |
iod | -0.045 |
SHARE | -0.041 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | +7.41e-01 |
Pos logit contributions | |
between | +0.012 |
Gaw | +0.010 |
undertaking | +0.007 |
pty | +0.005 |
devices | +0.004 |
Neg logit contributions | |
united | -0.064 |
CTV | -0.061 |
additive | -0.054 |
iod | -0.054 |
SHARE | -0.051 |
Token | : |
Token ID | 25 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
between | +0.766 |
Gaw | +0.717 |
undertaking | +0.668 |
pty | +0.648 |
abus | +0.639 |
Neg logit contributions | |
united | -0.474 |
CTV | -0.418 |
additive | -0.322 |
iod | -0.318 |
SHARE | -0.263 |
Token | j |
Token ID | 474 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
united | +0.257 |
CTV | +0.236 |
additive | +0.197 |
iod | +0.195 |
Bravo | +0.176 |
Neg logit contributions | |
between | -0.219 |
Gaw | -0.202 |
undertaking | -0.184 |
pty | -0.175 |
abus | -0.172 |
Token | wt |
Token ID | 46569 |
Feature activation | +3.44e-02 |
Pos logit contributions | |
united | +0.184 |
CTV | +0.168 |
additive | +0.141 |
iod | +0.139 |
SHARE | +0.127 |
Neg logit contributions | |
between | -0.142 |
Gaw | -0.131 |
undertaking | -0.119 |
pty | -0.112 |
abus | -0.109 |
Token | 0001 |
Token ID | 18005 |
Feature activation | -2.62e-02 |
Pos logit contributions | |
between | +0.027 |
Gaw | +0.025 |
undertaking | +0.022 |
pty | +0.021 |
abus | +0.021 |
Neg logit contributions | |
united | -0.031 |
CTV | -0.028 |
additive | -0.024 |
iod | -0.023 |
SHARE | -0.021 |
Token | - |
Token ID | 532 |
Feature activation | -4.67e-02 |
Pos logit contributions | |
united | +0.020 |
CTV | +0.018 |
additive | +0.014 |
iod | +0.014 |
SHARE | +0.013 |
Neg logit contributions | |
between | -0.024 |
Gaw | -0.022 |
undertaking | -0.021 |
pty | -0.020 |
abus | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | -6.08e-02 |
Pos logit contributions | |
united | +0.075 |
CTV | +0.068 |
additive | +0.055 |
iod | +0.054 |
SHARE | +0.048 |
Neg logit contributions | |
between | -0.078 |
Gaw | -0.073 |
undertaking | -0.067 |
pty | -0.064 |
abus | -0.063 |
Token | I |
Token ID | 314 |
Feature activation | -2.71e-02 |
Pos logit contributions | |
united | +0.056 |
CTV | +0.051 |
additive | +0.043 |
iod | +0.042 |
Bravo | +0.038 |
Neg logit contributions | |
between | -0.046 |
Gaw | -0.042 |
undertaking | -0.038 |
pty | -0.037 |
abus | -0.036 |
Token | think |
Token ID | 892 |
Feature activation | -6.27e-03 |
Pos logit contributions | |
united | +0.022 |
CTV | +0.020 |
additive | +0.017 |
iod | +0.016 |
SHARE | +0.015 |
Neg logit contributions | |
between | -0.023 |
Gaw | -0.021 |
undertaking | -0.019 |
pty | -0.019 |
abus | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | +5.50e-02 |
Pos logit contributions | |
united | +0.006 |
CTV | +0.005 |
additive | +0.004 |
iod | +0.004 |
SHARE | +0.004 |
Neg logit contributions | |
between | -0.005 |
Gaw | -0.004 |
undertaking | -0.004 |
pty | -0.004 |
abus | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +4.40e-02 |
Pos logit contributions | |
between | +0.041 |
Gaw | +0.038 |
undertaking | +0.034 |
pty | +0.033 |
abus | +0.032 |
Neg logit contributions | |
united | -0.051 |
CTV | -0.047 |
additive | -0.039 |
iod | -0.038 |
SHARE | -0.035 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | +7.07e-01 |
Pos logit contributions | |
between | +0.011 |
Gaw | +0.009 |
undertaking | +0.006 |
pty | +0.004 |
abus | +0.004 |
Neg logit contributions | |
united | -0.063 |
CTV | -0.059 |
additive | -0.053 |
iod | -0.053 |
SHARE | -0.050 |
Token | : |
Token ID | 25 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
between | +0.732 |
Gaw | +0.685 |
undertaking | +0.638 |
pty | +0.619 |
abus | +0.610 |
Neg logit contributions | |
united | -0.452 |
CTV | -0.399 |
additive | -0.307 |
iod | -0.303 |
SHARE | -0.251 |
Token | B |
Token ID | 347 |
Feature activation | -5.83e-02 |
Pos logit contributions | |
united | +0.246 |
CTV | +0.226 |
additive | +0.189 |
iod | +0.186 |
Bravo | +0.169 |
Neg logit contributions | |
between | -0.208 |
Gaw | -0.192 |
undertaking | -0.174 |
pty | -0.166 |
abus | -0.163 |
Token | iz |
Token ID | 528 |
Feature activation | +7.34e-02 |
Pos logit contributions | |
united | +0.053 |
CTV | +0.049 |
additive | +0.040 |
iod | +0.040 |
SHARE | +0.036 |
Neg logit contributions | |
between | -0.045 |
Gaw | -0.041 |
undertaking | -0.037 |
pty | -0.036 |
abus | -0.035 |
Token | r |
Token ID | 81 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
between | +0.056 |
Gaw | +0.052 |
undertaking | +0.047 |
pty | +0.045 |
abus | +0.044 |
Neg logit contributions | |
united | -0.067 |
CTV | -0.061 |
additive | -0.051 |
iod | -0.050 |
SHARE | -0.046 |
Token | Pix |
Token ID | 21642 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
united | +0.097 |
CTV | +0.088 |
additive | +0.073 |
iod | +0.072 |
SHARE | +0.065 |
Neg logit contributions | |
between | -0.085 |
Gaw | -0.079 |
undertaking | -0.072 |
pty | -0.068 |
devices | -0.067 |
Token | iff |
Token ID | 733 |
Feature activation | +1.09e-03 |
Pos logit contributions | |
united | +0.028 |
CTV | +0.026 |
additive | +0.022 |
iod | +0.022 |
SHARE | +0.020 |
Neg logit contributions | |
between | -0.023 |
Gaw | -0.021 |
undertaking | -0.019 |
pty | -0.018 |
abus | -0.017 |
Token | Tra |
Token ID | 15721 |
Feature activation | +6.03e-04 |
Pos logit contributions | |
between | +0.001 |
Gaw | +0.001 |
undertaking | +0.001 |
pty | +0.001 |
abus | +0.001 |
Neg logit contributions | |
united | -0.001 |
CTV | -0.001 |
additive | -0.001 |
iod | -0.001 |
SHARE | -0.001 |
Token | x |
Token ID | 87 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
between | +0.001 |
Gaw | +0.001 |
undertaking | +0.001 |
pty | +0.001 |
abus | +0.000 |
Neg logit contributions | |
united | -0.000 |
CTV | -0.000 |
additive | -0.000 |
iod | -0.000 |
SHARE | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | -3.08e-02 |
Pos logit contributions | |
united | +0.221 |
CTV | +0.203 |
additive | +0.170 |
iod | +0.167 |
SHARE | +0.152 |
Neg logit contributions | |
between | -0.181 |
Gaw | -0.167 |
undertaking | -0.151 |
pty | -0.144 |
abus | -0.141 |
Token |
|
Token ID | 198 |
Feature activation | -1.27e-02 |
Pos logit contributions | |
united | +0.028 |
CTV | +0.026 |
additive | +0.022 |
iod | +0.021 |
SHARE | +0.020 |
Neg logit contributions | |
between | -0.023 |
Gaw | -0.021 |
undertaking | -0.019 |
pty | -0.018 |
abus | -0.018 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | +7.05e-01 |
Pos logit contributions | |
united | +0.018 |
CTV | +0.017 |
additive | +0.015 |
iod | +0.015 |
SHARE | +0.014 |
Neg logit contributions | |
between | -0.003 |
Gaw | -0.002 |
undertaking | -0.002 |
pty | -0.001 |
abus | -0.001 |
Token | : |
Token ID | 25 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
between | +0.730 |
Gaw | +0.683 |
undertaking | +0.636 |
pty | +0.617 |
abus | +0.609 |
Neg logit contributions | |
united | -0.449 |
CTV | -0.397 |
additive | -0.304 |
iod | -0.301 |
SHARE | -0.249 |
Token | V |
Token ID | 569 |
Feature activation | -3.43e-02 |
Pos logit contributions | |
united | +0.276 |
CTV | +0.252 |
additive | +0.211 |
iod | +0.208 |
Bravo | +0.188 |
Neg logit contributions | |
between | -0.235 |
Gaw | -0.217 |
undertaking | -0.197 |
pty | -0.188 |
abus | -0.185 |
Token | the |
Token ID | 1169 |
Feature activation | +8.31e-02 |
Pos logit contributions | |
united | +0.031 |
CTV | +0.029 |
additive | +0.024 |
iod | +0.023 |
SHARE | +0.021 |
Neg logit contributions | |
between | -0.026 |
Gaw | -0.024 |
undertaking | -0.022 |
pty | -0.021 |
abus | -0.021 |
Token | Happy |
Token ID | 25082 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
between | +0.063 |
Gaw | +0.059 |
undertaking | +0.053 |
pty | +0.050 |
devices | +0.050 |
Neg logit contributions | |
united | -0.076 |
CTV | -0.069 |
additive | -0.058 |
iod | -0.057 |
SHARE | -0.052 |
Token | L |
Token ID | 43 |
Feature activation | -8.40e-02 |
Pos logit contributions | |
united | +0.168 |
CTV | +0.154 |
additive | +0.126 |
iod | +0.124 |
SHARE | +0.113 |
Neg logit contributions | |
between | -0.155 |
Gaw | -0.144 |
undertaking | -0.132 |
pty | -0.125 |
abus | -0.124 |
Token | was |
Token ID | 373 |
Feature activation | -8.05e-02 |
Pos logit contributions | |
united | +0.088 |
CTV | +0.081 |
additive | +0.068 |
iod | +0.067 |
Bravo | +0.061 |
Neg logit contributions | |
between | -0.070 |
Gaw | -0.065 |
undertaking | -0.058 |
pty | -0.056 |
abus | -0.055 |
Token | about |
Token ID | 546 |
Feature activation | -6.58e-02 |
Pos logit contributions | |
united | +0.075 |
CTV | +0.069 |
additive | +0.058 |
iod | +0.057 |
SHARE | +0.052 |
Neg logit contributions | |
between | -0.060 |
Gaw | -0.055 |
undertaking | -0.050 |
pty | -0.047 |
abus | -0.046 |
Token | homosexuality |
Token ID | 19822 |
Feature activation | +9.45e-02 |
Pos logit contributions | |
united | +0.060 |
CTV | +0.055 |
additive | +0.047 |
iod | +0.046 |
Bravo | +0.042 |
Neg logit contributions | |
between | -0.049 |
Gaw | -0.046 |
undertaking | -0.041 |
pty | -0.040 |
abus | -0.039 |
Token |
|
Token ID | 198 |
Feature activation | +4.73e-02 |
Pos logit contributions | |
between | +0.074 |
Gaw | +0.069 |
undertaking | +0.062 |
pty | +0.060 |
abus | +0.059 |
Neg logit contributions | |
united | -0.084 |
CTV | -0.077 |
additive | -0.064 |
iod | -0.063 |
SHARE | -0.057 |
Token |
|
Token ID | 198 |
Feature activation | +4.53e-02 |
Pos logit contributions | |
between | +0.035 |
Gaw | +0.033 |
undertaking | +0.030 |
pty | +0.028 |
abus | +0.028 |
Neg logit contributions | |
united | -0.044 |
CTV | -0.040 |
additive | -0.033 |
iod | -0.033 |
SHARE | -0.030 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | +6.98e-01 |
Pos logit contributions | |
between | +0.035 |
Gaw | +0.032 |
undertaking | +0.029 |
pty | +0.028 |
abus | +0.027 |
Neg logit contributions | |
united | -0.041 |
CTV | -0.038 |
additive | -0.031 |
iod | -0.031 |
SHARE | -0.028 |
Token | : |
Token ID | 25 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
between | +0.720 |
Gaw | +0.680 |
undertaking | +0.634 |
pty | +0.611 |
abus | +0.602 |
Neg logit contributions | |
united | -0.448 |
CTV | -0.394 |
additive | -0.298 |
iod | -0.296 |
SHARE | -0.248 |
Token | k |
Token ID | 479 |
Feature activation | +5.53e-02 |
Pos logit contributions | |
united | +0.255 |
CTV | +0.233 |
additive | +0.195 |
iod | +0.192 |
Bravo | +0.174 |
Neg logit contributions | |
between | -0.218 |
Gaw | -0.201 |
undertaking | -0.182 |
pty | -0.174 |
abus | -0.171 |
Token | imp |
Token ID | 11011 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
between | +0.040 |
Gaw | +0.037 |
undertaking | +0.034 |
pty | +0.031 |
devices | +0.031 |
Neg logit contributions | |
united | -0.052 |
CTV | -0.048 |
additive | -0.040 |
iod | -0.040 |
SHARE | -0.036 |
Token | unk |
Token ID | 2954 |
Feature activation | +3.19e-02 |
Pos logit contributions | |
between | +0.180 |
Gaw | +0.167 |
undertaking | +0.151 |
pty | +0.143 |
abus | +0.140 |
Neg logit contributions | |
united | -0.219 |
CTV | -0.201 |
additive | -0.168 |
iod | -0.165 |
SHARE | -0.150 |
Token | rock |
Token ID | 10823 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
between | +0.027 |
Gaw | +0.025 |
undertaking | +0.023 |
pty | +0.022 |
abus | +0.021 |
Neg logit contributions | |
united | -0.027 |
CTV | -0.024 |
additive | -0.020 |
iod | -0.020 |
SHARE | -0.017 |
Token | things |
Token ID | 1243 |
Feature activation | +9.31e-02 |
Pos logit contributions | |
united | +0.129 |
CTV | +0.117 |
additive | +0.095 |
iod | +0.094 |
SHARE | +0.083 |
Neg logit contributions | |
between | -0.135 |
Gaw | -0.127 |
undertaking | -0.116 |
pty | -0.111 |
abus | -0.109 |
Token | like |
Token ID | 588 |
Feature activation | -6.60e-02 |
Pos logit contributions | |
between | +0.079 |
Gaw | +0.073 |
undertaking | +0.067 |
pty | +0.064 |
abus | +0.063 |
Neg logit contributions | |
united | -0.077 |
CTV | -0.070 |
additive | -0.057 |
iod | -0.056 |
SHARE | -0.050 |
Token | � |
Token ID | 564 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
united | +0.052 |
CTV | +0.047 |
additive | +0.038 |
iod | +0.037 |
SHARE | +0.033 |
Neg logit contributions | |
between | -0.058 |
Gaw | -0.055 |
undertaking | -0.050 |
pty | -0.048 |
abus | -0.047 |
Token | � |
Token ID | 250 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
united | +0.109 |
CTV | +0.099 |
additive | +0.081 |
iod | +0.079 |
SHARE | +0.071 |
Neg logit contributions | |
between | -0.115 |
Gaw | -0.107 |
undertaking | -0.098 |
pty | -0.094 |
abus | -0.093 |
Token | Sm |
Token ID | 7556 |
Feature activation | -3.73e-02 |
Pos logit contributions | |
united | +0.107 |
CTV | +0.098 |
additive | +0.080 |
iod | +0.079 |
SHARE | +0.072 |
Neg logit contributions | |
between | -0.099 |
Gaw | -0.093 |
undertaking | -0.084 |
pty | -0.081 |
abus | -0.079 |
Token | ile |
Token ID | 576 |
Feature activation | +6.94e-01 |
Pos logit contributions | |
united | +0.036 |
CTV | +0.034 |
additive | +0.028 |
iod | +0.028 |
SHARE | +0.026 |
Neg logit contributions | |
between | -0.026 |
Gaw | -0.024 |
undertaking | -0.022 |
pty | -0.020 |
abus | -0.020 |
Token | if |
Token ID | 611 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
between | +0.572 |
Gaw | +0.534 |
undertaking | +0.485 |
pty | +0.465 |
abus | +0.457 |
Neg logit contributions | |
united | -0.588 |
CTV | -0.536 |
additive | -0.441 |
iod | -0.434 |
SHARE | -0.389 |
Token | you |
Token ID | 345 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
between | +0.089 |
Gaw | +0.082 |
undertaking | +0.074 |
pty | +0.071 |
abus | +0.070 |
Neg logit contributions | |
united | -0.111 |
CTV | -0.102 |
additive | -0.086 |
iod | -0.085 |
SHARE | -0.077 |
Token | masturb |
Token ID | 22938 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
between | +0.011 |
Gaw | +0.010 |
undertaking | +0.009 |
pty | +0.009 |
abus | +0.009 |
Neg logit contributions | |
united | -0.010 |
CTV | -0.010 |
additive | -0.008 |
iod | -0.008 |
SHARE | -0.007 |
Token | ate |
Token ID | 378 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
between | +0.195 |
Gaw | +0.182 |
undertaking | +0.165 |
pty | +0.157 |
devices | +0.154 |
Neg logit contributions | |
united | -0.228 |
CTV | -0.208 |
additive | -0.175 |
iod | -0.172 |
SHARE | -0.156 |
Token | � |
Token ID | 447 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
between | +0.083 |
Gaw | +0.077 |
undertaking | +0.070 |
pty | +0.067 |
abus | +0.066 |
Neg logit contributions | |
united | -0.091 |
CTV | -0.083 |
additive | -0.069 |
iod | -0.068 |
SHARE | -0.061 |
Token | bad |
Token ID | 2089 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
between | +0.028 |
Gaw | +0.026 |
undertaking | +0.023 |
pty | +0.022 |
abus | +0.022 |
Neg logit contributions | |
united | -0.041 |
CTV | -0.038 |
additive | -0.032 |
iod | -0.031 |
SHARE | -0.029 |
Token | idea |
Token ID | 2126 |
Feature activation | -8.61e-02 |
Pos logit contributions | |
between | +0.098 |
Gaw | +0.091 |
undertaking | +0.084 |
pty | +0.079 |
abus | +0.078 |
Neg logit contributions | |
united | -0.106 |
CTV | -0.097 |
additive | -0.079 |
iod | -0.078 |
SHARE | -0.071 |
Token | . |
Token ID | 13 |
Feature activation | -6.54e-03 |
Pos logit contributions | |
united | +0.079 |
CTV | +0.072 |
additive | +0.060 |
iod | +0.059 |
SHARE | +0.054 |
Neg logit contributions | |
between | -0.065 |
Gaw | -0.061 |
undertaking | -0.055 |
pty | -0.052 |
abus | -0.051 |
Token |
|
Token ID | 198 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
united | +0.006 |
CTV | +0.005 |
additive | +0.004 |
iod | +0.004 |
SHARE | +0.004 |
Neg logit contributions | |
between | -0.005 |
Gaw | -0.005 |
undertaking | -0.004 |
pty | -0.004 |
abus | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +1.43e-03 |
Pos logit contributions | |
between | +0.009 |
Gaw | +0.009 |
undertaking | +0.008 |
pty | +0.007 |
abus | +0.007 |
Neg logit contributions | |
united | -0.011 |
CTV | -0.011 |
additive | -0.009 |
iod | -0.009 |
SHARE | -0.008 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | +6.85e-01 |
Pos logit contributions | |
between | +0.000 |
Gaw | +0.000 |
undertaking | +0.000 |
pty | +0.000 |
abus | +0.000 |
Neg logit contributions | |
united | -0.002 |
CTV | -0.002 |
additive | -0.002 |
iod | -0.002 |
SHARE | -0.002 |
Token | : |
Token ID | 25 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
between | +0.709 |
Gaw | +0.664 |
undertaking | +0.619 |
pty | +0.599 |
abus | +0.591 |
Neg logit contributions | |
united | -0.438 |
CTV | -0.386 |
additive | -0.296 |
iod | -0.292 |
SHARE | -0.243 |
Token | Mike |
Token ID | 4995 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
united | +0.268 |
CTV | +0.245 |
additive | +0.205 |
iod | +0.202 |
Bravo | +0.183 |
Neg logit contributions | |
between | -0.226 |
Gaw | -0.208 |
undertaking | -0.189 |
pty | -0.181 |
abus | -0.178 |
Token | M |
Token ID | 44 |
Feature activation | -6.24e-02 |
Pos logit contributions | |
between | +0.114 |
Gaw | +0.105 |
undertaking | +0.096 |
pty | +0.091 |
abus | +0.089 |
Neg logit contributions | |
united | -0.135 |
CTV | -0.124 |
additive | -0.104 |
iod | -0.102 |
SHARE | -0.093 |
Token | anners |
Token ID | 15672 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
united | +0.048 |
CTV | +0.043 |
additive | +0.035 |
iod | +0.034 |
SHARE | +0.030 |
Neg logit contributions | |
between | -0.056 |
Gaw | -0.053 |
undertaking | -0.049 |
pty | -0.047 |
abus | -0.046 |
Token | - |
Token ID | 532 |
Feature activation | -3.95e-02 |
Pos logit contributions | |
united | +0.216 |
CTV | +0.195 |
additive | +0.158 |
iod | +0.155 |
SHARE | +0.139 |
Neg logit contributions | |
between | -0.232 |
Gaw | -0.217 |
undertaking | -0.200 |
pty | -0.191 |
abus | -0.189 |
Token | house |
Token ID | 2156 |
Feature activation | -7.40e-03 |
Pos logit contributions | |
united | +0.087 |
CTV | +0.080 |
additive | +0.067 |
iod | +0.065 |
SHARE | +0.059 |
Neg logit contributions | |
between | -0.074 |
Gaw | -0.069 |
undertaking | -0.062 |
pty | -0.060 |
abus | -0.059 |
Token | , |
Token ID | 11 |
Feature activation | -2.00e-02 |
Pos logit contributions | |
united | +0.007 |
CTV | +0.006 |
additive | +0.005 |
iod | +0.005 |
SHARE | +0.005 |
Neg logit contributions | |
between | -0.006 |
Gaw | -0.005 |
undertaking | -0.005 |
pty | -0.004 |
abus | -0.004 |
Token | gay |
Token ID | 5650 |
Feature activation | +4.03e-03 |
Pos logit contributions | |
united | +0.018 |
CTV | +0.017 |
additive | +0.014 |
iod | +0.014 |
Bravo | +0.012 |
Neg logit contributions | |
between | -0.015 |
Gaw | -0.014 |
undertaking | -0.013 |
pty | -0.012 |
abus | -0.012 |
Token | ish |
Token ID | 680 |
Feature activation | +8.43e-02 |
Pos logit contributions | |
between | +0.003 |
Gaw | +0.003 |
undertaking | +0.003 |
pty | +0.003 |
abus | +0.003 |
Neg logit contributions | |
united | -0.003 |
CTV | -0.003 |
additive | -0.003 |
iod | -0.003 |
SHARE | -0.002 |
Token | dance |
Token ID | 9280 |
Feature activation | -2.10e-02 |
Pos logit contributions | |
between | +0.067 |
Gaw | +0.062 |
undertaking | +0.056 |
pty | +0.053 |
abus | +0.053 |
Neg logit contributions | |
united | -0.074 |
CTV | -0.068 |
additive | -0.057 |
iod | -0.056 |
SHARE | -0.050 |
Token | trou |
Token ID | 4057 |
Feature activation | +6.80e-01 |
Pos logit contributions | |
united | +0.019 |
CTV | +0.017 |
additive | +0.014 |
iod | +0.014 |
SHARE | +0.013 |
Neg logit contributions | |
between | -0.017 |
Gaw | -0.015 |
undertaking | -0.014 |
pty | -0.013 |
abus | -0.013 |
Token | pe |
Token ID | 431 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
between | +0.524 |
Gaw | +0.485 |
undertaking | +0.441 |
pty | +0.417 |
abus | +0.412 |
Neg logit contributions | |
united | -0.614 |
CTV | -0.561 |
additive | -0.468 |
iod | -0.460 |
SHARE | -0.418 |
Token | , |
Token ID | 11 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
between | +0.194 |
Gaw | +0.181 |
undertaking | +0.165 |
pty | +0.157 |
abus | +0.155 |
Neg logit contributions | |
united | -0.205 |
CTV | -0.187 |
additive | -0.154 |
iod | -0.152 |
SHARE | -0.136 |
Token | and |
Token ID | 290 |
Feature activation | -2.87e-02 |
Pos logit contributions | |
united | +0.010 |
CTV | +0.009 |
additive | +0.008 |
iod | +0.007 |
SHARE | +0.007 |
Neg logit contributions | |
between | -0.009 |
Gaw | -0.008 |
undertaking | -0.007 |
pty | -0.007 |
abus | -0.007 |
Token | foam |
Token ID | 19828 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
united | +0.026 |
CTV | +0.024 |
additive | +0.020 |
iod | +0.020 |
SHARE | +0.018 |
Neg logit contributions | |
between | -0.022 |
Gaw | -0.020 |
undertaking | -0.018 |
pty | -0.018 |
abus | -0.017 |
Token | parties |
Token ID | 4671 |
Feature activation | +5.81e-02 |
Pos logit contributions | |
between | +0.094 |
Gaw | +0.087 |
undertaking | +0.079 |
pty | +0.075 |
abus | +0.074 |
Neg logit contributions | |
united | -0.110 |
CTV | -0.101 |
additive | -0.084 |
iod | -0.083 |
SHARE | -0.075 |
Token | er |
Token ID | 263 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
between | +0.223 |
Gaw | +0.204 |
undertaking | +0.183 |
pty | +0.174 |
abus | +0.171 |
Neg logit contributions | |
united | -0.304 |
CTV | -0.280 |
additive | -0.237 |
iod | -0.234 |
SHARE | -0.214 |
Token | magnet |
Token ID | 19972 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
between | +0.098 |
Gaw | +0.091 |
undertaking | +0.084 |
pty | +0.080 |
abus | +0.079 |
Neg logit contributions | |
united | -0.094 |
CTV | -0.085 |
additive | -0.069 |
iod | -0.068 |
SHARE | -0.062 |
Token | ? |
Token ID | 30 |
Feature activation | -3.67e-02 |
Pos logit contributions | |
united | +0.118 |
CTV | +0.107 |
additive | +0.085 |
iod | +0.084 |
SHARE | +0.073 |
Neg logit contributions | |
between | -0.144 |
Gaw | -0.135 |
undertaking | -0.125 |
pty | -0.120 |
abus | -0.119 |
Token |
|
Token ID | 198 |
Feature activation | +3.25e-02 |
Pos logit contributions | |
united | +0.034 |
CTV | +0.031 |
additive | +0.026 |
iod | +0.026 |
SHARE | +0.023 |
Neg logit contributions | |
between | -0.027 |
Gaw | -0.025 |
undertaking | -0.023 |
pty | -0.022 |
abus | -0.021 |
Token |
|
Token ID | 198 |
Feature activation | +8.10e-03 |
Pos logit contributions | |
between | +0.024 |
Gaw | +0.023 |
undertaking | +0.020 |
pty | +0.019 |
abus | +0.019 |
Neg logit contributions | |
united | -0.030 |
CTV | -0.028 |
additive | -0.023 |
iod | -0.023 |
SHARE | -0.021 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | +6.78e-01 |
Pos logit contributions | |
between | +0.002 |
Gaw | +0.002 |
undertaking | +0.001 |
pty | +0.001 |
devices | +0.001 |
Neg logit contributions | |
united | -0.011 |
CTV | -0.011 |
additive | -0.010 |
iod | -0.010 |
SHARE | -0.009 |
Token | : |
Token ID | 25 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
between | +0.702 |
Gaw | +0.657 |
undertaking | +0.612 |
pty | +0.593 |
abus | +0.585 |
Neg logit contributions | |
united | -0.434 |
CTV | -0.383 |
additive | -0.294 |
iod | -0.290 |
SHARE | -0.241 |
Token | hey |
Token ID | 17207 |
Feature activation | +4.32e-02 |
Pos logit contributions | |
united | +0.275 |
CTV | +0.252 |
additive | +0.211 |
iod | +0.208 |
Bravo | +0.188 |
Neg logit contributions | |
between | -0.232 |
Gaw | -0.214 |
undertaking | -0.194 |
pty | -0.185 |
abus | -0.182 |
Token | _ |
Token ID | 62 |
Feature activation | +5.11e-02 |
Pos logit contributions | |
between | +0.032 |
Gaw | +0.030 |
undertaking | +0.027 |
pty | +0.026 |
devices | +0.025 |
Neg logit contributions | |
united | -0.040 |
CTV | -0.037 |
additive | -0.031 |
iod | -0.030 |
SHARE | -0.027 |
Token | ler |
Token ID | 1754 |
Feature activation | +8.47e-02 |
Pos logit contributions | |
between | +0.037 |
Gaw | +0.035 |
undertaking | +0.032 |
pty | +0.030 |
devices | +0.029 |
Neg logit contributions | |
united | -0.048 |
CTV | -0.044 |
additive | -0.037 |
iod | -0.036 |
SHARE | -0.033 |
Token | oy |
Token ID | 726 |
Feature activation | +9.50e-02 |
Pos logit contributions | |
between | +0.064 |
Gaw | +0.059 |
undertaking | +0.054 |
pty | +0.051 |
abus | +0.050 |
Neg logit contributions | |
united | -0.078 |
CTV | -0.071 |
additive | -0.060 |
iod | -0.059 |
SHARE | -0.053 |
Token | was |
Token ID | 373 |
Feature activation | -3.06e-02 |
Pos logit contributions | |
united | +0.001 |
CTV | +0.001 |
additive | +0.001 |
iod | +0.001 |
SHARE | +0.001 |
Neg logit contributions | |
between | -0.001 |
Gaw | -0.001 |
undertaking | -0.001 |
pty | -0.001 |
abus | -0.001 |
Token | eaten |
Token ID | 17065 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
united | +0.027 |
CTV | +0.024 |
additive | +0.020 |
iod | +0.020 |
SHARE | +0.018 |
Neg logit contributions | |
between | -0.024 |
Gaw | -0.023 |
undertaking | -0.020 |
pty | -0.020 |
abus | -0.020 |
Token | by |
Token ID | 416 |
Feature activation | -2.28e-02 |
Pos logit contributions | |
between | +0.150 |
Gaw | +0.140 |
undertaking | +0.128 |
pty | +0.123 |
abus | +0.121 |
Neg logit contributions | |
united | -0.149 |
CTV | -0.136 |
additive | -0.112 |
iod | -0.110 |
SHARE | -0.098 |
Token | a |
Token ID | 257 |
Feature activation | +8.86e-02 |
Pos logit contributions | |
united | +0.022 |
CTV | +0.020 |
additive | +0.017 |
iod | +0.017 |
SHARE | +0.016 |
Neg logit contributions | |
between | -0.016 |
Gaw | -0.015 |
undertaking | -0.013 |
pty | -0.012 |
abus | -0.012 |
Token | crocod |
Token ID | 37565 |
Feature activation | +5.95e-01 |
Pos logit contributions | |
between | +0.059 |
Gaw | +0.053 |
undertaking | +0.048 |
pty | +0.045 |
abus | +0.044 |
Neg logit contributions | |
united | -0.090 |
CTV | -0.083 |
additive | -0.071 |
iod | -0.070 |
SHARE | -0.064 |
Token | ile |
Token ID | 576 |
Feature activation | +6.75e-01 |
Pos logit contributions | |
between | +0.225 |
Gaw | +0.194 |
undertaking | +0.154 |
pty | +0.133 |
devices | +0.132 |
Neg logit contributions | |
united | -0.769 |
CTV | -0.720 |
additive | -0.642 |
iod | -0.632 |
SHARE | -0.595 |
Token | that |
Token ID | 326 |
Feature activation | +5.67e-02 |
Pos logit contributions | |
between | +0.509 |
Gaw | +0.472 |
undertaking | +0.425 |
pty | +0.406 |
abus | +0.400 |
Neg logit contributions | |
united | -0.618 |
CTV | -0.568 |
additive | -0.477 |
iod | -0.468 |
SHARE | -0.425 |
Token | was |
Token ID | 373 |
Feature activation | -2.96e-04 |
Pos logit contributions | |
between | +0.045 |
Gaw | +0.042 |
undertaking | +0.038 |
pty | +0.036 |
abus | +0.036 |
Neg logit contributions | |
united | -0.050 |
CTV | -0.045 |
additive | -0.038 |
iod | -0.037 |
SHARE | -0.033 |
Token | never |
Token ID | 1239 |
Feature activation | +5.27e-02 |
Pos logit contributions | |
united | +0.000 |
CTV | +0.000 |
additive | +0.000 |
iod | +0.000 |
SHARE | +0.000 |
Neg logit contributions | |
between | -0.000 |
Gaw | -0.000 |
undertaking | -0.000 |
pty | -0.000 |
abus | -0.000 |
Token | caught |
Token ID | 4978 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
between | +0.038 |
Gaw | +0.035 |
undertaking | +0.031 |
pty | +0.030 |
abus | +0.029 |
Neg logit contributions | |
united | -0.051 |
CTV | -0.047 |
additive | -0.039 |
iod | -0.039 |
SHARE | -0.035 |
Token | . |
Token ID | 13 |
Feature activation | +7.96e-02 |
Pos logit contributions | |
between | +0.092 |
Gaw | +0.085 |
undertaking | +0.077 |
pty | +0.074 |
abus | +0.072 |
Neg logit contributions | |
united | -0.107 |
CTV | -0.098 |
additive | -0.082 |
iod | -0.081 |
SHARE | -0.073 |
Token | 2 |
Token ID | 362 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
between | +0.000 |
Gaw | +0.000 |
undertaking | +0.000 |
pty | +0.000 |
abus | +0.000 |
Neg logit contributions | |
united | -0.000 |
CTV | -0.000 |
additive | -0.000 |
iod | -0.000 |
SHARE | -0.000 |
Token | , |
Token ID | 11 |
Feature activation | +4.15e-02 |
Pos logit contributions | |
united | +0.162 |
CTV | +0.149 |
additive | +0.124 |
iod | +0.123 |
SHARE | +0.111 |
Neg logit contributions | |
between | -0.135 |
Gaw | -0.124 |
undertaking | -0.113 |
pty | -0.107 |
abus | -0.105 |
Token | 370 |
Token ID | 20167 |
Feature activation | -8.50e-02 |
Pos logit contributions | |
between | +0.031 |
Gaw | +0.029 |
undertaking | +0.026 |
pty | +0.025 |
abus | +0.025 |
Neg logit contributions | |
united | -0.038 |
CTV | -0.035 |
additive | -0.029 |
iod | -0.029 |
SHARE | -0.026 |
Token | pound |
Token ID | 14896 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
united | +0.078 |
CTV | +0.071 |
additive | +0.060 |
iod | +0.059 |
SHARE | +0.053 |
Neg logit contributions | |
between | -0.065 |
Gaw | -0.060 |
undertaking | -0.054 |
pty | -0.051 |
abus | -0.051 |
Token | crocod |
Token ID | 37565 |
Feature activation | +5.37e-01 |
Pos logit contributions | |
united | +0.011 |
CTV | +0.010 |
additive | +0.009 |
iod | +0.009 |
Bravo | +0.008 |
Neg logit contributions | |
between | -0.009 |
Gaw | -0.008 |
undertaking | -0.007 |
pty | -0.007 |
abus | -0.007 |
Token | ile |
Token ID | 576 |
Feature activation | +6.68e-01 |
Pos logit contributions | |
between | +0.209 |
Gaw | +0.182 |
undertaking | +0.144 |
devices | +0.127 |
pty | +0.124 |
Neg logit contributions | |
united | -0.686 |
CTV | -0.643 |
additive | -0.575 |
iod | -0.563 |
SHARE | -0.530 |
Token | . |
Token ID | 13 |
Feature activation | +7.16e-02 |
Pos logit contributions | |
between | +0.517 |
Gaw | +0.480 |
undertaking | +0.434 |
pty | +0.415 |
abus | +0.409 |
Neg logit contributions | |
united | -0.598 |
CTV | -0.549 |
additive | -0.458 |
iod | -0.451 |
SHARE | -0.408 |
Token | Two |
Token ID | 4930 |
Feature activation | -5.18e-02 |
Pos logit contributions | |
between | +0.056 |
Gaw | +0.051 |
undertaking | +0.047 |
pty | +0.045 |
abus | +0.044 |
Neg logit contributions | |
united | -0.064 |
CTV | -0.059 |
additive | -0.049 |
iod | -0.048 |
SHARE | -0.044 |
Token | years |
Token ID | 812 |
Feature activation | -3.18e-02 |
Pos logit contributions | |
united | +0.048 |
CTV | +0.044 |
additive | +0.037 |
iod | +0.036 |
SHARE | +0.033 |
Neg logit contributions | |
between | -0.039 |
Gaw | -0.036 |
undertaking | -0.032 |
pty | -0.031 |
abus | -0.031 |
Token | ago |
Token ID | 2084 |
Feature activation | +5.37e-02 |
Pos logit contributions | |
united | +0.034 |
CTV | +0.032 |
additive | +0.027 |
iod | +0.027 |
SHARE | +0.025 |
Neg logit contributions | |
between | -0.019 |
Gaw | -0.018 |
undertaking | -0.015 |
pty | -0.014 |
abus | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | -2.07e-02 |
Pos logit contributions | |
between | +0.045 |
Gaw | +0.042 |
undertaking | +0.038 |
pty | +0.037 |
abus | +0.036 |
Neg logit contributions | |
united | -0.045 |
CTV | -0.041 |
additive | -0.034 |
iod | -0.033 |
SHARE | -0.030 |
Token | i |
Token ID | 72 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
united | +0.202 |
CTV | +0.186 |
additive | +0.158 |
iod | +0.155 |
SHARE | +0.143 |
Neg logit contributions | |
between | -0.137 |
Gaw | -0.126 |
undertaking | -0.112 |
pty | -0.106 |
abus | -0.104 |
Token | Spe |
Token ID | 2531 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
between | +0.115 |
Gaw | +0.107 |
undertaking | +0.097 |
pty | +0.093 |
abus | +0.091 |
Neg logit contributions | |
united | -0.127 |
CTV | -0.116 |
additive | -0.096 |
iod | -0.095 |
SHARE | -0.085 |
Token | lling |
Token ID | 2680 |
Feature activation | +1.79e-03 |
Pos logit contributions | |
united | +0.127 |
CTV | +0.115 |
additive | +0.095 |
iod | +0.093 |
SHARE | +0.083 |
Neg logit contributions | |
between | -0.121 |
Gaw | -0.113 |
undertaking | -0.103 |
pty | -0.098 |
abus | -0.097 |
Token | was |
Token ID | 373 |
Feature activation | -8.09e-03 |
Pos logit contributions | |
between | +0.001 |
Gaw | +0.001 |
undertaking | +0.001 |
pty | +0.001 |
abus | +0.001 |
Neg logit contributions | |
united | -0.002 |
CTV | -0.001 |
additive | -0.001 |
iod | -0.001 |
SHARE | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | +6.95e-02 |
Pos logit contributions | |
united | +0.007 |
CTV | +0.007 |
additive | +0.006 |
iod | +0.005 |
SHARE | +0.005 |
Neg logit contributions | |
between | -0.006 |
Gaw | -0.006 |
undertaking | -0.005 |
pty | -0.005 |
abus | -0.005 |
Token | trou |
Token ID | 4057 |
Feature activation | +6.65e-01 |
Pos logit contributions | |
between | +0.056 |
Gaw | +0.052 |
undertaking | +0.048 |
pty | +0.046 |
abus | +0.045 |
Neg logit contributions | |
united | -0.060 |
CTV | -0.055 |
additive | -0.045 |
iod | -0.044 |
SHARE | -0.040 |
Token | per |
Token ID | 525 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
between | +0.508 |
Gaw | +0.472 |
undertaking | +0.431 |
pty | +0.406 |
abus | +0.401 |
Neg logit contributions | |
united | -0.603 |
CTV | -0.550 |
additive | -0.460 |
iod | -0.452 |
SHARE | -0.409 |
Token | and |
Token ID | 290 |
Feature activation | -3.27e-02 |
Pos logit contributions | |
united | +0.116 |
CTV | +0.106 |
additive | +0.089 |
iod | +0.087 |
SHARE | +0.079 |
Neg logit contributions | |
between | -0.097 |
Gaw | -0.090 |
undertaking | -0.081 |
pty | -0.078 |
abus | -0.077 |
Token | stuck |
Token ID | 7819 |
Feature activation | -7.05e-02 |
Pos logit contributions | |
united | +0.029 |
CTV | +0.027 |
additive | +0.022 |
iod | +0.022 |
SHARE | +0.020 |
Neg logit contributions | |
between | -0.026 |
Gaw | -0.024 |
undertaking | -0.022 |
pty | -0.021 |
abus | -0.020 |
Token | through |
Token ID | 832 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
united | +0.059 |
CTV | +0.053 |
additive | +0.044 |
iod | +0.043 |
Bravo | +0.039 |
Neg logit contributions | |
between | -0.059 |
Gaw | -0.055 |
undertaking | -0.050 |
pty | -0.048 |
abus | -0.048 |
Token | her |
Token ID | 607 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
united | +0.107 |
CTV | +0.098 |
additive | +0.082 |
iod | +0.080 |
Bravo | +0.073 |
Neg logit contributions | |
between | -0.094 |
Gaw | -0.087 |
undertaking | -0.079 |
pty | -0.076 |
abus | -0.075 |
Token | Song |
Token ID | 10940 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
between | +0.016 |
Gaw | +0.015 |
undertaking | +0.013 |
pty | +0.013 |
devices | +0.012 |
Neg logit contributions | |
united | -0.020 |
CTV | -0.018 |
additive | -0.015 |
iod | -0.015 |
Bravo | -0.014 |
Token | - |
Token ID | 12 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
between | +0.130 |
Gaw | +0.118 |
undertaking | +0.106 |
pty | +0.100 |
devices | +0.097 |
Neg logit contributions | |
united | -0.195 |
CTV | -0.180 |
additive | -0.153 |
iod | -0.151 |
Bravo | -0.140 |
Token | B |
Token ID | 33 |
Feature activation | -6.55e-02 |
Pos logit contributions | |
between | +0.125 |
Gaw | +0.116 |
undertaking | +0.106 |
pty | +0.101 |
abus | +0.099 |
Neg logit contributions | |
united | -0.139 |
CTV | -0.127 |
additive | -0.104 |
iod | -0.103 |
SHARE | -0.094 |
Token | obs |
Token ID | 8158 |
Feature activation | +7.27e-02 |
Pos logit contributions | |
united | +0.060 |
CTV | +0.055 |
additive | +0.046 |
iod | +0.045 |
SHARE | +0.041 |
Neg logit contributions | |
between | -0.049 |
Gaw | -0.046 |
undertaking | -0.041 |
pty | -0.039 |
abus | -0.039 |
Token | To |
Token ID | 1675 |
Feature activation | +1.93e-02 |
Pos logit contributions | |
between | +0.056 |
Gaw | +0.052 |
undertaking | +0.047 |
pty | +0.045 |
abus | +0.044 |
Neg logit contributions | |
united | -0.066 |
CTV | -0.060 |
additive | -0.050 |
iod | -0.050 |
SHARE | -0.045 |
Token | ilet |
Token ID | 41550 |
Feature activation | +6.58e-01 |
Pos logit contributions | |
between | +0.015 |
Gaw | +0.013 |
undertaking | +0.012 |
pty | +0.012 |
abus | +0.011 |
Neg logit contributions | |
united | -0.018 |
CTV | -0.016 |
additive | -0.014 |
iod | -0.013 |
SHARE | -0.012 |
Token | - |
Token ID | 12 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
between | +0.509 |
Gaw | +0.468 |
undertaking | +0.432 |
pty | +0.407 |
abus | +0.402 |
Neg logit contributions | |
united | -0.591 |
CTV | -0.540 |
additive | -0.450 |
iod | -0.441 |
Bravo | -0.406 |
Token | A |
Token ID | 32 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
between | +0.124 |
Gaw | +0.116 |
undertaking | +0.106 |
pty | +0.100 |
abus | +0.099 |
Neg logit contributions | |
united | -0.137 |
CTV | -0.125 |
additive | -0.103 |
iod | -0.101 |
SHARE | -0.092 |
Token | J |
Token ID | 41 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
between | +0.135 |
Gaw | +0.125 |
undertaking | +0.114 |
pty | +0.108 |
devices | +0.106 |
Neg logit contributions | |
united | -0.159 |
CTV | -0.145 |
additive | -0.121 |
iod | -0.119 |
Bravo | -0.108 |
Token | Po |
Token ID | 7695 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
united | +0.164 |
CTV | +0.150 |
additive | +0.125 |
iod | +0.123 |
Bravo | +0.112 |
Neg logit contributions | |
between | -0.138 |
Gaw | -0.127 |
undertaking | -0.116 |
pty | -0.110 |
abus | -0.108 |
Token | opy |
Token ID | 11081 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
between | +0.096 |
Gaw | +0.088 |
undertaking | +0.080 |
pty | +0.075 |
abus | +0.074 |
Neg logit contributions | |
united | -0.127 |
CTV | -0.117 |
additive | -0.098 |
iod | -0.097 |
Bravo | -0.089 |
Token | that |
Token ID | 326 |
Feature activation | +7.21e-02 |
Pos logit contributions | |
between | +0.001 |
Gaw | +0.001 |
undertaking | +0.000 |
pty | +0.000 |
abus | +0.000 |
Neg logit contributions | |
united | -0.001 |
CTV | -0.001 |
additive | -0.001 |
iod | -0.001 |
Bravo | -0.001 |
Token | they |
Token ID | 484 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
between | +0.052 |
Gaw | +0.048 |
undertaking | +0.043 |
pty | +0.042 |
abus | +0.041 |
Neg logit contributions | |
united | -0.068 |
CTV | -0.062 |
additive | -0.053 |
iod | -0.052 |
SHARE | -0.047 |
Token | saw |
Token ID | 2497 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
united | +0.104 |
CTV | +0.095 |
additive | +0.079 |
iod | +0.078 |
SHARE | +0.071 |
Neg logit contributions | |
between | -0.092 |
Gaw | -0.085 |
undertaking | -0.077 |
pty | -0.073 |
abus | -0.072 |
Token | a |
Token ID | 257 |
Feature activation | +9.88e-02 |
Pos logit contributions | |
between | +0.071 |
Gaw | +0.066 |
undertaking | +0.059 |
pty | +0.056 |
abus | +0.055 |
Neg logit contributions | |
united | -0.097 |
CTV | -0.090 |
additive | -0.077 |
iod | -0.076 |
SHARE | -0.069 |
Token | crocod |
Token ID | 37565 |
Feature activation | +6.01e-01 |
Pos logit contributions | |
between | +0.070 |
Gaw | +0.064 |
undertaking | +0.058 |
pty | +0.055 |
abus | +0.054 |
Neg logit contributions | |
united | -0.095 |
CTV | -0.088 |
additive | -0.074 |
iod | -0.073 |
Bravo | -0.067 |
Token | ile |
Token ID | 576 |
Feature activation | +6.47e-01 |
Pos logit contributions | |
between | +0.232 |
Gaw | +0.200 |
undertaking | +0.157 |
devices | +0.139 |
pty | +0.138 |
Neg logit contributions | |
united | -0.772 |
CTV | -0.722 |
additive | -0.645 |
iod | -0.635 |
SHARE | -0.596 |
Token | kill |
Token ID | 1494 |
Feature activation | -5.69e-02 |
Pos logit contributions | |
between | +0.483 |
Gaw | +0.448 |
undertaking | +0.403 |
pty | +0.385 |
abus | +0.379 |
Neg logit contributions | |
united | -0.597 |
CTV | -0.548 |
additive | -0.461 |
iod | -0.454 |
SHARE | -0.412 |
Token | a |
Token ID | 257 |
Feature activation | +8.19e-02 |
Pos logit contributions | |
united | +0.055 |
CTV | +0.050 |
additive | +0.043 |
iod | +0.042 |
SHARE | +0.038 |
Neg logit contributions | |
between | -0.040 |
Gaw | -0.037 |
undertaking | -0.033 |
pty | -0.032 |
abus | -0.031 |
Token | water |
Token ID | 1660 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
between | +0.064 |
Gaw | +0.059 |
undertaking | +0.054 |
pty | +0.052 |
abus | +0.051 |
Neg logit contributions | |
united | -0.073 |
CTV | -0.066 |
additive | -0.055 |
iod | -0.054 |
SHARE | -0.049 |
Token | buffalo |
Token ID | 45019 |
Feature activation | +4.71e-02 |
Pos logit contributions | |
between | +0.112 |
Gaw | +0.105 |
undertaking | +0.095 |
pty | +0.091 |
abus | +0.091 |
Neg logit contributions | |
united | -0.117 |
CTV | -0.106 |
additive | -0.088 |
iod | -0.086 |
SHARE | -0.077 |
Token | this |
Token ID | 428 |
Feature activation | +4.73e-03 |
Pos logit contributions | |
between | +0.036 |
Gaw | +0.033 |
undertaking | +0.030 |
pty | +0.029 |
abus | +0.028 |
Neg logit contributions | |
united | -0.043 |
CTV | -0.039 |
additive | -0.033 |
iod | -0.032 |
SHARE | -0.029 |
Token | � |
Token ID | 247 |
Feature activation | -3.89e-02 |
Pos logit contributions | |
united | +0.050 |
CTV | +0.045 |
additive | +0.037 |
iod | +0.037 |
SHARE | +0.033 |
Neg logit contributions | |
between | -0.049 |
Gaw | -0.045 |
undertaking | -0.042 |
pty | -0.040 |
abus | -0.039 |
Token | s |
Token ID | 82 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
united | +0.037 |
CTV | +0.034 |
additive | +0.029 |
iod | +0.028 |
SHARE | +0.026 |
Neg logit contributions | |
between | -0.028 |
Gaw | -0.026 |
undertaking | -0.023 |
pty | -0.022 |
abus | -0.022 |
Token | right |
Token ID | 826 |
Feature activation | -8.97e-02 |
Pos logit contributions | |
between | +0.008 |
Gaw | +0.008 |
undertaking | +0.007 |
pty | +0.006 |
abus | +0.006 |
Neg logit contributions | |
united | -0.011 |
CTV | -0.010 |
additive | -0.009 |
iod | -0.009 |
Bravo | -0.008 |
Token | in |
Token ID | 287 |
Feature activation | -1.91e-02 |
Pos logit contributions | |
united | +0.080 |
CTV | +0.073 |
additive | +0.061 |
iod | +0.060 |
SHARE | +0.055 |
Neg logit contributions | |
between | -0.070 |
Gaw | -0.065 |
undertaking | -0.059 |
pty | -0.056 |
abus | -0.055 |
Token | - |
Token ID | 12 |
Feature activation | +2.88e-02 |
Pos logit contributions | |
united | +0.019 |
CTV | +0.018 |
additive | +0.015 |
iod | +0.015 |
SHARE | +0.014 |
Neg logit contributions | |
between | -0.013 |
Gaw | -0.012 |
undertaking | -0.010 |
pty | -0.010 |
abus | -0.010 |
Token | between |
Token ID | 23395 |
Feature activation | +6.40e-01 |
Pos logit contributions | |
between | +0.021 |
Gaw | +0.020 |
undertaking | +0.018 |
pty | +0.017 |
abus | +0.017 |
Neg logit contributions | |
united | -0.027 |
CTV | -0.025 |
additive | -0.021 |
iod | -0.020 |
SHARE | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | -4.33e-02 |
Pos logit contributions | |
between | +0.490 |
Gaw | +0.455 |
undertaking | +0.410 |
pty | +0.395 |
abus | +0.392 |
Neg logit contributions | |
united | -0.578 |
CTV | -0.529 |
additive | -0.445 |
iod | -0.435 |
Bravo | -0.397 |
Token | at |
Token ID | 379 |
Feature activation | -6.51e-02 |
Pos logit contributions | |
united | +0.041 |
CTV | +0.037 |
additive | +0.032 |
iod | +0.031 |
Bravo | +0.029 |
Neg logit contributions | |
between | -0.031 |
Gaw | -0.029 |
undertaking | -0.026 |
pty | -0.025 |
abus | -0.025 |
Token | 32 |
Token ID | 3933 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
united | +0.062 |
CTV | +0.057 |
additive | +0.048 |
iod | +0.047 |
Bravo | +0.043 |
Neg logit contributions | |
between | -0.046 |
Gaw | -0.043 |
undertaking | -0.038 |
pty | -0.037 |
abus | -0.037 |
Token | %. |
Token ID | 7225 |
Feature activation | +5.89e-03 |
Pos logit contributions | |
united | +0.090 |
CTV | +0.082 |
additive | +0.067 |
iod | +0.066 |
SHARE | +0.059 |
Neg logit contributions | |
between | -0.091 |
Gaw | -0.085 |
undertaking | -0.077 |
pty | -0.074 |
abus | -0.073 |
Token | A |
Token ID | 317 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
between | +0.005 |
Gaw | +0.004 |
undertaking | +0.004 |
pty | +0.004 |
abus | +0.004 |
Neg logit contributions | |
united | -0.005 |
CTV | -0.005 |
additive | -0.004 |
iod | -0.004 |
Bravo | -0.004 |
Token | it |
Token ID | 340 |
Feature activation | -4.13e-02 |
Pos logit contributions | |
united | +0.003 |
CTV | +0.003 |
additive | +0.002 |
iod | +0.002 |
SHARE | +0.002 |
Neg logit contributions | |
between | -0.003 |
Gaw | -0.003 |
undertaking | -0.003 |
pty | -0.003 |
abus | -0.002 |
Token | 's |
Token ID | 338 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
united | +0.037 |
CTV | +0.034 |
additive | +0.028 |
iod | +0.028 |
SHARE | +0.025 |
Neg logit contributions | |
between | -0.032 |
Gaw | -0.030 |
undertaking | -0.027 |
pty | -0.026 |
abus | -0.025 |
Token | the |
Token ID | 262 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
united | +0.128 |
CTV | +0.118 |
additive | +0.099 |
iod | +0.097 |
SHARE | +0.088 |
Neg logit contributions | |
between | -0.106 |
Gaw | -0.098 |
undertaking | -0.088 |
pty | -0.085 |
abus | -0.083 |
Token | largest |
Token ID | 4387 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
between | +0.007 |
Gaw | +0.006 |
undertaking | +0.006 |
pty | +0.005 |
abus | +0.005 |
Neg logit contributions | |
united | -0.010 |
CTV | -0.009 |
additive | -0.008 |
iod | -0.008 |
Bravo | -0.007 |
Token | crocod |
Token ID | 37565 |
Feature activation | +5.64e-01 |
Pos logit contributions | |
between | +0.147 |
Gaw | +0.134 |
undertaking | +0.116 |
pty | +0.111 |
abus | +0.109 |
Neg logit contributions | |
united | -0.249 |
CTV | -0.231 |
additive | -0.201 |
iod | -0.197 |
Bravo | -0.182 |
Token | ile |
Token ID | 576 |
Feature activation | +6.39e-01 |
Pos logit contributions | |
between | +0.216 |
Gaw | +0.187 |
undertaking | +0.148 |
pty | +0.128 |
devices | +0.126 |
Neg logit contributions | |
united | -0.726 |
CTV | -0.680 |
additive | -0.605 |
iod | -0.597 |
SHARE | -0.561 |
Token | ever |
Token ID | 1683 |
Feature activation | -7.58e-03 |
Pos logit contributions | |
between | +0.480 |
Gaw | +0.445 |
undertaking | +0.398 |
pty | +0.383 |
abus | +0.379 |
Neg logit contributions | |
united | -0.584 |
CTV | -0.537 |
additive | -0.455 |
iod | -0.444 |
Bravo | -0.404 |
Token | to |
Token ID | 284 |
Feature activation | +3.77e-02 |
Pos logit contributions | |
united | +0.007 |
CTV | +0.007 |
additive | +0.006 |
iod | +0.006 |
Bravo | +0.005 |
Neg logit contributions | |
between | -0.005 |
Gaw | -0.005 |
undertaking | -0.004 |
pty | -0.004 |
abus | -0.004 |
Token | be |
Token ID | 307 |
Feature activation | +8.30e-02 |
Pos logit contributions | |
between | +0.029 |
Gaw | +0.027 |
undertaking | +0.024 |
pty | +0.023 |
abus | +0.023 |
Neg logit contributions | |
united | -0.034 |
CTV | -0.031 |
additive | -0.026 |
iod | -0.026 |
SHARE | -0.023 |
Token | taken |
Token ID | 2077 |
Feature activation | +5.16e-02 |
Pos logit contributions | |
between | +0.059 |
Gaw | +0.054 |
undertaking | +0.048 |
pty | +0.046 |
abus | +0.045 |
Neg logit contributions | |
united | -0.080 |
CTV | -0.074 |
additive | -0.062 |
iod | -0.061 |
SHARE | -0.056 |
Token | alive |
Token ID | 6776 |
Feature activation | +3.10e-02 |
Pos logit contributions | |
between | +0.045 |
Gaw | +0.042 |
undertaking | +0.039 |
pty | +0.037 |
abus | +0.037 |
Neg logit contributions | |
united | -0.041 |
CTV | -0.037 |
additive | -0.030 |
iod | -0.030 |
SHARE | -0.026 |
Token | are |
Token ID | 389 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
united | +0.124 |
CTV | +0.113 |
additive | +0.093 |
iod | +0.091 |
SHARE | +0.082 |
Neg logit contributions | |
between | -0.121 |
Gaw | -0.113 |
undertaking | -0.103 |
pty | -0.099 |
abus | -0.097 |
Token | Here |
Token ID | 3423 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
united | +0.080 |
CTV | +0.071 |
additive | +0.055 |
iod | +0.054 |
SHARE | +0.046 |
Neg logit contributions | |
between | -0.117 |
Gaw | -0.110 |
undertaking | -0.102 |
pty | -0.099 |
abus | -0.097 |
Token | .... |
Token ID | 1106 |
Feature activation | -2.41e-03 |
Pos logit contributions | |
united | +0.208 |
CTV | +0.188 |
additive | +0.153 |
iod | +0.151 |
SHARE | +0.134 |
Neg logit contributions | |
between | -0.217 |
Gaw | -0.204 |
undertaking | -0.187 |
pty | -0.180 |
abus | -0.176 |
Token |
|
Token ID | 198 |
Feature activation | -1.04e-03 |
Pos logit contributions | |
united | +0.002 |
CTV | +0.002 |
additive | +0.002 |
iod | +0.002 |
SHARE | +0.002 |
Neg logit contributions | |
between | -0.002 |
Gaw | -0.002 |
undertaking | -0.002 |
pty | -0.001 |
abus | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -2.01e-02 |
Pos logit contributions | |
united | +0.001 |
CTV | +0.001 |
additive | +0.001 |
iod | +0.001 |
SHARE | +0.001 |
Neg logit contributions | |
between | -0.001 |
Gaw | -0.001 |
undertaking | -0.001 |
pty | -0.001 |
abus | -0.001 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | +6.30e-01 |
Pos logit contributions | |
united | +0.029 |
CTV | +0.027 |
additive | +0.024 |
iod | +0.024 |
SHARE | +0.023 |
Neg logit contributions | |
between | -0.005 |
Gaw | -0.004 |
undertaking | -0.003 |
pty | -0.002 |
abus | -0.002 |
Token | : |
Token ID | 25 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
between | +0.652 |
Gaw | +0.611 |
undertaking | +0.569 |
pty | +0.551 |
abus | +0.544 |
Neg logit contributions | |
united | -0.402 |
CTV | -0.354 |
additive | -0.272 |
iod | -0.268 |
SHARE | -0.222 |
Token | SAS |
Token ID | 35516 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
united | +0.300 |
CTV | +0.275 |
additive | +0.231 |
iod | +0.228 |
Bravo | +0.206 |
Neg logit contributions | |
between | -0.249 |
Gaw | -0.229 |
undertaking | -0.208 |
pty | -0.198 |
abus | -0.195 |
Token | K |
Token ID | 42 |
Feature activation | -8.40e-02 |
Pos logit contributions | |
between | +0.108 |
Gaw | +0.101 |
undertaking | +0.092 |
pty | +0.087 |
abus | +0.086 |
Neg logit contributions | |
united | -0.119 |
CTV | -0.109 |
additive | -0.090 |
iod | -0.089 |
SHARE | -0.080 |
Token | ATCH |
Token ID | 11417 |
Feature activation | -5.43e-02 |
Pos logit contributions | |
united | +0.072 |
CTV | +0.066 |
additive | +0.054 |
iod | +0.053 |
SHARE | +0.048 |
Neg logit contributions | |
between | -0.068 |
Gaw | -0.064 |
undertaking | -0.058 |
pty | -0.055 |
devices | -0.054 |
Token | EW |
Token ID | 6217 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
united | +0.047 |
CTV | +0.043 |
additive | +0.035 |
iod | +0.035 |
SHARE | +0.031 |
Neg logit contributions | |
between | -0.044 |
Gaw | -0.041 |
undertaking | -0.037 |
pty | -0.036 |
devices | -0.035 |
Token | one |
Token ID | 530 |
Feature activation | +3.71e-02 |
Pos logit contributions | |
between | +0.044 |
Gaw | +0.041 |
undertaking | +0.037 |
pty | +0.035 |
abus | +0.035 |
Neg logit contributions | |
united | -0.053 |
CTV | -0.049 |
additive | -0.041 |
iod | -0.040 |
SHARE | -0.037 |
Token | element |
Token ID | 5002 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
between | +0.027 |
Gaw | +0.025 |
undertaking | +0.023 |
pty | +0.022 |
abus | +0.022 |
Neg logit contributions | |
united | -0.035 |
CTV | -0.032 |
additive | -0.027 |
iod | -0.026 |
SHARE | -0.024 |
Token | of |
Token ID | 286 |
Feature activation | +2.50e-02 |
Pos logit contributions | |
between | +0.118 |
Gaw | +0.109 |
undertaking | +0.097 |
pty | +0.093 |
abus | +0.093 |
Neg logit contributions | |
united | -0.147 |
CTV | -0.135 |
additive | -0.113 |
iod | -0.111 |
Bravo | -0.101 |
Token | a |
Token ID | 257 |
Feature activation | +7.55e-02 |
Pos logit contributions | |
between | +0.019 |
Gaw | +0.017 |
undertaking | +0.015 |
pty | +0.015 |
abus | +0.015 |
Neg logit contributions | |
united | -0.023 |
CTV | -0.021 |
additive | -0.018 |
iod | -0.018 |
Bravo | -0.016 |
Token | tri |
Token ID | 1333 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
between | +0.060 |
Gaw | +0.055 |
undertaking | +0.050 |
pty | +0.048 |
abus | +0.047 |
Neg logit contributions | |
united | -0.067 |
CTV | -0.061 |
additive | -0.051 |
iod | -0.050 |
SHARE | -0.045 |
Token | pty |
Token ID | 5835 |
Feature activation | +6.23e-01 |
Pos logit contributions | |
between | +0.095 |
Gaw | +0.087 |
undertaking | +0.078 |
pty | +0.072 |
abus | +0.072 |
Neg logit contributions | |
united | -0.141 |
CTV | -0.130 |
additive | -0.111 |
iod | -0.109 |
SHARE | -0.100 |
Token | ch |
Token ID | 354 |
Feature activation | +4.51e-02 |
Pos logit contributions | |
between | +0.400 |
Gaw | +0.365 |
undertaking | +0.321 |
abus | +0.299 |
devices | +0.299 |
Neg logit contributions | |
united | -0.644 |
CTV | -0.590 |
additive | -0.509 |
iod | -0.502 |
SHARE | -0.462 |
Token | called |
Token ID | 1444 |
Feature activation | -8.19e-02 |
Pos logit contributions | |
between | +0.033 |
Gaw | +0.030 |
undertaking | +0.027 |
pty | +0.026 |
abus | +0.026 |
Neg logit contributions | |
united | -0.042 |
CTV | -0.039 |
additive | -0.033 |
iod | -0.032 |
SHARE | -0.030 |
Token | Echo |
Token ID | 21455 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
united | +0.077 |
CTV | +0.070 |
additive | +0.059 |
iod | +0.058 |
SHARE | +0.053 |
Neg logit contributions | |
between | -0.060 |
Gaw | -0.055 |
undertaking | -0.050 |
pty | -0.048 |
abus | -0.047 |
Token | that |
Token ID | 326 |
Feature activation | +7.85e-02 |
Pos logit contributions | |
united | +0.111 |
CTV | +0.102 |
additive | +0.085 |
iod | +0.083 |
Bravo | +0.077 |
Neg logit contributions | |
between | -0.089 |
Gaw | -0.082 |
undertaking | -0.074 |
pty | -0.070 |
abus | -0.069 |
Token | Indigenous |
Token ID | 24033 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
between | +0.057 |
Gaw | +0.053 |
undertaking | +0.047 |
pty | +0.045 |
abus | +0.044 |
Neg logit contributions | |
united | -0.074 |
CTV | -0.068 |
additive | -0.057 |
iod | -0.057 |
SHARE | -0.052 |
Token | 45 |
Token ID | 2231 |
Feature activation | +1.46e-02 |
Pos logit contributions | |
between | +0.036 |
Gaw | +0.033 |
undertaking | +0.030 |
pty | +0.029 |
abus | +0.028 |
Neg logit contributions | |
united | -0.043 |
CTV | -0.039 |
additive | -0.033 |
iod | -0.032 |
SHARE | -0.029 |
Token | 366 |
Token ID | 44856 |
Feature activation | +3.67e-02 |
Pos logit contributions | |
between | +0.013 |
Gaw | +0.012 |
undertaking | +0.011 |
pty | +0.011 |
abus | +0.010 |
Neg logit contributions | |
united | -0.012 |
CTV | -0.011 |
additive | -0.009 |
iod | -0.008 |
Bravo | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
between | +0.029 |
Gaw | +0.027 |
undertaking | +0.024 |
pty | +0.023 |
abus | +0.023 |
Neg logit contributions | |
united | -0.033 |
CTV | -0.030 |
additive | -0.025 |
iod | -0.024 |
SHARE | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
between | +0.192 |
Gaw | +0.177 |
undertaking | +0.161 |
pty | +0.153 |
abus | +0.151 |
Neg logit contributions | |
united | -0.229 |
CTV | -0.210 |
additive | -0.175 |
iod | -0.173 |
SHARE | -0.157 |
Token |
|
Token ID | 198 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
between | +0.144 |
Gaw | +0.133 |
undertaking | +0.120 |
pty | +0.114 |
abus | +0.112 |
Neg logit contributions | |
united | -0.179 |
CTV | -0.164 |
additive | -0.138 |
iod | -0.136 |
SHARE | -0.124 |
Token | Topics |
Token ID | 25902 |
Feature activation | +6.18e-01 |
Pos logit contributions | |
between | +0.077 |
Gaw | +0.069 |
undertaking | +0.057 |
pty | +0.050 |
abus | +0.049 |
Neg logit contributions | |
united | -0.222 |
CTV | -0.209 |
additive | -0.182 |
iod | -0.180 |
SHARE | -0.171 |
Token | : |
Token ID | 25 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
between | +0.636 |
Gaw | +0.595 |
undertaking | +0.556 |
pty | +0.536 |
abus | +0.530 |
Neg logit contributions | |
united | -0.397 |
CTV | -0.354 |
additive | -0.271 |
iod | -0.267 |
SHARE | -0.224 |
Token | community |
Token ID | 2055 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
united | +0.010 |
CTV | +0.009 |
additive | +0.007 |
iod | +0.007 |
SHARE | +0.006 |
Neg logit contributions | |
between | -0.012 |
Gaw | -0.011 |
undertaking | -0.010 |
pty | -0.010 |
abus | -0.010 |
Token | - |
Token ID | 12 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
united | +0.107 |
CTV | +0.099 |
additive | +0.084 |
iod | +0.083 |
SHARE | +0.076 |
Neg logit contributions | |
between | -0.077 |
Gaw | -0.070 |
undertaking | -0.063 |
pty | -0.059 |
abus | -0.058 |
Token | and |
Token ID | 392 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
between | +0.167 |
Gaw | +0.152 |
undertaking | +0.140 |
pty | +0.133 |
devices | +0.131 |
Neg logit contributions | |
united | -0.183 |
CTV | -0.171 |
additive | -0.142 |
iod | -0.139 |
SHARE | -0.127 |
Token | - |
Token ID | 12 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
between | +0.092 |
Gaw | +0.084 |
undertaking | +0.076 |
pty | +0.071 |
abus | +0.070 |
Neg logit contributions | |
united | -0.132 |
CTV | -0.122 |
additive | -0.103 |
iod | -0.102 |
SHARE | -0.094 |
Token | Un |
Token ID | 791 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
united | +0.209 |
CTV | +0.190 |
additive | +0.157 |
iod | +0.154 |
SHARE | +0.138 |
Neg logit contributions | |
between | -0.202 |
Gaw | -0.188 |
undertaking | -0.172 |
pty | -0.164 |
abus | -0.162 |
Token | ilateral |
Token ID | 14796 |
Feature activation | -9.64e-02 |
Pos logit contributions | |
between | +0.009 |
Gaw | +0.008 |
undertaking | +0.008 |
pty | +0.007 |
abus | +0.007 |
Neg logit contributions | |
united | -0.011 |
CTV | -0.010 |
additive | -0.008 |
iod | -0.008 |
SHARE | -0.007 |
Token | de |
Token ID | 390 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
united | +0.087 |
CTV | +0.080 |
additive | +0.066 |
iod | +0.065 |
SHARE | +0.059 |
Neg logit contributions | |
between | -0.074 |
Gaw | -0.069 |
undertaking | -0.062 |
pty | -0.059 |
abus | -0.058 |
Token | Ind |
Token ID | 1423 |
Feature activation | +5.05e-02 |
Pos logit contributions | |
united | +0.213 |
CTV | +0.193 |
additive | +0.155 |
iod | +0.152 |
SHARE | +0.135 |
Neg logit contributions | |
between | -0.242 |
Gaw | -0.227 |
undertaking | -0.208 |
pty | -0.200 |
abus | -0.197 |
Token | epend |
Token ID | 2690 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
between | +0.045 |
Gaw | +0.042 |
undertaking | +0.039 |
pty | +0.037 |
abus | +0.037 |
Neg logit contributions | |
united | -0.039 |
CTV | -0.036 |
additive | -0.029 |
iod | -0.028 |
SHARE | -0.025 |
Token | encia |
Token ID | 29634 |
Feature activation | -7.72e-01 |
Pos logit contributions | |
united | +0.054 |
CTV | +0.041 |
additive | +0.019 |
iod | +0.018 |
SHARE | +0.007 |
Neg logit contributions | |
between | -0.216 |
Gaw | -0.207 |
undertaking | -0.196 |
pty | -0.191 |
abus | -0.189 |
Token | ) |
Token ID | 8 |
Feature activation | -7.70e-04 |
Pos logit contributions | |
united | +0.645 |
CTV | +0.586 |
additive | +0.481 |
iod | +0.473 |
SHARE | +0.424 |
Neg logit contributions | |
between | -0.646 |
Gaw | -0.602 |
undertaking | -0.550 |
pty | -0.527 |
abus | -0.519 |
Token | could |
Token ID | 714 |
Feature activation | -8.80e-02 |
Pos logit contributions | |
united | +0.001 |
CTV | +0.001 |
additive | +0.001 |
iod | +0.001 |
SHARE | +0.001 |
Neg logit contributions | |
between | -0.001 |
Gaw | -0.001 |
undertaking | -0.000 |
pty | -0.000 |
abus | -0.000 |
Token | be |
Token ID | 307 |
Feature activation | +9.94e-02 |
Pos logit contributions | |
united | +0.086 |
CTV | +0.080 |
additive | +0.068 |
iod | +0.067 |
SHARE | +0.061 |
Neg logit contributions | |
between | -0.061 |
Gaw | -0.056 |
undertaking | -0.050 |
pty | -0.047 |
abus | -0.046 |
Token | re |
Token ID | 302 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
between | +0.081 |
Gaw | +0.075 |
undertaking | +0.068 |
pty | +0.065 |
abus | +0.064 |
Neg logit contributions | |
united | -0.086 |
CTV | -0.078 |
additive | -0.064 |
iod | -0.063 |
SHARE | -0.057 |
Token | ph |
Token ID | 746 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
between | +0.011 |
Gaw | +0.010 |
undertaking | +0.009 |
pty | +0.009 |
abus | +0.009 |
Neg logit contributions | |
united | -0.014 |
CTV | -0.013 |
additive | -0.011 |
iod | -0.010 |
SHARE | -0.009 |
Token | uman |
Token ID | 3778 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
united | +0.187 |
CTV | +0.167 |
additive | +0.136 |
iod | +0.133 |
Bravo | +0.118 |
Neg logit contributions | |
between | -0.201 |
Gaw | -0.188 |
undertaking | -0.174 |
pty | -0.165 |
devices | -0.163 |
Token | and |
Token ID | 290 |
Feature activation | -9.82e-02 |
Pos logit contributions | |
united | +0.257 |
CTV | +0.235 |
additive | +0.195 |
iod | +0.191 |
SHARE | +0.172 |
Neg logit contributions | |
between | -0.237 |
Gaw | -0.220 |
undertaking | -0.200 |
pty | -0.191 |
abus | -0.188 |
Token | Saur |
Token ID | 46197 |
Feature activation | -7.24e-03 |
Pos logit contributions | |
united | +0.090 |
CTV | +0.082 |
additive | +0.069 |
iod | +0.068 |
Bravo | +0.062 |
Neg logit contributions | |
between | -0.074 |
Gaw | -0.068 |
undertaking | -0.062 |
pty | -0.059 |
abus | -0.058 |
Token | on |
Token ID | 261 |
Feature activation | -6.44e-02 |
Pos logit contributions | |
united | +0.005 |
CTV | +0.005 |
additive | +0.004 |
iod | +0.003 |
Bravo | +0.003 |
Neg logit contributions | |
between | -0.007 |
Gaw | -0.007 |
undertaking | -0.006 |
pty | -0.006 |
devices | -0.006 |
Token | kill |
Token ID | 1494 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
united | +0.056 |
CTV | +0.051 |
additive | +0.043 |
iod | +0.042 |
SHARE | +0.038 |
Neg logit contributions | |
between | -0.051 |
Gaw | -0.048 |
undertaking | -0.043 |
pty | -0.041 |
abus | -0.041 |
Token | Bor |
Token ID | 12182 |
Feature activation | -6.62e-01 |
Pos logit contributions | |
united | +0.142 |
CTV | +0.131 |
additive | +0.110 |
iod | +0.109 |
Bravo | +0.099 |
Neg logit contributions | |
between | -0.110 |
Gaw | -0.101 |
undertaking | -0.091 |
pty | -0.087 |
abus | -0.086 |
Token | om |
Token ID | 296 |
Feature activation | -4.05e-02 |
Pos logit contributions | |
united | +0.627 |
CTV | +0.575 |
additive | +0.483 |
iod | +0.477 |
Bravo | +0.435 |
Neg logit contributions | |
between | -0.478 |
Gaw | -0.441 |
undertaking | -0.399 |
pty | -0.380 |
devices | -0.370 |
Token | ir |
Token ID | 343 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
united | +0.036 |
CTV | +0.033 |
additive | +0.027 |
iod | +0.027 |
SHARE | +0.024 |
Neg logit contributions | |
between | -0.032 |
Gaw | -0.029 |
undertaking | -0.027 |
pty | -0.025 |
abus | -0.025 |
Token | and |
Token ID | 290 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
united | +0.154 |
CTV | +0.141 |
additive | +0.117 |
iod | +0.115 |
SHARE | +0.104 |
Neg logit contributions | |
between | -0.141 |
Gaw | -0.130 |
undertaking | -0.118 |
pty | -0.114 |
abus | -0.112 |
Token | capture |
Token ID | 8006 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
united | +0.108 |
CTV | +0.098 |
additive | +0.082 |
iod | +0.081 |
SHARE | +0.073 |
Neg logit contributions | |
between | -0.097 |
Gaw | -0.090 |
undertaking | -0.082 |
pty | -0.078 |
abus | -0.077 |
Token | Merry |
Token ID | 39001 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
between | +0.190 |
Gaw | +0.174 |
undertaking | +0.159 |
pty | +0.153 |
abus | +0.151 |
Neg logit contributions | |
united | -0.225 |
CTV | -0.206 |
additive | -0.172 |
iod | -0.170 |
Bravo | -0.154 |
Token | t |
Token ID | 83 |
Feature activation | -8.03e-02 |
Pos logit contributions | |
united | +0.041 |
CTV | +0.037 |
additive | +0.031 |
iod | +0.030 |
SHARE | +0.028 |
Neg logit contributions | |
between | -0.034 |
Gaw | -0.032 |
undertaking | -0.029 |
pty | -0.027 |
abus | -0.027 |
Token | even |
Token ID | 772 |
Feature activation | -2.20e-02 |
Pos logit contributions | |
united | +0.071 |
CTV | +0.065 |
additive | +0.054 |
iod | +0.053 |
SHARE | +0.048 |
Neg logit contributions | |
between | -0.063 |
Gaw | -0.059 |
undertaking | -0.053 |
pty | -0.051 |
abus | -0.051 |
Token | been |
Token ID | 587 |
Feature activation | -8.91e-02 |
Pos logit contributions | |
united | +0.019 |
CTV | +0.017 |
additive | +0.014 |
iod | +0.014 |
SHARE | +0.012 |
Neg logit contributions | |
between | -0.018 |
Gaw | -0.017 |
undertaking | -0.015 |
pty | -0.015 |
abus | -0.015 |
Token | on |
Token ID | 319 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
united | +0.074 |
CTV | +0.067 |
additive | +0.056 |
iod | +0.055 |
SHARE | +0.049 |
Neg logit contributions | |
between | -0.075 |
Gaw | -0.070 |
undertaking | -0.063 |
pty | -0.061 |
abus | -0.060 |
Token | the |
Token ID | 262 |
Feature activation | -3.65e-02 |
Pos logit contributions | |
united | +0.218 |
CTV | +0.201 |
additive | +0.170 |
iod | +0.168 |
Bravo | +0.153 |
Neg logit contributions | |
between | -0.161 |
Gaw | -0.148 |
undertaking | -0.133 |
pty | -0.126 |
abus | -0.124 |
Token | disabled |
Token ID | 10058 |
Feature activation | -6.52e-01 |
Pos logit contributions | |
united | +0.029 |
CTV | +0.026 |
additive | +0.021 |
iod | +0.021 |
SHARE | +0.018 |
Neg logit contributions | |
between | -0.032 |
Gaw | -0.030 |
undertaking | -0.028 |
pty | -0.027 |
abus | -0.026 |
Token | list |
Token ID | 1351 |
Feature activation | +7.22e-02 |
Pos logit contributions | |
united | +0.592 |
CTV | +0.543 |
additive | +0.451 |
iod | +0.444 |
SHARE | +0.404 |
Neg logit contributions | |
between | -0.500 |
Gaw | -0.461 |
undertaking | -0.421 |
pty | -0.399 |
abus | -0.391 |
Token | since |
Token ID | 1201 |
Feature activation | +8.93e-02 |
Pos logit contributions | |
between | +0.048 |
Gaw | +0.044 |
undertaking | +0.039 |
pty | +0.037 |
abus | +0.036 |
Neg logit contributions | |
united | -0.073 |
CTV | -0.067 |
additive | -0.057 |
iod | -0.057 |
SHARE | -0.052 |
Token | his |
Token ID | 465 |
Feature activation | -5.34e-02 |
Pos logit contributions | |
between | +0.066 |
Gaw | +0.061 |
undertaking | +0.054 |
pty | +0.053 |
abus | +0.052 |
Neg logit contributions | |
united | -0.083 |
CTV | -0.076 |
additive | -0.065 |
iod | -0.064 |
Bravo | -0.058 |
Token | previous |
Token ID | 2180 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
united | +0.051 |
CTV | +0.046 |
additive | +0.039 |
iod | +0.039 |
SHARE | +0.035 |
Neg logit contributions | |
between | -0.039 |
Gaw | -0.036 |
undertaking | -0.032 |
pty | -0.031 |
abus | -0.030 |
Token | Tommy |
Token ID | 19919 |
Feature activation | -2.06e-02 |
Pos logit contributions | |
between | +0.129 |
Gaw | +0.120 |
undertaking | +0.109 |
pty | +0.104 |
abus | +0.103 |
Neg logit contributions | |
united | -0.144 |
CTV | -0.132 |
additive | -0.110 |
iod | -0.108 |
SHARE | -0.097 |
Token | really |
Token ID | 1107 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
between | +0.052 |
Gaw | +0.048 |
undertaking | +0.043 |
pty | +0.041 |
abus | +0.041 |
Neg logit contributions | |
united | -0.073 |
CTV | -0.067 |
additive | -0.058 |
iod | -0.057 |
Bravo | -0.052 |
Token | great |
Token ID | 1049 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
between | +0.008 |
Gaw | +0.007 |
undertaking | +0.006 |
pty | +0.006 |
abus | +0.006 |
Neg logit contributions | |
united | -0.010 |
CTV | -0.009 |
additive | -0.008 |
iod | -0.007 |
Bravo | -0.007 |
Token | less |
Token ID | 1342 |
Feature activation | +5.67e-02 |
Pos logit contributions | |
between | +0.150 |
Gaw | +0.139 |
undertaking | +0.126 |
pty | +0.121 |
abus | +0.119 |
Neg logit contributions | |
united | -0.173 |
CTV | -0.158 |
additive | -0.133 |
iod | -0.130 |
Bravo | -0.117 |
Token | - |
Token ID | 12 |
Feature activation | +8.27e-02 |
Pos logit contributions | |
between | +0.046 |
Gaw | +0.042 |
undertaking | +0.039 |
pty | +0.037 |
abus | +0.036 |
Neg logit contributions | |
united | -0.049 |
CTV | -0.045 |
additive | -0.038 |
iod | -0.037 |
SHARE | -0.033 |
Token | f |
Token ID | 69 |
Feature activation | +6.33e-02 |
Pos logit contributions | |
between | +0.060 |
Gaw | +0.056 |
undertaking | +0.050 |
pty | +0.048 |
abus | +0.046 |
Neg logit contributions | |
united | -0.078 |
CTV | -0.072 |
additive | -0.060 |
iod | -0.060 |
SHARE | -0.055 |
Token | requently |
Token ID | 37971 |
Feature activation | -6.45e-01 |
Pos logit contributions | |
between | +0.049 |
Gaw | +0.046 |
undertaking | +0.041 |
pty | +0.039 |
abus | +0.039 |
Neg logit contributions | |
united | -0.057 |
CTV | -0.052 |
additive | -0.043 |
iod | -0.043 |
SHARE | -0.038 |
Token | used |
Token ID | 973 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
united | +0.500 |
CTV | +0.450 |
additive | +0.366 |
iod | +0.360 |
SHARE | +0.315 |
Neg logit contributions | |
between | -0.579 |
Gaw | -0.541 |
undertaking | -0.497 |
pty | -0.480 |
abus | -0.472 |
Token | options |
Token ID | 3689 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
united | +0.165 |
CTV | +0.151 |
additive | +0.126 |
iod | +0.124 |
Bravo | +0.112 |
Neg logit contributions | |
between | -0.146 |
Gaw | -0.135 |
undertaking | -0.123 |
pty | -0.118 |
abus | -0.116 |
Token | to |
Token ID | 284 |
Feature activation | +1.25e-03 |
Pos logit contributions | |
united | +0.117 |
CTV | +0.107 |
additive | +0.089 |
iod | +0.087 |
SHARE | +0.079 |
Neg logit contributions | |
between | -0.105 |
Gaw | -0.098 |
undertaking | -0.089 |
pty | -0.085 |
abus | -0.083 |
Token | consider |
Token ID | 2074 |
Feature activation | -3.10e-02 |
Pos logit contributions | |
between | +0.001 |
Gaw | +0.001 |
undertaking | +0.001 |
pty | +0.001 |
abus | +0.001 |
Neg logit contributions | |
united | -0.001 |
CTV | -0.001 |
additive | -0.001 |
iod | -0.001 |
SHARE | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
united | +0.028 |
CTV | +0.026 |
additive | +0.022 |
iod | +0.022 |
SHARE | +0.020 |
Neg logit contributions | |
between | -0.023 |
Gaw | -0.022 |
undertaking | -0.020 |
pty | -0.019 |
abus | -0.018 |
Token | K |
Token ID | 509 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
united | +0.020 |
CTV | +0.018 |
additive | +0.015 |
iod | +0.015 |
Bravo | +0.014 |
Neg logit contributions | |
between | -0.017 |
Gaw | -0.016 |
undertaking | -0.015 |
pty | -0.014 |
abus | -0.014 |
Token | aff |
Token ID | 2001 |
Feature activation | -4.28e-02 |
Pos logit contributions | |
united | +0.010 |
CTV | +0.009 |
additive | +0.008 |
iod | +0.008 |
SHARE | +0.007 |
Neg logit contributions | |
between | -0.009 |
Gaw | -0.008 |
undertaking | -0.007 |
pty | -0.007 |
devices | -0.007 |
Token | ir |
Token ID | 343 |
Feature activation | -7.86e-02 |
Pos logit contributions | |
united | +0.038 |
CTV | +0.035 |
additive | +0.029 |
iod | +0.029 |
SHARE | +0.026 |
Neg logit contributions | |
between | -0.033 |
Gaw | -0.031 |
undertaking | -0.028 |
pty | -0.027 |
abus | -0.026 |
Token | lime |
Token ID | 28738 |
Feature activation | -1.44e-02 |
Pos logit contributions | |
united | +0.073 |
CTV | +0.067 |
additive | +0.056 |
iod | +0.056 |
SHARE | +0.051 |
Neg logit contributions | |
between | -0.058 |
Gaw | -0.054 |
undertaking | -0.049 |
pty | -0.046 |
abus | -0.045 |
Token | leaves |
Token ID | 5667 |
Feature activation | -4.60e-02 |
Pos logit contributions | |
united | +0.013 |
CTV | +0.012 |
additive | +0.010 |
iod | +0.010 |
SHARE | +0.009 |
Neg logit contributions | |
between | -0.011 |
Gaw | -0.010 |
undertaking | -0.009 |
pty | -0.009 |
abus | -0.008 |
Token | impart |
Token ID | 23553 |
Feature activation | -6.41e-01 |
Pos logit contributions | |
united | +0.039 |
CTV | +0.035 |
additive | +0.029 |
iod | +0.028 |
SHARE | +0.025 |
Neg logit contributions | |
between | -0.038 |
Gaw | -0.036 |
undertaking | -0.033 |
pty | -0.031 |
abus | -0.031 |
Token | intense |
Token ID | 8157 |
Feature activation | -3.81e-02 |
Pos logit contributions | |
united | +0.618 |
CTV | +0.569 |
additive | +0.487 |
iod | +0.479 |
Bravo | +0.438 |
Neg logit contributions | |
between | -0.450 |
Gaw | -0.414 |
undertaking | -0.372 |
pty | -0.353 |
abus | -0.349 |
Token | fruit |
Token ID | 8234 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
united | +0.034 |
CTV | +0.032 |
additive | +0.026 |
iod | +0.026 |
SHARE | +0.024 |
Neg logit contributions | |
between | -0.029 |
Gaw | -0.027 |
undertaking | -0.024 |
pty | -0.023 |
abus | -0.023 |
Token | iness |
Token ID | 1272 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
united | +0.137 |
CTV | +0.127 |
additive | +0.109 |
iod | +0.107 |
SHARE | +0.099 |
Neg logit contributions | |
between | -0.087 |
Gaw | -0.079 |
undertaking | -0.070 |
pty | -0.066 |
abus | -0.065 |
Token | without |
Token ID | 1231 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
between | +0.128 |
Gaw | +0.119 |
undertaking | +0.108 |
pty | +0.103 |
abus | +0.102 |
Neg logit contributions | |
united | -0.138 |
CTV | -0.126 |
additive | -0.104 |
iod | -0.102 |
SHARE | -0.092 |
Token | the |
Token ID | 262 |
Feature activation | -8.12e-02 |
Pos logit contributions | |
united | +0.101 |
CTV | +0.094 |
additive | +0.080 |
iod | +0.079 |
Bravo | +0.072 |
Neg logit contributions | |
between | -0.071 |
Gaw | -0.065 |
undertaking | -0.058 |
pty | -0.055 |
abus | -0.054 |
Token | all |
Token ID | 477 |
Feature activation | -2.60e-02 |
Pos logit contributions | |
between | +0.066 |
Gaw | +0.061 |
undertaking | +0.055 |
pty | +0.052 |
abus | +0.051 |
Neg logit contributions | |
united | -0.088 |
CTV | -0.082 |
additive | -0.069 |
iod | -0.068 |
Bravo | -0.062 |
Token | the |
Token ID | 262 |
Feature activation | -9.43e-02 |
Pos logit contributions | |
united | +0.025 |
CTV | +0.023 |
additive | +0.019 |
iod | +0.019 |
Bravo | +0.017 |
Neg logit contributions | |
between | -0.019 |
Gaw | -0.017 |
undertaking | -0.016 |
pty | -0.015 |
abus | -0.015 |
Token | right |
Token ID | 826 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
united | +0.087 |
CTV | +0.079 |
additive | +0.067 |
iod | +0.066 |
Bravo | +0.060 |
Neg logit contributions | |
between | -0.071 |
Gaw | -0.065 |
undertaking | -0.059 |
pty | -0.057 |
abus | -0.056 |
Token | things |
Token ID | 1243 |
Feature activation | +8.55e-02 |
Pos logit contributions | |
united | +0.144 |
CTV | +0.134 |
additive | +0.116 |
iod | +0.115 |
SHARE | +0.107 |
Neg logit contributions | |
between | -0.073 |
Gaw | -0.065 |
undertaking | -0.057 |
pty | -0.053 |
abus | -0.051 |
Token | goal |
Token ID | 3061 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
between | +0.067 |
Gaw | +0.062 |
undertaking | +0.056 |
pty | +0.054 |
abus | +0.053 |
Neg logit contributions | |
united | -0.076 |
CTV | -0.070 |
additive | -0.058 |
iod | -0.057 |
SHARE | -0.052 |
Token | keepers |
Token ID | 24952 |
Feature activation | -6.36e-01 |
Pos logit contributions | |
united | +0.398 |
CTV | +0.364 |
additive | +0.304 |
iod | +0.299 |
SHARE | +0.271 |
Neg logit contributions | |
between | -0.339 |
Gaw | -0.314 |
undertaking | -0.284 |
pty | -0.271 |
abus | -0.267 |
Token | should |
Token ID | 815 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
united | +0.542 |
CTV | +0.494 |
additive | +0.407 |
iod | +0.400 |
SHARE | +0.360 |
Neg logit contributions | |
between | -0.522 |
Gaw | -0.485 |
undertaking | -0.443 |
pty | -0.423 |
abus | -0.417 |
Token | ," |
Token ID | 553 |
Feature activation | -4.50e-02 |
Pos logit contributions | |
united | +0.009 |
CTV | +0.008 |
additive | +0.006 |
iod | +0.006 |
Bravo | +0.006 |
Neg logit contributions | |
between | -0.008 |
Gaw | -0.008 |
undertaking | -0.007 |
pty | -0.007 |
abus | -0.007 |
Token | Y |
Token ID | 575 |
Feature activation | -2.79e-02 |
Pos logit contributions | |
united | +0.045 |
CTV | +0.041 |
additive | +0.035 |
iod | +0.035 |
Bravo | +0.032 |
Neg logit contributions | |
between | -0.030 |
Gaw | -0.028 |
undertaking | -0.025 |
pty | -0.024 |
abus | -0.023 |
Token | all |
Token ID | 439 |
Feature activation | -3.16e-02 |
Pos logit contributions | |
united | +0.029 |
CTV | +0.027 |
additive | +0.023 |
iod | +0.023 |
SHARE | +0.021 |
Neg logit contributions | |
between | -0.018 |
Gaw | -0.016 |
undertaking | -0.014 |
pty | -0.013 |
abus | -0.013 |
Token | op |
Token ID | 404 |
Feature activation | +8.82e-02 |
Pos logit contributions | |
united | +0.034 |
CTV | +0.031 |
additive | +0.027 |
iod | +0.027 |
SHARE | +0.025 |
Neg logit contributions | |
between | -0.019 |
Gaw | -0.017 |
undertaking | -0.015 |
pty | -0.014 |
devices | -0.014 |
Token | G |
Token ID | 402 |
Feature activation | +4.68e-02 |
Pos logit contributions | |
united | +0.020 |
CTV | +0.018 |
additive | +0.015 |
iod | +0.015 |
SHARE | +0.014 |
Neg logit contributions | |
between | -0.016 |
Gaw | -0.015 |
undertaking | -0.014 |
pty | -0.013 |
abus | -0.013 |
Token | ess |
Token ID | 408 |
Feature activation | +4.75e-02 |
Pos logit contributions | |
between | +0.035 |
Gaw | +0.032 |
undertaking | +0.029 |
pty | +0.028 |
abus | +0.027 |
Neg logit contributions | |
united | -0.043 |
CTV | -0.040 |
additive | -0.033 |
iod | -0.033 |
SHARE | -0.030 |
Token | berg |
Token ID | 3900 |
Feature activation | +3.66e-02 |
Pos logit contributions | |
between | +0.031 |
Gaw | +0.029 |
undertaking | +0.026 |
pty | +0.024 |
devices | +0.024 |
Neg logit contributions | |
united | -0.048 |
CTV | -0.044 |
additive | -0.038 |
iod | -0.037 |
Bravo | -0.034 |
Token | witz |
Token ID | 28155 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
between | +0.028 |
Gaw | +0.026 |
undertaking | +0.024 |
pty | +0.023 |
abus | +0.022 |
Neg logit contributions | |
united | -0.033 |
CTV | -0.030 |
additive | -0.025 |
iod | -0.025 |
SHARE | -0.022 |
Token | West |
Token ID | 2688 |
Feature activation | -3.46e-02 |
Pos logit contributions | |
between | +0.159 |
Gaw | +0.147 |
undertaking | +0.133 |
pty | +0.127 |
abus | +0.125 |
Neg logit contributions | |
united | -0.183 |
CTV | -0.168 |
additive | -0.140 |
iod | -0.138 |
SHARE | -0.125 |
Token | chester |
Token ID | 35983 |
Feature activation | -6.32e-01 |
Pos logit contributions | |
united | +0.031 |
CTV | +0.028 |
additive | +0.023 |
iod | +0.023 |
SHARE | +0.021 |
Neg logit contributions | |
between | -0.027 |
Gaw | -0.025 |
undertaking | -0.023 |
pty | -0.022 |
abus | -0.021 |
Token | 1 |
Token ID | 352 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
united | +0.458 |
CTV | +0.412 |
additive | +0.326 |
iod | +0.319 |
SHARE | +0.278 |
Neg logit contributions | |
between | -0.598 |
Gaw | -0.562 |
undertaking | -0.519 |
pty | -0.500 |
abus | -0.492 |
Token | hour |
Token ID | 1711 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
united | +0.274 |
CTV | +0.249 |
additive | +0.204 |
iod | +0.202 |
SHARE | +0.181 |
Neg logit contributions | |
between | -0.274 |
Gaw | -0.255 |
undertaking | -0.234 |
pty | -0.222 |
abus | -0.219 |
Token | ago |
Token ID | 2084 |
Feature activation | +7.51e-03 |
Pos logit contributions | |
united | +0.140 |
CTV | +0.130 |
additive | +0.112 |
iod | +0.110 |
SHARE | +0.102 |
Neg logit contributions | |
between | -0.087 |
Gaw | -0.079 |
undertaking | -0.070 |
pty | -0.066 |
abus | -0.064 |
Token | Pretty |
Token ID | 20090 |
Feature activation | -6.75e-02 |
Pos logit contributions | |
between | +0.006 |
Gaw | +0.005 |
undertaking | +0.005 |
pty | +0.005 |
abus | +0.005 |
Neg logit contributions | |
united | -0.007 |
CTV | -0.006 |
additive | -0.005 |
iod | -0.005 |
SHARE | -0.004 |
Token | simple |
Token ID | 2829 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
united | +0.060 |
CTV | +0.055 |
additive | +0.046 |
iod | +0.045 |
Bravo | +0.041 |
Neg logit contributions | |
between | -0.053 |
Gaw | -0.049 |
undertaking | -0.044 |
pty | -0.042 |
abus | -0.041 |
Token | Gutenberg |
Token ID | 20336 |
Feature activation | -9.07e-02 |
Pos logit contributions | |
between | +0.035 |
Gaw | +0.032 |
undertaking | +0.029 |
pty | +0.027 |
abus | +0.027 |
Neg logit contributions | |
united | -0.046 |
CTV | -0.043 |
additive | -0.036 |
iod | -0.035 |
SHARE | -0.032 |
Token | ( |
Token ID | 357 |
Feature activation | -7.47e-02 |
Pos logit contributions | |
united | +0.078 |
CTV | +0.071 |
additive | +0.059 |
iod | +0.058 |
SHARE | +0.052 |
Neg logit contributions | |
between | -0.074 |
Gaw | -0.069 |
undertaking | -0.062 |
pty | -0.060 |
abus | -0.059 |
Token | www |
Token ID | 2503 |
Feature activation | -7.61e-02 |
Pos logit contributions | |
united | +0.068 |
CTV | +0.063 |
additive | +0.052 |
iod | +0.052 |
SHARE | +0.047 |
Neg logit contributions | |
between | -0.057 |
Gaw | -0.053 |
undertaking | -0.048 |
pty | -0.045 |
abus | -0.044 |
Token | . |
Token ID | 13 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
united | +0.070 |
CTV | +0.064 |
additive | +0.054 |
iod | +0.053 |
SHARE | +0.048 |
Neg logit contributions | |
between | -0.057 |
Gaw | -0.053 |
undertaking | -0.048 |
pty | -0.045 |
abus | -0.045 |
Token | g |
Token ID | 70 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
between | +0.011 |
Gaw | +0.010 |
undertaking | +0.009 |
pty | +0.008 |
abus | +0.008 |
Neg logit contributions | |
united | -0.013 |
CTV | -0.012 |
additive | -0.010 |
iod | -0.010 |
SHARE | -0.009 |
Token | utenberg |
Token ID | 19028 |
Feature activation | -6.21e-01 |
Pos logit contributions | |
between | +0.148 |
Gaw | +0.142 |
undertaking | +0.134 |
pty | +0.130 |
devices | +0.129 |
Neg logit contributions | |
united | -0.041 |
CTV | -0.032 |
additive | -0.016 |
iod | -0.015 |
SHARE | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
united | +0.569 |
CTV | +0.519 |
additive | +0.432 |
iod | +0.426 |
SHARE | +0.387 |
Neg logit contributions | |
between | -0.471 |
Gaw | -0.440 |
undertaking | -0.396 |
pty | -0.376 |
abus | -0.369 |
Token | org |
Token ID | 2398 |
Feature activation | -2.98e-02 |
Pos logit contributions | |
united | +0.117 |
CTV | +0.107 |
additive | +0.091 |
iod | +0.090 |
SHARE | +0.082 |
Neg logit contributions | |
between | -0.084 |
Gaw | -0.077 |
undertaking | -0.069 |
pty | -0.065 |
abus | -0.064 |
Token | ). |
Token ID | 737 |
Feature activation | -8.81e-02 |
Pos logit contributions | |
united | +0.028 |
CTV | +0.025 |
additive | +0.021 |
iod | +0.021 |
SHARE | +0.019 |
Neg logit contributions | |
between | -0.022 |
Gaw | -0.021 |
undertaking | -0.019 |
pty | -0.018 |
abus | -0.017 |
Token | Any |
Token ID | 4377 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
united | +0.077 |
CTV | +0.070 |
additive | +0.058 |
iod | +0.057 |
SHARE | +0.052 |
Neg logit contributions | |
between | -0.071 |
Gaw | -0.065 |
undertaking | -0.060 |
pty | -0.057 |
abus | -0.056 |
Token | file |
Token ID | 2393 |
Feature activation | -9.43e-02 |
Pos logit contributions | |
united | +0.134 |
CTV | +0.123 |
additive | +0.104 |
iod | +0.103 |
SHARE | +0.094 |
Neg logit contributions | |
between | -0.097 |
Gaw | -0.089 |
undertaking | -0.080 |
pty | -0.076 |
abus | -0.075 |
Token | should |
Token ID | 815 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
between | +0.046 |
Gaw | +0.042 |
undertaking | +0.038 |
pty | +0.037 |
abus | +0.036 |
Neg logit contributions | |
united | -0.051 |
CTV | -0.047 |
additive | -0.039 |
iod | -0.038 |
SHARE | -0.035 |
Token | stay |
Token ID | 2652 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
between | +0.092 |
Gaw | +0.086 |
undertaking | +0.078 |
pty | +0.075 |
abus | +0.074 |
Neg logit contributions | |
united | -0.094 |
CTV | -0.085 |
additive | -0.070 |
iod | -0.069 |
SHARE | -0.062 |
Token | in |
Token ID | 287 |
Feature activation | +8.27e-02 |
Pos logit contributions | |
united | +0.107 |
CTV | +0.096 |
additive | +0.077 |
iod | +0.076 |
SHARE | +0.067 |
Neg logit contributions | |
between | -0.125 |
Gaw | -0.117 |
undertaking | -0.108 |
pty | -0.104 |
abus | -0.102 |
Token | the |
Token ID | 262 |
Feature activation | -5.68e-03 |
Pos logit contributions | |
between | +0.062 |
Gaw | +0.057 |
undertaking | +0.052 |
pty | +0.050 |
abus | +0.049 |
Neg logit contributions | |
united | -0.076 |
CTV | -0.070 |
additive | -0.059 |
iod | -0.058 |
Bravo | -0.052 |
Token | mountain |
Token ID | 8598 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
united | +0.005 |
CTV | +0.005 |
additive | +0.004 |
iod | +0.004 |
SHARE | +0.004 |
Neg logit contributions | |
between | -0.004 |
Gaw | -0.004 |
undertaking | -0.004 |
pty | -0.003 |
abus | -0.003 |
Token | shack |
Token ID | 32772 |
Feature activation | -6.20e-01 |
Pos logit contributions | |
between | +0.121 |
Gaw | +0.113 |
undertaking | +0.103 |
pty | +0.099 |
abus | +0.097 |
Neg logit contributions | |
united | -0.119 |
CTV | -0.108 |
additive | -0.088 |
iod | -0.087 |
SHARE | -0.078 |
Token | , |
Token ID | 11 |
Feature activation | -5.18e-02 |
Pos logit contributions | |
united | +0.553 |
CTV | +0.505 |
additive | +0.422 |
iod | +0.413 |
SHARE | +0.374 |
Neg logit contributions | |
between | -0.482 |
Gaw | -0.448 |
undertaking | -0.404 |
pty | -0.389 |
abus | -0.382 |
Token | and |
Token ID | 290 |
Feature activation | -4.27e-02 |
Pos logit contributions | |
united | +0.047 |
CTV | +0.042 |
additive | +0.036 |
iod | +0.035 |
Bravo | +0.032 |
Neg logit contributions | |
between | -0.040 |
Gaw | -0.037 |
undertaking | -0.033 |
pty | -0.032 |
abus | -0.032 |
Token | please |
Token ID | 3387 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
united | +0.037 |
CTV | +0.034 |
additive | +0.028 |
iod | +0.028 |
Bravo | +0.025 |
Neg logit contributions | |
between | -0.034 |
Gaw | -0.031 |
undertaking | -0.028 |
pty | -0.027 |
abus | -0.027 |
Token | rest |
Token ID | 1334 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
united | +0.111 |
CTV | +0.101 |
additive | +0.082 |
iod | +0.080 |
SHARE | +0.071 |
Neg logit contributions | |
between | -0.120 |
Gaw | -0.112 |
undertaking | -0.103 |
pty | -0.099 |
abus | -0.097 |
Token | and |
Token ID | 290 |
Feature activation | -1.77e-02 |
Pos logit contributions | |
between | +0.100 |
Gaw | +0.093 |
undertaking | +0.084 |
pty | +0.080 |
abus | +0.079 |
Neg logit contributions | |
united | -0.113 |
CTV | -0.103 |
additive | -0.086 |
iod | -0.084 |
SHARE | -0.076 |
Token | 16 |
Token ID | 1467 |
Feature activation | -7.96e-03 |
Pos logit contributions | |
between | +0.045 |
Gaw | +0.042 |
undertaking | +0.039 |
pty | +0.037 |
abus | +0.037 |
Neg logit contributions | |
united | -0.044 |
CTV | -0.040 |
additive | -0.032 |
iod | -0.032 |
SHARE | -0.028 |
Token | , |
Token ID | 11 |
Feature activation | -2.36e-02 |
Pos logit contributions | |
united | +0.006 |
CTV | +0.006 |
additive | +0.005 |
iod | +0.005 |
SHARE | +0.004 |
Neg logit contributions | |
between | -0.007 |
Gaw | -0.006 |
undertaking | -0.006 |
pty | -0.006 |
abus | -0.006 |
Token | 1981 |
Token ID | 14745 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
united | +0.027 |
CTV | +0.025 |
additive | +0.022 |
iod | +0.021 |
SHARE | +0.020 |
Neg logit contributions | |
between | -0.013 |
Gaw | -0.012 |
undertaking | -0.010 |
pty | -0.009 |
abus | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | +8.69e-03 |
Pos logit contributions | |
between | +0.076 |
Gaw | +0.070 |
undertaking | +0.063 |
pty | +0.060 |
abus | +0.059 |
Neg logit contributions | |
united | -0.099 |
CTV | -0.091 |
additive | -0.077 |
iod | -0.076 |
SHARE | -0.069 |
Token |
|
Token ID | 198 |
Feature activation | -1.33e-02 |
Pos logit contributions | |
between | +0.006 |
Gaw | +0.006 |
undertaking | +0.005 |
pty | +0.005 |
abus | +0.005 |
Neg logit contributions | |
united | -0.008 |
CTV | -0.007 |
additive | -0.006 |
iod | -0.006 |
SHARE | -0.006 |
Token | Birth |
Token ID | 38480 |
Feature activation | -6.10e-01 |
Pos logit contributions | |
united | +0.010 |
CTV | +0.009 |
additive | +0.007 |
iod | +0.007 |
Bravo | +0.006 |
Neg logit contributions | |
between | -0.012 |
Gaw | -0.011 |
undertaking | -0.010 |
pty | -0.010 |
abus | -0.010 |
Token | place |
Token ID | 5372 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
united | +0.467 |
CTV | +0.417 |
additive | +0.331 |
iod | +0.328 |
Bravo | +0.288 |
Neg logit contributions | |
between | -0.556 |
Gaw | -0.524 |
undertaking | -0.481 |
pty | -0.466 |
devices | -0.455 |
Token | : |
Token ID | 25 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
united | +0.108 |
CTV | +0.095 |
additive | +0.072 |
iod | +0.070 |
SHARE | +0.059 |
Neg logit contributions | |
between | -0.182 |
Gaw | -0.172 |
undertaking | -0.160 |
pty | -0.155 |
abus | -0.153 |
Token | Long |
Token ID | 5882 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
united | +0.325 |
CTV | +0.298 |
additive | +0.251 |
iod | +0.247 |
SHARE | +0.226 |
Neg logit contributions | |
between | -0.251 |
Gaw | -0.231 |
undertaking | -0.209 |
pty | -0.198 |
abus | -0.195 |
Token | Beach |
Token ID | 8511 |
Feature activation | -2.89e-02 |
Pos logit contributions | |
united | +0.219 |
CTV | +0.201 |
additive | +0.168 |
iod | +0.165 |
SHARE | +0.150 |
Neg logit contributions | |
between | -0.183 |
Gaw | -0.169 |
undertaking | -0.153 |
pty | -0.146 |
abus | -0.143 |
Token | , |
Token ID | 11 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
united | +0.024 |
CTV | +0.022 |
additive | +0.018 |
iod | +0.018 |
SHARE | +0.016 |
Neg logit contributions | |
between | -0.024 |
Gaw | -0.022 |
undertaking | -0.020 |
pty | -0.019 |
abus | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
united | +0.002 |
CTV | +0.002 |
additive | +0.002 |
iod | +0.002 |
Bravo | +0.001 |
Neg logit contributions | |
between | -0.002 |
Gaw | -0.002 |
undertaking | -0.002 |
pty | -0.001 |
abus | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -3.30e-02 |
Pos logit contributions | |
united | +0.014 |
CTV | +0.013 |
additive | +0.010 |
iod | +0.010 |
SHARE | +0.009 |
Neg logit contributions | |
between | -0.011 |
Gaw | -0.010 |
undertaking | -0.009 |
pty | -0.009 |
abus | -0.009 |
Token | At |
Token ID | 2953 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
united | +0.029 |
CTV | +0.026 |
additive | +0.021 |
iod | +0.021 |
SHARE | +0.019 |
Neg logit contributions | |
between | -0.027 |
Gaw | -0.025 |
undertaking | -0.023 |
pty | -0.022 |
abus | -0.021 |
Token | G |
Token ID | 402 |
Feature activation | +8.10e-02 |
Pos logit contributions | |
united | +0.105 |
CTV | +0.097 |
additive | +0.082 |
iod | +0.081 |
Bravo | +0.074 |
Neg logit contributions | |
between | -0.074 |
Gaw | -0.068 |
undertaking | -0.061 |
pty | -0.058 |
abus | -0.057 |
Token | f |
Token ID | 69 |
Feature activation | -3.28e-02 |
Pos logit contributions | |
between | +0.063 |
Gaw | +0.059 |
undertaking | +0.053 |
pty | +0.051 |
abus | +0.050 |
Neg logit contributions | |
united | -0.072 |
CTV | -0.066 |
additive | -0.055 |
iod | -0.054 |
SHARE | -0.049 |
Token | inity |
Token ID | 6269 |
Feature activation | -6.08e-01 |
Pos logit contributions | |
united | +0.020 |
CTV | +0.017 |
additive | +0.013 |
iod | +0.013 |
SHARE | +0.010 |
Neg logit contributions | |
between | -0.035 |
Gaw | -0.033 |
undertaking | -0.031 |
pty | -0.030 |
abus | -0.030 |
Token | 3 |
Token ID | 513 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
united | +0.537 |
CTV | +0.490 |
additive | +0.408 |
iod | +0.400 |
SHARE | +0.362 |
Neg logit contributions | |
between | -0.482 |
Gaw | -0.446 |
undertaking | -0.405 |
pty | -0.387 |
abus | -0.381 |
Token | r |
Token ID | 374 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
united | +0.164 |
CTV | +0.150 |
additive | +0.123 |
iod | +0.121 |
SHARE | +0.109 |
Neg logit contributions | |
between | -0.157 |
Gaw | -0.146 |
undertaking | -0.133 |
pty | -0.127 |
abus | -0.125 |
Token | ai |
Token ID | 1872 |
Feature activation | +2.74e-03 |
Pos logit contributions | |
united | +0.158 |
CTV | +0.145 |
additive | +0.121 |
iod | +0.120 |
SHARE | +0.109 |
Neg logit contributions | |
between | -0.130 |
Gaw | -0.120 |
undertaking | -0.108 |
pty | -0.103 |
abus | -0.101 |
Token | N |
Token ID | 45 |
Feature activation | -5.32e-02 |
Pos logit contributions | |
between | +0.002 |
Gaw | +0.002 |
undertaking | +0.002 |
pty | +0.002 |
abus | +0.002 |
Neg logit contributions | |
united | -0.002 |
CTV | -0.002 |
additive | -0.002 |
iod | -0.002 |
SHARE | -0.002 |
Token | had |
Token ID | 550 |
Feature activation | -6.70e-02 |
Pos logit contributions | |
united | +0.048 |
CTV | +0.043 |
additive | +0.036 |
iod | +0.036 |
SHARE | +0.032 |
Neg logit contributions | |
between | -0.042 |
Gaw | -0.038 |
undertaking | -0.035 |
pty | -0.033 |
abus | -0.033 |
Token | who |
Token ID | 508 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
united | +0.068 |
CTV | +0.062 |
additive | +0.053 |
iod | +0.052 |
Bravo | +0.048 |
Neg logit contributions | |
between | -0.046 |
Gaw | -0.041 |
undertaking | -0.037 |
pty | -0.036 |
abus | -0.035 |
Token | , |
Token ID | 11 |
Feature activation | -9.56e-02 |
Pos logit contributions | |
between | +0.111 |
Gaw | +0.102 |
undertaking | +0.092 |
pty | +0.087 |
abus | +0.086 |
Neg logit contributions | |
united | -0.151 |
CTV | -0.139 |
additive | -0.117 |
iod | -0.116 |
SHARE | -0.106 |
Token | unlike |
Token ID | 5023 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
united | +0.092 |
CTV | +0.085 |
additive | +0.072 |
iod | +0.071 |
Bravo | +0.065 |
Neg logit contributions | |
between | -0.067 |
Gaw | -0.061 |
undertaking | -0.055 |
pty | -0.053 |
abus | -0.052 |
Token | his |
Token ID | 465 |
Feature activation | -8.50e-02 |
Pos logit contributions | |
between | +0.110 |
Gaw | +0.100 |
undertaking | +0.091 |
pty | +0.088 |
abus | +0.086 |
Neg logit contributions | |
united | -0.133 |
CTV | -0.122 |
additive | -0.102 |
iod | -0.100 |
Bravo | -0.092 |
Token | brother |
Token ID | 3956 |
Feature activation | +3.65e-02 |
Pos logit contributions | |
united | +0.075 |
CTV | +0.068 |
additive | +0.057 |
iod | +0.056 |
SHARE | +0.050 |
Neg logit contributions | |
between | -0.068 |
Gaw | -0.063 |
undertaking | -0.057 |
pty | -0.055 |
abus | -0.054 |
Token | Bor |
Token ID | 12182 |
Feature activation | -6.04e-01 |
Pos logit contributions | |
between | +0.030 |
Gaw | +0.027 |
undertaking | +0.025 |
pty | +0.024 |
abus | +0.024 |
Neg logit contributions | |
united | -0.031 |
CTV | -0.029 |
additive | -0.024 |
iod | -0.023 |
Bravo | -0.021 |
Token | om |
Token ID | 296 |
Feature activation | -3.22e-02 |
Pos logit contributions | |
united | +0.571 |
CTV | +0.522 |
additive | +0.438 |
iod | +0.434 |
Bravo | +0.395 |
Neg logit contributions | |
between | -0.438 |
Gaw | -0.402 |
undertaking | -0.365 |
pty | -0.348 |
devices | -0.340 |
Token | ir |
Token ID | 343 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
united | +0.028 |
CTV | +0.026 |
additive | +0.022 |
iod | +0.021 |
SHARE | +0.019 |
Neg logit contributions | |
between | -0.025 |
Gaw | -0.024 |
undertaking | -0.021 |
pty | -0.020 |
abus | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | -6.83e-03 |
Pos logit contributions | |
united | +0.132 |
CTV | +0.120 |
additive | +0.098 |
iod | +0.096 |
SHARE | +0.086 |
Neg logit contributions | |
between | -0.140 |
Gaw | -0.130 |
undertaking | -0.120 |
pty | -0.115 |
abus | -0.113 |
Token | resists |
Token ID | 47786 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
united | +0.007 |
CTV | +0.006 |
additive | +0.005 |
iod | +0.005 |
Bravo | +0.005 |
Neg logit contributions | |
between | -0.005 |
Gaw | -0.004 |
undertaking | -0.004 |
pty | -0.004 |
abus | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | -4.58e-02 |
Pos logit contributions | |
between | +0.141 |
Gaw | +0.129 |
undertaking | +0.117 |
pty | +0.114 |
abus | +0.111 |
Neg logit contributions | |
united | -0.167 |
CTV | -0.153 |
additive | -0.128 |
iod | -0.126 |
Bravo | -0.114 |
Token | ik |
Token ID | 1134 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
united | +0.396 |
CTV | +0.365 |
additive | +0.312 |
iod | +0.309 |
Bravo | +0.283 |
Neg logit contributions | |
between | -0.252 |
Gaw | -0.231 |
undertaking | -0.207 |
pty | -0.191 |
devices | -0.190 |
Token | ov |
Token ID | 709 |
Feature activation | -7.33e-02 |
Pos logit contributions | |
between | +0.139 |
Gaw | +0.129 |
undertaking | +0.117 |
pty | +0.111 |
abus | +0.109 |
Neg logit contributions | |
united | -0.164 |
CTV | -0.150 |
additive | -0.126 |
iod | -0.124 |
SHARE | -0.112 |
Token | and |
Token ID | 290 |
Feature activation | -9.26e-02 |
Pos logit contributions | |
united | +0.063 |
CTV | +0.057 |
additive | +0.047 |
iod | +0.047 |
SHARE | +0.042 |
Neg logit contributions | |
between | -0.060 |
Gaw | -0.055 |
undertaking | -0.050 |
pty | -0.048 |
abus | -0.047 |
Token | And |
Token ID | 843 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
united | +0.091 |
CTV | +0.084 |
additive | +0.071 |
iod | +0.070 |
Bravo | +0.064 |
Neg logit contributions | |
between | -0.064 |
Gaw | -0.059 |
undertaking | -0.053 |
pty | -0.050 |
abus | -0.049 |
Token | rey |
Token ID | 4364 |
Feature activation | +6.34e-02 |
Pos logit contributions | |
united | +0.203 |
CTV | +0.185 |
additive | +0.158 |
iod | +0.155 |
Bravo | +0.144 |
Neg logit contributions | |
between | -0.144 |
Gaw | -0.134 |
undertaking | -0.121 |
pty | -0.112 |
devices | -0.111 |
Token | Bor |
Token ID | 12182 |
Feature activation | -6.01e-01 |
Pos logit contributions | |
between | +0.047 |
Gaw | +0.043 |
undertaking | +0.039 |
pty | +0.037 |
abus | +0.037 |
Neg logit contributions | |
united | -0.059 |
CTV | -0.054 |
additive | -0.046 |
iod | -0.045 |
Bravo | -0.041 |
Token | isen |
Token ID | 13254 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
united | +0.539 |
CTV | +0.491 |
additive | +0.407 |
iod | +0.402 |
SHARE | +0.362 |
Neg logit contributions | |
between | -0.465 |
Gaw | -0.436 |
undertaking | -0.396 |
pty | -0.372 |
devices | -0.366 |
Token | ko |
Token ID | 7204 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
united | +0.113 |
CTV | +0.104 |
additive | +0.087 |
iod | +0.086 |
SHARE | +0.078 |
Neg logit contributions | |
between | -0.092 |
Gaw | -0.085 |
undertaking | -0.076 |
pty | -0.073 |
abus | -0.071 |
Token | is |
Token ID | 318 |
Feature activation | +2.36e-02 |
Pos logit contributions | |
united | +0.106 |
CTV | +0.097 |
additive | +0.080 |
iod | +0.079 |
SHARE | +0.071 |
Neg logit contributions | |
between | -0.101 |
Gaw | -0.094 |
undertaking | -0.086 |
pty | -0.082 |
abus | -0.081 |
Token | scheduled |
Token ID | 7530 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
between | +0.019 |
Gaw | +0.018 |
undertaking | +0.016 |
pty | +0.016 |
abus | +0.015 |
Neg logit contributions | |
united | -0.020 |
CTV | -0.018 |
additive | -0.015 |
iod | -0.015 |
Bravo | -0.014 |
Token | to |
Token ID | 284 |
Feature activation | -6.53e-02 |
Pos logit contributions | |
united | +0.362 |
CTV | +0.334 |
additive | +0.281 |
iod | +0.277 |
SHARE | +0.253 |
Neg logit contributions | |
between | -0.278 |
Gaw | -0.256 |
undertaking | -0.231 |
pty | -0.219 |
abus | -0.215 |
Token | � |
Token ID | 247 |
Feature activation | +3.06e-02 |
Pos logit contributions | |
united | +0.076 |
CTV | +0.070 |
additive | +0.057 |
iod | +0.056 |
SHARE | +0.051 |
Neg logit contributions | |
between | -0.074 |
Gaw | -0.068 |
undertaking | -0.062 |
pty | -0.060 |
abus | -0.059 |
Token | s |
Token ID | 82 |
Feature activation | -2.22e-02 |
Pos logit contributions | |
between | +0.022 |
Gaw | +0.020 |
undertaking | +0.018 |
pty | +0.017 |
abus | +0.017 |
Neg logit contributions | |
united | -0.029 |
CTV | -0.027 |
additive | -0.023 |
iod | -0.022 |
SHARE | -0.020 |
Token | agent |
Token ID | 5797 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
united | +0.018 |
CTV | +0.016 |
additive | +0.013 |
iod | +0.013 |
SHARE | +0.012 |
Neg logit contributions | |
between | -0.019 |
Gaw | -0.018 |
undertaking | -0.017 |
pty | -0.016 |
abus | -0.016 |
Token | , |
Token ID | 11 |
Feature activation | -7.94e-02 |
Pos logit contributions | |
united | +0.329 |
CTV | +0.301 |
additive | +0.250 |
iod | +0.246 |
SHARE | +0.222 |
Neg logit contributions | |
between | -0.294 |
Gaw | -0.273 |
undertaking | -0.248 |
pty | -0.237 |
abus | -0.233 |
Token | Scott |
Token ID | 4746 |
Feature activation | -4.16e-02 |
Pos logit contributions | |
united | +0.079 |
CTV | +0.073 |
additive | +0.062 |
iod | +0.061 |
SHARE | +0.056 |
Neg logit contributions | |
between | -0.054 |
Gaw | -0.049 |
undertaking | -0.044 |
pty | -0.042 |
abus | -0.041 |
Token | Bor |
Token ID | 12182 |
Feature activation | -5.98e-01 |
Pos logit contributions | |
united | +0.038 |
CTV | +0.035 |
additive | +0.029 |
iod | +0.029 |
SHARE | +0.026 |
Neg logit contributions | |
between | -0.031 |
Gaw | -0.029 |
undertaking | -0.026 |
pty | -0.025 |
abus | -0.025 |
Token | as |
Token ID | 292 |
Feature activation | -3.36e-02 |
Pos logit contributions | |
united | +0.610 |
CTV | +0.563 |
additive | +0.480 |
iod | +0.476 |
SHARE | +0.437 |
Neg logit contributions | |
between | -0.391 |
Gaw | -0.358 |
undertaking | -0.317 |
pty | -0.298 |
devices | -0.291 |
Token | . |
Token ID | 13 |
Feature activation | -4.62e-02 |
Pos logit contributions | |
united | +0.029 |
CTV | +0.026 |
additive | +0.022 |
iod | +0.022 |
SHARE | +0.019 |
Neg logit contributions | |
between | -0.027 |
Gaw | -0.025 |
undertaking | -0.023 |
pty | -0.022 |
abus | -0.022 |
Token | With |
Token ID | 2080 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
united | +0.041 |
CTV | +0.037 |
additive | +0.031 |
iod | +0.031 |
SHARE | +0.028 |
Neg logit contributions | |
between | -0.036 |
Gaw | -0.034 |
undertaking | -0.030 |
pty | -0.029 |
abus | -0.029 |
Token | the |
Token ID | 262 |
Feature activation | -7.48e-02 |
Pos logit contributions | |
united | +0.014 |
CTV | +0.013 |
additive | +0.011 |
iod | +0.011 |
SHARE | +0.010 |
Neg logit contributions | |
between | -0.011 |
Gaw | -0.010 |
undertaking | -0.009 |
pty | -0.009 |
abus | -0.009 |
Token | slot |
Token ID | 10852 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
united | +0.067 |
CTV | +0.062 |
additive | +0.051 |
iod | +0.050 |
SHARE | +0.046 |
Neg logit contributions | |
between | -0.058 |
Gaw | -0.054 |
undertaking | -0.049 |
pty | -0.046 |
abus | -0.046 |
Token | small |
Token ID | 1402 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
between | +0.012 |
Gaw | +0.011 |
undertaking | +0.010 |
pty | +0.010 |
abus | +0.010 |
Neg logit contributions | |
united | -0.014 |
CTV | -0.013 |
additive | -0.011 |
iod | -0.010 |
SHARE | -0.009 |
Token | distance |
Token ID | 5253 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
united | +0.076 |
CTV | +0.068 |
additive | +0.054 |
iod | +0.053 |
SHARE | +0.047 |
Neg logit contributions | |
between | -0.094 |
Gaw | -0.088 |
undertaking | -0.081 |
pty | -0.078 |
abus | -0.077 |
Token | to |
Token ID | 284 |
Feature activation | +2.61e-02 |
Pos logit contributions | |
united | +0.080 |
CTV | +0.072 |
additive | +0.056 |
iod | +0.055 |
SHARE | +0.048 |
Neg logit contributions | |
between | -0.108 |
Gaw | -0.101 |
undertaking | -0.094 |
pty | -0.090 |
abus | -0.089 |
Token | the |
Token ID | 262 |
Feature activation | -4.85e-02 |
Pos logit contributions | |
between | +0.019 |
Gaw | +0.018 |
undertaking | +0.016 |
pty | +0.015 |
abus | +0.015 |
Neg logit contributions | |
united | -0.024 |
CTV | -0.022 |
additive | -0.019 |
iod | -0.019 |
SHARE | -0.017 |
Token | mountain |
Token ID | 8598 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
united | +0.042 |
CTV | +0.038 |
additive | +0.032 |
iod | +0.031 |
SHARE | +0.028 |
Neg logit contributions | |
between | -0.039 |
Gaw | -0.037 |
undertaking | -0.033 |
pty | -0.032 |
abus | -0.031 |
Token | shack |
Token ID | 32772 |
Feature activation | -5.92e-01 |
Pos logit contributions | |
between | +0.160 |
Gaw | +0.149 |
undertaking | +0.135 |
pty | +0.129 |
abus | +0.127 |
Neg logit contributions | |
united | -0.179 |
CTV | -0.163 |
additive | -0.135 |
iod | -0.133 |
SHARE | -0.121 |
Token | , |
Token ID | 11 |
Feature activation | -2.87e-02 |
Pos logit contributions | |
united | +0.519 |
CTV | +0.473 |
additive | +0.393 |
iod | +0.386 |
SHARE | +0.349 |
Neg logit contributions | |
between | -0.470 |
Gaw | -0.436 |
undertaking | -0.396 |
pty | -0.380 |
abus | -0.374 |
Token | and |
Token ID | 290 |
Feature activation | -4.52e-02 |
Pos logit contributions | |
united | +0.027 |
CTV | +0.025 |
additive | +0.021 |
iod | +0.021 |
SHARE | +0.019 |
Neg logit contributions | |
between | -0.020 |
Gaw | -0.019 |
undertaking | -0.017 |
pty | -0.016 |
abus | -0.016 |
Token | by |
Token ID | 416 |
Feature activation | -9.08e-02 |
Pos logit contributions | |
united | +0.043 |
CTV | +0.039 |
additive | +0.033 |
iod | +0.033 |
Bravo | +0.030 |
Neg logit contributions | |
between | -0.033 |
Gaw | -0.030 |
undertaking | -0.027 |
pty | -0.026 |
abus | -0.026 |
Token | the |
Token ID | 262 |
Feature activation | -1.76e-02 |
Pos logit contributions | |
united | +0.087 |
CTV | +0.079 |
additive | +0.068 |
iod | +0.067 |
Bravo | +0.061 |
Neg logit contributions | |
between | -0.064 |
Gaw | -0.059 |
undertaking | -0.053 |
pty | -0.051 |
abus | -0.050 |
Token | time |
Token ID | 640 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
united | +0.018 |
CTV | +0.016 |
additive | +0.014 |
iod | +0.014 |
Bravo | +0.013 |
Neg logit contributions | |
between | -0.012 |
Gaw | -0.011 |
undertaking | -0.010 |
pty | -0.009 |
abus | -0.009 |
Token | total |
Token ID | 2472 |
Feature activation | +9.72e-02 |
Pos logit contributions | |
united | +0.068 |
CTV | +0.062 |
additive | +0.052 |
iod | +0.051 |
SHARE | +0.046 |
Neg logit contributions | |
between | -0.058 |
Gaw | -0.054 |
undertaking | -0.049 |
pty | -0.047 |
abus | -0.046 |
Token | mass |
Token ID | 2347 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
between | +0.083 |
Gaw | +0.077 |
undertaking | +0.071 |
pty | +0.068 |
abus | +0.067 |
Neg logit contributions | |
united | -0.080 |
CTV | -0.072 |
additive | -0.059 |
iod | -0.058 |
SHARE | -0.052 |
Token | that |
Token ID | 326 |
Feature activation | -4.32e-02 |
Pos logit contributions | |
united | +0.106 |
CTV | +0.098 |
additive | +0.082 |
iod | +0.081 |
SHARE | +0.074 |
Neg logit contributions | |
between | -0.084 |
Gaw | -0.078 |
undertaking | -0.070 |
pty | -0.067 |
abus | -0.066 |
Token | the |
Token ID | 262 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
united | +0.038 |
CTV | +0.035 |
additive | +0.029 |
iod | +0.029 |
SHARE | +0.026 |
Neg logit contributions | |
between | -0.034 |
Gaw | -0.031 |
undertaking | -0.028 |
pty | -0.027 |
abus | -0.027 |
Token | v |
Token ID | 410 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
united | +0.110 |
CTV | +0.101 |
additive | +0.084 |
iod | +0.083 |
SHARE | +0.075 |
Neg logit contributions | |
between | -0.094 |
Gaw | -0.087 |
undertaking | -0.079 |
pty | -0.075 |
abus | -0.074 |
Token | ort |
Token ID | 419 |
Feature activation | -5.91e-01 |
Pos logit contributions | |
united | +0.234 |
CTV | +0.210 |
additive | +0.166 |
iod | +0.163 |
SHARE | +0.142 |
Neg logit contributions | |
between | -0.308 |
Gaw | -0.288 |
undertaking | -0.267 |
pty | -0.258 |
abus | -0.254 |
Token | ons |
Token ID | 684 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
united | +0.435 |
CTV | +0.391 |
additive | +0.310 |
iod | +0.304 |
SHARE | +0.266 |
Neg logit contributions | |
between | -0.553 |
Gaw | -0.519 |
undertaking | -0.480 |
pty | -0.462 |
abus | -0.456 |
Token | carry |
Token ID | 3283 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
united | +0.323 |
CTV | +0.292 |
additive | +0.238 |
iod | +0.234 |
SHARE | +0.207 |
Neg logit contributions | |
between | -0.348 |
Gaw | -0.326 |
undertaking | -0.298 |
pty | -0.287 |
abus | -0.283 |
Token | needs |
Token ID | 2476 |
Feature activation | +7.20e-02 |
Pos logit contributions | |
united | +0.216 |
CTV | +0.200 |
additive | +0.171 |
iod | +0.169 |
SHARE | +0.154 |
Neg logit contributions | |
between | -0.149 |
Gaw | -0.137 |
undertaking | -0.121 |
pty | -0.116 |
abus | -0.113 |
Token | to |
Token ID | 284 |
Feature activation | -2.85e-02 |
Pos logit contributions | |
between | +0.053 |
Gaw | +0.049 |
undertaking | +0.044 |
pty | +0.042 |
abus | +0.041 |
Neg logit contributions | |
united | -0.068 |
CTV | -0.062 |
additive | -0.053 |
iod | -0.052 |
SHARE | -0.047 |
Token | match |
Token ID | 2872 |
Feature activation | -4.12e-02 |
Pos logit contributions | |
united | +0.026 |
CTV | +0.024 |
additive | +0.020 |
iod | +0.020 |
SHARE | +0.018 |
Neg logit contributions | |
between | -0.021 |
Gaw | -0.020 |
undertaking | -0.018 |
pty | -0.017 |
abus | -0.017 |
Token | publication |
Token ID | 9207 |
Feature activation | +6.99e-02 |
Pos logit contributions | |
between | +0.044 |
Gaw | +0.040 |
undertaking | +0.035 |
pty | +0.033 |
abus | +0.032 |
Neg logit contributions | |
united | -0.083 |
CTV | -0.077 |
additive | -0.067 |
iod | -0.066 |
SHARE | -0.061 |
Token | in |
Token ID | 287 |
Feature activation | +4.52e-02 |
Pos logit contributions | |
between | +0.054 |
Gaw | +0.050 |
undertaking | +0.046 |
pty | +0.043 |
abus | +0.043 |
Neg logit contributions | |
united | -0.063 |
CTV | -0.057 |
additive | -0.048 |
iod | -0.047 |
SHARE | -0.043 |
Token | the |
Token ID | 262 |
Feature activation | -2.69e-02 |
Pos logit contributions | |
between | +0.033 |
Gaw | +0.031 |
undertaking | +0.028 |
pty | +0.026 |
abus | +0.026 |
Neg logit contributions | |
united | -0.043 |
CTV | -0.039 |
additive | -0.033 |
iod | -0.032 |
SHARE | -0.030 |
Token | Ast |
Token ID | 8304 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
united | +0.026 |
CTV | +0.024 |
additive | +0.020 |
iod | +0.020 |
SHARE | +0.018 |
Neg logit contributions | |
between | -0.019 |
Gaw | -0.017 |
undertaking | -0.016 |
pty | -0.015 |
abus | -0.014 |
Token | roph |
Token ID | 10051 |
Feature activation | -9.91e-02 |
Pos logit contributions | |
united | +0.254 |
CTV | +0.236 |
additive | +0.204 |
iod | +0.201 |
SHARE | +0.187 |
Neg logit contributions | |
between | -0.137 |
Gaw | -0.124 |
undertaking | -0.108 |
pty | -0.101 |
abus | -0.099 |
Token | ysical |
Token ID | 15380 |
Feature activation | -5.88e-01 |
Pos logit contributions | |
united | +0.050 |
CTV | +0.042 |
additive | +0.029 |
iod | +0.027 |
SHARE | +0.021 |
Neg logit contributions | |
between | -0.116 |
Gaw | -0.110 |
undertaking | -0.104 |
pty | -0.101 |
abus | -0.100 |
Token | Journal |
Token ID | 4913 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
united | +0.394 |
CTV | +0.349 |
additive | +0.271 |
iod | +0.265 |
SHARE | +0.226 |
Neg logit contributions | |
between | -0.587 |
Gaw | -0.556 |
undertaking | -0.515 |
pty | -0.499 |
abus | -0.493 |
Token | ( |
Token ID | 357 |
Feature activation | -5.22e-02 |
Pos logit contributions | |
united | +0.277 |
CTV | +0.253 |
additive | +0.213 |
iod | +0.209 |
Bravo | +0.189 |
Neg logit contributions | |
between | -0.235 |
Gaw | -0.217 |
undertaking | -0.196 |
pty | -0.188 |
abus | -0.184 |
Token | ar |
Token ID | 283 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
united | +0.046 |
CTV | +0.042 |
additive | +0.035 |
iod | +0.034 |
SHARE | +0.031 |
Neg logit contributions | |
between | -0.042 |
Gaw | -0.039 |
undertaking | -0.035 |
pty | -0.033 |
abus | -0.033 |
Token | X |
Token ID | 55 |
Feature activation | -4.70e-02 |
Pos logit contributions | |
united | +0.153 |
CTV | +0.140 |
additive | +0.115 |
iod | +0.112 |
SHARE | +0.101 |
Neg logit contributions | |
between | -0.152 |
Gaw | -0.142 |
undertaking | -0.130 |
pty | -0.124 |
devices | -0.121 |
Token | iv |
Token ID | 452 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
united | +0.054 |
CTV | +0.050 |
additive | +0.044 |
iod | +0.043 |
SHARE | +0.041 |
Neg logit contributions | |
between | -0.024 |
Gaw | -0.023 |
undertaking | -0.019 |
pty | -0.018 |
devices | -0.017 |
Token | format |
Token ID | 5794 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
united | +0.082 |
CTV | +0.075 |
additive | +0.063 |
iod | +0.062 |
SHARE | +0.056 |
Neg logit contributions | |
between | -0.070 |
Gaw | -0.064 |
undertaking | -0.058 |
pty | -0.056 |
abus | -0.055 |
Token | , |
Token ID | 11 |
Feature activation | -9.19e-02 |
Pos logit contributions | |
united | +0.150 |
CTV | +0.137 |
additive | +0.115 |
iod | +0.113 |
SHARE | +0.102 |
Neg logit contributions | |
between | -0.127 |
Gaw | -0.117 |
undertaking | -0.106 |
pty | -0.101 |
abus | -0.100 |
Token | enabling |
Token ID | 15882 |
Feature activation | -6.05e-02 |
Pos logit contributions | |
united | +0.099 |
CTV | +0.092 |
additive | +0.080 |
iod | +0.079 |
SHARE | +0.073 |
Neg logit contributions | |
between | -0.054 |
Gaw | -0.049 |
undertaking | -0.042 |
pty | -0.040 |
abus | -0.039 |
Token | a |
Token ID | 257 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
united | +0.051 |
CTV | +0.046 |
additive | +0.038 |
iod | +0.037 |
SHARE | +0.034 |
Neg logit contributions | |
between | -0.050 |
Gaw | -0.047 |
undertaking | -0.043 |
pty | -0.041 |
abus | -0.040 |
Token | single |
Token ID | 2060 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
between | +0.011 |
Gaw | +0.011 |
undertaking | +0.010 |
pty | +0.009 |
abus | +0.009 |
Neg logit contributions | |
united | -0.011 |
CTV | -0.010 |
additive | -0.008 |
iod | -0.008 |
SHARE | -0.007 |
Token | binary |
Token ID | 13934 |
Feature activation | -5.87e-01 |
Pos logit contributions | |
united | +0.341 |
CTV | +0.312 |
additive | +0.256 |
iod | +0.254 |
SHARE | +0.230 |
Neg logit contributions | |
between | -0.302 |
Gaw | -0.281 |
undertaking | -0.256 |
pty | -0.243 |
abus | -0.237 |
Token | package |
Token ID | 5301 |
Feature activation | -5.75e-02 |
Pos logit contributions | |
united | +0.536 |
CTV | +0.491 |
additive | +0.411 |
iod | +0.405 |
SHARE | +0.367 |
Neg logit contributions | |
between | -0.446 |
Gaw | -0.412 |
undertaking | -0.373 |
pty | -0.355 |
abus | -0.349 |
Token | to |
Token ID | 284 |
Feature activation | -2.51e-02 |
Pos logit contributions | |
united | +0.053 |
CTV | +0.048 |
additive | +0.041 |
iod | +0.040 |
SHARE | +0.036 |
Neg logit contributions | |
between | -0.043 |
Gaw | -0.040 |
undertaking | -0.036 |
pty | -0.034 |
abus | -0.034 |
Token | work |
Token ID | 670 |
Feature activation | -8.81e-02 |
Pos logit contributions | |
united | +0.024 |
CTV | +0.023 |
additive | +0.019 |
iod | +0.019 |
SHARE | +0.017 |
Neg logit contributions | |
between | -0.018 |
Gaw | -0.016 |
undertaking | -0.014 |
pty | -0.014 |
abus | -0.013 |
Token | perfectly |
Token ID | 7138 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
united | +0.072 |
CTV | +0.066 |
additive | +0.053 |
iod | +0.053 |
SHARE | +0.047 |
Neg logit contributions | |
between | -0.075 |
Gaw | -0.070 |
undertaking | -0.064 |
pty | -0.061 |
abus | -0.060 |
Token | and |
Token ID | 290 |
Feature activation | -5.21e-02 |
Pos logit contributions | |
united | +0.209 |
CTV | +0.191 |
additive | +0.156 |
iod | +0.154 |
SHARE | +0.139 |
Neg logit contributions | |
between | -0.204 |
Gaw | -0.189 |
undertaking | -0.173 |
pty | -0.165 |
abus | -0.162 |
Token | Get |
Token ID | 3855 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
united | +0.062 |
CTV | +0.055 |
additive | +0.042 |
iod | +0.041 |
SHARE | +0.036 |
Neg logit contributions | |
between | -0.094 |
Gaw | -0.089 |
undertaking | -0.083 |
pty | -0.080 |
abus | -0.079 |
Token | Mass |
Token ID | 20273 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
united | +0.176 |
CTV | +0.159 |
additive | +0.128 |
iod | +0.125 |
SHARE | +0.111 |
Neg logit contributions | |
between | -0.202 |
Gaw | -0.189 |
undertaking | -0.174 |
pty | -0.167 |
abus | -0.165 |
Token | ( |
Token ID | 7 |
Feature activation | +2.75e-02 |
Pos logit contributions | |
united | +0.227 |
CTV | +0.207 |
additive | +0.172 |
iod | +0.169 |
SHARE | +0.152 |
Neg logit contributions | |
between | -0.210 |
Gaw | -0.195 |
undertaking | -0.177 |
pty | -0.169 |
abus | -0.167 |
Token | ambient |
Token ID | 25237 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
between | +0.022 |
Gaw | +0.021 |
undertaking | +0.019 |
pty | +0.018 |
abus | +0.018 |
Neg logit contributions | |
united | -0.023 |
CTV | -0.021 |
additive | -0.018 |
iod | -0.017 |
SHARE | -0.016 |
Token | D |
Token ID | 35 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
united | +0.201 |
CTV | +0.183 |
additive | +0.149 |
iod | +0.148 |
SHARE | +0.132 |
Neg logit contributions | |
between | -0.204 |
Gaw | -0.189 |
undertaking | -0.173 |
pty | -0.166 |
abus | -0.164 |
Token | ensity |
Token ID | 6377 |
Feature activation | -5.85e-01 |
Pos logit contributions | |
united | +0.118 |
CTV | +0.105 |
additive | +0.080 |
iod | +0.079 |
SHARE | +0.068 |
Neg logit contributions | |
between | -0.180 |
Gaw | -0.168 |
undertaking | -0.157 |
pty | -0.152 |
abus | -0.150 |
Token | ). |
Token ID | 6739 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
united | +0.471 |
CTV | +0.427 |
additive | +0.346 |
iod | +0.341 |
SHARE | +0.303 |
Neg logit contributions | |
between | -0.508 |
Gaw | -0.474 |
undertaking | -0.435 |
pty | -0.417 |
abus | -0.411 |
Token | // |
Token ID | 3373 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
united | +0.127 |
CTV | +0.116 |
additive | +0.095 |
iod | +0.094 |
SHARE | +0.084 |
Neg logit contributions | |
between | -0.122 |
Gaw | -0.114 |
undertaking | -0.104 |
pty | -0.099 |
abus | -0.098 |
Token | This |
Token ID | 770 |
Feature activation | -4.03e-02 |
Pos logit contributions | |
united | +0.135 |
CTV | +0.124 |
additive | +0.103 |
iod | +0.101 |
SHARE | +0.091 |
Neg logit contributions | |
between | -0.124 |
Gaw | -0.115 |
undertaking | -0.105 |
pty | -0.100 |
abus | -0.099 |
Token | is |
Token ID | 318 |
Feature activation | +6.53e-02 |
Pos logit contributions | |
united | +0.037 |
CTV | +0.034 |
additive | +0.029 |
iod | +0.028 |
SHARE | +0.026 |
Neg logit contributions | |
between | -0.030 |
Gaw | -0.028 |
undertaking | -0.025 |
pty | -0.024 |
abus | -0.024 |
Token | because |
Token ID | 780 |
Feature activation | +3.05e-02 |
Pos logit contributions | |
between | +0.050 |
Gaw | +0.046 |
undertaking | +0.041 |
pty | +0.040 |
abus | +0.039 |
Neg logit contributions | |
united | -0.060 |
CTV | -0.055 |
additive | -0.046 |
iod | -0.045 |
SHARE | -0.041 |
Token | Far |
Token ID | 6755 |
Feature activation | -4.81e-03 |
Pos logit contributions | |
between | +0.024 |
Gaw | +0.022 |
undertaking | +0.020 |
pty | +0.019 |
abus | +0.019 |
Neg logit contributions | |
united | -0.029 |
CTV | -0.027 |
additive | -0.022 |
iod | -0.022 |
SHARE | -0.020 |
Token | rah |
Token ID | 11392 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
united | +0.004 |
CTV | +0.003 |
additive | +0.003 |
iod | +0.003 |
Bravo | +0.002 |
Neg logit contributions | |
between | -0.004 |
Gaw | -0.004 |
undertaking | -0.004 |
pty | -0.003 |
abus | -0.003 |
Token | W |
Token ID | 370 |
Feature activation | +5.29e-02 |
Pos logit contributions | |
between | +0.094 |
Gaw | +0.085 |
undertaking | +0.075 |
pty | +0.070 |
abus | +0.069 |
Neg logit contributions | |
united | -0.159 |
CTV | -0.148 |
additive | -0.127 |
iod | -0.126 |
SHARE | -0.116 |
Token | ether |
Token ID | 6750 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
between | +0.039 |
Gaw | +0.036 |
undertaking | +0.032 |
pty | +0.031 |
abus | +0.030 |
Neg logit contributions | |
united | -0.049 |
CTV | -0.045 |
additive | -0.038 |
iod | -0.038 |
SHARE | -0.034 |
Token | s |
Token ID | 82 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
united | +0.183 |
CTV | +0.168 |
additive | +0.142 |
iod | +0.140 |
Bravo | +0.128 |
Neg logit contributions | |
between | -0.136 |
Gaw | -0.125 |
undertaking | -0.113 |
pty | -0.107 |
abus | -0.106 |
Token | Mysteries |
Token ID | 28298 |
Feature activation | -5.83e-01 |
Pos logit contributions | |
between | +0.088 |
Gaw | +0.082 |
undertaking | +0.075 |
pty | +0.071 |
abus | +0.070 |
Neg logit contributions | |
united | -0.093 |
CTV | -0.085 |
additive | -0.070 |
iod | -0.069 |
SHARE | -0.062 |
Token | , |
Token ID | 11 |
Feature activation | -4.30e-02 |
Pos logit contributions | |
united | +0.495 |
CTV | +0.451 |
additive | +0.371 |
iod | +0.365 |
SHARE | +0.328 |
Neg logit contributions | |
between | -0.480 |
Gaw | -0.447 |
undertaking | -0.408 |
pty | -0.390 |
abus | -0.385 |
Token | comic |
Token ID | 9048 |
Feature activation | +3.73e-02 |
Pos logit contributions | |
united | +0.039 |
CTV | +0.036 |
additive | +0.030 |
iod | +0.029 |
Bravo | +0.027 |
Neg logit contributions | |
between | -0.033 |
Gaw | -0.030 |
undertaking | -0.027 |
pty | -0.026 |
abus | -0.026 |
Token | book |
Token ID | 1492 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
between | +0.025 |
Gaw | +0.023 |
undertaking | +0.020 |
pty | +0.019 |
abus | +0.019 |
Neg logit contributions | |
united | -0.037 |
CTV | -0.034 |
additive | -0.029 |
iod | -0.029 |
Bravo | -0.027 |
Token | short |
Token ID | 1790 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
between | +0.162 |
Gaw | +0.150 |
undertaking | +0.136 |
pty | +0.130 |
abus | +0.127 |
Neg logit contributions | |
united | -0.195 |
CTV | -0.179 |
additive | -0.150 |
iod | -0.147 |
SHARE | -0.134 |
Token | stories |
Token ID | 3923 |
Feature activation | -8.53e-02 |
Pos logit contributions | |
united | +0.171 |
CTV | +0.157 |
additive | +0.132 |
iod | +0.129 |
SHARE | +0.118 |
Neg logit contributions | |
between | -0.141 |
Gaw | -0.130 |
undertaking | -0.118 |
pty | -0.112 |
abus | -0.111 |
Token | Bal |
Token ID | 8528 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
between | +0.063 |
Gaw | +0.058 |
undertaking | +0.053 |
pty | +0.050 |
abus | +0.049 |
Neg logit contributions | |
united | -0.079 |
CTV | -0.072 |
additive | -0.061 |
iod | -0.060 |
Bravo | -0.055 |
Token | rog |
Token ID | 3828 |
Feature activation | +9.58e-02 |
Pos logit contributions | |
between | +0.221 |
Gaw | +0.206 |
undertaking | +0.188 |
pty | +0.178 |
devices | +0.175 |
Neg logit contributions | |
united | -0.256 |
CTV | -0.233 |
additive | -0.194 |
iod | -0.191 |
SHARE | -0.172 |
Token | . |
Token ID | 13 |
Feature activation | +8.50e-03 |
Pos logit contributions | |
between | +0.074 |
Gaw | +0.068 |
undertaking | +0.062 |
pty | +0.059 |
abus | +0.059 |
Neg logit contributions | |
united | -0.086 |
CTV | -0.079 |
additive | -0.065 |
iod | -0.064 |
Bravo | -0.059 |
Token | Gand |
Token ID | 17727 |
Feature activation | +4.79e-02 |
Pos logit contributions | |
between | +0.007 |
Gaw | +0.006 |
undertaking | +0.006 |
pty | +0.005 |
abus | +0.005 |
Neg logit contributions | |
united | -0.008 |
CTV | -0.007 |
additive | -0.006 |
iod | -0.006 |
Bravo | -0.005 |
Token | alf |
Token ID | 1604 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
between | +0.033 |
Gaw | +0.030 |
undertaking | +0.027 |
pty | +0.026 |
abus | +0.025 |
Neg logit contributions | |
united | -0.047 |
CTV | -0.043 |
additive | -0.037 |
iod | -0.036 |
SHARE | -0.033 |
Token | faces |
Token ID | 6698 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
between | +0.148 |
Gaw | +0.136 |
undertaking | +0.123 |
pty | +0.117 |
abus | +0.115 |
Neg logit contributions | |
united | -0.185 |
CTV | -0.170 |
additive | -0.143 |
iod | -0.141 |
SHARE | -0.129 |
Token | the |
Token ID | 262 |
Feature activation | +3.06e-02 |
Pos logit contributions | |
between | +0.316 |
Gaw | +0.292 |
undertaking | +0.267 |
pty | +0.256 |
abus | +0.252 |
Neg logit contributions | |
united | -0.334 |
CTV | -0.305 |
additive | -0.252 |
iod | -0.248 |
Bravo | -0.223 |
Token | Bal |
Token ID | 8528 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
between | +0.022 |
Gaw | +0.020 |
undertaking | +0.018 |
pty | +0.017 |
abus | +0.017 |
Neg logit contributions | |
united | -0.030 |
CTV | -0.027 |
additive | -0.023 |
iod | -0.023 |
Bravo | -0.021 |
Token | rog |
Token ID | 3828 |
Feature activation | +6.57e-02 |
Pos logit contributions | |
between | +0.160 |
Gaw | +0.147 |
undertaking | +0.131 |
pty | +0.122 |
abus | +0.118 |
Neg logit contributions | |
united | -0.269 |
CTV | -0.249 |
additive | -0.213 |
iod | -0.210 |
Bravo | -0.194 |
Token | , |
Token ID | 11 |
Feature activation | -2.50e-02 |
Pos logit contributions | |
between | +0.053 |
Gaw | +0.049 |
undertaking | +0.044 |
pty | +0.042 |
abus | +0.042 |
Neg logit contributions | |
united | -0.057 |
CTV | -0.052 |
additive | -0.043 |
iod | -0.043 |
Bravo | -0.038 |
Token | and |
Token ID | 290 |
Feature activation | -4.24e-02 |
Pos logit contributions | |
united | +0.026 |
CTV | +0.024 |
additive | +0.021 |
iod | +0.021 |
Bravo | +0.019 |
Neg logit contributions | |
between | -0.015 |
Gaw | -0.014 |
undertaking | -0.012 |
pty | -0.012 |
abus | -0.012 |
Token | come |
Token ID | 1282 |
Feature activation | -9.05e-02 |
Pos logit contributions | |
between | +0.050 |
Gaw | +0.046 |
undertaking | +0.042 |
pty | +0.040 |
abus | +0.040 |
Neg logit contributions | |
united | -0.054 |
CTV | -0.049 |
additive | -0.040 |
iod | -0.040 |
SHARE | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | +2.61e-02 |
Pos logit contributions | |
united | +0.076 |
CTV | +0.069 |
additive | +0.057 |
iod | +0.056 |
SHARE | +0.050 |
Neg logit contributions | |
between | -0.075 |
Gaw | -0.070 |
undertaking | -0.064 |
pty | -0.062 |
abus | -0.061 |
Token | She |
Token ID | 1375 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
between | +0.020 |
Gaw | +0.019 |
undertaking | +0.017 |
pty | +0.016 |
abus | +0.016 |
Neg logit contributions | |
united | -0.023 |
CTV | -0.021 |
additive | -0.018 |
iod | -0.017 |
SHARE | -0.016 |
Token | finds |
Token ID | 7228 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
united | +0.116 |
CTV | +0.107 |
additive | +0.090 |
iod | +0.088 |
SHARE | +0.080 |
Neg logit contributions | |
between | -0.094 |
Gaw | -0.086 |
undertaking | -0.078 |
pty | -0.074 |
abus | -0.073 |
Token | a |
Token ID | 257 |
Feature activation | +4.80e-02 |
Pos logit contributions | |
between | +0.330 |
Gaw | +0.310 |
undertaking | +0.288 |
pty | +0.279 |
abus | +0.276 |
Neg logit contributions | |
united | -0.230 |
CTV | -0.205 |
additive | -0.159 |
iod | -0.156 |
SHARE | -0.135 |
Token | sword |
Token ID | 8429 |
Feature activation | +3.96e-01 |
Pos logit contributions | |
between | +0.039 |
Gaw | +0.037 |
undertaking | +0.034 |
pty | +0.032 |
abus | +0.032 |
Neg logit contributions | |
united | -0.041 |
CTV | -0.037 |
additive | -0.031 |
iod | -0.030 |
SHARE | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | -2.27e-02 |
Pos logit contributions | |
between | +0.307 |
Gaw | +0.285 |
undertaking | +0.258 |
pty | +0.247 |
abus | +0.243 |
Neg logit contributions | |
united | -0.355 |
CTV | -0.325 |
additive | -0.271 |
iod | -0.267 |
SHARE | -0.241 |
Token | hops |
Token ID | 29438 |
Feature activation | +4.53e-03 |
Pos logit contributions | |
united | +0.021 |
CTV | +0.020 |
additive | +0.017 |
iod | +0.016 |
SHARE | +0.015 |
Neg logit contributions | |
between | -0.016 |
Gaw | -0.015 |
undertaking | -0.014 |
pty | -0.013 |
abus | -0.013 |
Token | on |
Token ID | 319 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
between | +0.004 |
Gaw | +0.004 |
undertaking | +0.004 |
pty | +0.004 |
abus | +0.004 |
Neg logit contributions | |
united | -0.003 |
CTV | -0.003 |
additive | -0.002 |
iod | -0.002 |
SHARE | -0.002 |
Token | her |
Token ID | 607 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
united | +0.161 |
CTV | +0.148 |
additive | +0.125 |
iod | +0.123 |
Bravo | +0.112 |
Neg logit contributions | |
between | -0.130 |
Gaw | -0.119 |
undertaking | -0.108 |
pty | -0.103 |
abus | -0.101 |
Token | dragon |
Token ID | 10441 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
united | +0.328 |
CTV | +0.304 |
additive | +0.259 |
iod | +0.255 |
SHARE | +0.234 |
Neg logit contributions | |
between | -0.224 |
Gaw | -0.205 |
undertaking | -0.183 |
pty | -0.174 |
abus | -0.170 |
Token | gamble |
Token ID | 32385 |
Feature activation | -8.77e-02 |
Pos logit contributions | |
between | +0.030 |
Gaw | +0.027 |
undertaking | +0.025 |
pty | +0.024 |
abus | +0.023 |
Neg logit contributions | |
united | -0.039 |
CTV | -0.035 |
additive | -0.030 |
iod | -0.030 |
SHARE | -0.027 |
Token | ' |
Token ID | 6 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
united | +0.082 |
CTV | +0.075 |
additive | +0.063 |
iod | +0.062 |
SHARE | +0.057 |
Neg logit contributions | |
between | -0.065 |
Gaw | -0.060 |
undertaking | -0.054 |
pty | -0.051 |
devices | -0.050 |
Token |
|
Token ID | 198 |
Feature activation | +4.42e-02 |
Pos logit contributions | |
between | +0.087 |
Gaw | +0.081 |
undertaking | +0.073 |
pty | +0.070 |
abus | +0.069 |
Neg logit contributions | |
united | -0.103 |
CTV | -0.095 |
additive | -0.079 |
iod | -0.078 |
SHARE | -0.071 |
Token |
|
Token ID | 198 |
Feature activation | +4.71e-02 |
Pos logit contributions | |
between | +0.033 |
Gaw | +0.031 |
undertaking | +0.028 |
pty | +0.027 |
abus | +0.027 |
Neg logit contributions | |
united | -0.040 |
CTV | -0.037 |
additive | -0.031 |
iod | -0.030 |
SHARE | -0.028 |
Token | While |
Token ID | 3633 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
between | +0.032 |
Gaw | +0.030 |
undertaking | +0.027 |
pty | +0.025 |
abus | +0.025 |
Neg logit contributions | |
united | -0.047 |
CTV | -0.043 |
additive | -0.035 |
iod | -0.035 |
SHARE | -0.034 |
Token | Lord |
Token ID | 4453 |
Feature activation | +4.53e-01 |
Pos logit contributions | |
between | +0.158 |
Gaw | +0.142 |
undertaking | +0.124 |
pty | +0.122 |
abus | +0.120 |
Neg logit contributions | |
united | -0.240 |
CTV | -0.221 |
additive | -0.191 |
iod | -0.188 |
Bravo | -0.173 |
Token | Hes |
Token ID | 44773 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
between | +0.337 |
Gaw | +0.308 |
undertaking | +0.279 |
pty | +0.266 |
abus | +0.261 |
Neg logit contributions | |
united | -0.422 |
CTV | -0.387 |
additive | -0.327 |
iod | -0.321 |
Bravo | -0.293 |
Token | elt |
Token ID | 2120 |
Feature activation | -2.62e-02 |
Pos logit contributions | |
united | +0.141 |
CTV | +0.132 |
additive | +0.111 |
iod | +0.109 |
SHARE | +0.101 |
Neg logit contributions | |
between | -0.103 |
Gaw | -0.093 |
undertaking | -0.084 |
pty | -0.080 |
abus | -0.078 |
Token | ine |
Token ID | 500 |
Feature activation | +3.51e-02 |
Pos logit contributions | |
united | +0.028 |
CTV | +0.026 |
additive | +0.023 |
iod | +0.023 |
SHARE | +0.021 |
Neg logit contributions | |
between | -0.015 |
Gaw | -0.014 |
undertaking | -0.012 |
pty | -0.011 |
abus | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | +4.26e-02 |
Pos logit contributions | |
between | +0.025 |
Gaw | +0.023 |
undertaking | +0.021 |
pty | +0.020 |
abus | +0.019 |
Neg logit contributions | |
united | -0.034 |
CTV | -0.031 |
additive | -0.026 |
iod | -0.026 |
SHARE | -0.024 |
Token | a |
Token ID | 257 |
Feature activation | +5.65e-02 |
Pos logit contributions | |
between | +0.028 |
Gaw | +0.025 |
undertaking | +0.022 |
pty | +0.021 |
abus | +0.021 |
Neg logit contributions | |
united | -0.043 |
CTV | -0.040 |
additive | -0.035 |
iod | -0.034 |
Bravo | -0.032 |
Token | ache |
Token ID | 4891 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
between | +0.103 |
Gaw | +0.095 |
undertaking | +0.085 |
pty | +0.080 |
devices | +0.079 |
Neg logit contributions | |
united | -0.148 |
CTV | -0.136 |
additive | -0.115 |
iod | -0.114 |
SHARE | -0.104 |
Token | and |
Token ID | 290 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
between | +0.103 |
Gaw | +0.095 |
undertaking | +0.086 |
pty | +0.081 |
abus | +0.080 |
Neg logit contributions | |
united | -0.136 |
CTV | -0.125 |
additive | -0.106 |
iod | -0.104 |
SHARE | -0.095 |
Token | a |
Token ID | 257 |
Feature activation | +7.84e-02 |
Pos logit contributions | |
united | +0.013 |
CTV | +0.012 |
additive | +0.010 |
iod | +0.010 |
Bravo | +0.009 |
Neg logit contributions | |
between | -0.011 |
Gaw | -0.010 |
undertaking | -0.009 |
pty | -0.008 |
abus | -0.008 |
Token | bit |
Token ID | 1643 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
between | +0.062 |
Gaw | +0.057 |
undertaking | +0.052 |
pty | +0.050 |
abus | +0.049 |
Neg logit contributions | |
united | -0.069 |
CTV | -0.063 |
additive | -0.052 |
iod | -0.052 |
SHARE | -0.047 |
Token | of |
Token ID | 286 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
united | +0.105 |
CTV | +0.097 |
additive | +0.082 |
iod | +0.081 |
SHARE | +0.073 |
Neg logit contributions | |
between | -0.080 |
Gaw | -0.074 |
undertaking | -0.066 |
pty | -0.063 |
abus | -0.062 |
Token | Paul |
Token ID | 3362 |
Feature activation | +4.84e-01 |
Pos logit contributions | |
between | +0.008 |
Gaw | +0.007 |
undertaking | +0.006 |
pty | +0.006 |
abus | +0.006 |
Neg logit contributions | |
united | -0.010 |
CTV | -0.009 |
additive | -0.008 |
iod | -0.008 |
Bravo | -0.007 |
Token | Newman |
Token ID | 27698 |
Feature activation | +5.36e-03 |
Pos logit contributions | |
between | +0.356 |
Gaw | +0.325 |
undertaking | +0.297 |
pty | +0.281 |
devices | +0.278 |
Neg logit contributions | |
united | -0.454 |
CTV | -0.416 |
additive | -0.351 |
iod | -0.344 |
Bravo | -0.318 |
Token | about |
Token ID | 546 |
Feature activation | -7.18e-03 |
Pos logit contributions | |
between | +0.004 |
Gaw | +0.004 |
undertaking | +0.004 |
pty | +0.003 |
abus | +0.003 |
Neg logit contributions | |
united | -0.005 |
CTV | -0.004 |
additive | -0.004 |
iod | -0.004 |
Bravo | -0.003 |
Token | him |
Token ID | 683 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
united | +0.005 |
CTV | +0.005 |
additive | +0.004 |
iod | +0.004 |
SHARE | +0.003 |
Neg logit contributions | |
between | -0.007 |
Gaw | -0.006 |
undertaking | -0.006 |
pty | -0.006 |
abus | -0.006 |
Token | '. |
Token ID | 4458 |
Feature activation | +3.00e-01 |
Pos logit contributions | |
united | +0.185 |
CTV | +0.170 |
additive | +0.145 |
iod | +0.143 |
SHARE | +0.131 |
Neg logit contributions | |
between | -0.129 |
Gaw | -0.118 |
undertaking | -0.105 |
pty | -0.100 |
abus | -0.098 |
Token | Photograph |
Token ID | 18903 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
between | +0.171 |
Gaw | +0.153 |
undertaking | +0.134 |
pty | +0.125 |
abus | +0.122 |
Neg logit contributions | |
united | -0.331 |
CTV | -0.308 |
additive | -0.266 |
iod | -0.263 |
SHARE | -0.245 |
Token | ists |
Token ID | 1023 |
Feature activation | -6.48e-03 |
Pos logit contributions | |
between | +0.087 |
Gaw | +0.079 |
undertaking | +0.069 |
pty | +0.064 |
abus | +0.063 |
Neg logit contributions | |
united | -0.161 |
CTV | -0.149 |
additive | -0.129 |
iod | -0.128 |
SHARE | -0.118 |
Token | have |
Token ID | 423 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
united | +0.006 |
CTV | +0.005 |
additive | +0.004 |
iod | +0.004 |
SHARE | +0.004 |
Neg logit contributions | |
between | -0.005 |
Gaw | -0.005 |
undertaking | -0.004 |
pty | -0.004 |
abus | -0.004 |
Token | been |
Token ID | 587 |
Feature activation | -3.52e-02 |
Pos logit contributions | |
united | +0.015 |
CTV | +0.013 |
additive | +0.011 |
iod | +0.011 |
SHARE | +0.010 |
Neg logit contributions | |
between | -0.012 |
Gaw | -0.011 |
undertaking | -0.010 |
pty | -0.009 |
abus | -0.009 |
Token | present |
Token ID | 1944 |
Feature activation | -2.44e-02 |
Pos logit contributions | |
united | +0.032 |
CTV | +0.030 |
additive | +0.025 |
iod | +0.025 |
SHARE | +0.022 |
Neg logit contributions | |
between | -0.026 |
Gaw | -0.024 |
undertaking | -0.022 |
pty | -0.021 |
abus | -0.021 |
Token | in |
Token ID | 287 |
Feature activation | +1.68e-02 |
Pos logit contributions | |
united | +0.022 |
CTV | +0.020 |
additive | +0.017 |
iod | +0.016 |
SHARE | +0.015 |
Neg logit contributions | |
between | -0.019 |
Gaw | -0.018 |
undertaking | -0.016 |
pty | -0.015 |
abus | -0.015 |
Token | Greece |
Token ID | 10315 |
Feature activation | +4.86e-01 |
Pos logit contributions | |
between | +0.009 |
Gaw | +0.008 |
undertaking | +0.007 |
abus | +0.006 |
pty | +0.006 |
Neg logit contributions | |
united | -0.019 |
CTV | -0.018 |
additive | -0.015 |
iod | -0.015 |
Bravo | -0.014 |
Token | from |
Token ID | 422 |
Feature activation | -3.42e-02 |
Pos logit contributions | |
between | +0.353 |
Gaw | +0.326 |
undertaking | +0.292 |
pty | +0.279 |
abus | +0.274 |
Neg logit contributions | |
united | -0.459 |
CTV | -0.421 |
additive | -0.356 |
iod | -0.350 |
SHARE | -0.319 |
Token | the |
Token ID | 262 |
Feature activation | -3.21e-02 |
Pos logit contributions | |
united | +0.032 |
CTV | +0.030 |
additive | +0.025 |
iod | +0.025 |
Bravo | +0.023 |
Neg logit contributions | |
between | -0.024 |
Gaw | -0.022 |
undertaking | -0.020 |
pty | -0.019 |
abus | -0.019 |
Token | 1900 |
Token ID | 21489 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
united | +0.034 |
CTV | +0.032 |
additive | +0.027 |
iod | +0.027 |
Bravo | +0.025 |
Neg logit contributions | |
between | -0.019 |
Gaw | -0.018 |
undertaking | -0.015 |
pty | -0.015 |
abus | -0.014 |
Token | � |
Token ID | 447 |
Feature activation | +2.18e-02 |
Pos logit contributions | |
between | +0.128 |
Gaw | +0.118 |
undertaking | +0.105 |
pty | +0.100 |
abus | +0.098 |
Neg logit contributions | |
united | -0.178 |
CTV | -0.164 |
additive | -0.139 |
iod | -0.137 |
SHARE | -0.125 |
Token | � |
Token ID | 247 |
Feature activation | +4.98e-02 |
Pos logit contributions | |
between | +0.018 |
Gaw | +0.017 |
undertaking | +0.015 |
pty | +0.015 |
abus | +0.014 |
Neg logit contributions | |
united | -0.018 |
CTV | -0.017 |
additive | -0.014 |
iod | -0.013 |
SHARE | -0.012 |
Token | communities |
Token ID | 5348 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
united | +0.044 |
CTV | +0.040 |
additive | +0.034 |
iod | +0.033 |
SHARE | +0.030 |
Neg logit contributions | |
between | -0.034 |
Gaw | -0.032 |
undertaking | -0.029 |
pty | -0.027 |
abus | -0.027 |
Token | that |
Token ID | 326 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
united | +0.155 |
CTV | +0.142 |
additive | +0.119 |
iod | +0.117 |
SHARE | +0.106 |
Neg logit contributions | |
between | -0.130 |
Gaw | -0.121 |
undertaking | -0.108 |
pty | -0.104 |
abus | -0.103 |
Token | bear |
Token ID | 6842 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
between | +0.009 |
Gaw | +0.008 |
undertaking | +0.007 |
pty | +0.007 |
abus | +0.007 |
Neg logit contributions | |
united | -0.009 |
CTV | -0.009 |
additive | -0.007 |
iod | -0.007 |
SHARE | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | +1.77e-02 |
Pos logit contributions | |
between | +0.135 |
Gaw | +0.124 |
undertaking | +0.112 |
pty | +0.107 |
abus | +0.105 |
Neg logit contributions | |
united | -0.171 |
CTV | -0.157 |
additive | -0.133 |
iod | -0.131 |
SHARE | -0.119 |
Token | extraction |
Token ID | 22236 |
Feature activation | -8.50e-02 |
Pos logit contributions | |
between | +0.012 |
Gaw | +0.011 |
undertaking | +0.009 |
pty | +0.009 |
abus | +0.009 |
Neg logit contributions | |
united | -0.018 |
CTV | -0.016 |
additive | -0.014 |
iod | -0.014 |
SHARE | -0.013 |
Token | costs |
Token ID | 3484 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
united | +0.076 |
CTV | +0.070 |
additive | +0.059 |
iod | +0.058 |
SHARE | +0.052 |
Neg logit contributions | |
between | -0.065 |
Gaw | -0.060 |
undertaking | -0.054 |
pty | -0.052 |
abus | -0.051 |
Token | . |
Token ID | 13 |
Feature activation | +6.44e-02 |
Pos logit contributions | |
between | +0.144 |
Gaw | +0.133 |
undertaking | +0.120 |
pty | +0.115 |
abus | +0.113 |
Neg logit contributions | |
united | -0.177 |
CTV | -0.163 |
additive | -0.137 |
iod | -0.135 |
SHARE | -0.122 |
Token |
|
Token ID | 198 |
Feature activation | +2.49e-02 |
Pos logit contributions | |
between | +0.050 |
Gaw | +0.046 |
undertaking | +0.042 |
pty | +0.040 |
abus | +0.040 |
Neg logit contributions | |
united | -0.057 |
CTV | -0.053 |
additive | -0.044 |
iod | -0.043 |
Bravo | -0.039 |
Token |
|
Token ID | 198 |
Feature activation | +2.59e-02 |
Pos logit contributions | |
between | +0.019 |
Gaw | +0.017 |
undertaking | +0.016 |
pty | +0.015 |
abus | +0.015 |
Neg logit contributions | |
united | -0.023 |
CTV | -0.021 |
additive | -0.018 |
iod | -0.017 |
SHARE | -0.016 |
Token | L |
Token ID | 43 |
Feature activation | -8.28e-02 |
Pos logit contributions | |
between | +0.020 |
Gaw | +0.019 |
undertaking | +0.017 |
pty | +0.016 |
abus | +0.016 |
Neg logit contributions | |
united | -0.023 |
CTV | -0.021 |
additive | -0.017 |
iod | -0.017 |
SHARE | -0.016 |
Token | NG |
Token ID | 10503 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
united | +0.091 |
CTV | +0.086 |
additive | +0.074 |
iod | +0.073 |
SHARE | +0.068 |
Neg logit contributions | |
between | -0.047 |
Gaw | -0.043 |
undertaking | -0.037 |
pty | -0.034 |
devices | -0.033 |
Token | lan |
Token ID | 26992 |
Feature activation | +4.73e-03 |
Pos logit contributions | |
between | +0.004 |
Gaw | +0.003 |
undertaking | +0.003 |
pty | +0.003 |
abus | +0.003 |
Neg logit contributions | |
united | -0.004 |
CTV | -0.004 |
additive | -0.003 |
iod | -0.003 |
SHARE | -0.003 |
Token | ak |
Token ID | 461 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
between | +0.003 |
Gaw | +0.003 |
undertaking | +0.003 |
pty | +0.003 |
abus | +0.003 |
Neg logit contributions | |
united | -0.004 |
CTV | -0.004 |
additive | -0.003 |
iod | -0.003 |
SHARE | -0.003 |
Token | ila |
Token ID | 10102 |
Feature activation | +6.74e-02 |
Pos logit contributions | |
between | +0.164 |
Gaw | +0.151 |
undertaking | +0.136 |
pty | +0.128 |
abus | +0.126 |
Neg logit contributions | |
united | -0.220 |
CTV | -0.202 |
additive | -0.170 |
iod | -0.169 |
SHARE | -0.153 |
Token | i |
Token ID | 1312 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
between | +0.053 |
Gaw | +0.049 |
undertaking | +0.045 |
pty | +0.043 |
abus | +0.042 |
Neg logit contributions | |
united | -0.060 |
CTV | -0.054 |
additive | -0.045 |
iod | -0.045 |
SHARE | -0.040 |
Token | ā |
Token ID | 10235 |
Feature activation | +5.92e-01 |
Pos logit contributions | |
between | +0.113 |
Gaw | +0.105 |
undertaking | +0.096 |
pty | +0.092 |
abus | +0.090 |
Neg logit contributions | |
united | -0.120 |
CTV | -0.109 |
additive | -0.090 |
iod | -0.089 |
SHARE | -0.080 |
Token | Kal |
Token ID | 12612 |
Feature activation | +3.51e-02 |
Pos logit contributions | |
between | +0.471 |
Gaw | +0.437 |
undertaking | +0.397 |
pty | +0.379 |
abus | +0.374 |
Neg logit contributions | |
united | -0.519 |
CTV | -0.474 |
additive | -0.394 |
iod | -0.388 |
SHARE | -0.350 |
Token | an |
Token ID | 272 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
between | +0.021 |
Gaw | +0.019 |
undertaking | +0.017 |
pty | +0.016 |
abus | +0.016 |
Neg logit contributions | |
united | -0.037 |
CTV | -0.035 |
additive | -0.030 |
iod | -0.029 |
SHARE | -0.027 |
Token | ial |
Token ID | 498 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
between | +0.202 |
Gaw | +0.184 |
undertaking | +0.164 |
pty | +0.155 |
abus | +0.152 |
Neg logit contributions | |
united | -0.303 |
CTV | -0.280 |
additive | -0.239 |
iod | -0.236 |
SHARE | -0.217 |
Token | i |
Token ID | 72 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
between | +0.105 |
Gaw | +0.096 |
undertaking | +0.086 |
pty | +0.081 |
abus | +0.079 |
Neg logit contributions | |
united | -0.154 |
CTV | -0.141 |
additive | -0.120 |
iod | -0.119 |
SHARE | -0.109 |
Token | � |
Token ID | 134 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
between | +0.188 |
Gaw | +0.174 |
undertaking | +0.159 |
pty | +0.152 |
abus | +0.149 |
Neg logit contributions | |
united | -0.204 |
CTV | -0.186 |
additive | -0.154 |
iod | -0.152 |
SHARE | -0.137 |
Token | � |
Token ID | 119 |
Feature activation | -3.60e-02 |
Pos logit contributions | |
between | +0.290 |
Gaw | +0.273 |
undertaking | +0.253 |
pty | +0.244 |
abus | +0.240 |
Neg logit contributions | |
united | -0.217 |
CTV | -0.194 |
additive | -0.153 |
iod | -0.150 |
SHARE | -0.130 |
Token | which |
Token ID | 543 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
united | +0.078 |
CTV | +0.073 |
additive | +0.063 |
iod | +0.061 |
Bravo | +0.057 |
Neg logit contributions | |
between | -0.056 |
Gaw | -0.051 |
undertaking | -0.046 |
pty | -0.044 |
abus | -0.044 |
Token | you |
Token ID | 345 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
between | +0.226 |
Gaw | +0.208 |
undertaking | +0.188 |
pty | +0.179 |
abus | +0.176 |
Neg logit contributions | |
united | -0.290 |
CTV | -0.267 |
additive | -0.226 |
iod | -0.222 |
Bravo | -0.203 |
Token | can |
Token ID | 460 |
Feature activation | +4.53e-02 |
Pos logit contributions | |
between | +0.095 |
Gaw | +0.089 |
undertaking | +0.081 |
pty | +0.078 |
abus | +0.076 |
Neg logit contributions | |
united | -0.098 |
CTV | -0.089 |
additive | -0.074 |
iod | -0.073 |
SHARE | -0.065 |
Token | 't |
Token ID | 470 |
Feature activation | -2.05e-02 |
Pos logit contributions | |
between | +0.036 |
Gaw | +0.033 |
undertaking | +0.030 |
pty | +0.029 |
abus | +0.028 |
Neg logit contributions | |
united | -0.040 |
CTV | -0.037 |
additive | -0.031 |
iod | -0.030 |
Bravo | -0.027 |
Token | really |
Token ID | 1107 |
Feature activation | +4.06e-02 |
Pos logit contributions | |
united | +0.017 |
CTV | +0.016 |
additive | +0.013 |
iod | +0.013 |
SHARE | +0.012 |
Neg logit contributions | |
between | -0.017 |
Gaw | -0.016 |
undertaking | -0.014 |
pty | -0.014 |
abus | -0.014 |
Token | pick |
Token ID | 2298 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
between | +0.032 |
Gaw | +0.029 |
undertaking | +0.027 |
pty | +0.025 |
abus | +0.025 |
Neg logit contributions | |
united | -0.036 |
CTV | -0.033 |
additive | -0.028 |
iod | -0.027 |
SHARE | -0.024 |
Token | out |
Token ID | 503 |
Feature activation | -4.00e-02 |
Pos logit contributions | |
between | +0.205 |
Gaw | +0.194 |
undertaking | +0.181 |
pty | +0.175 |
abus | +0.173 |
Neg logit contributions | |
united | -0.124 |
CTV | -0.109 |
additive | -0.082 |
iod | -0.080 |
SHARE | -0.068 |
Token | with |
Token ID | 351 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
united | +0.036 |
CTV | +0.033 |
additive | +0.027 |
iod | +0.027 |
SHARE | +0.024 |
Neg logit contributions | |
between | -0.031 |
Gaw | -0.029 |
undertaking | -0.026 |
pty | -0.025 |
abus | -0.025 |
Token | the |
Token ID | 262 |
Feature activation | +5.42e-02 |
Pos logit contributions | |
between | +0.174 |
Gaw | +0.160 |
undertaking | +0.144 |
pty | +0.137 |
abus | +0.136 |
Neg logit contributions | |
united | -0.223 |
CTV | -0.206 |
additive | -0.174 |
iod | -0.171 |
Bravo | -0.156 |
Token | camera |
Token ID | 4676 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
between | +0.042 |
Gaw | +0.039 |
undertaking | +0.035 |
pty | +0.034 |
abus | +0.033 |
Neg logit contributions | |
united | -0.048 |
CTV | -0.044 |
additive | -0.037 |
iod | -0.037 |
SHARE | -0.033 |
Token | in |
Token ID | 287 |
Feature activation | +9.26e-02 |
Pos logit contributions | |
between | +0.155 |
Gaw | +0.144 |
undertaking | +0.130 |
pty | +0.125 |
abus | +0.123 |
Neg logit contributions | |
united | -0.168 |
CTV | -0.153 |
additive | -0.127 |
iod | -0.125 |
SHARE | -0.113 |
Token | but |
Token ID | 475 |
Feature activation | +7.88e-02 |
Pos logit contributions | |
united | +0.118 |
CTV | +0.109 |
additive | +0.092 |
iod | +0.091 |
SHARE | +0.083 |
Neg logit contributions | |
between | -0.091 |
Gaw | -0.084 |
undertaking | -0.075 |
pty | -0.072 |
abus | -0.071 |
Token | he |
Token ID | 339 |
Feature activation | +6.94e-02 |
Pos logit contributions | |
between | +0.055 |
Gaw | +0.051 |
undertaking | +0.045 |
pty | +0.044 |
abus | +0.043 |
Neg logit contributions | |
united | -0.076 |
CTV | -0.070 |
additive | -0.060 |
iod | -0.059 |
Bravo | -0.054 |
Token | might |
Token ID | 1244 |
Feature activation | +6.72e-02 |
Pos logit contributions | |
between | +0.051 |
Gaw | +0.047 |
undertaking | +0.042 |
pty | +0.040 |
abus | +0.039 |
Neg logit contributions | |
united | -0.065 |
CTV | -0.060 |
additive | -0.050 |
iod | -0.050 |
SHARE | -0.045 |
Token | also |
Token ID | 635 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
between | +0.043 |
Gaw | +0.039 |
undertaking | +0.035 |
pty | +0.033 |
abus | +0.032 |
Neg logit contributions | |
united | -0.069 |
CTV | -0.064 |
additive | -0.055 |
iod | -0.054 |
SHARE | -0.050 |
Token | have |
Token ID | 423 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
between | +0.139 |
Gaw | +0.128 |
undertaking | +0.117 |
pty | +0.111 |
abus | +0.109 |
Neg logit contributions | |
united | -0.160 |
CTV | -0.146 |
additive | -0.122 |
iod | -0.120 |
SHARE | -0.109 |
Token | one |
Token ID | 530 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
between | +0.010 |
Gaw | +0.009 |
undertaking | +0.008 |
pty | +0.008 |
abus | +0.008 |
Neg logit contributions | |
united | -0.013 |
CTV | -0.012 |
additive | -0.010 |
iod | -0.010 |
Bravo | -0.009 |
Token | caveat |
Token ID | 36531 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
between | +0.010 |
Gaw | +0.009 |
undertaking | +0.008 |
pty | +0.008 |
abus | +0.008 |
Neg logit contributions | |
united | -0.012 |
CTV | -0.011 |
additive | -0.010 |
iod | -0.010 |
SHARE | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | +3.29e-02 |
Pos logit contributions | |
between | +0.110 |
Gaw | +0.103 |
undertaking | +0.094 |
pty | +0.090 |
abus | +0.088 |
Neg logit contributions | |
united | -0.108 |
CTV | -0.098 |
additive | -0.080 |
iod | -0.079 |
SHARE | -0.070 |
Token | Yes |
Token ID | 3363 |
Feature activation | -8.84e-02 |
Pos logit contributions | |
between | +0.025 |
Gaw | +0.023 |
undertaking | +0.021 |
pty | +0.020 |
abus | +0.020 |
Neg logit contributions | |
united | -0.030 |
CTV | -0.027 |
additive | -0.023 |
iod | -0.022 |
Bravo | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | +2.68e-02 |
Pos logit contributions | |
united | +0.073 |
CTV | +0.066 |
additive | +0.054 |
iod | +0.053 |
SHARE | +0.047 |
Neg logit contributions | |
between | -0.075 |
Gaw | -0.070 |
undertaking | -0.064 |
pty | -0.062 |
abus | -0.061 |
Token | his |
Token ID | 465 |
Feature activation | -3.49e-02 |
Pos logit contributions | |
between | +0.020 |
Gaw | +0.018 |
undertaking | +0.016 |
pty | +0.016 |
abus | +0.015 |
Neg logit contributions | |
united | -0.025 |
CTV | -0.023 |
additive | -0.020 |
iod | -0.019 |
Bravo | -0.017 |
Token | appreciated |
Token ID | 16373 |
Feature activation | +5.22e-02 |
Pos logit contributions | |
between | +0.085 |
Gaw | +0.079 |
undertaking | +0.072 |
pty | +0.068 |
abus | +0.067 |
Neg logit contributions | |
united | -0.091 |
CTV | -0.083 |
additive | -0.068 |
iod | -0.067 |
SHARE | -0.061 |
Token | that |
Token ID | 326 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
between | +0.037 |
Gaw | +0.034 |
undertaking | +0.030 |
pty | +0.029 |
abus | +0.029 |
Neg logit contributions | |
united | -0.050 |
CTV | -0.046 |
additive | -0.040 |
iod | -0.039 |
Bravo | -0.036 |
Token | they |
Token ID | 484 |
Feature activation | -5.83e-02 |
Pos logit contributions | |
between | +0.114 |
Gaw | +0.106 |
undertaking | +0.095 |
pty | +0.091 |
abus | +0.090 |
Neg logit contributions | |
united | -0.133 |
CTV | -0.122 |
additive | -0.103 |
iod | -0.100 |
Bravo | -0.091 |
Token | were |
Token ID | 547 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
united | +0.047 |
CTV | +0.043 |
additive | +0.035 |
iod | +0.034 |
SHARE | +0.031 |
Neg logit contributions | |
between | -0.050 |
Gaw | -0.047 |
undertaking | -0.043 |
pty | -0.041 |
abus | -0.040 |
Token | able |
Token ID | 1498 |
Feature activation | -5.37e-02 |
Pos logit contributions | |
united | +0.112 |
CTV | +0.104 |
additive | +0.088 |
iod | +0.087 |
SHARE | +0.079 |
Neg logit contributions | |
between | -0.082 |
Gaw | -0.075 |
undertaking | -0.067 |
pty | -0.064 |
abus | -0.063 |
Token | to |
Token ID | 284 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
united | +0.051 |
CTV | +0.047 |
additive | +0.040 |
iod | +0.039 |
SHARE | +0.036 |
Neg logit contributions | |
between | -0.039 |
Gaw | -0.035 |
undertaking | -0.032 |
pty | -0.030 |
abus | -0.030 |
Token | keep |
Token ID | 1394 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
between | +0.010 |
Gaw | +0.009 |
undertaking | +0.008 |
pty | +0.008 |
abus | +0.008 |
Neg logit contributions | |
united | -0.009 |
CTV | -0.008 |
additive | -0.006 |
iod | -0.006 |
SHARE | -0.006 |
Token | things |
Token ID | 1243 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
united | +0.174 |
CTV | +0.159 |
additive | +0.135 |
iod | +0.132 |
Bravo | +0.120 |
Neg logit contributions | |
between | -0.140 |
Gaw | -0.129 |
undertaking | -0.116 |
pty | -0.111 |
abus | -0.110 |
Token | fresh |
Token ID | 4713 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
between | +0.154 |
Gaw | +0.143 |
undertaking | +0.131 |
pty | +0.125 |
abus | +0.123 |
Neg logit contributions | |
united | -0.158 |
CTV | -0.144 |
additive | -0.119 |
iod | -0.117 |
SHARE | -0.105 |
Token | with |
Token ID | 351 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
between | +0.140 |
Gaw | +0.130 |
undertaking | +0.118 |
pty | +0.112 |
abus | +0.111 |
Neg logit contributions | |
united | -0.161 |
CTV | -0.147 |
additive | -0.123 |
iod | -0.121 |
SHARE | -0.109 |
Token | The |
Token ID | 383 |
Feature activation | +3.30e-02 |
Pos logit contributions | |
between | +0.122 |
Gaw | +0.113 |
undertaking | +0.101 |
pty | +0.097 |
abus | +0.095 |
Neg logit contributions | |
united | -0.152 |
CTV | -0.140 |
additive | -0.118 |
iod | -0.116 |
Bravo | -0.105 |
Token | the |
Token ID | 262 |
Feature activation | -4.97e-02 |
Pos logit contributions | |
united | +0.017 |
CTV | +0.015 |
additive | +0.013 |
iod | +0.013 |
Bravo | +0.012 |
Neg logit contributions | |
between | -0.013 |
Gaw | -0.012 |
undertaking | -0.011 |
pty | -0.010 |
abus | -0.010 |
Token | broader |
Token ID | 11622 |
Feature activation | +5.55e-02 |
Pos logit contributions | |
united | +0.047 |
CTV | +0.043 |
additive | +0.037 |
iod | +0.036 |
Bravo | +0.033 |
Neg logit contributions | |
between | -0.036 |
Gaw | -0.033 |
undertaking | -0.029 |
pty | -0.028 |
abus | -0.028 |
Token | context |
Token ID | 4732 |
Feature activation | -8.40e-02 |
Pos logit contributions | |
between | +0.042 |
Gaw | +0.039 |
undertaking | +0.035 |
pty | +0.034 |
abus | +0.033 |
Neg logit contributions | |
united | -0.050 |
CTV | -0.046 |
additive | -0.039 |
iod | -0.038 |
SHARE | -0.034 |
Token | of |
Token ID | 286 |
Feature activation | -3.77e-02 |
Pos logit contributions | |
united | +0.078 |
CTV | +0.072 |
additive | +0.061 |
iod | +0.060 |
SHARE | +0.054 |
Neg logit contributions | |
between | -0.062 |
Gaw | -0.057 |
undertaking | -0.052 |
pty | -0.049 |
abus | -0.048 |
Token | a |
Token ID | 257 |
Feature activation | +3.19e-02 |
Pos logit contributions | |
united | +0.034 |
CTV | +0.031 |
additive | +0.026 |
iod | +0.026 |
Bravo | +0.023 |
Neg logit contributions | |
between | -0.029 |
Gaw | -0.027 |
undertaking | -0.024 |
pty | -0.023 |
abus | -0.023 |
Token | highly |
Token ID | 4047 |
Feature activation | -6.18e-02 |
Pos logit contributions | |
between | +0.024 |
Gaw | +0.023 |
undertaking | +0.020 |
pty | +0.019 |
abus | +0.019 |
Neg logit contributions | |
united | -0.029 |
CTV | -0.027 |
additive | -0.022 |
iod | -0.022 |
SHARE | -0.020 |
Token | competitive |
Token ID | 7606 |
Feature activation | +4.45e-02 |
Pos logit contributions | |
united | +0.054 |
CTV | +0.049 |
additive | +0.040 |
iod | +0.040 |
SHARE | +0.036 |
Neg logit contributions | |
between | -0.050 |
Gaw | -0.046 |
undertaking | -0.042 |
pty | -0.040 |
abus | -0.040 |
Token | industry |
Token ID | 2831 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
between | +0.035 |
Gaw | +0.032 |
undertaking | +0.029 |
pty | +0.028 |
abus | +0.027 |
Neg logit contributions | |
united | -0.040 |
CTV | -0.036 |
additive | -0.030 |
iod | -0.030 |
SHARE | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | -4.26e-02 |
Pos logit contributions | |
united | +0.132 |
CTV | +0.120 |
additive | +0.098 |
iod | +0.096 |
SHARE | +0.086 |
Neg logit contributions | |
between | -0.134 |
Gaw | -0.125 |
undertaking | -0.114 |
pty | -0.110 |
abus | -0.108 |
Token | many |
Token ID | 867 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
united | +0.040 |
CTV | +0.037 |
additive | +0.031 |
iod | +0.031 |
Bravo | +0.028 |
Neg logit contributions | |
between | -0.031 |
Gaw | -0.028 |
undertaking | -0.026 |
pty | -0.025 |
abus | -0.024 |
Token | of |
Token ID | 286 |
Feature activation | -2.18e-02 |
Pos logit contributions | |
between | +0.094 |
Gaw | +0.087 |
undertaking | +0.078 |
pty | +0.075 |
abus | +0.073 |
Neg logit contributions | |
united | -0.114 |
CTV | -0.105 |
additive | -0.089 |
iod | -0.087 |
SHARE | -0.079 |
Token | below |
Token ID | 2174 |
Feature activation | +2.59e-02 |
Pos logit contributions | |
united | +0.082 |
CTV | +0.073 |
additive | +0.057 |
iod | +0.056 |
SHARE | +0.048 |
Neg logit contributions | |
between | -0.118 |
Gaw | -0.111 |
undertaking | -0.103 |
pty | -0.099 |
abus | -0.098 |
Token | to |
Token ID | 284 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
between | +0.019 |
Gaw | +0.017 |
undertaking | +0.015 |
pty | +0.015 |
abus | +0.014 |
Neg logit contributions | |
united | -0.025 |
CTV | -0.023 |
additive | -0.019 |
iod | -0.019 |
SHARE | -0.017 |
Token | become |
Token ID | 1716 |
Feature activation | -5.34e-03 |
Pos logit contributions | |
between | +0.137 |
Gaw | +0.128 |
undertaking | +0.117 |
pty | +0.112 |
abus | +0.110 |
Neg logit contributions | |
united | -0.141 |
CTV | -0.128 |
additive | -0.106 |
iod | -0.104 |
SHARE | -0.093 |
Token | an |
Token ID | 281 |
Feature activation | +7.43e-02 |
Pos logit contributions | |
united | +0.006 |
CTV | +0.005 |
additive | +0.004 |
iod | +0.004 |
SHARE | +0.004 |
Neg logit contributions | |
between | -0.003 |
Gaw | -0.003 |
undertaking | -0.003 |
pty | -0.003 |
render | -0.002 |
Token | In |
Token ID | 554 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
between | +0.057 |
Gaw | +0.053 |
undertaking | +0.048 |
pty | +0.046 |
abus | +0.045 |
Neg logit contributions | |
united | -0.067 |
CTV | -0.061 |
additive | -0.051 |
iod | -0.050 |
SHARE | -0.046 |
Token | Daily |
Token ID | 28545 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
between | +0.011 |
Gaw | +0.011 |
undertaking | +0.010 |
pty | +0.010 |
abus | +0.009 |
Neg logit contributions | |
united | -0.009 |
CTV | -0.008 |
additive | -0.006 |
iod | -0.006 |
SHARE | -0.005 |
Token | supporter |
Token ID | 15525 |
Feature activation | +2.14e-02 |
Pos logit contributions | |
united | +0.141 |
CTV | +0.128 |
iod | +0.104 |
additive | +0.104 |
SHARE | +0.093 |
Neg logit contributions | |
between | -0.146 |
Gaw | -0.136 |
undertaking | -0.127 |
pty | -0.119 |
render | -0.117 |
Token | . |
Token ID | 13 |
Feature activation | +3.58e-02 |
Pos logit contributions | |
between | +0.017 |
Gaw | +0.015 |
undertaking | +0.014 |
pty | +0.013 |
abus | +0.013 |
Neg logit contributions | |
united | -0.019 |
CTV | -0.018 |
additive | -0.015 |
iod | -0.014 |
SHARE | -0.013 |
Token | Powered |
Token ID | 45090 |
Feature activation | +3.25e-02 |
Pos logit contributions | |
between | +0.030 |
Gaw | +0.027 |
undertaking | +0.025 |
pty | +0.024 |
abus | +0.024 |
Neg logit contributions | |
united | -0.030 |
CTV | -0.028 |
additive | -0.022 |
iod | -0.022 |
SHARE | -0.020 |
Token | by |
Token ID | 416 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
between | +0.026 |
Gaw | +0.024 |
undertaking | +0.023 |
pty | +0.021 |
abus | +0.021 |
Neg logit contributions | |
united | -0.028 |
CTV | -0.025 |
additive | -0.021 |
iod | -0.021 |
SHARE | -0.019 |
Token | Press |
Token ID | 4332 |
Feature activation | -6.08e-02 |
Pos logit contributions | |
united | +0.012 |
CTV | +0.011 |
iod | +0.009 |
additive | +0.008 |
Bravo | +0.007 |
Neg logit contributions | |
between | -0.014 |
Gaw | -0.013 |
undertaking | -0.012 |
pty | -0.012 |
devices | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | +4.02e-02 |
Pos logit contributions | |
between | +0.046 |
Gaw | +0.043 |
undertaking | +0.039 |
pty | +0.037 |
abus | +0.036 |
Neg logit contributions | |
united | -0.056 |
CTV | -0.052 |
additive | -0.043 |
iod | -0.042 |
SHARE | -0.039 |
Token | void |
Token ID | 19382 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
between | +0.034 |
Gaw | +0.032 |
undertaking | +0.029 |
pty | +0.028 |
abus | +0.027 |
Neg logit contributions | |
united | -0.033 |
CTV | -0.030 |
additive | -0.025 |
iod | -0.024 |
SHARE | -0.022 |
Token | V |
Token ID | 569 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
between | +0.209 |
Gaw | +0.195 |
undertaking | +0.177 |
pty | +0.168 |
abus | +0.166 |
Neg logit contributions | |
united | -0.224 |
CTV | -0.204 |
additive | -0.168 |
iod | -0.166 |
SHARE | -0.150 |
Token | ort |
Token ID | 419 |
Feature activation | -5.09e-01 |
Pos logit contributions | |
united | +0.079 |
CTV | +0.071 |
additive | +0.056 |
iod | +0.055 |
SHARE | +0.048 |
Neg logit contributions | |
between | -0.102 |
Gaw | -0.095 |
undertaking | -0.088 |
pty | -0.085 |
abus | -0.084 |
Token | on |
Token ID | 261 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
united | +0.384 |
CTV | +0.345 |
additive | +0.275 |
iod | +0.270 |
SHARE | +0.238 |
Neg logit contributions | |
between | -0.468 |
Gaw | -0.438 |
undertaking | -0.404 |
pty | -0.389 |
abus | -0.384 |
Token | Sim |
Token ID | 8890 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
united | +0.148 |
CTV | +0.132 |
additive | +0.104 |
iod | +0.102 |
SHARE | +0.088 |
Neg logit contributions | |
between | -0.197 |
Gaw | -0.185 |
undertaking | -0.171 |
pty | -0.165 |
abus | -0.163 |
Token | :: |
Token ID | 3712 |
Feature activation | +3.60e-02 |
Pos logit contributions | |
united | +0.202 |
CTV | +0.182 |
additive | +0.145 |
iod | +0.142 |
SHARE | +0.125 |
Neg logit contributions | |
between | -0.246 |
Gaw | -0.231 |
undertaking | -0.213 |
pty | -0.205 |
abus | -0.202 |
Token | Pop |
Token ID | 16979 |
Feature activation | +7.54e-02 |
Pos logit contributions | |
between | +0.028 |
Gaw | +0.026 |
undertaking | +0.024 |
pty | +0.023 |
abus | +0.022 |
Neg logit contributions | |
united | -0.032 |
CTV | -0.029 |
additive | -0.024 |
iod | -0.024 |
SHARE | -0.022 |
Token | ulate |
Token ID | 5039 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
between | +0.077 |
Gaw | +0.072 |
undertaking | +0.067 |
pty | +0.065 |
abus | +0.064 |
Neg logit contributions | |
united | -0.049 |
CTV | -0.044 |
additive | -0.033 |
iod | -0.033 |
SHARE | -0.028 |
Token | D |
Token ID | 35 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
united | +0.153 |
CTV | +0.139 |
additive | +0.114 |
iod | +0.112 |
SHARE | +0.100 |
Neg logit contributions | |
between | -0.156 |
Gaw | -0.146 |
undertaking | -0.134 |
pty | -0.128 |
abus | -0.126 |
Token | ensity |
Token ID | 6377 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
united | +0.087 |
CTV | +0.077 |
additive | +0.058 |
iod | +0.057 |
SHARE | +0.048 |
Neg logit contributions | |
between | -0.136 |
Gaw | -0.129 |
undertaking | -0.120 |
pty | -0.115 |
abus | -0.114 |
Token | He |
Token ID | 679 |
Feature activation | +7.33e-02 |
Pos logit contributions | |
between | +0.011 |
Gaw | +0.010 |
undertaking | +0.009 |
pty | +0.009 |
abus | +0.009 |
Neg logit contributions | |
united | -0.014 |
CTV | -0.012 |
additive | -0.010 |
iod | -0.010 |
Bravo | -0.009 |
Token | began |
Token ID | 2540 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
between | +0.062 |
Gaw | +0.058 |
undertaking | +0.053 |
pty | +0.051 |
abus | +0.050 |
Neg logit contributions | |
united | -0.060 |
CTV | -0.055 |
additive | -0.045 |
iod | -0.044 |
SHARE | -0.040 |
Token | training |
Token ID | 3047 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
united | +0.128 |
CTV | +0.118 |
additive | +0.100 |
iod | +0.099 |
SHARE | +0.090 |
Neg logit contributions | |
between | -0.096 |
Gaw | -0.089 |
undertaking | -0.078 |
pty | -0.076 |
abus | -0.075 |
Token | the |
Token ID | 262 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
united | +0.156 |
CTV | +0.143 |
additive | +0.120 |
iod | +0.118 |
Bravo | +0.107 |
Neg logit contributions | |
between | -0.129 |
Gaw | -0.119 |
undertaking | -0.108 |
pty | -0.103 |
abus | -0.102 |
Token | turtles |
Token ID | 36288 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
united | +0.111 |
CTV | +0.102 |
additive | +0.087 |
iod | +0.086 |
Bravo | +0.078 |
Neg logit contributions | |
between | -0.083 |
Gaw | -0.076 |
undertaking | -0.068 |
pty | -0.065 |
abus | -0.064 |
Token | in |
Token ID | 287 |
Feature activation | -6.43e-02 |
Pos logit contributions | |
between | +0.206 |
Gaw | +0.191 |
undertaking | +0.174 |
pty | +0.165 |
abus | +0.162 |
Neg logit contributions | |
united | -0.239 |
CTV | -0.219 |
additive | -0.182 |
iod | -0.180 |
SHARE | -0.163 |
Token | the |
Token ID | 262 |
Feature activation | -9.51e-02 |
Pos logit contributions | |
united | +0.059 |
CTV | +0.054 |
additive | +0.045 |
iod | +0.044 |
Bravo | +0.040 |
Neg logit contributions | |
between | -0.049 |
Gaw | -0.045 |
undertaking | -0.041 |
pty | -0.039 |
abus | -0.039 |
Token | art |
Token ID | 1242 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
united | +0.086 |
CTV | +0.079 |
additive | +0.066 |
iod | +0.065 |
SHARE | +0.059 |
Neg logit contributions | |
between | -0.073 |
Gaw | -0.068 |
undertaking | -0.061 |
pty | -0.058 |
abus | -0.058 |
Token | of |
Token ID | 286 |
Feature activation | -6.49e-02 |
Pos logit contributions | |
between | +0.188 |
Gaw | +0.173 |
undertaking | +0.156 |
pty | +0.148 |
abus | +0.145 |
Neg logit contributions | |
united | -0.245 |
CTV | -0.225 |
additive | -0.191 |
iod | -0.187 |
SHARE | -0.171 |
Token | nin |
Token ID | 13462 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
united | +0.062 |
CTV | +0.057 |
additive | +0.048 |
iod | +0.047 |
SHARE | +0.043 |
Neg logit contributions | |
between | -0.047 |
Gaw | -0.043 |
undertaking | -0.039 |
pty | -0.037 |
abus | -0.036 |
Token | j |
Token ID | 73 |
Feature activation | -3.88e-02 |
Pos logit contributions | |
between | +0.114 |
Gaw | +0.107 |
undertaking | +0.098 |
pty | +0.093 |
abus | +0.092 |
Neg logit contributions | |
united | -0.117 |
CTV | -0.106 |
additive | -0.087 |
iod | -0.086 |
Bravo | -0.077 |
Token | One |
Token ID | 1881 |
Feature activation | +7.94e-03 |
Pos logit contributions | |
between | +0.056 |
Gaw | +0.052 |
undertaking | +0.047 |
pty | +0.045 |
abus | +0.045 |
Neg logit contributions | |
united | -0.058 |
CTV | -0.053 |
additive | -0.043 |
iod | -0.043 |
SHARE | -0.038 |
Token | Jill |
Token ID | 22772 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
between | +0.006 |
Gaw | +0.005 |
undertaking | +0.005 |
pty | +0.005 |
abus | +0.005 |
Neg logit contributions | |
united | -0.007 |
CTV | -0.007 |
additive | -0.006 |
iod | -0.006 |
Bravo | -0.005 |
Token | ste |
Token ID | 2876 |
Feature activation | -4.22e-02 |
Pos logit contributions | |
between | +0.069 |
Gaw | +0.064 |
undertaking | +0.057 |
pty | +0.054 |
abus | +0.053 |
Neg logit contributions | |
united | -0.098 |
CTV | -0.090 |
additive | -0.077 |
iod | -0.076 |
SHARE | -0.069 |
Token | in |
Token ID | 259 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
united | +0.035 |
CTV | +0.031 |
additive | +0.025 |
iod | +0.025 |
SHARE | +0.022 |
Neg logit contributions | |
between | -0.036 |
Gaw | -0.034 |
undertaking | -0.031 |
pty | -0.030 |
abus | -0.029 |
Token | supporter |
Token ID | 15525 |
Feature activation | -4.07e-02 |
Pos logit contributions | |
united | +0.011 |
CTV | +0.010 |
additive | +0.009 |
iod | +0.009 |
SHARE | +0.008 |
Neg logit contributions | |
between | -0.010 |
Gaw | -0.009 |
undertaking | -0.008 |
pty | -0.008 |
abus | -0.008 |
Token | told |
Token ID | 1297 |
Feature activation | -1.76e-02 |
Pos logit contributions | |
united | +0.037 |
CTV | +0.034 |
additive | +0.029 |
iod | +0.028 |
SHARE | +0.026 |
Neg logit contributions | |
between | -0.031 |
Gaw | -0.028 |
undertaking | -0.026 |
pty | -0.024 |
abus | -0.024 |
Token | us |
Token ID | 514 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
united | +0.012 |
CTV | +0.010 |
additive | +0.008 |
iod | +0.008 |
SHARE | +0.007 |
Neg logit contributions | |
between | -0.018 |
Gaw | -0.017 |
undertaking | -0.016 |
pty | -0.015 |
abus | -0.015 |
Token | three |
Token ID | 1115 |
Feature activation | +4.58e-02 |
Pos logit contributions | |
united | +0.166 |
CTV | +0.152 |
additive | +0.126 |
iod | +0.124 |
SHARE | +0.112 |
Neg logit contributions | |
between | -0.148 |
Gaw | -0.137 |
undertaking | -0.124 |
pty | -0.119 |
abus | -0.117 |
Token | whole |
Token ID | 2187 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
between | +0.036 |
Gaw | +0.033 |
undertaking | +0.030 |
pty | +0.029 |
abus | +0.028 |
Neg logit contributions | |
united | -0.041 |
CTV | -0.037 |
additive | -0.031 |
iod | -0.031 |
SHARE | -0.028 |
Token | buses |
Token ID | 16893 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
between | +0.144 |
Gaw | +0.133 |
undertaking | +0.121 |
pty | +0.116 |
abus | +0.114 |
Neg logit contributions | |
united | -0.165 |
CTV | -0.151 |
additive | -0.125 |
iod | -0.124 |
SHARE | -0.112 |
Token | of |
Token ID | 286 |
Feature activation | +4.84e-02 |
Pos logit contributions | |
between | +0.147 |
Gaw | +0.137 |
undertaking | +0.126 |
pty | +0.119 |
abus | +0.118 |
Neg logit contributions | |
united | -0.149 |
CTV | -0.137 |
additive | -0.112 |
iod | -0.110 |
SHARE | -0.099 |
Token | one |
Token ID | 530 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
united | +0.007 |
CTV | +0.007 |
additive | +0.006 |
iod | +0.006 |
SHARE | +0.005 |
Neg logit contributions | |
between | -0.006 |
Gaw | -0.005 |
undertaking | -0.005 |
pty | -0.004 |
abus | -0.004 |
Token | of |
Token ID | 286 |
Feature activation | -2.30e-03 |
Pos logit contributions | |
between | +0.009 |
Gaw | +0.008 |
undertaking | +0.007 |
pty | +0.007 |
abus | +0.007 |
Neg logit contributions | |
united | -0.011 |
CTV | -0.010 |
additive | -0.008 |
iod | -0.008 |
Bravo | -0.008 |
Token | my |
Token ID | 616 |
Feature activation | +1.85e-02 |
Pos logit contributions | |
united | +0.002 |
CTV | +0.002 |
additive | +0.002 |
iod | +0.002 |
Bravo | +0.001 |
Neg logit contributions | |
between | -0.002 |
Gaw | -0.002 |
undertaking | -0.001 |
pty | -0.001 |
abus | -0.001 |
Token | favorite |
Token ID | 4004 |
Feature activation | -5.56e-02 |
Pos logit contributions | |
between | +0.015 |
Gaw | +0.014 |
undertaking | +0.013 |
pty | +0.012 |
abus | +0.012 |
Neg logit contributions | |
united | -0.016 |
CTV | -0.015 |
additive | -0.012 |
iod | -0.012 |
SHARE | -0.011 |
Token | fl |
Token ID | 781 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
united | +0.049 |
CTV | +0.045 |
additive | +0.038 |
iod | +0.037 |
SHARE | +0.033 |
Neg logit contributions | |
between | -0.044 |
Gaw | -0.040 |
undertaking | -0.037 |
pty | -0.035 |
abus | -0.035 |
Token | ours |
Token ID | 4662 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
united | +0.085 |
CTV | +0.077 |
additive | +0.063 |
iod | +0.061 |
SHARE | +0.055 |
Neg logit contributions | |
between | -0.086 |
Gaw | -0.081 |
undertaking | -0.075 |
pty | -0.071 |
abus | -0.070 |
Token | to |
Token ID | 284 |
Feature activation | +3.74e-02 |
Pos logit contributions | |
united | +0.388 |
CTV | +0.355 |
additive | +0.298 |
iod | +0.293 |
SHARE | +0.263 |
Neg logit contributions | |
between | -0.343 |
Gaw | -0.318 |
undertaking | -0.288 |
pty | -0.277 |
abus | -0.272 |
Token | work |
Token ID | 670 |
Feature activation | +2.51e-02 |
Pos logit contributions | |
between | +0.035 |
Gaw | +0.033 |
undertaking | +0.031 |
pty | +0.029 |
abus | +0.029 |
Neg logit contributions | |
united | -0.027 |
CTV | -0.024 |
additive | -0.019 |
iod | -0.019 |
SHARE | -0.017 |
Token | with |
Token ID | 351 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
between | +0.016 |
Gaw | +0.015 |
undertaking | +0.013 |
pty | +0.013 |
abus | +0.012 |
Neg logit contributions | |
united | -0.025 |
CTV | -0.024 |
additive | -0.020 |
iod | -0.020 |
SHARE | -0.018 |
Token | , |
Token ID | 11 |
Feature activation | -1.74e-02 |
Pos logit contributions | |
between | +0.089 |
Gaw | +0.083 |
undertaking | +0.075 |
pty | +0.071 |
abus | +0.070 |
Neg logit contributions | |
united | -0.106 |
CTV | -0.097 |
additive | -0.081 |
iod | -0.080 |
SHARE | -0.072 |
Token | although |
Token ID | 3584 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
united | +0.017 |
CTV | +0.015 |
additive | +0.013 |
iod | +0.013 |
SHARE | +0.012 |
Neg logit contributions | |
between | -0.012 |
Gaw | -0.011 |
undertaking | -0.010 |
pty | -0.010 |
abus | -0.010 |
Token | String |
Token ID | 10100 |
Feature activation | +4.76e-02 |
Pos logit contributions | |
united | +0.084 |
CTV | +0.077 |
additive | +0.064 |
iod | +0.062 |
SHARE | +0.057 |
Neg logit contributions | |
between | -0.074 |
Gaw | -0.069 |
undertaking | -0.062 |
pty | -0.059 |
abus | -0.058 |
Token | Al |
Token ID | 2348 |
Feature activation | -8.54e-02 |
Pos logit contributions | |
between | +0.034 |
Gaw | +0.032 |
undertaking | +0.029 |
pty | +0.027 |
abus | +0.027 |
Neg logit contributions | |
united | -0.045 |
CTV | -0.042 |
additive | -0.035 |
iod | -0.034 |
SHARE | -0.032 |
Token | ignment |
Token ID | 16747 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
united | +0.048 |
CTV | +0.041 |
additive | +0.029 |
iod | +0.028 |
SHARE | +0.023 |
Neg logit contributions | |
between | -0.095 |
Gaw | -0.091 |
undertaking | -0.085 |
pty | -0.082 |
abus | -0.081 |
Token | ] |
Token ID | 60 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
united | +0.276 |
CTV | +0.248 |
additive | +0.196 |
iod | +0.192 |
SHARE | +0.169 |
Neg logit contributions | |
between | -0.352 |
Gaw | -0.331 |
undertaking | -0.306 |
pty | -0.294 |
abus | -0.291 |
Token | :: |
Token ID | 3712 |
Feature activation | -8.48e-02 |
Pos logit contributions | |
united | +0.102 |
CTV | +0.092 |
additive | +0.073 |
iod | +0.071 |
SHARE | +0.063 |
Neg logit contributions | |
between | -0.128 |
Gaw | -0.120 |
undertaking | -0.111 |
pty | -0.107 |
abus | -0.105 |
Token | Center |
Token ID | 23656 |
Feature activation | -4.64e-01 |
Pos logit contributions | |
united | +0.062 |
CTV | +0.056 |
additive | +0.044 |
iod | +0.043 |
SHARE | +0.038 |
Neg logit contributions | |
between | -0.079 |
Gaw | -0.075 |
undertaking | -0.070 |
pty | -0.067 |
abus | -0.066 |
Token | $ |
Token ID | 720 |
Feature activation | -5.75e-02 |
Pos logit contributions | |
united | +0.369 |
CTV | +0.334 |
additive | +0.271 |
iod | +0.266 |
SHARE | +0.236 |
Neg logit contributions | |
between | -0.406 |
Gaw | -0.380 |
undertaking | -0.349 |
pty | -0.335 |
abus | -0.330 |
Token | s |
Token ID | 82 |
Feature activation | +9.95e-03 |
Pos logit contributions | |
united | +0.056 |
CTV | +0.052 |
additive | +0.044 |
iod | +0.043 |
SHARE | +0.040 |
Neg logit contributions | |
between | -0.040 |
Gaw | -0.037 |
undertaking | -0.033 |
pty | -0.031 |
abus | -0.031 |
Token | Format |
Token ID | 26227 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
between | +0.008 |
Gaw | +0.008 |
undertaking | +0.007 |
pty | +0.007 |
abus | +0.007 |
Neg logit contributions | |
united | -0.008 |
CTV | -0.008 |
additive | -0.006 |
iod | -0.006 |
SHARE | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
united | +0.164 |
CTV | +0.151 |
additive | +0.125 |
iod | +0.123 |
SHARE | +0.113 |
Neg logit contributions | |
between | -0.138 |
Gaw | -0.129 |
undertaking | -0.117 |
pty | -0.111 |
abus | -0.109 |
Token | Line |
Token ID | 13949 |
Feature activation | +4.56e-02 |
Pos logit contributions | |
united | +0.089 |
CTV | +0.081 |
additive | +0.066 |
iod | +0.065 |
SHARE | +0.059 |
Neg logit contributions | |
between | -0.089 |
Gaw | -0.083 |
undertaking | -0.077 |
pty | -0.073 |
abus | -0.072 |
Token | from |
Token ID | 422 |
Feature activation | +2.48e-02 |
Pos logit contributions | |
between | +0.160 |
Gaw | +0.149 |
undertaking | +0.134 |
pty | +0.128 |
abus | +0.126 |
Neg logit contributions | |
united | -0.193 |
CTV | -0.177 |
additive | -0.148 |
iod | -0.146 |
SHARE | -0.133 |
Token | Kaiser |
Token ID | 32670 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
between | +0.019 |
Gaw | +0.017 |
undertaking | +0.016 |
pty | +0.015 |
abus | +0.015 |
Neg logit contributions | |
united | -0.023 |
CTV | -0.021 |
additive | -0.017 |
iod | -0.017 |
SHARE | -0.016 |
Token | Family |
Token ID | 7884 |
Feature activation | +3.92e-02 |
Pos logit contributions | |
united | +0.085 |
CTV | +0.077 |
additive | +0.063 |
iod | +0.062 |
SHARE | +0.056 |
Neg logit contributions | |
between | -0.086 |
Gaw | -0.080 |
undertaking | -0.073 |
pty | -0.071 |
abus | -0.070 |
Token | Foundation |
Token ID | 5693 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
between | +0.042 |
Gaw | +0.040 |
undertaking | +0.037 |
pty | +0.036 |
abus | +0.035 |
Neg logit contributions | |
united | -0.024 |
CTV | -0.021 |
additive | -0.015 |
iod | -0.015 |
SHARE | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | +2.65e-02 |
Pos logit contributions | |
united | +0.133 |
CTV | +0.122 |
additive | +0.102 |
iod | +0.101 |
SHARE | +0.091 |
Neg logit contributions | |
between | -0.112 |
Gaw | -0.103 |
undertaking | -0.094 |
pty | -0.089 |
abus | -0.088 |
Token | promoted |
Token ID | 13722 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
between | +0.019 |
Gaw | +0.018 |
undertaking | +0.016 |
pty | +0.015 |
abus | +0.015 |
Neg logit contributions | |
united | -0.025 |
CTV | -0.023 |
additive | -0.020 |
iod | -0.019 |
SHARE | -0.018 |
Token | prominently |
Token ID | 31015 |
Feature activation | +7.21e-03 |
Pos logit contributions | |
united | +0.384 |
CTV | +0.349 |
additive | +0.285 |
iod | +0.282 |
SHARE | +0.253 |
Neg logit contributions | |
between | -0.378 |
Gaw | -0.353 |
undertaking | -0.322 |
pty | -0.308 |
abus | -0.302 |
Token | in |
Token ID | 287 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
between | +0.006 |
Gaw | +0.006 |
undertaking | +0.005 |
pty | +0.005 |
abus | +0.005 |
Neg logit contributions | |
united | -0.006 |
CTV | -0.005 |
additive | -0.004 |
iod | -0.004 |
SHARE | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | -3.14e-02 |
Pos logit contributions | |
united | +0.015 |
CTV | +0.013 |
additive | +0.011 |
iod | +0.011 |
SHARE | +0.010 |
Neg logit contributions | |
between | -0.012 |
Gaw | -0.011 |
undertaking | -0.010 |
pty | -0.009 |
abus | -0.009 |
Token | media |
Token ID | 2056 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
united | +0.027 |
CTV | +0.025 |
additive | +0.020 |
iod | +0.020 |
SHARE | +0.018 |
Neg logit contributions | |
between | -0.026 |
Gaw | -0.024 |
undertaking | -0.022 |
pty | -0.021 |
abus | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | -1.33e-02 |
Pos logit contributions | |
united | +0.128 |
CTV | +0.117 |
additive | +0.096 |
iod | +0.094 |
SHARE | +0.085 |
Neg logit contributions | |
between | -0.123 |
Gaw | -0.114 |
undertaking | -0.105 |
pty | -0.100 |
abus | -0.098 |
Token | June |
Token ID | 2795 |
Feature activation | +5.85e-03 |
Pos logit contributions | |
united | +0.137 |
CTV | +0.124 |
additive | +0.100 |
iod | +0.098 |
SHARE | +0.087 |
Neg logit contributions | |
between | -0.154 |
Gaw | -0.143 |
undertaking | -0.132 |
pty | -0.126 |
devices | -0.125 |
Token | 26 |
Token ID | 2608 |
Feature activation | -3.02e-02 |
Pos logit contributions | |
between | +0.005 |
Gaw | +0.005 |
undertaking | +0.004 |
pty | +0.004 |
abus | +0.004 |
Neg logit contributions | |
united | -0.005 |
CTV | -0.004 |
additive | -0.003 |
iod | -0.003 |
SHARE | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +5.31e-02 |
Pos logit contributions | |
united | +0.027 |
CTV | +0.025 |
additive | +0.021 |
iod | +0.020 |
SHARE | +0.019 |
Neg logit contributions | |
between | -0.023 |
Gaw | -0.022 |
undertaking | -0.020 |
pty | -0.019 |
abus | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | -1.00e-02 |
Pos logit contributions | |
between | +0.042 |
Gaw | +0.039 |
undertaking | +0.035 |
pty | +0.034 |
abus | +0.033 |
Neg logit contributions | |
united | -0.047 |
CTV | -0.043 |
additive | -0.036 |
iod | -0.035 |
SHARE | -0.032 |
Token |
|
Token ID | 198 |
Feature activation | -1.98e-02 |
Pos logit contributions | |
united | +0.009 |
CTV | +0.009 |
additive | +0.007 |
iod | +0.007 |
SHARE | +0.006 |
Neg logit contributions | |
between | -0.007 |
Gaw | -0.007 |
undertaking | -0.006 |
pty | -0.006 |
abus | -0.006 |
Token | Thanks |
Token ID | 9690 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
united | +0.017 |
CTV | +0.015 |
additive | +0.012 |
iod | +0.012 |
SHARE | +0.011 |
Neg logit contributions | |
between | -0.017 |
Gaw | -0.015 |
undertaking | -0.014 |
pty | -0.014 |
abus | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | +6.93e-03 |
Pos logit contributions | |
united | +0.324 |
CTV | +0.295 |
additive | +0.242 |
iod | +0.238 |
SHARE | +0.213 |
Neg logit contributions | |
between | -0.323 |
Gaw | -0.302 |
undertaking | -0.275 |
pty | -0.264 |
abus | -0.259 |
Token | Wii |
Token ID | 16591 |
Feature activation | +2.73e-02 |
Pos logit contributions | |
between | +0.005 |
Gaw | +0.005 |
undertaking | +0.004 |
pty | +0.004 |
abus | +0.004 |
Neg logit contributions | |
united | -0.006 |
CTV | -0.006 |
additive | -0.005 |
iod | -0.005 |
SHARE | -0.004 |
Token | UM |
Token ID | 5883 |
Feature activation | -6.02e-02 |
Pos logit contributions | |
between | +0.023 |
Gaw | +0.022 |
undertaking | +0.020 |
pty | +0.019 |
abus | +0.019 |
Neg logit contributions | |
united | -0.022 |
CTV | -0.020 |
additive | -0.017 |
iod | -0.016 |
SHARE | -0.015 |
Token | aster |
Token ID | 1603 |
Feature activation | +6.68e-02 |
Pos logit contributions | |
united | +0.054 |
CTV | +0.050 |
additive | +0.041 |
iod | +0.041 |
SHARE | +0.037 |
Neg logit contributions | |
between | -0.046 |
Gaw | -0.043 |
undertaking | -0.039 |
pty | -0.037 |
abus | -0.036 |
Token | Race |
Token ID | 35157 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
between | +0.052 |
Gaw | +0.048 |
undertaking | +0.044 |
pty | +0.042 |
abus | +0.041 |
Neg logit contributions | |
united | -0.060 |
CTV | -0.055 |
additive | -0.046 |
iod | -0.045 |
SHARE | -0.041 |
Token |
|
Token ID | 198 |
Feature activation | +6.25e-02 |
Pos logit contributions | |
between | +0.058 |
Gaw | +0.054 |
undertaking | +0.049 |
pty | +0.046 |
abus | +0.046 |
Neg logit contributions | |
united | -0.071 |
CTV | -0.066 |
additive | -0.055 |
iod | -0.054 |
SHARE | -0.049 |
Token | Officials |
Token ID | 25883 |
Feature activation | -7.94e-02 |
Pos logit contributions | |
between | +0.050 |
Gaw | +0.047 |
undertaking | +0.043 |
pty | +0.041 |
abus | +0.040 |
Neg logit contributions | |
united | -0.054 |
CTV | -0.049 |
additive | -0.040 |
iod | -0.040 |
SHARE | -0.036 |
Token | said |
Token ID | 531 |
Feature activation | +8.96e-02 |
Pos logit contributions | |
united | +0.073 |
CTV | +0.067 |
additive | +0.056 |
iod | +0.055 |
SHARE | +0.050 |
Neg logit contributions | |
between | -0.060 |
Gaw | -0.055 |
undertaking | -0.050 |
pty | -0.047 |
abus | -0.047 |
Token | May |
Token ID | 1737 |
Feature activation | -1.81e-02 |
Pos logit contributions | |
between | +0.060 |
Gaw | +0.055 |
undertaking | +0.049 |
pty | +0.047 |
abus | +0.046 |
Neg logit contributions | |
united | -0.089 |
CTV | -0.083 |
additive | -0.070 |
iod | -0.069 |
SHARE | -0.064 |
Token | ra |
Token ID | 430 |
Feature activation | -3.00e-02 |
Pos logit contributions | |
united | +0.016 |
CTV | +0.014 |
additive | +0.012 |
iod | +0.012 |
SHARE | +0.010 |
Neg logit contributions | |
between | -0.015 |
Gaw | -0.014 |
undertaking | -0.012 |
pty | -0.012 |
abus | -0.012 |
Token | Martinez |
Token ID | 20741 |
Feature activation | -4.13e-01 |
Pos logit contributions | |
united | +0.028 |
CTV | +0.026 |
additive | +0.021 |
iod | +0.021 |
SHARE | +0.019 |
Neg logit contributions | |
between | -0.022 |
Gaw | -0.021 |
undertaking | -0.019 |
pty | -0.018 |
abus | -0.017 |
Token | was |
Token ID | 373 |
Feature activation | +3.07e-02 |
Pos logit contributions | |
united | +0.361 |
CTV | +0.330 |
additive | +0.274 |
iod | +0.269 |
SHARE | +0.243 |
Neg logit contributions | |
between | -0.329 |
Gaw | -0.306 |
undertaking | -0.278 |
pty | -0.265 |
abus | -0.261 |
Token | brought |
Token ID | 3181 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
between | +0.024 |
Gaw | +0.022 |
undertaking | +0.020 |
pty | +0.019 |
abus | +0.019 |
Neg logit contributions | |
united | -0.028 |
CTV | -0.026 |
additive | -0.021 |
iod | -0.021 |
SHARE | -0.019 |
Token | to |
Token ID | 284 |
Feature activation | +9.60e-02 |
Pos logit contributions | |
united | +0.092 |
CTV | +0.084 |
additive | +0.070 |
iod | +0.069 |
SHARE | +0.062 |
Neg logit contributions | |
between | -0.084 |
Gaw | -0.078 |
undertaking | -0.071 |
pty | -0.068 |
abus | -0.067 |
Token | the |
Token ID | 262 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
between | +0.072 |
Gaw | +0.067 |
undertaking | +0.060 |
pty | +0.057 |
abus | +0.056 |
Neg logit contributions | |
united | -0.088 |
CTV | -0.081 |
additive | -0.068 |
iod | -0.067 |
SHARE | -0.061 |
Token | jail |
Token ID | 7356 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
between | +0.018 |
Gaw | +0.017 |
undertaking | +0.016 |
pty | +0.015 |
devices | +0.015 |
Neg logit contributions | |
united | -0.015 |
CTV | -0.013 |
additive | -0.010 |
iod | -0.010 |
SHARE | -0.009 |