Token | � |
Token ID | 447 |
Feature activation | -1.28e-03 |
Pos logit contributions | |
Story | +0.002 |
ylan | +0.002 |
Brist | +0.002 |
kok | +0.001 |
Kyr | +0.001 |
Neg logit contributions | |
Pope | -0.002 |
angel | -0.001 |
Towards | -0.001 |
Deng | -0.001 |
Chu | -0.001 |
Token | � |
Token ID | 251 |
Feature activation | -4.81e-03 |
Pos logit contributions | |
Story | +0.001 |
ylan | +0.001 |
Brist | +0.001 |
kok | +0.001 |
Kyr | +0.001 |
Neg logit contributions | |
Pope | -0.001 |
angel | -0.001 |
Towards | -0.001 |
Deng | -0.001 |
Chu | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +6.99e-03 |
Pos logit contributions | |
Story | +0.004 |
ylan | +0.004 |
Brist | +0.004 |
kok | +0.003 |
Kyr | +0.003 |
Neg logit contributions | |
Pope | -0.004 |
angel | -0.004 |
Towards | -0.003 |
Deng | -0.003 |
Chu | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +1.02e-03 |
Pos logit contributions | |
Pope | +0.006 |
angel | +0.005 |
Towards | +0.004 |
Deng | +0.004 |
Chu | +0.004 |
Neg logit contributions | |
Story | -0.005 |
ylan | -0.005 |
Brist | -0.005 |
kok | -0.005 |
Kyr | -0.005 |
Token | Ev |
Token ID | 15200 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
Pope | +0.001 |
angel | +0.001 |
Towards | +0.001 |
Deng | +0.001 |
Chu | +0.001 |
Neg logit contributions | |
Story | -0.001 |
ylan | -0.001 |
Brist | -0.001 |
kok | -0.001 |
Kyr | -0.001 |
Token | angel |
Token ID | 8368 |
Feature activation | +5.88e-01 |
Pos logit contributions | |
Pope | +0.160 |
angel | +0.145 |
Towards | +0.119 |
Deng | +0.117 |
Chu | +0.114 |
Neg logit contributions | |
Story | -0.212 |
ylan | -0.210 |
Brist | -0.207 |
kok | -0.201 |
Kyr | -0.193 |
Token | ical |
Token ID | 605 |
Feature activation | -3.79e-02 |
Pos logit contributions | |
Pope | +0.469 |
angel | +0.434 |
Towards | +0.368 |
Deng | +0.364 |
Chu | +0.357 |
Neg logit contributions | |
Story | -0.443 |
ylan | -0.439 |
Brist | -0.432 |
kok | -0.416 |
Kyr | -0.399 |
Token | adults |
Token ID | 6490 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
Story | +0.030 |
ylan | +0.030 |
Brist | +0.029 |
kok | +0.028 |
Kyr | +0.027 |
Neg logit contributions | |
Pope | -0.029 |
angel | -0.026 |
Towards | -0.022 |
Deng | -0.022 |
atum | -0.022 |
Token | , |
Token ID | 11 |
Feature activation | +1.58e-03 |
Pos logit contributions | |
Pope | +0.093 |
angel | +0.086 |
Towards | +0.073 |
Deng | +0.072 |
Chu | +0.071 |
Neg logit contributions | |
Story | -0.085 |
ylan | -0.084 |
Brist | -0.083 |
kok | -0.080 |
Kyr | -0.077 |
Token | like |
Token ID | 588 |
Feature activation | +6.61e-02 |
Pos logit contributions | |
Pope | +0.001 |
angel | +0.001 |
Towards | +0.001 |
Deng | +0.001 |
Chu | +0.001 |
Neg logit contributions | |
Story | -0.001 |
ylan | -0.001 |
Brist | -0.001 |
kok | -0.001 |
Kyr | -0.001 |
Token | believers |
Token ID | 23142 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
Pope | +0.053 |
angel | +0.049 |
Towards | +0.042 |
Deng | +0.041 |
atum | +0.041 |
Neg logit contributions | |
Story | -0.049 |
ylan | -0.049 |
Brist | -0.048 |
kok | -0.046 |
Kyr | -0.044 |
Token | hope |
Token ID | 2911 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
Pope | +0.009 |
angel | +0.009 |
Towards | +0.007 |
Deng | +0.007 |
Chu | +0.007 |
Neg logit contributions | |
Story | -0.008 |
ylan | -0.008 |
Brist | -0.008 |
kok | -0.008 |
Kyr | -0.007 |
Token | that |
Token ID | 326 |
Feature activation | -1.65e-02 |
Pos logit contributions | |
Story | +0.085 |
ylan | +0.084 |
Brist | +0.083 |
kok | +0.080 |
Kyr | +0.076 |
Neg logit contributions | |
Pope | -0.090 |
angel | -0.084 |
Towards | -0.071 |
Deng | -0.070 |
Chu | -0.069 |
Token | a |
Token ID | 257 |
Feature activation | +6.69e-03 |
Pos logit contributions | |
Story | +0.013 |
ylan | +0.012 |
Brist | +0.012 |
kok | +0.012 |
Kyr | +0.011 |
Neg logit contributions | |
Pope | -0.013 |
angel | -0.012 |
Towards | -0.010 |
Deng | -0.010 |
Chu | -0.010 |
Token | com |
Token ID | 401 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
Pope | +0.006 |
angel | +0.005 |
Towards | +0.004 |
Deng | +0.004 |
Chu | +0.004 |
Neg logit contributions | |
Story | -0.005 |
ylan | -0.005 |
Brist | -0.005 |
kok | -0.005 |
Kyr | -0.004 |
Token | er |
Token ID | 263 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
Pope | +0.120 |
angel | +0.111 |
Towards | +0.096 |
Deng | +0.095 |
Chu | +0.093 |
Neg logit contributions | |
Story | -0.098 |
ylan | -0.097 |
Brist | -0.095 |
kok | -0.091 |
Kyr | -0.087 |
Token | cial |
Token ID | 2413 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
Story | +0.157 |
ylan | +0.156 |
Brist | +0.154 |
kok | +0.148 |
Kyr | +0.142 |
Neg logit contributions | |
Pope | -0.156 |
angel | -0.144 |
Towards | -0.122 |
Deng | -0.120 |
Chu | -0.118 |
Token | version |
Token ID | 2196 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
Pope | +0.420 |
angel | +0.390 |
Towards | +0.333 |
Deng | +0.329 |
Chu | +0.322 |
Neg logit contributions | |
Story | -0.373 |
ylan | -0.369 |
Brist | -0.363 |
kok | -0.349 |
Kyr | -0.334 |
Token | of |
Token ID | 286 |
Feature activation | +3.09e-03 |
Pos logit contributions | |
Story | +0.126 |
ylan | +0.125 |
Brist | +0.123 |
kok | +0.118 |
Kyr | +0.113 |
Neg logit contributions | |
Pope | -0.136 |
angel | -0.126 |
Towards | -0.107 |
Deng | -0.106 |
Chu | -0.104 |
Token | the |
Token ID | 262 |
Feature activation | +3.53e-03 |
Pos logit contributions | |
Pope | +0.002 |
angel | +0.002 |
Towards | +0.002 |
Deng | +0.002 |
Chu | +0.002 |
Neg logit contributions | |
Story | -0.002 |
ylan | -0.002 |
Brist | -0.002 |
kok | -0.002 |
Kyr | -0.002 |
Token | Rift |
Token ID | 21222 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
Pope | +0.003 |
angel | +0.003 |
Towards | +0.002 |
Deng | +0.002 |
Chu | +0.002 |
Neg logit contributions | |
Story | -0.003 |
ylan | -0.003 |
Brist | -0.003 |
kok | -0.002 |
Kyr | -0.002 |
Token | would |
Token ID | 561 |
Feature activation | -1.65e-02 |
Pos logit contributions | |
Pope | +0.142 |
angel | +0.131 |
Towards | +0.112 |
Deng | +0.110 |
Chu | +0.108 |
Neg logit contributions | |
Story | -0.128 |
ylan | -0.126 |
Brist | -0.124 |
kok | -0.119 |
Kyr | -0.114 |
Token | hope |
Token ID | 2911 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
Pope | +0.010 |
angel | +0.010 |
Towards | +0.008 |
Deng | +0.008 |
Chu | +0.008 |
Neg logit contributions | |
Story | -0.006 |
ylan | -0.006 |
Brist | -0.006 |
kok | -0.006 |
Kyr | -0.005 |
Token | that |
Token ID | 326 |
Feature activation | -2.02e-02 |
Pos logit contributions | |
Story | +0.088 |
ylan | +0.087 |
Brist | +0.086 |
kok | +0.083 |
Kyr | +0.079 |
Neg logit contributions | |
Pope | -0.104 |
angel | -0.096 |
Towards | -0.083 |
Deng | -0.082 |
Chu | -0.080 |
Token | a |
Token ID | 257 |
Feature activation | +2.20e-03 |
Pos logit contributions | |
Story | +0.015 |
ylan | +0.015 |
Brist | +0.015 |
kok | +0.014 |
Kyr | +0.014 |
Neg logit contributions | |
Pope | -0.016 |
angel | -0.015 |
Towards | -0.013 |
Deng | -0.013 |
Chu | -0.012 |
Token | com |
Token ID | 401 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
Pope | +0.001 |
angel | +0.001 |
Towards | +0.001 |
Deng | +0.001 |
Chu | +0.001 |
Neg logit contributions | |
Story | -0.002 |
ylan | -0.002 |
Brist | -0.002 |
kok | -0.002 |
Kyr | -0.002 |
Token | er |
Token ID | 263 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
Pope | +0.143 |
angel | +0.135 |
Towards | +0.120 |
Deng | +0.119 |
Chu | +0.117 |
Neg logit contributions | |
Story | -0.068 |
ylan | -0.067 |
Brist | -0.065 |
kok | -0.062 |
Kyr | -0.058 |
Token | cial |
Token ID | 2413 |
Feature activation | +5.02e-01 |
Pos logit contributions | |
Story | +0.277 |
ylan | +0.275 |
Brist | +0.273 |
kok | +0.267 |
Kyr | +0.261 |
Neg logit contributions | |
Pope | -0.041 |
angel | -0.029 |
Towards | -0.006 |
Deng | -0.004 |
Chu | -0.002 |
Token | version |
Token ID | 2196 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
Pope | +0.501 |
angel | +0.471 |
Towards | +0.415 |
Deng | +0.411 |
Chu | +0.405 |
Neg logit contributions | |
Story | -0.278 |
ylan | -0.275 |
Brist | -0.269 |
kok | -0.255 |
Kyr | -0.240 |
Token | of |
Token ID | 286 |
Feature activation | +8.44e-04 |
Pos logit contributions | |
Story | +0.134 |
ylan | +0.132 |
Brist | +0.130 |
kok | +0.125 |
Kyr | +0.120 |
Neg logit contributions | |
Pope | -0.142 |
angel | -0.132 |
Towards | -0.112 |
Deng | -0.110 |
atum | -0.108 |
Token | the |
Token ID | 262 |
Feature activation | -5.48e-03 |
Pos logit contributions | |
Pope | +0.001 |
angel | +0.001 |
Towards | +0.001 |
Deng | +0.001 |
Chu | +0.001 |
Neg logit contributions | |
Story | -0.001 |
ylan | -0.001 |
Brist | -0.001 |
kok | -0.001 |
Kyr | -0.001 |
Token | Rift |
Token ID | 21222 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
Story | +0.005 |
ylan | +0.005 |
Brist | +0.005 |
kok | +0.005 |
Kyr | +0.005 |
Neg logit contributions | |
Pope | -0.003 |
angel | -0.003 |
Towards | -0.002 |
Deng | -0.002 |
Chu | -0.002 |
Token | would |
Token ID | 561 |
Feature activation | -2.31e-02 |
Pos logit contributions | |
Pope | +0.139 |
angel | +0.130 |
Towards | +0.111 |
Deng | +0.110 |
Chu | +0.108 |
Neg logit contributions | |
Story | -0.116 |
ylan | -0.115 |
Brist | -0.113 |
kok | -0.108 |
Kyr | -0.103 |
Token | next |
Token ID | 1306 |
Feature activation | -2.58e-02 |
Pos logit contributions | |
Story | +0.001 |
ylan | +0.001 |
Brist | +0.001 |
kok | +0.001 |
Kyr | +0.001 |
Neg logit contributions | |
Pope | -0.001 |
angel | -0.001 |
Towards | -0.001 |
Deng | -0.001 |
Chu | -0.001 |
Token | strongest |
Token ID | 12841 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
Story | +0.019 |
ylan | +0.019 |
Brist | +0.019 |
kok | +0.018 |
Kyr | +0.017 |
Neg logit contributions | |
Pope | -0.021 |
angel | -0.019 |
Towards | -0.016 |
Deng | -0.016 |
Chu | -0.016 |
Token | candidates |
Token ID | 5871 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
Pope | +0.130 |
angel | +0.121 |
Towards | +0.104 |
Deng | +0.103 |
Chu | +0.101 |
Neg logit contributions | |
Story | -0.109 |
ylan | -0.108 |
Brist | -0.106 |
kok | -0.102 |
Kyr | -0.097 |
Token | - |
Token ID | 532 |
Feature activation | -2.62e-02 |
Pos logit contributions | |
Story | +0.077 |
ylan | +0.076 |
Brist | +0.075 |
kok | +0.072 |
Kyr | +0.069 |
Neg logit contributions | |
Pope | -0.082 |
angel | -0.076 |
Towards | -0.064 |
Deng | -0.064 |
Chu | -0.062 |
Token | Z |
Token ID | 1168 |
Feature activation | +8.72e-02 |
Pos logit contributions | |
Story | +0.019 |
ylan | +0.019 |
Brist | +0.019 |
kok | +0.018 |
Kyr | +0.017 |
Neg logit contributions | |
Pope | -0.021 |
angel | -0.020 |
Towards | -0.017 |
Deng | -0.016 |
atum | -0.016 |
Token | alm |
Token ID | 38182 |
Feature activation | +5.02e-01 |
Pos logit contributions | |
Pope | +0.071 |
angel | +0.066 |
Towards | +0.056 |
Deng | +0.056 |
Chu | +0.055 |
Neg logit contributions | |
Story | -0.064 |
ylan | -0.063 |
Brist | -0.062 |
kok | -0.060 |
Kyr | -0.057 |
Token | ai |
Token ID | 1872 |
Feature activation | -6.06e-02 |
Pos logit contributions | |
Pope | +0.406 |
angel | +0.379 |
Towards | +0.322 |
Deng | +0.320 |
Chu | +0.314 |
Neg logit contributions | |
Story | -0.371 |
ylan | -0.366 |
Brist | -0.361 |
kok | -0.347 |
saddle | -0.332 |
Token | R |
Token ID | 371 |
Feature activation | -4.67e-02 |
Pos logit contributions | |
Story | +0.044 |
ylan | +0.044 |
Brist | +0.043 |
kok | +0.041 |
Kyr | +0.039 |
Neg logit contributions | |
Pope | -0.050 |
angel | -0.046 |
Towards | -0.040 |
Deng | -0.039 |
Chu | -0.038 |
Token | ass |
Token ID | 562 |
Feature activation | +4.56e-02 |
Pos logit contributions | |
Story | +0.037 |
ylan | +0.037 |
Brist | +0.036 |
kok | +0.035 |
Kyr | +0.033 |
Neg logit contributions | |
Pope | -0.035 |
angel | -0.033 |
Towards | -0.028 |
Deng | -0.027 |
Chu | -0.027 |
Token | ul |
Token ID | 377 |
Feature activation | -5.83e-02 |
Pos logit contributions | |
Pope | +0.036 |
angel | +0.033 |
Towards | +0.028 |
Deng | +0.028 |
Chu | +0.027 |
Neg logit contributions | |
Story | -0.035 |
ylan | -0.034 |
Brist | -0.034 |
kok | -0.033 |
Kyr | -0.031 |
Token | and |
Token ID | 290 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
Story | +0.043 |
ylan | +0.043 |
Brist | +0.042 |
kok | +0.040 |
Kyr | +0.038 |
Neg logit contributions | |
Pope | -0.047 |
angel | -0.044 |
Towards | -0.038 |
Deng | -0.037 |
Chu | -0.036 |
Token | ." |
Token ID | 526 |
Feature activation | +2.54e-02 |
Pos logit contributions | |
Pope | +0.007 |
angel | +0.007 |
Towards | +0.006 |
Deng | +0.006 |
Chu | +0.005 |
Neg logit contributions | |
Story | -0.007 |
ylan | -0.007 |
Brist | -0.007 |
kok | -0.006 |
Kyr | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | +1.31e-03 |
Pos logit contributions | |
Pope | +0.020 |
angel | +0.019 |
Towards | +0.016 |
Deng | +0.016 |
Chu | +0.015 |
Neg logit contributions | |
Story | -0.019 |
ylan | -0.019 |
Brist | -0.019 |
kok | -0.018 |
Kyr | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | +5.83e-03 |
Pos logit contributions | |
Pope | +0.001 |
angel | +0.001 |
Towards | +0.001 |
Deng | +0.001 |
Chu | +0.001 |
Neg logit contributions | |
Story | -0.001 |
ylan | -0.001 |
Brist | -0.001 |
kok | -0.001 |
Kyr | -0.001 |
Token | Lu |
Token ID | 25596 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
Pope | +0.005 |
angel | +0.004 |
Towards | +0.004 |
Deng | +0.004 |
Chu | +0.004 |
Neg logit contributions | |
Story | -0.004 |
ylan | -0.004 |
Brist | -0.004 |
kok | -0.004 |
Kyr | -0.004 |
Token | ol |
Token ID | 349 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
Pope | +0.289 |
angel | +0.275 |
Towards | +0.251 |
Deng | +0.249 |
Chu | +0.246 |
Neg logit contributions | |
Story | -0.056 |
ylan | -0.055 |
Brist | -0.051 |
kok | -0.046 |
Kyr | -0.039 |
Token | Deng |
Token ID | 41985 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
Story | +0.525 |
ylan | +0.522 |
Brist | +0.519 |
kok | +0.507 |
Kyr | +0.496 |
Neg logit contributions | |
Pope | -0.079 |
angel | -0.055 |
Towards | -0.012 |
Chu | -0.002 |
atum | -0.002 |
Token | was |
Token ID | 373 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
Pope | +0.407 |
angel | +0.378 |
Towards | +0.322 |
Deng | +0.317 |
Chu | +0.312 |
Neg logit contributions | |
Story | -0.363 |
ylan | -0.359 |
Brist | -0.353 |
kok | -0.339 |
Kyr | -0.325 |
Token | traded |
Token ID | 14018 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
Pope | +0.008 |
angel | +0.008 |
Towards | +0.007 |
Deng | +0.006 |
Chu | +0.006 |
Neg logit contributions | |
Story | -0.008 |
ylan | -0.008 |
Brist | -0.008 |
kok | -0.007 |
Kyr | -0.007 |
Token | to |
Token ID | 284 |
Feature activation | -9.62e-04 |
Pos logit contributions | |
Pope | +0.013 |
angel | +0.012 |
Towards | +0.010 |
Deng | +0.010 |
Chu | +0.010 |
Neg logit contributions | |
Story | -0.012 |
ylan | -0.012 |
Brist | -0.012 |
kok | -0.011 |
Kyr | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | -3.17e-03 |
Pos logit contributions | |
Story | +0.001 |
ylan | +0.001 |
Brist | +0.001 |
kok | +0.001 |
Kyr | +0.001 |
Neg logit contributions | |
Pope | -0.001 |
angel | -0.001 |
Towards | -0.001 |
Deng | -0.001 |
Chu | -0.001 |
Token | Cavs |
Token ID | 38943 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
Story | +0.002 |
ylan | +0.002 |
Brist | +0.002 |
kok | +0.002 |
Kyr | +0.002 |
Neg logit contributions | |
Pope | -0.003 |
angel | -0.002 |
Towards | -0.002 |
Deng | -0.002 |
Chu | -0.002 |
Token | 's |
Token ID | 338 |
Feature activation | -3.53e-02 |
Pos logit contributions | |
Story | +0.112 |
ylan | +0.111 |
Brist | +0.109 |
kok | +0.105 |
Kyr | +0.101 |
Neg logit contributions | |
Pope | -0.122 |
angel | -0.113 |
Towards | -0.096 |
Deng | -0.095 |
Chu | -0.093 |
Token | published |
Token ID | 3199 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
Story | +0.025 |
ylan | +0.025 |
Brist | +0.025 |
kok | +0.024 |
Kyr | +0.023 |
Neg logit contributions | |
Pope | -0.029 |
angel | -0.027 |
Towards | -0.023 |
Deng | -0.023 |
Chu | -0.022 |
Token | scouting |
Token ID | 27088 |
Feature activation | +6.92e-02 |
Pos logit contributions | |
Pope | +0.191 |
angel | +0.178 |
Towards | +0.152 |
Deng | +0.151 |
Chu | +0.148 |
Neg logit contributions | |
Story | -0.158 |
ylan | -0.156 |
Brist | -0.154 |
kok | -0.148 |
Kyr | -0.141 |
Token | report |
Token ID | 989 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
Pope | +0.037 |
angel | +0.032 |
Towards | +0.025 |
Deng | +0.024 |
Chu | +0.023 |
Neg logit contributions | |
Story | -0.071 |
ylan | -0.070 |
Brist | -0.069 |
kok | -0.067 |
saddle | -0.066 |
Token | on |
Token ID | 319 |
Feature activation | -2.12e-02 |
Pos logit contributions | |
Pope | +0.217 |
angel | +0.201 |
Towards | +0.170 |
Deng | +0.168 |
Chu | +0.165 |
Neg logit contributions | |
Story | -0.200 |
ylan | -0.198 |
Brist | -0.195 |
kok | -0.187 |
Kyr | -0.180 |
Token | Deng |
Token ID | 41985 |
Feature activation | +4.93e-01 |
Pos logit contributions | |
Story | +0.021 |
ylan | +0.021 |
Brist | +0.020 |
kok | +0.020 |
Kyr | +0.019 |
Neg logit contributions | |
Pope | -0.012 |
angel | -0.011 |
Towards | -0.008 |
atum | -0.008 |
Deng | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | +5.60e-03 |
Pos logit contributions | |
Pope | +0.404 |
angel | +0.374 |
Towards | +0.320 |
Deng | +0.314 |
Chu | +0.309 |
Neg logit contributions | |
Story | -0.361 |
ylan | -0.357 |
Brist | -0.352 |
kok | -0.338 |
Kyr | -0.324 |
Token | who |
Token ID | 508 |
Feature activation | +2.75e-03 |
Pos logit contributions | |
Pope | +0.004 |
angel | +0.004 |
Towards | +0.004 |
Deng | +0.003 |
Chu | +0.003 |
Neg logit contributions | |
Story | -0.004 |
ylan | -0.004 |
Brist | -0.004 |
kok | -0.004 |
Kyr | -0.004 |
Token | was |
Token ID | 373 |
Feature activation | +2.10e-02 |
Pos logit contributions | |
Pope | +0.002 |
angel | +0.002 |
Towards | +0.002 |
Deng | +0.002 |
atum | +0.002 |
Neg logit contributions | |
Story | -0.002 |
ylan | -0.002 |
Brist | -0.002 |
kok | -0.002 |
Kyr | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | +2.12e-03 |
Pos logit contributions | |
Pope | +0.017 |
angel | +0.016 |
Towards | +0.013 |
Deng | +0.013 |
Chu | +0.013 |
Neg logit contributions | |
Story | -0.015 |
ylan | -0.015 |
Brist | -0.015 |
kok | -0.015 |
Kyr | -0.014 |
Token | redacted |
Token ID | 44740 |
Feature activation | -7.15e-02 |
Pos logit contributions | |
Pope | +0.002 |
angel | +0.002 |
Towards | +0.001 |
Deng | +0.001 |
atum | +0.001 |
Neg logit contributions | |
Story | -0.002 |
ylan | -0.002 |
Brist | -0.002 |
kok | -0.002 |
Kyr | -0.001 |
Token | types |
Token ID | 3858 |
Feature activation | +8.00e-02 |
Pos logit contributions | |
Story | +0.105 |
ylan | +0.104 |
Brist | +0.103 |
kok | +0.099 |
Kyr | +0.096 |
Neg logit contributions | |
Pope | -0.089 |
angel | -0.082 |
Towards | -0.067 |
Deng | -0.067 |
Chu | -0.065 |
Token | of |
Token ID | 286 |
Feature activation | +9.86e-04 |
Pos logit contributions | |
Pope | +0.063 |
angel | +0.058 |
Towards | +0.049 |
Deng | +0.048 |
Chu | +0.047 |
Neg logit contributions | |
Story | -0.061 |
ylan | -0.061 |
Brist | -0.060 |
kok | -0.058 |
Kyr | -0.055 |
Token | block |
Token ID | 2512 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
Pope | +0.001 |
angel | +0.001 |
Towards | +0.001 |
Deng | +0.001 |
Chu | +0.001 |
Neg logit contributions | |
Story | -0.001 |
ylan | -0.001 |
Brist | -0.001 |
kok | -0.001 |
Kyr | -0.001 |
Token | syntax |
Token ID | 15582 |
Feature activation | -1.76e-02 |
Pos logit contributions | |
Pope | +0.103 |
angel | +0.096 |
Towards | +0.081 |
Deng | +0.080 |
Chu | +0.079 |
Neg logit contributions | |
Story | -0.097 |
ylan | -0.096 |
Brist | -0.095 |
kok | -0.091 |
Kyr | -0.087 |
Token | . |
Token ID | 13 |
Feature activation | -6.88e-03 |
Pos logit contributions | |
Story | +0.013 |
ylan | +0.013 |
Brist | +0.013 |
kok | +0.012 |
Kyr | +0.012 |
Neg logit contributions | |
Pope | -0.014 |
angel | -0.013 |
Towards | -0.011 |
Deng | -0.011 |
Chu | -0.011 |
Token | Towards |
Token ID | 49953 |
Feature activation | +4.92e-01 |
Pos logit contributions | |
Story | +0.005 |
ylan | +0.005 |
Brist | +0.005 |
kok | +0.005 |
Kyr | +0.005 |
Neg logit contributions | |
Pope | -0.005 |
angel | -0.005 |
Towards | -0.004 |
Deng | -0.004 |
atum | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +1.56e-03 |
Pos logit contributions | |
Pope | +0.397 |
angel | +0.367 |
Towards | +0.311 |
Deng | +0.309 |
Chu | +0.302 |
Neg logit contributions | |
Story | -0.367 |
ylan | -0.363 |
Brist | -0.357 |
kok | -0.344 |
Kyr | -0.330 |
Token | end |
Token ID | 886 |
Feature activation | -2.35e-02 |
Pos logit contributions | |
Pope | +0.001 |
angel | +0.001 |
Towards | +0.001 |
Deng | +0.001 |
atum | +0.001 |
Neg logit contributions | |
Story | -0.001 |
ylan | -0.001 |
Brist | -0.001 |
kok | -0.001 |
Kyr | -0.001 |
Token | of |
Token ID | 286 |
Feature activation | +3.52e-03 |
Pos logit contributions | |
Story | +0.018 |
ylan | +0.018 |
Brist | +0.017 |
kok | +0.017 |
Kyr | +0.016 |
Neg logit contributions | |
Pope | -0.018 |
angel | -0.017 |
Towards | -0.014 |
Deng | -0.014 |
Chu | -0.014 |
Token | that |
Token ID | 326 |
Feature activation | -1.80e-02 |
Pos logit contributions | |
Pope | +0.003 |
angel | +0.003 |
Towards | +0.002 |
Deng | +0.002 |
Chu | +0.002 |
Neg logit contributions | |
Story | -0.003 |
ylan | -0.003 |
Brist | -0.003 |
kok | -0.003 |
Kyr | -0.002 |
Token | post |
Token ID | 1281 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
Story | +0.018 |
ylan | +0.018 |
Brist | +0.018 |
kok | +0.017 |
Kyr | +0.017 |
Neg logit contributions | |
Pope | -0.010 |
angel | -0.009 |
Towards | -0.007 |
Deng | -0.006 |
Chu | -0.006 |
Token | at |
Token ID | 265 |
Feature activation | +2.77e-02 |
Pos logit contributions | |
Pope | +0.086 |
angel | +0.080 |
Towards | +0.068 |
Deng | +0.068 |
Chu | +0.066 |
Neg logit contributions | |
Story | -0.076 |
ylan | -0.075 |
Brist | -0.073 |
kok | -0.071 |
Kyr | -0.068 |
Token | ribe |
Token ID | 4892 |
Feature activation | -2.35e-02 |
Pos logit contributions | |
Pope | +0.024 |
angel | +0.023 |
Towards | +0.020 |
Deng | +0.019 |
Chu | +0.019 |
Neg logit contributions | |
Story | -0.018 |
ylan | -0.018 |
Brist | -0.018 |
kok | -0.017 |
Kyr | -0.016 |
Token | on |
Token ID | 319 |
Feature activation | -1.97e-02 |
Pos logit contributions | |
Story | +0.017 |
ylan | +0.017 |
Brist | +0.017 |
kok | +0.016 |
Kyr | +0.016 |
Neg logit contributions | |
Pope | -0.019 |
angel | -0.018 |
Towards | -0.015 |
Deng | -0.015 |
atum | -0.014 |
Token | Lu |
Token ID | 6026 |
Feature activation | +8.09e-02 |
Pos logit contributions | |
Story | +0.015 |
ylan | +0.015 |
Brist | +0.015 |
kok | +0.014 |
Kyr | +0.014 |
Neg logit contributions | |
Pope | -0.015 |
angel | -0.014 |
Towards | -0.012 |
Deng | -0.012 |
atum | -0.012 |
Token | ol |
Token ID | 349 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
Pope | +0.064 |
angel | +0.059 |
Towards | +0.050 |
Deng | +0.050 |
Chu | +0.049 |
Neg logit contributions | |
Story | -0.061 |
ylan | -0.061 |
Brist | -0.060 |
kok | -0.058 |
Kyr | -0.055 |
Token | Deng |
Token ID | 41985 |
Feature activation | +4.92e-01 |
Pos logit contributions | |
Story | +0.477 |
ylan | +0.475 |
Brist | +0.471 |
kok | +0.461 |
Kyr | +0.448 |
Neg logit contributions | |
Pope | -0.116 |
angel | -0.089 |
Towards | -0.049 |
atum | -0.041 |
cial | -0.040 |
Token | as |
Token ID | 355 |
Feature activation | +8.70e-03 |
Pos logit contributions | |
Pope | +0.402 |
angel | +0.373 |
Towards | +0.318 |
Deng | +0.312 |
Chu | +0.308 |
Neg logit contributions | |
Story | -0.361 |
ylan | -0.358 |
Brist | -0.352 |
kok | -0.338 |
Kyr | -0.324 |
Token | belonging |
Token ID | 16686 |
Feature activation | +4.92e-02 |
Pos logit contributions | |
Pope | +0.007 |
angel | +0.006 |
Towards | +0.005 |
Deng | +0.005 |
atum | +0.005 |
Neg logit contributions | |
Story | -0.007 |
ylan | -0.007 |
Brist | -0.007 |
kok | -0.006 |
Kyr | -0.006 |
Token | to |
Token ID | 284 |
Feature activation | -2.07e-03 |
Pos logit contributions | |
Pope | +0.039 |
angel | +0.037 |
Towards | +0.031 |
Deng | +0.031 |
Chu | +0.030 |
Neg logit contributions | |
Story | -0.037 |
ylan | -0.036 |
Brist | -0.036 |
kok | -0.035 |
Kyr | -0.033 |
Token | someone |
Token ID | 2130 |
Feature activation | +2.45e-02 |
Pos logit contributions | |
Story | +0.002 |
ylan | +0.002 |
Brist | +0.002 |
kok | +0.001 |
Kyr | +0.001 |
Neg logit contributions | |
Pope | -0.002 |
angel | -0.001 |
Towards | -0.001 |
Deng | -0.001 |
atum | -0.001 |
Token | else |
Token ID | 2073 |
Feature activation | +8.36e-02 |
Pos logit contributions | |
Pope | +0.019 |
angel | +0.018 |
Towards | +0.015 |
Deng | +0.015 |
atum | +0.015 |
Neg logit contributions | |
Story | -0.019 |
ylan | -0.019 |
Brist | -0.018 |
kok | -0.018 |
Kyr | -0.017 |
Token | was |
Token ID | 373 |
Feature activation | +1.99e-02 |
Pos logit contributions | |
Story | +0.018 |
ylan | +0.018 |
Brist | +0.018 |
kok | +0.017 |
Kyr | +0.016 |
Neg logit contributions | |
Pope | -0.020 |
angel | -0.018 |
Towards | -0.016 |
Deng | -0.015 |
Chu | -0.015 |
Token | given |
Token ID | 1813 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
Pope | +0.017 |
angel | +0.016 |
Towards | +0.013 |
Deng | +0.013 |
Chu | +0.013 |
Neg logit contributions | |
Story | -0.014 |
ylan | -0.014 |
Brist | -0.014 |
kok | -0.013 |
Kyr | -0.013 |
Token | an |
Token ID | 281 |
Feature activation | +6.66e-03 |
Pos logit contributions | |
Story | +0.168 |
ylan | +0.166 |
Brist | +0.164 |
kok | +0.157 |
Kyr | +0.151 |
Neg logit contributions | |
Pope | -0.184 |
angel | -0.171 |
Towards | -0.146 |
Deng | -0.143 |
Chu | -0.141 |
Token | ult |
Token ID | 3789 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
Pope | +0.005 |
angel | +0.005 |
Towards | +0.004 |
Deng | +0.004 |
Chu | +0.004 |
Neg logit contributions | |
Story | -0.005 |
ylan | -0.005 |
Brist | -0.005 |
kok | -0.005 |
Kyr | -0.004 |
Token | im |
Token ID | 320 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
Pope | +0.212 |
angel | +0.192 |
Towards | +0.155 |
Deng | +0.154 |
Chu | +0.150 |
Neg logit contributions | |
Story | -0.297 |
ylan | -0.293 |
Brist | -0.290 |
kok | -0.284 |
Kyr | -0.272 |
Token | atum |
Token ID | 21307 |
Feature activation | +4.91e-01 |
Pos logit contributions | |
Pope | +0.039 |
angel | +0.030 |
Towards | +0.012 |
Deng | +0.011 |
Chu | +0.009 |
Neg logit contributions | |
Story | -0.210 |
ylan | -0.210 |
Brist | -0.206 |
kok | -0.203 |
Kyr | -0.198 |
Token | and |
Token ID | 290 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
Pope | +0.391 |
angel | +0.361 |
Towards | +0.307 |
Deng | +0.303 |
Chu | +0.297 |
Neg logit contributions | |
Story | -0.371 |
ylan | -0.367 |
Brist | -0.362 |
kok | -0.349 |
Kyr | -0.334 |
Token | a |
Token ID | 257 |
Feature activation | +4.59e-03 |
Pos logit contributions | |
Pope | +0.012 |
angel | +0.011 |
Towards | +0.010 |
Deng | +0.010 |
Chu | +0.010 |
Neg logit contributions | |
Story | -0.011 |
ylan | -0.011 |
Brist | -0.011 |
kok | -0.010 |
Kyr | -0.010 |
Token | day |
Token ID | 1110 |
Feature activation | -4.79e-02 |
Pos logit contributions | |
Pope | +0.004 |
angel | +0.003 |
Towards | +0.003 |
Deng | +0.003 |
Chu | +0.003 |
Neg logit contributions | |
Story | -0.003 |
ylan | -0.003 |
Brist | -0.003 |
kok | -0.003 |
Kyr | -0.003 |
Token | to |
Token ID | 284 |
Feature activation | -1.47e-03 |
Pos logit contributions | |
Story | +0.038 |
ylan | +0.038 |
Brist | +0.037 |
kok | +0.036 |
Kyr | +0.034 |
Neg logit contributions | |
Pope | -0.036 |
angel | -0.033 |
Towards | -0.028 |
Deng | -0.028 |
Chu | -0.027 |
Token | think |
Token ID | 892 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
Story | +0.001 |
ylan | +0.001 |
Brist | +0.001 |
kok | +0.001 |
Kyr | +0.001 |
Neg logit contributions | |
Pope | -0.001 |
angel | -0.001 |
Towards | -0.001 |
Deng | -0.001 |
Chu | -0.001 |
Token | re |
Token ID | 302 |
Feature activation | +7.72e-04 |
Pos logit contributions | |
Pope | +0.010 |
angel | +0.009 |
Towards | +0.008 |
Deng | +0.008 |
Chu | +0.008 |
Neg logit contributions | |
Story | -0.009 |
ylan | -0.009 |
Brist | -0.009 |
kok | -0.009 |
Kyr | -0.008 |
Token | - |
Token ID | 12 |
Feature activation | -1.79e-02 |
Pos logit contributions | |
Pope | +0.001 |
angel | +0.001 |
Towards | +0.000 |
Deng | +0.000 |
Chu | +0.000 |
Neg logit contributions | |
Story | -0.001 |
ylan | -0.001 |
Brist | -0.001 |
kok | -0.001 |
Kyr | -0.001 |
Token | stud |
Token ID | 19149 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
Story | +0.013 |
ylan | +0.013 |
Brist | +0.013 |
kok | +0.013 |
Kyr | +0.012 |
Neg logit contributions | |
Pope | -0.014 |
angel | -0.013 |
Towards | -0.011 |
Deng | -0.011 |
Chu | -0.011 |
Token | ying |
Token ID | 1112 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
Story | +0.190 |
ylan | +0.189 |
Brist | +0.186 |
kok | +0.181 |
Kyr | +0.173 |
Neg logit contributions | |
Pope | -0.158 |
angel | -0.143 |
Towards | -0.119 |
Deng | -0.117 |
Chu | -0.114 |
Token | the |
Token ID | 262 |
Feature activation | -2.26e-03 |
Pos logit contributions | |
Pope | +0.119 |
angel | +0.110 |
Towards | +0.093 |
Deng | +0.091 |
atum | +0.090 |
Neg logit contributions | |
Story | -0.109 |
ylan | -0.108 |
Brist | -0.107 |
kok | -0.102 |
Kyr | -0.098 |
Token | Deng |
Token ID | 41985 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
Story | +0.002 |
ylan | +0.002 |
Brist | +0.002 |
kok | +0.002 |
Kyr | +0.002 |
Neg logit contributions | |
Pope | -0.002 |
angel | -0.002 |
Towards | -0.001 |
Deng | -0.001 |
Chu | -0.001 |
Token | intelligence |
Token ID | 4430 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
Pope | +0.405 |
angel | +0.376 |
Towards | +0.322 |
Deng | +0.314 |
Chu | +0.311 |
Neg logit contributions | |
Story | -0.356 |
ylan | -0.351 |
Brist | -0.345 |
kok | -0.332 |
Kyr | -0.317 |
Token | report |
Token ID | 989 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
Story | +0.007 |
ylan | +0.007 |
Brist | +0.007 |
kok | +0.007 |
Kyr | +0.007 |
Neg logit contributions | |
Pope | -0.009 |
angel | -0.008 |
Towards | -0.007 |
Deng | -0.007 |
Chu | -0.007 |
Token | – |
Token ID | 784 |
Feature activation | +2.36e-02 |
Pos logit contributions | |
Pope | +0.214 |
angel | +0.198 |
Towards | +0.169 |
Deng | +0.168 |
Chu | +0.165 |
Neg logit contributions | |
Story | -0.191 |
ylan | -0.189 |
Brist | -0.186 |
kok | -0.179 |
Kyr | -0.171 |
Token | a |
Token ID | 257 |
Feature activation | +6.41e-03 |
Pos logit contributions | |
Pope | +0.019 |
angel | +0.018 |
Towards | +0.015 |
Deng | +0.015 |
Chu | +0.015 |
Neg logit contributions | |
Story | -0.017 |
ylan | -0.017 |
Brist | -0.017 |
kok | -0.016 |
Kyr | -0.016 |
Token | player |
Token ID | 2137 |
Feature activation | -9.56e-02 |
Pos logit contributions | |
Pope | +0.005 |
angel | +0.005 |
Towards | +0.004 |
Deng | +0.004 |
Chu | +0.004 |
Neg logit contributions | |
Story | -0.005 |
ylan | -0.005 |
Brist | -0.005 |
kok | -0.005 |
Kyr | -0.004 |
Token | tactical |
Token ID | 16106 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
Pope | +0.158 |
angel | +0.147 |
Towards | +0.128 |
Deng | +0.127 |
Chu | +0.124 |
Neg logit contributions | |
Story | -0.122 |
ylan | -0.121 |
Brist | -0.118 |
kok | -0.114 |
Kyr | -0.108 |
Token | advantage |
Token ID | 4621 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
Story | +0.010 |
ylan | +0.010 |
Brist | +0.010 |
kok | +0.009 |
Kyr | +0.009 |
Neg logit contributions | |
Pope | -0.015 |
angel | -0.014 |
Towards | -0.012 |
Deng | -0.012 |
Chu | -0.011 |
Token | over |
Token ID | 625 |
Feature activation | -8.78e-02 |
Pos logit contributions | |
Story | +0.110 |
ylan | +0.109 |
Brist | +0.107 |
kok | +0.103 |
Kyr | +0.098 |
Neg logit contributions | |
Pope | -0.128 |
angel | -0.119 |
Towards | -0.102 |
Deng | -0.101 |
Chu | -0.099 |
Token | the |
Token ID | 262 |
Feature activation | +5.68e-03 |
Pos logit contributions | |
Story | +0.068 |
ylan | +0.068 |
Brist | +0.067 |
kok | +0.064 |
Kyr | +0.061 |
Neg logit contributions | |
Pope | -0.068 |
angel | -0.063 |
Towards | -0.053 |
Deng | -0.052 |
Chu | -0.051 |
Token | ch |
Token ID | 442 |
Feature activation | +1.93e-02 |
Pos logit contributions | |
Pope | +0.005 |
angel | +0.004 |
Towards | +0.004 |
Deng | +0.003 |
Chu | +0.003 |
Neg logit contributions | |
Story | -0.004 |
ylan | -0.004 |
Brist | -0.004 |
kok | -0.004 |
Kyr | -0.004 |
Token | asm |
Token ID | 8597 |
Feature activation | +4.88e-01 |
Pos logit contributions | |
Pope | +0.016 |
angel | +0.014 |
Towards | +0.013 |
Deng | +0.012 |
Chu | +0.012 |
Neg logit contributions | |
Story | -0.014 |
ylan | -0.014 |
Brist | -0.014 |
kok | -0.013 |
earch | -0.013 |
Token | below |
Token ID | 2174 |
Feature activation | +9.39e-02 |
Pos logit contributions | |
Pope | +0.386 |
angel | +0.357 |
Towards | +0.303 |
Deng | +0.299 |
Chu | +0.293 |
Neg logit contributions | |
Story | -0.371 |
ylan | -0.368 |
Brist | -0.361 |
kok | -0.348 |
Kyr | -0.334 |
Token | . |
Token ID | 13 |
Feature activation | +3.58e-03 |
Pos logit contributions | |
Pope | +0.074 |
angel | +0.068 |
Towards | +0.058 |
Deng | +0.058 |
Chu | +0.056 |
Neg logit contributions | |
Story | -0.071 |
ylan | -0.071 |
Brist | -0.070 |
kok | -0.067 |
Kyr | -0.064 |
Token | War |
Token ID | 1810 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
Pope | +0.003 |
angel | +0.003 |
Towards | +0.002 |
Deng | +0.002 |
Chu | +0.002 |
Neg logit contributions | |
Story | -0.003 |
ylan | -0.003 |
Brist | -0.003 |
kok | -0.003 |
saddle | -0.002 |
Token | th |
Token ID | 400 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
Story | +0.104 |
ylan | +0.103 |
Brist | +0.101 |
kok | +0.097 |
saddle | +0.093 |
Neg logit contributions | |
Pope | -0.113 |
angel | -0.104 |
Towards | -0.089 |
Deng | -0.087 |
Chu | -0.086 |
Token | ogs |
Token ID | 18463 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
Story | +0.118 |
ylan | +0.118 |
Brist | +0.116 |
kok | +0.112 |
Kyr | +0.107 |
Neg logit contributions | |
Pope | -0.112 |
angel | -0.103 |
Towards | -0.086 |
Deng | -0.085 |
Chu | -0.083 |
Token | to |
Token ID | 284 |
Feature activation | -9.49e-03 |
Pos logit contributions | |
Pope | +0.096 |
angel | +0.089 |
Towards | +0.076 |
Deng | +0.075 |
Chu | +0.074 |
Neg logit contributions | |
Story | -0.088 |
ylan | -0.087 |
Brist | -0.086 |
kok | -0.083 |
Kyr | -0.079 |
Token | describe |
Token ID | 6901 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
Story | +0.007 |
ylan | +0.007 |
Brist | +0.007 |
kok | +0.006 |
saddle | +0.006 |
Neg logit contributions | |
Pope | -0.008 |
angel | -0.007 |
Towards | -0.006 |
Deng | -0.006 |
Chu | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | -4.91e-03 |
Pos logit contributions | |
Pope | +0.174 |
angel | +0.160 |
Towards | +0.133 |
Deng | +0.130 |
Chu | +0.128 |
Neg logit contributions | |
Story | -0.197 |
ylan | -0.196 |
Brist | -0.193 |
kok | -0.186 |
Kyr | -0.179 |
Token | shortcomings |
Token ID | 31731 |
Feature activation | +5.15e-02 |
Pos logit contributions | |
Story | +0.004 |
ylan | +0.004 |
Brist | +0.004 |
kok | +0.004 |
Kyr | +0.003 |
Neg logit contributions | |
Pope | -0.004 |
angel | -0.004 |
Towards | -0.003 |
Deng | -0.003 |
atum | -0.003 |
Token | of |
Token ID | 286 |
Feature activation | -2.07e-03 |
Pos logit contributions | |
Pope | +0.041 |
angel | +0.038 |
Towards | +0.032 |
Deng | +0.032 |
atum | +0.031 |
Neg logit contributions | |
Story | -0.039 |
ylan | -0.038 |
Brist | -0.038 |
kok | -0.036 |
Kyr | -0.035 |
Token | Deng |
Token ID | 41985 |
Feature activation | +4.87e-01 |
Pos logit contributions | |
Story | +0.002 |
ylan | +0.002 |
Brist | +0.002 |
kok | +0.002 |
Kyr | +0.002 |
Neg logit contributions | |
Pope | -0.002 |
angel | -0.001 |
Towards | -0.001 |
Deng | -0.001 |
atum | -0.001 |
Token | in |
Token ID | 287 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
Pope | +0.399 |
angel | +0.370 |
Towards | +0.315 |
Deng | +0.310 |
Chu | +0.305 |
Neg logit contributions | |
Story | -0.357 |
ylan | -0.354 |
Brist | -0.348 |
kok | -0.334 |
Kyr | -0.320 |
Token | a |
Token ID | 257 |
Feature activation | -9.94e-04 |
Pos logit contributions | |
Story | +0.008 |
ylan | +0.008 |
Brist | +0.008 |
kok | +0.008 |
Kyr | +0.008 |
Neg logit contributions | |
Pope | -0.009 |
angel | -0.009 |
Towards | -0.007 |
Deng | -0.007 |
atum | -0.007 |
Token | way |
Token ID | 835 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
Story | +0.001 |
ylan | +0.001 |
Brist | +0.001 |
kok | +0.001 |
Kyr | +0.001 |
Neg logit contributions | |
Pope | -0.001 |
angel | -0.001 |
Towards | -0.001 |
Deng | -0.001 |
atum | -0.001 |
Token | that |
Token ID | 326 |
Feature activation | -2.04e-02 |
Pos logit contributions | |
Pope | +0.099 |
angel | +0.092 |
Towards | +0.079 |
Deng | +0.077 |
atum | +0.076 |
Neg logit contributions | |
Story | -0.086 |
ylan | -0.085 |
Brist | -0.084 |
kok | -0.080 |
Kyr | -0.077 |
Token | never |
Token ID | 1239 |
Feature activation | -3.46e-02 |
Pos logit contributions | |
Story | +0.015 |
ylan | +0.015 |
Brist | +0.014 |
kok | +0.014 |
Kyr | +0.013 |
Neg logit contributions | |
Pope | -0.017 |
angel | -0.016 |
Towards | -0.013 |
Deng | -0.013 |
Chu | -0.013 |
Token | 4 |
Token ID | 604 |
Feature activation | +6.29e-02 |
Pos logit contributions | |
Pope | +0.001 |
angel | +0.000 |
Towards | +0.000 |
Deng | +0.000 |
atum | +0.000 |
Neg logit contributions | |
Story | -0.001 |
ylan | -0.001 |
Brist | -0.001 |
kok | -0.000 |
Kyr | -0.000 |
Token | ms |
Token ID | 907 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
Pope | +0.064 |
angel | +0.061 |
Towards | +0.054 |
Deng | +0.053 |
Chu | +0.052 |
Neg logit contributions | |
Story | -0.033 |
ylan | -0.033 |
Brist | -0.032 |
kok | -0.030 |
Kyr | -0.028 |
Token | G |
Token ID | 402 |
Feature activation | +8.17e-02 |
Pos logit contributions | |
Story | +0.177 |
ylan | +0.175 |
Brist | +0.173 |
kok | +0.167 |
Kyr | +0.162 |
Neg logit contributions | |
Pope | -0.137 |
angel | -0.125 |
Towards | -0.102 |
Deng | -0.100 |
atum | -0.098 |
Token | 2 |
Token ID | 17 |
Feature activation | +8.08e-02 |
Pos logit contributions | |
Pope | +0.057 |
angel | +0.052 |
Towards | +0.043 |
Deng | +0.042 |
Chu | +0.041 |
Neg logit contributions | |
Story | -0.070 |
ylan | -0.069 |
Brist | -0.068 |
kok | -0.066 |
Kyr | -0.064 |
Token | G |
Token ID | 38 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
Pope | +0.055 |
angel | +0.050 |
Towards | +0.041 |
Deng | +0.041 |
Chu | +0.040 |
Neg logit contributions | |
Story | -0.071 |
ylan | -0.069 |
Brist | -0.069 |
kok | -0.066 |
Kyr | -0.064 |
Token | Sharp |
Token ID | 22835 |
Feature activation | +4.85e-01 |
Pos logit contributions | |
Pope | +0.066 |
angel | +0.060 |
Towards | +0.048 |
Deng | +0.047 |
Chu | +0.046 |
Neg logit contributions | |
Story | -0.098 |
ylan | -0.097 |
Brist | -0.096 |
kok | -0.093 |
Kyr | -0.090 |
Token | M |
Token ID | 337 |
Feature activation | +1.88e-02 |
Pos logit contributions | |
Pope | +0.374 |
angel | +0.346 |
Towards | +0.292 |
Deng | +0.288 |
atum | +0.282 |
Neg logit contributions | |
Story | -0.378 |
ylan | -0.372 |
Brist | -0.368 |
kok | -0.353 |
Kyr | -0.339 |
Token | VA |
Token ID | 11731 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
Pope | +0.015 |
angel | +0.014 |
Towards | +0.012 |
Deng | +0.012 |
Chu | +0.011 |
Neg logit contributions | |
Story | -0.014 |
ylan | -0.014 |
Brist | -0.014 |
kok | -0.013 |
Kyr | -0.013 |
Token | + |
Token ID | 1343 |
Feature activation | +4.23e-02 |
Pos logit contributions | |
Pope | +0.164 |
angel | +0.152 |
Towards | +0.130 |
Deng | +0.128 |
Chu | +0.126 |
Neg logit contributions | |
Story | -0.147 |
ylan | -0.145 |
Brist | -0.143 |
kok | -0.137 |
Kyr | -0.131 |
Token | 120 |
Token ID | 7982 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
Pope | +0.033 |
angel | +0.030 |
Towards | +0.025 |
Deng | +0.025 |
atum | +0.025 |
Neg logit contributions | |
Story | -0.033 |
ylan | -0.033 |
Brist | -0.032 |
kok | -0.031 |
Kyr | -0.030 |
Token | Hz |
Token ID | 7399 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
Pope | +0.122 |
angel | +0.113 |
Towards | +0.096 |
Deng | +0.095 |
Chu | +0.093 |
Neg logit contributions | |
Story | -0.115 |
ylan | -0.114 |
Brist | -0.113 |
kok | -0.108 |
Kyr | -0.104 |
Token | Similarly |
Token ID | 28039 |
Feature activation | -6.94e-02 |
Pos logit contributions | |
Pope | +0.005 |
angel | +0.004 |
Towards | +0.004 |
Deng | +0.004 |
Chu | +0.004 |
Neg logit contributions | |
Story | -0.004 |
ylan | -0.004 |
Brist | -0.004 |
kok | -0.004 |
Kyr | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | +4.24e-03 |
Pos logit contributions | |
Story | +0.052 |
ylan | +0.052 |
Brist | +0.051 |
kok | +0.049 |
Kyr | +0.047 |
Neg logit contributions | |
Pope | -0.055 |
angel | -0.051 |
Towards | -0.044 |
Deng | -0.043 |
Chu | -0.042 |
Token | compare |
Token ID | 8996 |
Feature activation | -5.80e-03 |
Pos logit contributions | |
Pope | +0.003 |
angel | +0.003 |
Towards | +0.003 |
Deng | +0.003 |
Chu | +0.003 |
Neg logit contributions | |
Story | -0.003 |
ylan | -0.003 |
Brist | -0.003 |
kok | -0.003 |
Kyr | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | +1.38e-03 |
Pos logit contributions | |
Story | +0.004 |
ylan | +0.004 |
Brist | +0.004 |
kok | +0.004 |
Kyr | +0.004 |
Neg logit contributions | |
Pope | -0.005 |
angel | -0.004 |
Towards | -0.004 |
Deng | -0.003 |
Chu | -0.003 |
Token | ch |
Token ID | 442 |
Feature activation | +2.01e-02 |
Pos logit contributions | |
Pope | +0.001 |
angel | +0.001 |
Towards | +0.001 |
Deng | +0.001 |
Chu | +0.001 |
Neg logit contributions | |
Story | -0.001 |
ylan | -0.001 |
Brist | -0.001 |
kok | -0.001 |
Kyr | -0.001 |
Token | asm |
Token ID | 8597 |
Feature activation | +4.85e-01 |
Pos logit contributions | |
Pope | +0.015 |
angel | +0.014 |
Towards | +0.012 |
Deng | +0.012 |
Chu | +0.011 |
Neg logit contributions | |
Story | -0.016 |
ylan | -0.016 |
Brist | -0.016 |
kok | -0.015 |
Kyr | -0.014 |
Token | in |
Token ID | 287 |
Feature activation | -2.24e-03 |
Pos logit contributions | |
Pope | +0.371 |
angel | +0.342 |
Towards | +0.288 |
Deng | +0.284 |
Chu | +0.278 |
Neg logit contributions | |
Story | -0.380 |
ylan | -0.377 |
Brist | -0.371 |
kok | -0.358 |
Kyr | -0.344 |
Token | rational |
Token ID | 9377 |
Feature activation | +4.64e-02 |
Pos logit contributions | |
Story | +0.002 |
ylan | +0.002 |
Brist | +0.002 |
kok | +0.001 |
Kyr | +0.001 |
Neg logit contributions | |
Pope | -0.002 |
angel | -0.002 |
Towards | -0.002 |
Deng | -0.001 |
Chu | -0.001 |
Token | analysis |
Token ID | 3781 |
Feature activation | -3.68e-02 |
Pos logit contributions | |
Pope | +0.039 |
angel | +0.037 |
Towards | +0.031 |
Deng | +0.031 |
Chu | +0.030 |
Neg logit contributions | |
Story | -0.033 |
ylan | -0.032 |
Brist | -0.032 |
kok | -0.031 |
Kyr | -0.029 |
Token | separating |
Token ID | 27259 |
Feature activation | +6.07e-02 |
Pos logit contributions | |
Story | +0.028 |
ylan | +0.028 |
Brist | +0.028 |
kok | +0.027 |
Kyr | +0.026 |
Neg logit contributions | |
Pope | -0.029 |
angel | -0.026 |
Towards | -0.022 |
Deng | -0.022 |
Chu | -0.021 |
Token | the |
Token ID | 262 |
Feature activation | +5.55e-03 |
Pos logit contributions | |
Pope | +0.050 |
angel | +0.046 |
Towards | +0.039 |
Deng | +0.039 |
atum | +0.038 |
Neg logit contributions | |
Story | -0.044 |
ylan | -0.044 |
Brist | -0.043 |
kok | -0.042 |
Kyr | -0.040 |
Token | doubt |
Token ID | 4719 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
Story | +0.045 |
ylan | +0.044 |
Brist | +0.044 |
kok | +0.042 |
Kyr | +0.041 |
Neg logit contributions | |
Pope | -0.036 |
angel | -0.033 |
Towards | -0.027 |
Deng | -0.027 |
Chu | -0.026 |
Token | be |
Token ID | 307 |
Feature activation | -3.90e-03 |
Pos logit contributions | |
Pope | +0.087 |
angel | +0.081 |
Towards | +0.069 |
Deng | +0.068 |
Chu | +0.067 |
Neg logit contributions | |
Story | -0.077 |
ylan | -0.076 |
Brist | -0.075 |
kok | -0.072 |
Kyr | -0.069 |
Token | having |
Token ID | 1719 |
Feature activation | +3.56e-02 |
Pos logit contributions | |
Story | +0.003 |
ylan | +0.003 |
Brist | +0.003 |
kok | +0.003 |
Kyr | +0.003 |
Neg logit contributions | |
Pope | -0.003 |
angel | -0.003 |
Towards | -0.003 |
Deng | -0.003 |
Chu | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | +2.92e-03 |
Pos logit contributions | |
Pope | +0.029 |
angel | +0.026 |
Towards | +0.022 |
Deng | +0.022 |
atum | +0.022 |
Neg logit contributions | |
Story | -0.027 |
ylan | -0.026 |
Brist | -0.026 |
kok | -0.025 |
Kyr | -0.024 |
Token | sp |
Token ID | 599 |
Feature activation | -3.72e-02 |
Pos logit contributions | |
Pope | +0.002 |
angel | +0.002 |
Towards | +0.002 |
Deng | +0.002 |
Chu | +0.002 |
Neg logit contributions | |
Story | -0.002 |
ylan | -0.002 |
Brist | -0.002 |
kok | -0.002 |
Kyr | -0.002 |
Token | asm |
Token ID | 8597 |
Feature activation | +4.83e-01 |
Pos logit contributions | |
Story | +0.031 |
ylan | +0.030 |
Brist | +0.030 |
kok | +0.029 |
earch | +0.028 |
Neg logit contributions | |
Pope | -0.027 |
angel | -0.025 |
Towards | -0.021 |
Deng | -0.020 |
Chu | -0.020 |
Token | or |
Token ID | 393 |
Feature activation | -6.69e-02 |
Pos logit contributions | |
Pope | +0.385 |
angel | +0.355 |
Towards | +0.302 |
Deng | +0.298 |
Chu | +0.292 |
Neg logit contributions | |
Story | -0.364 |
ylan | -0.360 |
Brist | -0.354 |
kok | -0.342 |
saddle | -0.327 |
Token | two |
Token ID | 734 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
Story | +0.048 |
ylan | +0.048 |
Brist | +0.047 |
kok | +0.045 |
saddle | +0.044 |
Neg logit contributions | |
Pope | -0.055 |
angel | -0.051 |
Towards | -0.044 |
Deng | -0.043 |
atum | -0.042 |
Token | trying |
Token ID | 2111 |
Feature activation | -3.45e-02 |
Pos logit contributions | |
Story | +0.013 |
ylan | +0.013 |
Brist | +0.013 |
kok | +0.012 |
Kyr | +0.012 |
Neg logit contributions | |
Pope | -0.014 |
angel | -0.013 |
Towards | -0.011 |
Deng | -0.011 |
atum | -0.010 |
Token | to |
Token ID | 284 |
Feature activation | -1.89e-03 |
Pos logit contributions | |
Story | +0.026 |
ylan | +0.026 |
Brist | +0.025 |
kok | +0.024 |
Kyr | +0.023 |
Neg logit contributions | |
Pope | -0.028 |
angel | -0.026 |
Towards | -0.022 |
Deng | -0.021 |
Chu | -0.021 |
Token | make |
Token ID | 787 |
Feature activation | -6.30e-02 |
Pos logit contributions | |
Story | +0.001 |
ylan | +0.001 |
Brist | +0.001 |
kok | +0.001 |
Kyr | +0.001 |
Neg logit contributions | |
Pope | -0.002 |
angel | -0.001 |
Towards | -0.001 |
Deng | -0.001 |
Chu | -0.001 |
Token | was |
Token ID | 373 |
Feature activation | +1.86e-02 |
Pos logit contributions | |
Story | +0.065 |
ylan | +0.065 |
Brist | +0.064 |
kok | +0.061 |
Kyr | +0.058 |
Neg logit contributions | |
Pope | -0.078 |
angel | -0.072 |
Towards | -0.062 |
Deng | -0.061 |
Chu | -0.060 |
Token | tweeted |
Token ID | 10830 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
Pope | +0.014 |
angel | +0.013 |
Towards | +0.011 |
Deng | +0.010 |
Chu | +0.010 |
Neg logit contributions | |
Story | -0.015 |
ylan | -0.015 |
Brist | -0.015 |
kok | -0.014 |
Kyr | -0.014 |
Token | by |
Token ID | 416 |
Feature activation | -2.86e-03 |
Pos logit contributions | |
Pope | +0.139 |
angel | +0.129 |
Towards | +0.109 |
Deng | +0.108 |
Chu | +0.106 |
Neg logit contributions | |
Story | -0.128 |
ylan | -0.127 |
Brist | -0.125 |
kok | -0.120 |
Kyr | -0.115 |
Token | Diana |
Token ID | 25752 |
Feature activation | +6.47e-03 |
Pos logit contributions | |
Story | +0.002 |
ylan | +0.002 |
Brist | +0.002 |
kok | +0.002 |
Kyr | +0.002 |
Neg logit contributions | |
Pope | -0.002 |
angel | -0.002 |
Towards | -0.002 |
Deng | -0.002 |
Chu | -0.002 |
Token | Al |
Token ID | 978 |
Feature activation | +8.40e-02 |
Pos logit contributions | |
Pope | +0.005 |
angel | +0.005 |
Towards | +0.004 |
Deng | +0.004 |
atum | +0.004 |
Neg logit contributions | |
Story | -0.005 |
ylan | -0.005 |
Brist | -0.005 |
kok | -0.005 |
Kyr | -0.004 |
Token | ze |
Token ID | 2736 |
Feature activation | +4.71e-01 |
Pos logit contributions | |
Pope | +0.067 |
angel | +0.062 |
Towards | +0.052 |
Deng | +0.052 |
Chu | +0.051 |
Neg logit contributions | |
Story | -0.063 |
ylan | -0.063 |
Brist | -0.062 |
kok | -0.060 |
Kyr | -0.057 |
Token | er |
Token ID | 263 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
Pope | +0.379 |
angel | +0.353 |
Towards | +0.299 |
Deng | +0.296 |
Chu | +0.291 |
Neg logit contributions | |
Story | -0.351 |
ylan | -0.344 |
Brist | -0.342 |
kok | -0.327 |
saddle | -0.314 |
Token | . |
Token ID | 13 |
Feature activation | -3.38e-03 |
Pos logit contributions | |
Story | +0.165 |
ylan | +0.164 |
Brist | +0.161 |
kok | +0.156 |
Kyr | +0.150 |
Neg logit contributions | |
Pope | -0.154 |
angel | -0.142 |
Towards | -0.119 |
Deng | -0.117 |
Chu | -0.115 |
Token |
|
Token ID | 198 |
Feature activation | +6.55e-03 |
Pos logit contributions | |
Story | +0.003 |
ylan | +0.003 |
Brist | +0.003 |
kok | +0.002 |
Kyr | +0.002 |
Neg logit contributions | |
Pope | -0.003 |
angel | -0.002 |
Towards | -0.002 |
Deng | -0.002 |
Chu | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
Pope | +0.005 |
angel | +0.005 |
Towards | +0.004 |
Deng | +0.004 |
Chu | +0.004 |
Neg logit contributions | |
Story | -0.005 |
ylan | -0.005 |
Brist | -0.005 |
kok | -0.005 |
Kyr | -0.004 |
Token | � |
Token ID | 447 |
Feature activation | +5.97e-04 |
Pos logit contributions | |
Pope | +0.008 |
angel | +0.008 |
Towards | +0.007 |
Deng | +0.007 |
Chu | +0.006 |
Neg logit contributions | |
Story | -0.008 |
ylan | -0.008 |
Brist | -0.008 |
kok | -0.007 |
Kyr | -0.007 |
Token | citizens |
Token ID | 4290 |
Feature activation | +7.44e-03 |
Pos logit contributions | |
Story | +0.117 |
ylan | +0.116 |
Brist | +0.114 |
kok | +0.110 |
Kyr | +0.106 |
Neg logit contributions | |
Pope | -0.117 |
angel | -0.108 |
Towards | -0.091 |
Deng | -0.090 |
atum | -0.088 |
Token | the |
Token ID | 262 |
Feature activation | -8.97e-03 |
Pos logit contributions | |
Pope | +0.006 |
angel | +0.006 |
Towards | +0.005 |
Deng | +0.005 |
atum | +0.005 |
Neg logit contributions | |
Story | -0.005 |
ylan | -0.005 |
Brist | -0.005 |
kok | -0.005 |
Kyr | -0.005 |
Token | right |
Token ID | 826 |
Feature activation | -8.40e-03 |
Pos logit contributions | |
Story | +0.007 |
ylan | +0.007 |
Brist | +0.007 |
kok | +0.006 |
Kyr | +0.006 |
Neg logit contributions | |
Pope | -0.007 |
angel | -0.007 |
Towards | -0.006 |
Deng | -0.005 |
Chu | -0.005 |
Token | to |
Token ID | 284 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
Story | +0.006 |
ylan | +0.006 |
Brist | +0.006 |
kok | +0.006 |
Kyr | +0.006 |
Neg logit contributions | |
Pope | -0.007 |
angel | -0.006 |
Towards | -0.005 |
Deng | -0.005 |
Chu | -0.005 |
Token | gra |
Token ID | 7933 |
Feature activation | +1.19e-03 |
Pos logit contributions | |
Story | +0.010 |
ylan | +0.010 |
Brist | +0.010 |
kok | +0.009 |
saddle | +0.009 |
Neg logit contributions | |
Pope | -0.010 |
angel | -0.010 |
Towards | -0.008 |
Deng | -0.008 |
Chu | -0.008 |
Token | ze |
Token ID | 2736 |
Feature activation | +4.70e-01 |
Pos logit contributions | |
Pope | +0.000 |
angel | +0.000 |
Towards | +0.000 |
Deng | +0.000 |
Chu | +0.000 |
Neg logit contributions | |
Story | -0.002 |
ylan | -0.002 |
Brist | -0.002 |
kok | -0.001 |
saddle | -0.001 |
Token | sheep |
Token ID | 15900 |
Feature activation | -6.85e-02 |
Pos logit contributions | |
Pope | +0.379 |
angel | +0.350 |
Towards | +0.297 |
Deng | +0.294 |
Chu | +0.288 |
Neg logit contributions | |
Story | -0.350 |
ylan | -0.348 |
Brist | -0.343 |
kok | -0.329 |
Kyr | -0.316 |
Token | on |
Token ID | 319 |
Feature activation | -2.44e-02 |
Pos logit contributions | |
Story | +0.051 |
ylan | +0.051 |
Brist | +0.050 |
kok | +0.048 |
Kyr | +0.046 |
Neg logit contributions | |
Pope | -0.055 |
angel | -0.051 |
Towards | -0.043 |
Deng | -0.043 |
Chu | -0.042 |
Token | any |
Token ID | 597 |
Feature activation | -6.88e-02 |
Pos logit contributions | |
Story | +0.018 |
ylan | +0.018 |
Brist | +0.018 |
kok | +0.017 |
Kyr | +0.016 |
Neg logit contributions | |
Pope | -0.020 |
angel | -0.018 |
Towards | -0.016 |
Deng | -0.015 |
Chu | -0.015 |
Token | golf |
Token ID | 13126 |
Feature activation | -8.95e-02 |
Pos logit contributions | |
Story | +0.053 |
ylan | +0.052 |
Brist | +0.052 |
kok | +0.050 |
saddle | +0.048 |
Neg logit contributions | |
Pope | -0.054 |
angel | -0.050 |
Towards | -0.042 |
Deng | -0.041 |
Chu | -0.040 |
Token | course |
Token ID | 1781 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
Story | +0.046 |
ylan | +0.046 |
Brist | +0.045 |
kok | +0.042 |
saddle | +0.040 |
Neg logit contributions | |
Pope | -0.093 |
angel | -0.087 |
Towards | -0.077 |
Deng | -0.077 |
Chu | -0.075 |
Token | executive |
Token ID | 4640 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
Story | +0.027 |
ylan | +0.026 |
Brist | +0.026 |
kok | +0.025 |
Kyr | +0.024 |
Neg logit contributions | |
Pope | -0.028 |
angel | -0.026 |
Towards | -0.021 |
Deng | -0.021 |
atum | -0.021 |
Token | director |
Token ID | 3437 |
Feature activation | -2.40e-02 |
Pos logit contributions | |
Pope | +0.102 |
angel | +0.095 |
Towards | +0.082 |
Deng | +0.080 |
atum | +0.079 |
Neg logit contributions | |
Story | -0.085 |
ylan | -0.084 |
Brist | -0.083 |
kok | -0.080 |
Kyr | -0.076 |
Token | David |
Token ID | 3271 |
Feature activation | -4.31e-02 |
Pos logit contributions | |
Story | +0.018 |
ylan | +0.018 |
Brist | +0.017 |
kok | +0.017 |
Kyr | +0.016 |
Neg logit contributions | |
Pope | -0.019 |
angel | -0.018 |
Towards | -0.015 |
Deng | -0.015 |
atum | -0.015 |
Token | Re |
Token ID | 797 |
Feature activation | -1.84e-02 |
Pos logit contributions | |
Story | +0.033 |
ylan | +0.033 |
Brist | +0.032 |
kok | +0.031 |
Kyr | +0.030 |
Neg logit contributions | |
Pope | -0.034 |
angel | -0.031 |
Towards | -0.026 |
Deng | -0.026 |
atum | -0.026 |
Token | it |
Token ID | 270 |
Feature activation | +4.64e-02 |
Pos logit contributions | |
Story | +0.014 |
ylan | +0.014 |
Brist | +0.013 |
kok | +0.013 |
Kyr | +0.012 |
Neg logit contributions | |
Pope | -0.015 |
angel | -0.014 |
Towards | -0.012 |
Deng | -0.012 |
Chu | -0.011 |
Token | ze |
Token ID | 2736 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
Pope | +0.040 |
angel | +0.037 |
Towards | +0.032 |
Deng | +0.032 |
Chu | +0.031 |
Neg logit contributions | |
Story | -0.032 |
ylan | -0.032 |
Brist | -0.031 |
kok | -0.030 |
earch | -0.028 |
Token | says |
Token ID | 1139 |
Feature activation | +4.45e-02 |
Pos logit contributions | |
Pope | +0.374 |
angel | +0.345 |
Towards | +0.294 |
Deng | +0.289 |
Chu | +0.283 |
Neg logit contributions | |
Story | -0.352 |
ylan | -0.350 |
Brist | -0.345 |
kok | -0.333 |
Kyr | -0.318 |
Token | that |
Token ID | 326 |
Feature activation | -2.56e-02 |
Pos logit contributions | |
Pope | +0.036 |
angel | +0.033 |
Towards | +0.029 |
Deng | +0.028 |
Chu | +0.028 |
Neg logit contributions | |
Story | -0.033 |
ylan | -0.033 |
Brist | -0.032 |
kok | -0.031 |
Kyr | -0.030 |
Token | this |
Token ID | 428 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
Story | +0.019 |
ylan | +0.019 |
Brist | +0.019 |
kok | +0.018 |
Kyr | +0.017 |
Neg logit contributions | |
Pope | -0.021 |
angel | -0.019 |
Towards | -0.016 |
Deng | -0.016 |
atum | -0.016 |
Token | practice |
Token ID | 3357 |
Feature activation | +7.04e-02 |
Pos logit contributions | |
Pope | +0.081 |
angel | +0.076 |
Towards | +0.064 |
Deng | +0.063 |
atum | +0.062 |
Neg logit contributions | |
Story | -0.075 |
ylan | -0.075 |
Brist | -0.073 |
kok | -0.071 |
Kyr | -0.068 |
Token | will |
Token ID | 481 |
Feature activation | +7.04e-03 |
Pos logit contributions | |
Pope | +0.058 |
angel | +0.054 |
Towards | +0.046 |
Deng | +0.045 |
Chu | +0.044 |
Neg logit contributions | |
Story | -0.051 |
ylan | -0.051 |
Brist | -0.050 |
kok | -0.048 |
Kyr | -0.046 |
Token | the |
Token ID | 262 |
Feature activation | -1.74e-04 |
Pos logit contributions | |
Pope | +0.009 |
angel | +0.008 |
Towards | +0.007 |
Deng | +0.007 |
Chu | +0.007 |
Neg logit contributions | |
Story | -0.008 |
ylan | -0.008 |
Brist | -0.007 |
kok | -0.007 |
Kyr | -0.007 |
Token | death |
Token ID | 1918 |
Feature activation | +7.54e-02 |
Pos logit contributions | |
Story | +0.000 |
ylan | +0.000 |
Brist | +0.000 |
kok | +0.000 |
Kyr | +0.000 |
Neg logit contributions | |
Pope | -0.000 |
angel | -0.000 |
Towards | -0.000 |
Deng | -0.000 |
Chu | -0.000 |
Token | of |
Token ID | 286 |
Feature activation | +5.16e-03 |
Pos logit contributions | |
Pope | +0.059 |
angel | +0.055 |
Towards | +0.046 |
Deng | +0.046 |
Chu | +0.045 |
Neg logit contributions | |
Story | -0.058 |
ylan | -0.057 |
Brist | -0.056 |
kok | -0.054 |
Kyr | -0.052 |
Token | the |
Token ID | 262 |
Feature activation | -2.98e-03 |
Pos logit contributions | |
Pope | +0.004 |
angel | +0.004 |
Towards | +0.003 |
Deng | +0.003 |
atum | +0.003 |
Neg logit contributions | |
Story | -0.004 |
ylan | -0.004 |
Brist | -0.004 |
kok | -0.003 |
Kyr | -0.003 |
Token | Dru |
Token ID | 21295 |
Feature activation | -4.63e-02 |
Pos logit contributions | |
Story | +0.002 |
ylan | +0.002 |
Brist | +0.002 |
kok | +0.002 |
Kyr | +0.002 |
Neg logit contributions | |
Pope | -0.002 |
angel | -0.002 |
Towards | -0.002 |
Deng | -0.002 |
atum | -0.002 |
Token | ze |
Token ID | 2736 |
Feature activation | +4.68e-01 |
Pos logit contributions | |
Story | +0.059 |
ylan | +0.059 |
Brist | +0.058 |
kok | +0.057 |
saddle | +0.056 |
Neg logit contributions | |
Pope | -0.012 |
angel | -0.009 |
Towards | -0.005 |
Deng | -0.004 |
Chu | -0.004 |
Token | police |
Token ID | 1644 |
Feature activation | -2.92e-02 |
Pos logit contributions | |
Pope | +0.370 |
angel | +0.343 |
Towards | +0.291 |
Deng | +0.288 |
atum | +0.281 |
Neg logit contributions | |
Story | -0.354 |
ylan | -0.351 |
Brist | -0.346 |
kok | -0.332 |
Kyr | -0.319 |
Token | officer |
Token ID | 3818 |
Feature activation | -6.99e-02 |
Pos logit contributions | |
Story | +0.023 |
ylan | +0.023 |
Brist | +0.023 |
kok | +0.022 |
Kyr | +0.021 |
Neg logit contributions | |
Pope | -0.022 |
angel | -0.020 |
Towards | -0.017 |
Deng | -0.017 |
atum | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -4.02e-03 |
Pos logit contributions | |
Story | +0.052 |
ylan | +0.052 |
Brist | +0.051 |
kok | +0.049 |
Kyr | +0.047 |
Neg logit contributions | |
Pope | -0.056 |
angel | -0.052 |
Towards | -0.044 |
Deng | -0.044 |
Chu | -0.043 |
Token |
|
Token ID | 198 |
Feature activation | +7.70e-03 |
Pos logit contributions | |
Story | +0.003 |
ylan | +0.003 |
Brist | +0.003 |
kok | +0.003 |
Kyr | +0.003 |
Neg logit contributions | |
Pope | -0.003 |
angel | -0.003 |
Towards | -0.002 |
Deng | -0.002 |
Chu | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +1.58e-03 |
Pos logit contributions | |
Pope | +0.006 |
angel | +0.006 |
Towards | +0.005 |
Deng | +0.005 |
Chu | +0.005 |
Neg logit contributions | |
Story | -0.006 |
ylan | -0.006 |
Brist | -0.006 |
kok | -0.005 |
Kyr | -0.005 |
Token | Jewish |
Token ID | 5582 |
Feature activation | +3.18e-02 |
Pos logit contributions | |
Pope | +0.019 |
angel | +0.018 |
Towards | +0.015 |
Deng | +0.015 |
Chu | +0.015 |
Neg logit contributions | |
Story | -0.018 |
ylan | -0.018 |
Brist | -0.018 |
kok | -0.017 |
Kyr | -0.016 |
Token | , |
Token ID | 11 |
Feature activation | -1.73e-03 |
Pos logit contributions | |
Pope | +0.025 |
angel | +0.023 |
Towards | +0.019 |
Deng | +0.019 |
atum | +0.019 |
Neg logit contributions | |
Story | -0.024 |
ylan | -0.024 |
Brist | -0.024 |
kok | -0.023 |
Kyr | -0.022 |
Token | Arab |
Token ID | 4498 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
Story | +0.001 |
ylan | +0.001 |
Brist | +0.001 |
kok | +0.001 |
Kyr | +0.001 |
Neg logit contributions | |
Pope | -0.002 |
angel | -0.001 |
Towards | -0.001 |
Deng | -0.001 |
Chu | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | +5.15e-03 |
Pos logit contributions | |
Story | +0.092 |
ylan | +0.092 |
Brist | +0.090 |
kok | +0.087 |
Kyr | +0.083 |
Neg logit contributions | |
Pope | -0.094 |
angel | -0.087 |
Towards | -0.073 |
Deng | -0.072 |
Chu | -0.071 |
Token | Dru |
Token ID | 21295 |
Feature activation | -5.27e-02 |
Pos logit contributions | |
Pope | +0.004 |
angel | +0.004 |
Towards | +0.004 |
Deng | +0.003 |
atum | +0.003 |
Neg logit contributions | |
Story | -0.004 |
ylan | -0.004 |
Brist | -0.003 |
kok | -0.003 |
Kyr | -0.003 |
Token | ze |
Token ID | 2736 |
Feature activation | +4.68e-01 |
Pos logit contributions | |
Story | +0.069 |
ylan | +0.068 |
Brist | +0.067 |
kok | +0.066 |
Kyr | +0.065 |
Neg logit contributions | |
Pope | -0.013 |
angel | -0.010 |
Towards | -0.004 |
Deng | -0.004 |
Chu | -0.003 |
Token | – |
Token ID | 784 |
Feature activation | +1.76e-02 |
Pos logit contributions | |
Pope | +0.357 |
angel | +0.330 |
Towards | +0.278 |
Deng | +0.275 |
Chu | +0.269 |
Neg logit contributions | |
Story | -0.367 |
ylan | -0.364 |
Brist | -0.358 |
kok | -0.346 |
Kyr | -0.331 |
Token | who |
Token ID | 508 |
Feature activation | -2.33e-03 |
Pos logit contributions | |
Pope | +0.014 |
angel | +0.013 |
Towards | +0.011 |
Deng | +0.011 |
Chu | +0.011 |
Neg logit contributions | |
Story | -0.013 |
ylan | -0.013 |
Brist | -0.013 |
kok | -0.012 |
Kyr | -0.012 |
Token | came |
Token ID | 1625 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
Story | +0.002 |
ylan | +0.002 |
Brist | +0.002 |
kok | +0.002 |
Kyr | +0.002 |
Neg logit contributions | |
Pope | -0.002 |
angel | -0.002 |
Towards | -0.001 |
Deng | -0.001 |
Chu | -0.001 |
Token | together |
Token ID | 1978 |
Feature activation | -8.47e-02 |
Pos logit contributions | |
Pope | +0.136 |
angel | +0.126 |
Towards | +0.108 |
Deng | +0.106 |
Chu | +0.104 |
Neg logit contributions | |
Story | -0.124 |
ylan | -0.123 |
Brist | -0.121 |
kok | -0.116 |
Kyr | -0.111 |
Token | for |
Token ID | 329 |
Feature activation | -3.74e-03 |
Pos logit contributions | |
Story | +0.063 |
ylan | +0.062 |
Brist | +0.061 |
kok | +0.059 |
Kyr | +0.057 |
Neg logit contributions | |
Pope | -0.068 |
angel | -0.063 |
Towards | -0.054 |
Deng | -0.053 |
Chu | -0.052 |
Token | ( |
Token ID | 357 |
Feature activation | -7.08e-02 |
Pos logit contributions | |
Story | +0.001 |
ylan | +0.001 |
Brist | +0.001 |
kok | +0.001 |
Kyr | +0.001 |
Neg logit contributions | |
Pope | -0.002 |
angel | -0.002 |
Towards | -0.001 |
Deng | -0.001 |
atum | -0.001 |
Token | AP |
Token ID | 2969 |
Feature activation | -4.88e-02 |
Pos logit contributions | |
Story | +0.050 |
ylan | +0.049 |
Brist | +0.048 |
kok | +0.046 |
Kyr | +0.044 |
Neg logit contributions | |
Pope | -0.060 |
angel | -0.056 |
Towards | -0.048 |
Deng | -0.047 |
Chu | -0.047 |
Token | ) |
Token ID | 8 |
Feature activation | -3.60e-02 |
Pos logit contributions | |
Story | +0.030 |
ylan | +0.030 |
Brist | +0.029 |
kok | +0.028 |
Kyr | +0.027 |
Neg logit contributions | |
Pope | -0.045 |
angel | -0.042 |
Towards | -0.037 |
Deng | -0.037 |
Chu | -0.036 |
Token |
|
Token ID | 198 |
Feature activation | +6.18e-04 |
Pos logit contributions | |
Story | +0.026 |
ylan | +0.026 |
Brist | +0.026 |
kok | +0.025 |
Kyr | +0.024 |
Neg logit contributions | |
Pope | -0.029 |
angel | -0.027 |
Towards | -0.023 |
Deng | -0.023 |
atum | -0.023 |
Token |
|
Token ID | 198 |
Feature activation | +3.81e-03 |
Pos logit contributions | |
Pope | +0.000 |
angel | +0.000 |
Towards | +0.000 |
Deng | +0.000 |
Chu | +0.000 |
Neg logit contributions | |
Story | -0.000 |
ylan | -0.000 |
Brist | -0.000 |
kok | -0.000 |
Kyr | -0.000 |
Token | Story |
Token ID | 11605 |
Feature activation | -6.28e-01 |
Pos logit contributions | |
Pope | +0.003 |
angel | +0.003 |
Towards | +0.002 |
Deng | +0.002 |
Chu | +0.002 |
Neg logit contributions | |
Story | -0.003 |
ylan | -0.003 |
Brist | -0.003 |
kok | -0.003 |
Kyr | -0.003 |
Token | continues |
Token ID | 4477 |
Feature activation | -5.59e-02 |
Pos logit contributions | |
Story | +0.426 |
ylan | +0.420 |
Brist | +0.412 |
kok | +0.394 |
Kyr | +0.374 |
Neg logit contributions | |
Pope | -0.551 |
angel | -0.514 |
Towards | -0.441 |
Deng | -0.437 |
Chu | -0.429 |
Token |
|
Token ID | 198 |
Feature activation | +3.81e-03 |
Pos logit contributions | |
Story | +0.048 |
ylan | +0.048 |
Brist | +0.047 |
kok | +0.046 |
Kyr | +0.044 |
Neg logit contributions | |
Pope | -0.038 |
angel | -0.035 |
Towards | -0.029 |
Deng | -0.028 |
Chu | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | +5.31e-03 |
Pos logit contributions | |
Pope | +0.003 |
angel | +0.003 |
Towards | +0.002 |
Deng | +0.002 |
Chu | +0.002 |
Neg logit contributions | |
Story | -0.003 |
ylan | -0.003 |
Brist | -0.003 |
kok | -0.003 |
Kyr | -0.003 |
Token | There |
Token ID | 1858 |
Feature activation | -9.15e-02 |
Pos logit contributions | |
Pope | +0.007 |
angel | +0.007 |
Towards | +0.007 |
Deng | +0.007 |
Chu | +0.006 |
Neg logit contributions | |
Story | -0.001 |
ylan | -0.001 |
Brist | -0.001 |
kok | -0.001 |
Kyr | -0.000 |
Token | were |
Token ID | 547 |
Feature activation | -2.66e-02 |
Pos logit contributions | |
Story | +0.068 |
ylan | +0.067 |
Brist | +0.066 |
kok | +0.064 |
Kyr | +0.061 |
Neg logit contributions | |
Pope | -0.074 |
angel | -0.069 |
Towards | -0.058 |
Deng | -0.058 |
Chu | -0.057 |
Token | continues |
Token ID | 4477 |
Feature activation | -6.08e-02 |
Pos logit contributions | |
Story | +0.427 |
ylan | +0.424 |
Brist | +0.418 |
kok | +0.401 |
Kyr | +0.383 |
Neg logit contributions | |
Pope | -0.534 |
angel | -0.497 |
Towards | -0.428 |
Deng | -0.423 |
Chu | -0.416 |
Token | below |
Token ID | 2174 |
Feature activation | +8.70e-02 |
Pos logit contributions | |
Story | +0.054 |
ylan | +0.054 |
Brist | +0.053 |
kok | +0.052 |
Kyr | +0.050 |
Neg logit contributions | |
Pope | -0.040 |
angel | -0.036 |
Towards | -0.030 |
Deng | -0.029 |
Chu | -0.028 |
Token | advertisement |
Token ID | 15422 |
Feature activation | +2.27e-02 |
Pos logit contributions | |
Pope | +0.068 |
angel | +0.063 |
Towards | +0.053 |
Deng | +0.052 |
Chu | +0.051 |
Neg logit contributions | |
Story | -0.067 |
ylan | -0.067 |
Brist | -0.065 |
kok | -0.063 |
Kyr | -0.060 |
Token |
|
Token ID | 198 |
Feature activation | -1.31e-03 |
Pos logit contributions | |
Pope | +0.018 |
angel | +0.017 |
Towards | +0.014 |
Deng | +0.014 |
Chu | +0.014 |
Neg logit contributions | |
Story | -0.017 |
ylan | -0.017 |
Brist | -0.017 |
kok | -0.016 |
Kyr | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | -3.18e-03 |
Pos logit contributions | |
Story | +0.001 |
ylan | +0.001 |
Brist | +0.001 |
kok | +0.001 |
Kyr | +0.001 |
Neg logit contributions | |
Pope | -0.001 |
angel | -0.001 |
Towards | -0.001 |
Deng | -0.001 |
Chu | -0.001 |
Token | Story |
Token ID | 11605 |
Feature activation | -6.24e-01 |
Pos logit contributions | |
ylan | +0.000 |
Story | +0.000 |
Brist | +0.000 |
kok | +0.000 |
Kyr | +0.000 |
Neg logit contributions | |
Pope | -0.005 |
angel | -0.004 |
Towards | -0.004 |
Deng | -0.004 |
Chu | -0.004 |
Token | continues |
Token ID | 4477 |
Feature activation | -6.01e-02 |
Pos logit contributions | |
Story | +0.425 |
ylan | +0.422 |
Brist | +0.415 |
kok | +0.397 |
Kyr | +0.379 |
Neg logit contributions | |
Pope | -0.541 |
angel | -0.504 |
Towards | -0.434 |
Deng | -0.430 |
Chu | -0.422 |
Token | below |
Token ID | 2174 |
Feature activation | +8.61e-02 |
Pos logit contributions | |
Story | +0.053 |
ylan | +0.052 |
Brist | +0.052 |
kok | +0.050 |
Kyr | +0.048 |
Neg logit contributions | |
Pope | -0.040 |
angel | -0.037 |
Towards | -0.030 |
Deng | -0.030 |
Chu | -0.029 |
Token | advertisement |
Token ID | 15422 |
Feature activation | +2.05e-02 |
Pos logit contributions | |
Pope | +0.065 |
angel | +0.060 |
Towards | +0.051 |
Deng | +0.050 |
Chu | +0.049 |
Neg logit contributions | |
Story | -0.068 |
ylan | -0.068 |
Brist | -0.067 |
kok | -0.064 |
Kyr | -0.062 |
Token |
|
Token ID | 198 |
Feature activation | +3.31e-03 |
Pos logit contributions | |
Pope | +0.016 |
angel | +0.015 |
Towards | +0.013 |
Deng | +0.013 |
Chu | +0.012 |
Neg logit contributions | |
Story | -0.016 |
ylan | -0.015 |
Brist | -0.015 |
kok | -0.015 |
Kyr | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | -5.40e-04 |
Pos logit contributions | |
Pope | +0.003 |
angel | +0.002 |
Towards | +0.002 |
Deng | +0.002 |
Chu | +0.002 |
Neg logit contributions | |
Story | -0.003 |
ylan | -0.003 |
Brist | -0.002 |
kok | -0.002 |
Kyr | -0.002 |
Token | of |
Token ID | 286 |
Feature activation | +6.58e-04 |
Pos logit contributions | |
Pope | +0.055 |
angel | +0.051 |
Towards | +0.044 |
Deng | +0.043 |
Chu | +0.042 |
Neg logit contributions | |
Story | -0.052 |
ylan | -0.052 |
Brist | -0.051 |
kok | -0.049 |
Kyr | -0.047 |
Token | dollars |
Token ID | 5054 |
Feature activation | -6.69e-02 |
Pos logit contributions | |
Pope | +0.001 |
angel | +0.001 |
Towards | +0.000 |
Deng | +0.000 |
Chu | +0.000 |
Neg logit contributions | |
Story | -0.000 |
ylan | -0.000 |
Brist | -0.000 |
kok | -0.000 |
Kyr | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | -6.24e-03 |
Pos logit contributions | |
Story | +0.050 |
ylan | +0.049 |
Brist | +0.048 |
kok | +0.047 |
Kyr | +0.045 |
Neg logit contributions | |
Pope | -0.054 |
angel | -0.050 |
Towards | -0.042 |
Deng | -0.042 |
Chu | -0.041 |
Token |
|
Token ID | 198 |
Feature activation | +1.73e-04 |
Pos logit contributions | |
ylan | +0.005 |
Story | +0.005 |
Brist | +0.005 |
kok | +0.005 |
saddle | +0.004 |
Neg logit contributions | |
Pope | -0.005 |
angel | -0.004 |
Towards | -0.004 |
Deng | -0.004 |
Chu | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -1.90e-04 |
Pos logit contributions | |
Pope | +0.000 |
angel | +0.000 |
Towards | +0.000 |
Deng | +0.000 |
Chu | +0.000 |
Neg logit contributions | |
Story | -0.000 |
ylan | -0.000 |
Brist | -0.000 |
kok | -0.000 |
Kyr | -0.000 |
Token | Story |
Token ID | 11605 |
Feature activation | -6.21e-01 |
Pos logit contributions | |
Story | +0.000 |
ylan | +0.000 |
Brist | +0.000 |
kok | +0.000 |
Kyr | +0.000 |
Neg logit contributions | |
Pope | -0.000 |
angel | -0.000 |
Towards | -0.000 |
Deng | -0.000 |
Chu | -0.000 |
Token | continues |
Token ID | 4477 |
Feature activation | -6.08e-02 |
Pos logit contributions | |
Story | +0.427 |
ylan | +0.424 |
Brist | +0.418 |
kok | +0.401 |
Kyr | +0.383 |
Neg logit contributions | |
Pope | -0.534 |
angel | -0.497 |
Towards | -0.428 |
Deng | -0.423 |
Chu | -0.416 |
Token | below |
Token ID | 2174 |
Feature activation | +8.70e-02 |
Pos logit contributions | |
Story | +0.054 |
ylan | +0.054 |
Brist | +0.053 |
kok | +0.052 |
Kyr | +0.050 |
Neg logit contributions | |
Pope | -0.040 |
angel | -0.036 |
Towards | -0.030 |
Deng | -0.029 |
Chu | -0.028 |
Token | advertisement |
Token ID | 15422 |
Feature activation | +2.27e-02 |
Pos logit contributions | |
Pope | +0.068 |
angel | +0.063 |
Towards | +0.053 |
Deng | +0.052 |
Chu | +0.051 |
Neg logit contributions | |
Story | -0.067 |
ylan | -0.067 |
Brist | -0.065 |
kok | -0.063 |
Kyr | -0.060 |
Token |
|
Token ID | 198 |
Feature activation | -1.31e-03 |
Pos logit contributions | |
Pope | +0.018 |
angel | +0.017 |
Towards | +0.014 |
Deng | +0.014 |
Chu | +0.014 |
Neg logit contributions | |
Story | -0.017 |
ylan | -0.017 |
Brist | -0.017 |
kok | -0.016 |
Kyr | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | -3.18e-03 |
Pos logit contributions | |
Story | +0.001 |
ylan | +0.001 |
Brist | +0.001 |
kok | +0.001 |
Kyr | +0.001 |
Neg logit contributions | |
Pope | -0.001 |
angel | -0.001 |
Towards | -0.001 |
Deng | -0.001 |
Chu | -0.001 |
Token | She |
Token ID | 1375 |
Feature activation | +2.50e-02 |
Pos logit contributions | |
Pope | +0.109 |
angel | +0.101 |
Towards | +0.086 |
Deng | +0.085 |
Chu | +0.084 |
Neg logit contributions | |
Story | -0.097 |
ylan | -0.096 |
Brist | -0.095 |
kok | -0.091 |
Kyr | -0.087 |
Token | pell |
Token ID | 23506 |
Feature activation | +9.70e-02 |
Pos logit contributions | |
Pope | +0.018 |
angel | +0.016 |
Towards | +0.013 |
Deng | +0.013 |
Chu | +0.013 |
Neg logit contributions | |
Story | -0.021 |
ylan | -0.021 |
Brist | -0.020 |
kok | -0.020 |
Kyr | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | -5.97e-03 |
Pos logit contributions | |
Pope | +0.077 |
angel | +0.071 |
Towards | +0.060 |
Deng | +0.060 |
Chu | +0.058 |
Neg logit contributions | |
Story | -0.074 |
ylan | -0.073 |
Brist | -0.072 |
kok | -0.069 |
Kyr | -0.066 |
Token |
|
Token ID | 198 |
Feature activation | +6.93e-03 |
Pos logit contributions | |
Story | +0.005 |
ylan | +0.005 |
Brist | +0.004 |
kok | +0.004 |
saddle | +0.004 |
Neg logit contributions | |
Pope | -0.005 |
angel | -0.004 |
Towards | -0.004 |
Deng | -0.004 |
Chu | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -9.58e-04 |
Pos logit contributions | |
Pope | +0.005 |
angel | +0.005 |
Towards | +0.004 |
Deng | +0.004 |
Chu | +0.004 |
Neg logit contributions | |
Story | -0.005 |
ylan | -0.005 |
Brist | -0.005 |
kok | -0.005 |
Kyr | -0.005 |
Token | Story |
Token ID | 11605 |
Feature activation | -6.21e-01 |
Pos logit contributions | |
Story | +0.001 |
ylan | +0.001 |
Brist | +0.001 |
kok | +0.001 |
Kyr | +0.001 |
Neg logit contributions | |
Pope | -0.001 |
angel | -0.001 |
Towards | -0.001 |
Deng | -0.001 |
Chu | -0.001 |
Token | continues |
Token ID | 4477 |
Feature activation | -5.73e-02 |
Pos logit contributions | |
Story | +0.426 |
ylan | +0.423 |
Brist | +0.417 |
kok | +0.399 |
Kyr | +0.381 |
Neg logit contributions | |
Pope | -0.535 |
angel | -0.499 |
Towards | -0.429 |
Deng | -0.424 |
Chu | -0.417 |
Token | below |
Token ID | 2174 |
Feature activation | +8.98e-02 |
Pos logit contributions | |
Story | +0.051 |
ylan | +0.051 |
Brist | +0.050 |
kok | +0.048 |
Kyr | +0.047 |
Neg logit contributions | |
Pope | -0.038 |
angel | -0.034 |
Towards | -0.028 |
Deng | -0.028 |
Chu | -0.027 |
Token | advertisement |
Token ID | 15422 |
Feature activation | +2.19e-02 |
Pos logit contributions | |
Pope | +0.067 |
angel | +0.062 |
Towards | +0.052 |
Deng | +0.052 |
Chu | +0.050 |
Neg logit contributions | |
Story | -0.071 |
ylan | -0.071 |
Brist | -0.070 |
kok | -0.068 |
Kyr | -0.065 |
Token |
|
Token ID | 198 |
Feature activation | -4.13e-03 |
Pos logit contributions | |
Pope | +0.017 |
angel | +0.016 |
Towards | +0.014 |
Deng | +0.013 |
Chu | +0.013 |
Neg logit contributions | |
Story | -0.017 |
ylan | -0.017 |
Brist | -0.016 |
kok | -0.016 |
Kyr | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | +7.44e-03 |
Pos logit contributions | |
Story | +0.003 |
ylan | +0.003 |
Brist | +0.003 |
kok | +0.003 |
Kyr | +0.003 |
Neg logit contributions | |
Pope | -0.003 |
angel | -0.003 |
Towards | -0.003 |
Deng | -0.003 |
Chu | -0.002 |
Token | PC |
Token ID | 4217 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
Pope | +0.002 |
angel | +0.002 |
Towards | +0.001 |
Deng | +0.001 |
Chu | +0.001 |
Neg logit contributions | |
Story | -0.002 |
ylan | -0.002 |
Brist | -0.002 |
kok | -0.001 |
Kyr | -0.001 |
Token | � |
Token ID | 447 |
Feature activation | +2.87e-03 |
Pos logit contributions | |
Pope | +0.162 |
angel | +0.151 |
Towards | +0.128 |
Deng | +0.126 |
Chu | +0.124 |
Neg logit contributions | |
Story | -0.152 |
ylan | -0.151 |
Brist | -0.149 |
kok | -0.144 |
Kyr | -0.137 |
Token | � |
Token ID | 247 |
Feature activation | +2.38e-03 |
Pos logit contributions | |
Pope | +0.002 |
angel | +0.002 |
Towards | +0.002 |
Deng | +0.002 |
Chu | +0.002 |
Neg logit contributions | |
Story | -0.002 |
ylan | -0.002 |
Brist | -0.002 |
kok | -0.002 |
Kyr | -0.002 |
Token | s |
Token ID | 82 |
Feature activation | -1.59e-03 |
Pos logit contributions | |
Pope | +0.002 |
angel | +0.002 |
Towards | +0.001 |
Deng | +0.001 |
Chu | +0.001 |
Neg logit contributions | |
Story | -0.002 |
ylan | -0.002 |
Brist | -0.002 |
kok | -0.002 |
Kyr | -0.002 |
Token | Back |
Token ID | 5157 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
Story | +0.001 |
ylan | +0.001 |
Brist | +0.001 |
kok | +0.001 |
Kyr | +0.001 |
Neg logit contributions | |
Pope | -0.001 |
angel | -0.001 |
Towards | -0.001 |
Deng | -0.001 |
Chu | -0.001 |
Token | Story |
Token ID | 11605 |
Feature activation | -6.21e-01 |
Pos logit contributions | |
Story | +0.080 |
ylan | +0.080 |
Brist | +0.078 |
kok | +0.075 |
Kyr | +0.072 |
Neg logit contributions | |
Pope | -0.100 |
angel | -0.093 |
Towards | -0.080 |
Deng | -0.079 |
Chu | -0.078 |
Token | : |
Token ID | 25 |
Feature activation | +2.33e-03 |
Pos logit contributions | |
Story | +0.469 |
ylan | +0.461 |
Brist | +0.455 |
kok | +0.437 |
Kyr | +0.420 |
Neg logit contributions | |
Pope | -0.496 |
angel | -0.459 |
Towards | -0.388 |
Deng | -0.385 |
Chu | -0.377 |
Token | ( |
Token ID | 357 |
Feature activation | -7.45e-02 |
Pos logit contributions | |
Pope | +0.002 |
angel | +0.002 |
Towards | +0.002 |
Deng | +0.002 |
Chu | +0.002 |
Neg logit contributions | |
Story | -0.002 |
ylan | -0.002 |
Brist | -0.002 |
kok | -0.002 |
Kyr | -0.001 |
Token | Example |
Token ID | 16281 |
Feature activation | -2.41e-02 |
Pos logit contributions | |
Story | +0.053 |
ylan | +0.053 |
Brist | +0.052 |
kok | +0.050 |
Kyr | +0.047 |
Neg logit contributions | |
Pope | -0.062 |
angel | -0.058 |
Towards | -0.050 |
Deng | -0.049 |
Chu | -0.048 |
Token | : |
Token ID | 25 |
Feature activation | +5.41e-03 |
Pos logit contributions | |
Story | +0.019 |
ylan | +0.018 |
Brist | +0.018 |
kok | +0.018 |
Kyr | +0.017 |
Neg logit contributions | |
Pope | -0.019 |
angel | -0.017 |
Towards | -0.015 |
Deng | -0.014 |
Chu | -0.014 |
Token | Th |
Token ID | 536 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
Pope | +0.004 |
angel | +0.004 |
Towards | +0.003 |
Deng | +0.003 |
Chu | +0.003 |
Neg logit contributions | |
Story | -0.004 |
ylan | -0.004 |
Brist | -0.004 |
kok | -0.004 |
Kyr | -0.004 |
Token | ' |
Token ID | 705 |
Feature activation | +4.71e-03 |
Pos logit contributions | |
Pope | +0.105 |
angel | +0.097 |
Towards | +0.082 |
Deng | +0.081 |
Chu | +0.079 |
Neg logit contributions | |
Story | -0.102 |
ylan | -0.101 |
Brist | -0.099 |
kok | -0.096 |
Kyr | -0.092 |
Token | keeper |
Token ID | 13884 |
Feature activation | +8.33e-02 |
Pos logit contributions | |
Pope | +0.003 |
angel | +0.003 |
Towards | +0.003 |
Deng | +0.003 |
Chu | +0.003 |
Neg logit contributions | |
Story | -0.004 |
ylan | -0.004 |
Brist | -0.004 |
kok | -0.004 |
Kyr | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +2.73e-04 |
Pos logit contributions | |
Pope | +0.067 |
angel | +0.062 |
Towards | +0.053 |
Deng | +0.052 |
Chu | +0.051 |
Neg logit contributions | |
Story | -0.062 |
ylan | -0.061 |
Brist | -0.060 |
kok | -0.058 |
Kyr | -0.056 |
Token |
|
Token ID | 198 |
Feature activation | +6.13e-03 |
Pos logit contributions | |
Pope | +0.000 |
angel | +0.000 |
Towards | +0.000 |
Deng | +0.000 |
Chu | +0.000 |
Neg logit contributions | |
Story | -0.000 |
ylan | -0.000 |
Brist | -0.000 |
kok | -0.000 |
Kyr | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | +5.22e-03 |
Pos logit contributions | |
Pope | +0.005 |
angel | +0.004 |
Towards | +0.004 |
Deng | +0.004 |
Chu | +0.004 |
Neg logit contributions | |
Story | -0.005 |
ylan | -0.005 |
Brist | -0.005 |
kok | -0.004 |
Kyr | -0.004 |
Token | Story |
Token ID | 11605 |
Feature activation | -6.20e-01 |
Pos logit contributions | |
Pope | +0.004 |
angel | +0.004 |
Towards | +0.004 |
Deng | +0.004 |
Chu | +0.003 |
Neg logit contributions | |
Story | -0.004 |
ylan | -0.004 |
Brist | -0.004 |
kok | -0.003 |
Kyr | -0.003 |
Token | continues |
Token ID | 4477 |
Feature activation | -5.08e-02 |
Pos logit contributions | |
Story | +0.420 |
ylan | +0.415 |
Brist | +0.407 |
kok | +0.391 |
Kyr | +0.372 |
Neg logit contributions | |
Pope | -0.542 |
angel | -0.505 |
Towards | -0.436 |
Deng | -0.432 |
Chu | -0.424 |
Token | below |
Token ID | 2174 |
Feature activation | +9.20e-02 |
Pos logit contributions | |
Story | +0.045 |
ylan | +0.044 |
Brist | +0.044 |
kok | +0.043 |
Kyr | +0.041 |
Neg logit contributions | |
Pope | -0.034 |
angel | -0.031 |
Towards | -0.025 |
Deng | -0.025 |
Chu | -0.024 |
Token | advertisement |
Token ID | 15422 |
Feature activation | +2.59e-02 |
Pos logit contributions | |
Pope | +0.069 |
angel | +0.063 |
Towards | +0.053 |
Deng | +0.053 |
Chu | +0.052 |
Neg logit contributions | |
Story | -0.073 |
ylan | -0.073 |
Brist | -0.072 |
kok | -0.069 |
Kyr | -0.066 |
Token |
|
Token ID | 198 |
Feature activation | +4.97e-03 |
Pos logit contributions | |
Pope | +0.020 |
angel | +0.019 |
Towards | +0.016 |
Deng | +0.016 |
Chu | +0.015 |
Neg logit contributions | |
Story | -0.020 |
ylan | -0.020 |
Brist | -0.019 |
kok | -0.019 |
Kyr | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | +6.22e-03 |
Pos logit contributions | |
Pope | +0.004 |
angel | +0.004 |
Towards | +0.003 |
Deng | +0.003 |
Chu | +0.003 |
Neg logit contributions | |
Story | -0.004 |
ylan | -0.004 |
Brist | -0.004 |
kok | -0.004 |
Kyr | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | -9.40e-04 |
Pos logit contributions | |
Pope | +0.005 |
angel | +0.004 |
Towards | +0.004 |
Deng | +0.004 |
Chu | +0.004 |
Neg logit contributions | |
Story | -0.004 |
ylan | -0.004 |
Brist | -0.004 |
kok | -0.004 |
Kyr | -0.004 |
Token | club |
Token ID | 3430 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
Story | +0.001 |
ylan | +0.001 |
Brist | +0.001 |
kok | +0.001 |
Kyr | +0.001 |
Neg logit contributions | |
Pope | -0.001 |
angel | -0.001 |
Towards | -0.001 |
Deng | -0.001 |
Chu | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -7.22e-03 |
Pos logit contributions | |
Story | +0.087 |
ylan | +0.086 |
Brist | +0.084 |
kok | +0.082 |
earch | +0.078 |
Neg logit contributions | |
Pope | -0.089 |
angel | -0.082 |
Towards | -0.070 |
Deng | -0.069 |
Chu | -0.068 |
Token |
|
Token ID | 198 |
Feature activation | +3.66e-03 |
Pos logit contributions | |
Story | +0.006 |
ylan | +0.006 |
Brist | +0.005 |
kok | +0.005 |
saddle | +0.005 |
Neg logit contributions | |
Pope | -0.006 |
angel | -0.005 |
Towards | -0.004 |
Deng | -0.004 |
Chu | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -7.64e-04 |
Pos logit contributions | |
Pope | +0.003 |
angel | +0.003 |
Towards | +0.002 |
Deng | +0.002 |
Chu | +0.002 |
Neg logit contributions | |
Story | -0.003 |
ylan | -0.003 |
Brist | -0.003 |
kok | -0.003 |
Kyr | -0.003 |
Token | Story |
Token ID | 11605 |
Feature activation | -6.19e-01 |
Pos logit contributions | |
ylan | +0.001 |
Story | +0.001 |
Brist | +0.000 |
kok | +0.000 |
saddle | +0.000 |
Neg logit contributions | |
Pope | -0.001 |
angel | -0.001 |
Towards | -0.001 |
Deng | -0.001 |
Chu | -0.001 |
Token | continues |
Token ID | 4477 |
Feature activation | -5.43e-02 |
Pos logit contributions | |
Story | +0.419 |
ylan | +0.415 |
Brist | +0.407 |
kok | +0.391 |
Kyr | +0.372 |
Neg logit contributions | |
Pope | -0.540 |
angel | -0.504 |
Towards | -0.435 |
Deng | -0.430 |
Chu | -0.423 |
Token | below |
Token ID | 2174 |
Feature activation | +8.84e-02 |
Pos logit contributions | |
Story | +0.048 |
ylan | +0.047 |
Brist | +0.047 |
kok | +0.045 |
Kyr | +0.044 |
Neg logit contributions | |
Pope | -0.036 |
angel | -0.033 |
Towards | -0.027 |
Deng | -0.027 |
Chu | -0.026 |
Token | advertisement |
Token ID | 15422 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
Pope | +0.066 |
angel | +0.061 |
Towards | +0.051 |
Deng | +0.051 |
Chu | +0.050 |
Neg logit contributions | |
Story | -0.070 |
ylan | -0.070 |
Brist | -0.069 |
kok | -0.067 |
Kyr | -0.064 |
Token |
|
Token ID | 198 |
Feature activation | +7.75e-03 |
Pos logit contributions | |
Pope | +0.013 |
angel | +0.012 |
Towards | +0.010 |
Deng | +0.010 |
Chu | +0.010 |
Neg logit contributions | |
Story | -0.013 |
ylan | -0.013 |
Brist | -0.013 |
kok | -0.012 |
Kyr | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | +2.21e-04 |
Pos logit contributions | |
Pope | +0.006 |
angel | +0.006 |
Towards | +0.005 |
Deng | +0.005 |
Chu | +0.005 |
Neg logit contributions | |
Story | -0.006 |
ylan | -0.006 |
Brist | -0.006 |
kok | -0.006 |
Kyr | -0.005 |
Token | continues |
Token ID | 4477 |
Feature activation | -5.08e-02 |
Pos logit contributions | |
Story | +0.420 |
ylan | +0.415 |
Brist | +0.407 |
kok | +0.391 |
Kyr | +0.372 |
Neg logit contributions | |
Pope | -0.542 |
angel | -0.505 |
Towards | -0.436 |
Deng | -0.432 |
Chu | -0.424 |
Token | below |
Token ID | 2174 |
Feature activation | +9.20e-02 |
Pos logit contributions | |
Story | +0.045 |
ylan | +0.044 |
Brist | +0.044 |
kok | +0.043 |
Kyr | +0.041 |
Neg logit contributions | |
Pope | -0.034 |
angel | -0.031 |
Towards | -0.025 |
Deng | -0.025 |
Chu | -0.024 |
Token | advertisement |
Token ID | 15422 |
Feature activation | +2.59e-02 |
Pos logit contributions | |
Pope | +0.069 |
angel | +0.063 |
Towards | +0.053 |
Deng | +0.053 |
Chu | +0.052 |
Neg logit contributions | |
Story | -0.073 |
ylan | -0.073 |
Brist | -0.072 |
kok | -0.069 |
Kyr | -0.066 |
Token |
|
Token ID | 198 |
Feature activation | +4.97e-03 |
Pos logit contributions | |
Pope | +0.020 |
angel | +0.019 |
Towards | +0.016 |
Deng | +0.016 |
Chu | +0.015 |
Neg logit contributions | |
Story | -0.020 |
ylan | -0.020 |
Brist | -0.019 |
kok | -0.019 |
Kyr | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | +6.22e-03 |
Pos logit contributions | |
Pope | +0.004 |
angel | +0.004 |
Towards | +0.003 |
Deng | +0.003 |
Chu | +0.003 |
Neg logit contributions | |
Story | -0.004 |
ylan | -0.004 |
Brist | -0.004 |
kok | -0.004 |
Kyr | -0.003 |
Token | Story |
Token ID | 11605 |
Feature activation | -6.18e-01 |
Pos logit contributions | |
Pope | +0.009 |
angel | +0.009 |
Towards | +0.008 |
Deng | +0.008 |
Chu | +0.008 |
Neg logit contributions | |
Story | -0.000 |
ylan | -0.000 |
Brist | -0.000 |
kok | +0.000 |
Kyr | +0.000 |
Token | continues |
Token ID | 4477 |
Feature activation | -5.45e-02 |
Pos logit contributions | |
Story | +0.419 |
ylan | +0.415 |
Brist | +0.407 |
kok | +0.391 |
Kyr | +0.372 |
Neg logit contributions | |
Pope | -0.539 |
angel | -0.503 |
Towards | -0.434 |
Deng | -0.429 |
Chu | -0.421 |
Token | below |
Token ID | 2174 |
Feature activation | +9.73e-02 |
Pos logit contributions | |
Story | +0.048 |
ylan | +0.047 |
Brist | +0.047 |
kok | +0.045 |
Kyr | +0.044 |
Neg logit contributions | |
Pope | -0.037 |
angel | -0.033 |
Towards | -0.027 |
Deng | -0.027 |
Chu | -0.026 |
Token | advertisement |
Token ID | 15422 |
Feature activation | +2.14e-02 |
Pos logit contributions | |
Pope | +0.073 |
angel | +0.068 |
Towards | +0.057 |
Deng | +0.057 |
Chu | +0.055 |
Neg logit contributions | |
Story | -0.077 |
ylan | -0.076 |
Brist | -0.075 |
kok | -0.073 |
Kyr | -0.070 |
Token |
|
Token ID | 198 |
Feature activation | +9.12e-03 |
Pos logit contributions | |
Pope | +0.017 |
angel | +0.016 |
Towards | +0.013 |
Deng | +0.013 |
Chu | +0.013 |
Neg logit contributions | |
Story | -0.016 |
ylan | -0.016 |
Brist | -0.016 |
kok | -0.015 |
Kyr | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | +9.31e-03 |
Pos logit contributions | |
Pope | +0.007 |
angel | +0.007 |
Towards | +0.006 |
Deng | +0.006 |
Chu | +0.005 |
Neg logit contributions | |
Story | -0.007 |
ylan | -0.007 |
Brist | -0.007 |
kok | -0.007 |
Kyr | -0.006 |
Token | to |
Token ID | 284 |
Feature activation | -3.53e-03 |
Pos logit contributions | |
Pope | +0.020 |
angel | +0.018 |
Towards | +0.015 |
Deng | +0.015 |
Chu | +0.015 |
Neg logit contributions | |
Story | -0.018 |
ylan | -0.018 |
Brist | -0.018 |
kok | -0.017 |
Kyr | -0.016 |
Token | vote |
Token ID | 3015 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
Story | +0.003 |
ylan | +0.003 |
Brist | +0.003 |
kok | +0.002 |
Kyr | +0.002 |
Neg logit contributions | |
Pope | -0.003 |
angel | -0.003 |
Towards | -0.002 |
Deng | -0.002 |
Chu | -0.002 |
Token | accordingly |
Token ID | 16062 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
Pope | +0.084 |
angel | +0.078 |
Towards | +0.066 |
Deng | +0.065 |
atum | +0.064 |
Neg logit contributions | |
Story | -0.079 |
ylan | -0.078 |
Brist | -0.077 |
kok | -0.074 |
Kyr | -0.071 |
Token | . |
Token ID | 13 |
Feature activation | -1.49e-03 |
Pos logit contributions | |
Pope | +0.112 |
angel | +0.104 |
Towards | +0.088 |
Deng | +0.087 |
Chu | +0.085 |
Neg logit contributions | |
Story | -0.106 |
ylan | -0.105 |
Brist | -0.104 |
kok | -0.100 |
Kyr | -0.096 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
Story | +0.001 |
ylan | +0.001 |
Brist | +0.001 |
kok | +0.001 |
Kyr | +0.001 |
Neg logit contributions | |
Pope | -0.001 |
angel | -0.001 |
Towards | -0.001 |
Deng | -0.001 |
Chu | -0.001 |
Token | Story |
Token ID | 11605 |
Feature activation | -6.17e-01 |
Pos logit contributions | |
Story | +0.150 |
ylan | +0.148 |
Brist | +0.145 |
kok | +0.140 |
Kyr | +0.134 |
Neg logit contributions | |
Pope | -0.161 |
angel | -0.149 |
Towards | -0.128 |
Deng | -0.126 |
Chu | -0.124 |
Token | highlights |
Token ID | 11330 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
Story | +0.509 |
ylan | +0.499 |
Brist | +0.493 |
kok | +0.474 |
Kyr | +0.454 |
Neg logit contributions | |
Pope | -0.452 |
angel | -0.418 |
Towards | -0.346 |
Deng | -0.342 |
atum | -0.335 |
Token | Police |
Token ID | 4287 |
Feature activation | -5.59e-02 |
Pos logit contributions | |
Pope | +0.084 |
angel | +0.078 |
Towards | +0.066 |
Deng | +0.065 |
Chu | +0.064 |
Neg logit contributions | |
Story | -0.080 |
ylan | -0.079 |
Brist | -0.078 |
kok | -0.075 |
Kyr | -0.072 |
Token | chief |
Token ID | 4039 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
Story | +0.040 |
ylan | +0.040 |
Brist | +0.039 |
kok | +0.038 |
Kyr | +0.036 |
Neg logit contributions | |
Pope | -0.046 |
angel | -0.043 |
Towards | -0.037 |
Deng | -0.036 |
Chu | -0.036 |
Token | vows |
Token ID | 36605 |
Feature activation | +8.90e-02 |
Pos logit contributions | |
Pope | +0.111 |
angel | +0.103 |
Towards | +0.087 |
Deng | +0.085 |
Chu | +0.084 |
Neg logit contributions | |
Story | -0.110 |
ylan | -0.109 |
Brist | -0.107 |
kok | -0.103 |
Kyr | -0.099 |
Token | wanted |
Token ID | 2227 |
Feature activation | +7.57e-02 |
Pos logit contributions | |
Pope | +0.072 |
angel | +0.067 |
Towards | +0.057 |
Deng | +0.056 |
Chu | +0.055 |
Neg logit contributions | |
Story | -0.066 |
ylan | -0.065 |
Brist | -0.064 |
kok | -0.061 |
Kyr | -0.059 |
Token | big |
Token ID | 1263 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
Pope | +0.003 |
angel | +0.003 |
Towards | +0.003 |
Deng | +0.003 |
Chu | +0.002 |
Neg logit contributions | |
Story | -0.003 |
ylan | -0.003 |
Brist | -0.003 |
kok | -0.003 |
Kyr | -0.003 |
Token | stage |
Token ID | 3800 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
Pope | +0.201 |
angel | +0.183 |
Towards | +0.149 |
Deng | +0.147 |
Chu | +0.144 |
Neg logit contributions | |
Story | -0.270 |
ylan | -0.269 |
Brist | -0.266 |
kok | -0.258 |
Kyr | -0.248 |
Token | . |
Token ID | 13 |
Feature activation | -1.56e-03 |
Pos logit contributions | |
Pope | +0.085 |
angel | +0.079 |
Towards | +0.067 |
Deng | +0.066 |
Chu | +0.065 |
Neg logit contributions | |
Story | -0.081 |
ylan | -0.081 |
Brist | -0.079 |
kok | -0.076 |
Kyr | -0.073 |
Token |
|
Token ID | 198 |
Feature activation | +4.66e-03 |
Pos logit contributions | |
Story | +0.001 |
ylan | +0.001 |
Brist | +0.001 |
kok | +0.001 |
Kyr | +0.001 |
Neg logit contributions | |
Pope | -0.001 |
angel | -0.001 |
Towards | -0.001 |
Deng | -0.001 |
Chu | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +1.13e-03 |
Pos logit contributions | |
Pope | +0.004 |
angel | +0.003 |
Towards | +0.003 |
Deng | +0.003 |
Chu | +0.003 |
Neg logit contributions | |
Story | -0.004 |
ylan | -0.003 |
Brist | -0.003 |
kok | -0.003 |
Kyr | -0.003 |
Token | Story |
Token ID | 11605 |
Feature activation | -6.17e-01 |
Pos logit contributions | |
Pope | +0.001 |
angel | +0.001 |
Towards | +0.001 |
Deng | +0.001 |
Chu | +0.001 |
Neg logit contributions | |
Story | -0.001 |
ylan | -0.001 |
Brist | -0.001 |
kok | -0.001 |
Kyr | -0.001 |
Token | continues |
Token ID | 4477 |
Feature activation | -5.59e-02 |
Pos logit contributions | |
Story | +0.408 |
ylan | +0.400 |
Brist | +0.391 |
kok | +0.373 |
saddle | +0.355 |
Neg logit contributions | |
Pope | -0.555 |
angel | -0.518 |
Towards | -0.445 |
Deng | -0.443 |
Chu | -0.436 |
Token | below |
Token ID | 2174 |
Feature activation | +9.38e-02 |
Pos logit contributions | |
Story | +0.049 |
ylan | +0.049 |
Brist | +0.048 |
kok | +0.047 |
Kyr | +0.045 |
Neg logit contributions | |
Pope | -0.037 |
angel | -0.034 |
Towards | -0.028 |
Deng | -0.027 |
Chu | -0.027 |
Token | advertisement |
Token ID | 15422 |
Feature activation | +2.53e-02 |
Pos logit contributions | |
Pope | +0.073 |
angel | +0.067 |
Towards | +0.057 |
Deng | +0.056 |
Chu | +0.055 |
Neg logit contributions | |
Story | -0.072 |
ylan | -0.072 |
Brist | -0.071 |
kok | -0.068 |
Kyr | -0.065 |
Token |
|
Token ID | 198 |
Feature activation | +4.08e-03 |
Pos logit contributions | |
Pope | +0.020 |
angel | +0.018 |
Towards | +0.016 |
Deng | +0.015 |
Chu | +0.015 |
Neg logit contributions | |
Story | -0.019 |
ylan | -0.019 |
Brist | -0.019 |
kok | -0.018 |
Kyr | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | +3.49e-03 |
Pos logit contributions | |
Pope | +0.003 |
angel | +0.003 |
Towards | +0.003 |
Deng | +0.002 |
Chu | +0.002 |
Neg logit contributions | |
Story | -0.003 |
ylan | -0.003 |
Brist | -0.003 |
kok | -0.003 |
Kyr | -0.003 |
Token | disclosure |
Token ID | 13019 |
Feature activation | -6.56e-02 |
Pos logit contributions | |
Pope | +0.016 |
angel | +0.015 |
Towards | +0.013 |
Deng | +0.013 |
Chu | +0.012 |
Neg logit contributions | |
Story | -0.014 |
ylan | -0.014 |
Brist | -0.013 |
kok | -0.013 |
Kyr | -0.012 |
Token | statement |
Token ID | 2643 |
Feature activation | -6.27e-02 |
Pos logit contributions | |
Story | +0.049 |
ylan | +0.049 |
Brist | +0.048 |
kok | +0.046 |
Kyr | +0.044 |
Neg logit contributions | |
Pope | -0.053 |
angel | -0.049 |
Towards | -0.041 |
Deng | -0.041 |
Chu | -0.040 |
Token | . |
Token ID | 13 |
Feature activation | -4.53e-03 |
Pos logit contributions | |
Story | +0.047 |
ylan | +0.047 |
Brist | +0.046 |
kok | +0.045 |
Kyr | +0.043 |
Neg logit contributions | |
Pope | -0.050 |
angel | -0.046 |
Towards | -0.039 |
Deng | -0.039 |
Chu | -0.038 |
Token |
|
Token ID | 198 |
Feature activation | -3.43e-04 |
Pos logit contributions | |
Story | +0.003 |
ylan | +0.003 |
Brist | +0.003 |
kok | +0.003 |
saddle | +0.003 |
Neg logit contributions | |
Pope | -0.004 |
angel | -0.003 |
Towards | -0.003 |
Deng | -0.003 |
Chu | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +1.95e-03 |
Pos logit contributions | |
Story | +0.000 |
ylan | +0.000 |
Brist | +0.000 |
kok | +0.000 |
Kyr | +0.000 |
Neg logit contributions | |
Pope | -0.000 |
angel | -0.000 |
Towards | -0.000 |
Deng | -0.000 |
Chu | -0.000 |
Token | Story |
Token ID | 11605 |
Feature activation | -6.16e-01 |
Pos logit contributions | |
Pope | +0.002 |
angel | +0.002 |
Towards | +0.002 |
Deng | +0.002 |
Chu | +0.002 |
Neg logit contributions | |
Story | -0.001 |
ylan | -0.001 |
Brist | -0.001 |
kok | -0.001 |
Kyr | -0.001 |
Token | continues |
Token ID | 4477 |
Feature activation | -5.52e-02 |
Pos logit contributions | |
Story | +0.419 |
ylan | +0.416 |
Brist | +0.409 |
kok | +0.392 |
Kyr | +0.373 |
Neg logit contributions | |
Pope | -0.534 |
angel | -0.498 |
Towards | -0.429 |
Deng | -0.425 |
Chu | -0.417 |
Token | below |
Token ID | 2174 |
Feature activation | +9.17e-02 |
Pos logit contributions | |
Story | +0.049 |
ylan | +0.048 |
Brist | +0.048 |
kok | +0.046 |
Kyr | +0.045 |
Neg logit contributions | |
Pope | -0.037 |
angel | -0.033 |
Towards | -0.027 |
Deng | -0.027 |
Chu | -0.026 |
Token | advertisement |
Token ID | 15422 |
Feature activation | +2.68e-02 |
Pos logit contributions | |
Pope | +0.068 |
angel | +0.063 |
Towards | +0.053 |
Deng | +0.053 |
Chu | +0.051 |
Neg logit contributions | |
ylan | -0.073 |
Story | -0.073 |
Brist | -0.072 |
kok | -0.069 |
Kyr | -0.066 |
Token |
|
Token ID | 198 |
Feature activation | +1.02e-03 |
Pos logit contributions | |
Pope | +0.021 |
angel | +0.020 |
Towards | +0.017 |
Deng | +0.016 |
Chu | +0.016 |
Neg logit contributions | |
Story | -0.021 |
ylan | -0.020 |
Brist | -0.020 |
kok | -0.019 |
Kyr | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | +1.32e-03 |
Pos logit contributions | |
Pope | +0.001 |
angel | +0.001 |
Towards | +0.001 |
Deng | +0.001 |
Chu | +0.001 |
Neg logit contributions | |
Story | -0.001 |
ylan | -0.001 |
Brist | -0.001 |
kok | -0.001 |
Kyr | -0.001 |
Token | - |
Token ID | 12 |
Feature activation | -1.65e-02 |
Pos logit contributions | |
Pope | +0.111 |
angel | +0.103 |
Towards | +0.087 |
Deng | +0.087 |
Chu | +0.085 |
Neg logit contributions | |
Story | -0.104 |
ylan | -0.102 |
Brist | -0.101 |
kok | -0.097 |
Kyr | -0.093 |
Token | t |
Token ID | 83 |
Feature activation | +8.24e-03 |
Pos logit contributions | |
Story | +0.013 |
ylan | +0.012 |
Brist | +0.012 |
kok | +0.012 |
Kyr | +0.011 |
Neg logit contributions | |
Pope | -0.013 |
angel | -0.012 |
Towards | -0.010 |
Deng | -0.010 |
Chu | -0.010 |
Token | weet |
Token ID | 7277 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
Pope | +0.005 |
angel | +0.005 |
Towards | +0.004 |
Deng | +0.004 |
Chu | +0.004 |
Neg logit contributions | |
Story | -0.007 |
ylan | -0.007 |
Brist | -0.007 |
kok | -0.007 |
Kyr | -0.007 |
Token | / |
Token ID | 14 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
Pope | +0.120 |
angel | +0.111 |
Towards | +0.094 |
Deng | +0.093 |
Chu | +0.092 |
Neg logit contributions | |
Story | -0.112 |
ylan | -0.110 |
Brist | -0.108 |
kok | -0.105 |
Kyr | -0.100 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
Pope | +0.106 |
angel | +0.099 |
Towards | +0.085 |
Deng | +0.084 |
Chu | +0.083 |
Neg logit contributions | |
Story | -0.082 |
ylan | -0.081 |
Brist | -0.080 |
kok | -0.076 |
Kyr | -0.073 |
Token | Story |
Token ID | 11605 |
Feature activation | -6.16e-01 |
Pos logit contributions | |
Story | +0.154 |
ylan | +0.151 |
Brist | +0.148 |
kok | +0.144 |
Kyr | +0.137 |
Neg logit contributions | |
Pope | -0.164 |
angel | -0.153 |
Towards | -0.130 |
Deng | -0.129 |
Chu | -0.126 |
Token | highlights |
Token ID | 11330 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
Story | +0.509 |
ylan | +0.500 |
Brist | +0.493 |
kok | +0.475 |
Kyr | +0.455 |
Neg logit contributions | |
Pope | -0.450 |
angel | -0.415 |
Towards | -0.344 |
Deng | -0.340 |
Chu | -0.333 |
Token | Secretary |
Token ID | 4986 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
Pope | +0.082 |
angel | +0.076 |
Towards | +0.064 |
Deng | +0.063 |
Chu | +0.062 |
Neg logit contributions | |
Story | -0.078 |
ylan | -0.077 |
Brist | -0.076 |
kok | -0.073 |
Kyr | -0.070 |
Token | of |
Token ID | 286 |
Feature activation | -5.07e-03 |
Pos logit contributions | |
Pope | +0.132 |
angel | +0.122 |
Towards | +0.103 |
Deng | +0.102 |
Chu | +0.100 |
Neg logit contributions | |
Story | -0.129 |
ylan | -0.128 |
Brist | -0.126 |
kok | -0.122 |
saddle | -0.116 |
Token | Defense |
Token ID | 5947 |
Feature activation | -3.91e-02 |
Pos logit contributions | |
Story | +0.004 |
ylan | +0.004 |
Brist | +0.004 |
kok | +0.004 |
Kyr | +0.004 |
Neg logit contributions | |
Pope | -0.004 |
angel | -0.003 |
Towards | -0.003 |
Deng | -0.003 |
Chu | -0.003 |
Token | Chuck |
Token ID | 14663 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
Story | +0.026 |
ylan | +0.026 |
Brist | +0.025 |
kok | +0.024 |
Kyr | +0.023 |
Neg logit contributions | |
Pope | -0.034 |
angel | -0.032 |
Towards | -0.028 |
Deng | -0.028 |
Chu | -0.027 |
Token | On |
Token ID | 1550 |
Feature activation | +4.06e-02 |
Pos logit contributions | |
Story | +0.050 |
ylan | +0.050 |
Brist | +0.049 |
kok | +0.048 |
Kyr | +0.046 |
Neg logit contributions | |
Pope | -0.046 |
angel | -0.043 |
Towards | -0.036 |
Deng | -0.035 |
Chu | -0.034 |
Token | stad |
Token ID | 24107 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
Pope | +0.016 |
angel | +0.014 |
Towards | +0.009 |
Deng | +0.009 |
Chu | +0.009 |
Neg logit contributions | |
Story | -0.046 |
ylan | -0.046 |
Brist | -0.046 |
kok | -0.045 |
Kyr | -0.043 |
Token | . |
Token ID | 13 |
Feature activation | -3.37e-03 |
Pos logit contributions | |
Pope | +0.271 |
angel | +0.251 |
Towards | +0.212 |
Deng | +0.210 |
Chu | +0.206 |
Neg logit contributions | |
Story | -0.264 |
ylan | -0.262 |
Brist | -0.257 |
kok | -0.249 |
Kyr | -0.237 |
Token |
|
Token ID | 198 |
Feature activation | +1.10e-03 |
Pos logit contributions | |
Story | +0.003 |
ylan | +0.003 |
Brist | +0.003 |
kok | +0.003 |
Kyr | +0.003 |
Neg logit contributions | |
Pope | -0.002 |
angel | -0.002 |
Towards | -0.002 |
Deng | -0.002 |
Chu | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +3.63e-03 |
Pos logit contributions | |
Pope | +0.001 |
angel | +0.001 |
Towards | +0.001 |
Deng | +0.001 |
Chu | +0.001 |
Neg logit contributions | |
Story | -0.001 |
ylan | -0.001 |
Brist | -0.001 |
kok | -0.001 |
Kyr | -0.001 |
Token | Story |
Token ID | 11605 |
Feature activation | -6.14e-01 |
Pos logit contributions | |
Pope | +0.003 |
angel | +0.003 |
Towards | +0.003 |
Deng | +0.003 |
Chu | +0.002 |
Neg logit contributions | |
ylan | -0.002 |
Story | -0.002 |
Brist | -0.002 |
kok | -0.002 |
saddle | -0.002 |
Token | continues |
Token ID | 4477 |
Feature activation | -5.64e-02 |
Pos logit contributions | |
Story | +0.415 |
ylan | +0.410 |
Brist | +0.402 |
kok | +0.386 |
Kyr | +0.367 |
Neg logit contributions | |
Pope | -0.538 |
angel | -0.501 |
Towards | -0.433 |
Deng | -0.428 |
Chu | -0.421 |
Token | below |
Token ID | 2174 |
Feature activation | +9.09e-02 |
Pos logit contributions | |
Story | +0.049 |
ylan | +0.049 |
Brist | +0.048 |
kok | +0.047 |
Kyr | +0.045 |
Neg logit contributions | |
Pope | -0.038 |
angel | -0.035 |
Towards | -0.028 |
Deng | -0.028 |
Chu | -0.027 |
Token | advertisement |
Token ID | 15422 |
Feature activation | +2.17e-02 |
Pos logit contributions | |
Pope | +0.068 |
angel | +0.063 |
Towards | +0.053 |
Deng | +0.052 |
Chu | +0.051 |
Neg logit contributions | |
Story | -0.072 |
ylan | -0.072 |
Brist | -0.071 |
kok | -0.069 |
Kyr | -0.066 |
Token |
|
Token ID | 198 |
Feature activation | -1.59e-03 |
Pos logit contributions | |
Pope | +0.017 |
angel | +0.016 |
Towards | +0.013 |
Deng | +0.013 |
Chu | +0.013 |
Neg logit contributions | |
Story | -0.017 |
ylan | -0.016 |
Brist | -0.016 |
kok | -0.016 |
Kyr | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | +2.49e-03 |
Pos logit contributions | |
Story | +0.001 |
ylan | +0.001 |
Brist | +0.001 |
kok | +0.001 |
Kyr | +0.001 |
Neg logit contributions | |
Pope | -0.001 |
angel | -0.001 |
Towards | -0.001 |
Deng | -0.001 |
Chu | -0.001 |
Token | season |
Token ID | 1622 |
Feature activation | +7.75e-02 |
Pos logit contributions | |
Pope | +0.102 |
angel | +0.095 |
Towards | +0.080 |
Deng | +0.079 |
Chu | +0.077 |
Neg logit contributions | |
Story | -0.107 |
ylan | -0.106 |
Brist | -0.104 |
kok | -0.101 |
Kyr | -0.097 |
Token | one |
Token ID | 530 |
Feature activation | -1.62e-03 |
Pos logit contributions | |
Pope | +0.061 |
angel | +0.057 |
Towards | +0.048 |
Deng | +0.048 |
Chu | +0.047 |
Neg logit contributions | |
Story | -0.058 |
ylan | -0.058 |
Brist | -0.057 |
kok | -0.055 |
earch | -0.053 |
Token | ! |
Token ID | 0 |
Feature activation | +4.95e-02 |
Pos logit contributions | |
Story | +0.001 |
ylan | +0.001 |
Brist | +0.001 |
kok | +0.001 |
Kyr | +0.001 |
Neg logit contributions | |
Pope | -0.001 |
angel | -0.001 |
Towards | -0.001 |
Deng | -0.001 |
Chu | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +2.37e-03 |
Pos logit contributions | |
Pope | +0.040 |
angel | +0.037 |
Towards | +0.031 |
Deng | +0.031 |
atum | +0.030 |
Neg logit contributions | |
Story | -0.037 |
ylan | -0.037 |
Brist | -0.036 |
kok | -0.035 |
Kyr | -0.033 |
Token |
|
Token ID | 198 |
Feature activation | +8.93e-03 |
Pos logit contributions | |
Pope | +0.002 |
angel | +0.002 |
Towards | +0.001 |
Deng | +0.001 |
Chu | +0.001 |
Neg logit contributions | |
Story | -0.002 |
ylan | -0.002 |
Brist | -0.002 |
kok | -0.002 |
Kyr | -0.002 |
Token | Story |
Token ID | 11605 |
Feature activation | -6.11e-01 |
Pos logit contributions | |
Pope | +0.007 |
angel | +0.007 |
Towards | +0.006 |
Deng | +0.006 |
Chu | +0.006 |
Neg logit contributions | |
Story | -0.007 |
ylan | -0.007 |
Brist | -0.006 |
kok | -0.006 |
Kyr | -0.006 |
Token | Editor |
Token ID | 12058 |
Feature activation | -2.11e-02 |
Pos logit contributions | |
Story | +0.461 |
ylan | +0.452 |
Brist | +0.447 |
kok | +0.428 |
Kyr | +0.410 |
Neg logit contributions | |
Pope | -0.490 |
angel | -0.452 |
Towards | -0.383 |
Deng | -0.379 |
atum | -0.372 |
Token | and |
Token ID | 290 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
Story | +0.016 |
ylan | +0.016 |
Brist | +0.015 |
kok | +0.015 |
Kyr | +0.014 |
Neg logit contributions | |
Pope | -0.017 |
angel | -0.016 |
Towards | -0.013 |
Deng | -0.013 |
Chu | -0.013 |
Token | Producer |
Token ID | 30436 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
Pope | +0.013 |
angel | +0.012 |
Towards | +0.011 |
Deng | +0.010 |
Chu | +0.010 |
Neg logit contributions | |
Story | -0.006 |
ylan | -0.006 |
Brist | -0.006 |
kok | -0.006 |
Kyr | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | +4.20e-03 |
Pos logit contributions | |
Story | +0.152 |
ylan | +0.150 |
Brist | +0.148 |
kok | +0.142 |
Kyr | +0.136 |
Neg logit contributions | |
Pope | -0.170 |
angel | -0.157 |
Towards | -0.134 |
Deng | -0.132 |
Chu | -0.130 |
Token |
|
Token ID | 198 |
Feature activation | +1.79e-03 |
Pos logit contributions | |
Pope | +0.003 |
angel | +0.003 |
Towards | +0.003 |
Deng | +0.003 |
Chu | +0.003 |
Neg logit contributions | |
Story | -0.003 |
ylan | -0.003 |
Brist | -0.003 |
kok | -0.003 |
Kyr | -0.003 |
Token | Coach |
Token ID | 16393 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
Story | +0.037 |
ylan | +0.037 |
Brist | +0.036 |
kok | +0.034 |
Kyr | +0.033 |
Neg logit contributions | |
Pope | -0.042 |
angel | -0.039 |
Towards | -0.033 |
Deng | -0.032 |
atum | -0.032 |
Token | [ |
Token ID | 685 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
Pope | +0.111 |
angel | +0.103 |
Towards | +0.087 |
Deng | +0.086 |
atum | +0.084 |
Neg logit contributions | |
Story | -0.103 |
ylan | -0.102 |
Brist | -0.101 |
kok | -0.097 |
Kyr | -0.093 |
Token | Doug |
Token ID | 42297 |
Feature activation | +9.89e-02 |
Pos logit contributions | |
Story | +0.096 |
ylan | +0.093 |
Brist | +0.091 |
kok | +0.089 |
Kyr | +0.084 |
Neg logit contributions | |
Pope | -0.104 |
angel | -0.097 |
Towards | -0.084 |
Deng | -0.082 |
Chu | -0.081 |
Token | ] |
Token ID | 60 |
Feature activation | -7.27e-02 |
Pos logit contributions | |
Pope | +0.087 |
angel | +0.081 |
Towards | +0.070 |
Deng | +0.069 |
atum | +0.068 |
Neg logit contributions | |
Story | -0.066 |
ylan | -0.066 |
Brist | -0.065 |
kok | -0.062 |
Kyr | -0.059 |
Token | Mar |
Token ID | 1526 |
Feature activation | +5.65e-02 |
Pos logit contributions | |
Story | +0.057 |
ylan | +0.056 |
Brist | +0.056 |
kok | +0.054 |
Kyr | +0.052 |
Neg logit contributions | |
Pope | -0.055 |
angel | -0.051 |
Towards | -0.043 |
Deng | -0.042 |
atum | -0.042 |
Token | rone |
Token ID | 33171 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
Pope | +0.080 |
angel | +0.077 |
Towards | +0.070 |
Deng | +0.069 |
atum | +0.069 |
Neg logit contributions | |
Story | -0.008 |
ylan | -0.007 |
Brist | -0.007 |
kok | -0.005 |
Kyr | -0.004 |
Token | has |
Token ID | 468 |
Feature activation | -1.92e-02 |
Pos logit contributions | |
Story | +0.373 |
ylan | +0.368 |
Brist | +0.363 |
kok | +0.349 |
Kyr | +0.335 |
Neg logit contributions | |
Pope | -0.417 |
angel | -0.387 |
Towards | -0.330 |
Deng | -0.324 |
Chu | -0.318 |
Token | instructed |
Token ID | 17767 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
Story | +0.014 |
ylan | +0.014 |
Brist | +0.014 |
kok | +0.013 |
Kyr | +0.013 |
Neg logit contributions | |
Pope | -0.016 |
angel | -0.014 |
Towards | -0.012 |
Deng | -0.012 |
atum | -0.012 |
Token | him |
Token ID | 683 |
Feature activation | -7.64e-02 |
Pos logit contributions | |
Pope | +0.132 |
angel | +0.123 |
Towards | +0.105 |
Deng | +0.104 |
atum | +0.102 |
Neg logit contributions | |
Story | -0.109 |
ylan | -0.107 |
Brist | -0.106 |
kok | -0.101 |
Kyr | -0.098 |
Token | to |
Token ID | 284 |
Feature activation | -5.95e-03 |
Pos logit contributions | |
Story | +0.056 |
ylan | +0.055 |
Brist | +0.054 |
kok | +0.052 |
Kyr | +0.050 |
Neg logit contributions | |
Pope | -0.063 |
angel | -0.059 |
Towards | -0.050 |
Deng | -0.049 |
Chu | -0.048 |
Token | do |
Token ID | 466 |
Feature activation | +2.02e-02 |
Pos logit contributions | |
Story | +0.004 |
ylan | +0.004 |
Brist | +0.004 |
kok | +0.004 |
saddle | +0.004 |
Neg logit contributions | |
Pope | -0.005 |
angel | -0.005 |
Towards | -0.004 |
Deng | -0.004 |
Chu | -0.004 |
Token | about |
Token ID | 546 |
Feature activation | -7.97e-02 |
Pos logit contributions | |
Pope | +0.080 |
angel | +0.074 |
Towards | +0.063 |
Deng | +0.062 |
Chu | +0.061 |
Neg logit contributions | |
Story | -0.070 |
ylan | -0.069 |
Brist | -0.068 |
kok | -0.066 |
Kyr | -0.063 |
Token | its |
Token ID | 663 |
Feature activation | -3.21e-02 |
Pos logit contributions | |
Story | +0.058 |
ylan | +0.058 |
Brist | +0.057 |
kok | +0.055 |
Kyr | +0.052 |
Neg logit contributions | |
Pope | -0.065 |
angel | -0.060 |
Towards | -0.051 |
Deng | -0.051 |
Chu | -0.050 |
Token | drug |
Token ID | 2563 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
Story | +0.025 |
ylan | +0.024 |
Brist | +0.024 |
kok | +0.023 |
Kyr | +0.022 |
Neg logit contributions | |
Pope | -0.025 |
angel | -0.023 |
Towards | -0.020 |
Deng | -0.019 |
Chu | -0.019 |
Token | defer |
Token ID | 29135 |
Feature activation | +8.10e-02 |
Pos logit contributions | |
Story | +0.111 |
ylan | +0.109 |
Brist | +0.107 |
kok | +0.104 |
Kyr | +0.099 |
Neg logit contributions | |
Pope | -0.121 |
angel | -0.112 |
Towards | -0.096 |
Deng | -0.095 |
Chu | -0.093 |
Token | ip |
Token ID | 541 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
Pope | +0.059 |
angel | +0.054 |
Towards | +0.045 |
Deng | +0.044 |
Chu | +0.043 |
Neg logit contributions | |
Story | -0.067 |
ylan | -0.066 |
Brist | -0.065 |
kok | -0.063 |
Kyr | -0.061 |
Token | rone |
Token ID | 33171 |
Feature activation | -5.08e-01 |
Pos logit contributions | |
Story | +0.087 |
ylan | +0.085 |
Brist | +0.084 |
kok | +0.081 |
Kyr | +0.077 |
Neg logit contributions | |
Pope | -0.109 |
angel | -0.103 |
Towards | -0.088 |
Deng | -0.087 |
atum | -0.086 |
Token | , |
Token ID | 11 |
Feature activation | +4.31e-04 |
Pos logit contributions | |
Story | +0.388 |
ylan | +0.381 |
Brist | +0.376 |
kok | +0.363 |
Kyr | +0.349 |
Neg logit contributions | |
Pope | -0.400 |
angel | -0.371 |
Towards | -0.315 |
Deng | -0.313 |
atum | -0.307 |
Token | which |
Token ID | 543 |
Feature activation | -7.19e-02 |
Pos logit contributions | |
Pope | +0.000 |
angel | +0.000 |
Towards | +0.000 |
Deng | +0.000 |
Chu | +0.000 |
Neg logit contributions | |
Story | -0.000 |
ylan | -0.000 |
Brist | -0.000 |
kok | -0.000 |
Kyr | -0.000 |
Token | is |
Token ID | 318 |
Feature activation | -1.63e-04 |
Pos logit contributions | |
Story | +0.052 |
ylan | +0.051 |
Brist | +0.050 |
kok | +0.048 |
Kyr | +0.046 |
Neg logit contributions | |
Pope | -0.060 |
angel | -0.055 |
Towards | -0.047 |
Deng | -0.047 |
Chu | -0.046 |
Token | used |
Token ID | 973 |
Feature activation | +4.63e-02 |
Pos logit contributions | |
Story | +0.000 |
ylan | +0.000 |
Brist | +0.000 |
kok | +0.000 |
Kyr | +0.000 |
Neg logit contributions | |
Pope | -0.000 |
angel | -0.000 |
Towards | -0.000 |
Deng | -0.000 |
Chu | -0.000 |
Token | to |
Token ID | 284 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
Pope | +0.036 |
angel | +0.034 |
Towards | +0.029 |
Deng | +0.028 |
Chu | +0.028 |
Neg logit contributions | |
Story | -0.035 |
ylan | -0.035 |
Brist | -0.034 |
kok | -0.033 |
Kyr | -0.032 |
Token | , |
Token ID | 11 |
Feature activation | -2.61e-03 |
Pos logit contributions | |
Pope | +0.103 |
angel | +0.095 |
Towards | +0.081 |
Deng | +0.080 |
Chu | +0.078 |
Neg logit contributions | |
Story | -0.095 |
ylan | -0.094 |
Brist | -0.093 |
kok | -0.089 |
Kyr | -0.086 |
Token | specifically |
Token ID | 5734 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
Story | +0.002 |
ylan | +0.002 |
Brist | +0.002 |
kok | +0.002 |
Kyr | +0.002 |
Neg logit contributions | |
Pope | -0.002 |
angel | -0.002 |
Towards | -0.002 |
Deng | -0.002 |
Chu | -0.002 |
Token | concerning |
Token ID | 9305 |
Feature activation | -2.43e-02 |
Pos logit contributions | |
Pope | +0.084 |
angel | +0.078 |
Towards | +0.066 |
Deng | +0.065 |
Chu | +0.064 |
Neg logit contributions | |
Story | -0.079 |
ylan | -0.078 |
Brist | -0.077 |
kok | -0.074 |
Kyr | -0.071 |
Token | " |
Token ID | 366 |
Feature activation | +6.18e-02 |
Pos logit contributions | |
Story | +0.018 |
ylan | +0.018 |
Brist | +0.018 |
kok | +0.017 |
Kyr | +0.016 |
Neg logit contributions | |
Pope | -0.020 |
angel | -0.018 |
Towards | -0.015 |
Deng | -0.015 |
atum | -0.015 |
Token | mis |
Token ID | 25413 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
Pope | +0.051 |
angel | +0.047 |
Towards | +0.040 |
Deng | +0.040 |
Chu | +0.039 |
Neg logit contributions | |
Story | -0.045 |
ylan | -0.044 |
Brist | -0.044 |
kok | -0.042 |
Kyr | -0.040 |
Token | represent |
Token ID | 15603 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
Story | +0.079 |
ylan | +0.078 |
Brist | +0.077 |
kok | +0.073 |
Kyr | +0.069 |
Neg logit contributions | |
Pope | -0.132 |
angel | -0.124 |
Towards | -0.108 |
Deng | -0.108 |
Chu | -0.106 |
Token | ations |
Token ID | 602 |
Feature activation | -9.98e-02 |
Pos logit contributions | |
Story | +0.323 |
ylan | +0.320 |
Brist | +0.313 |
kok | +0.300 |
Kyr | +0.285 |
Neg logit contributions | |
Pope | -0.456 |
angel | -0.426 |
Towards | -0.370 |
Deng | -0.367 |
Chu | -0.361 |
Token | " |
Token ID | 1 |
Feature activation | +3.89e-03 |
Pos logit contributions | |
Story | +0.075 |
ylan | +0.074 |
Brist | +0.073 |
kok | +0.070 |
Kyr | +0.067 |
Neg logit contributions | |
Pope | -0.080 |
angel | -0.074 |
Towards | -0.063 |
Deng | -0.062 |
Chu | -0.061 |
Token | made |
Token ID | 925 |
Feature activation | -4.91e-02 |
Pos logit contributions | |
Pope | +0.003 |
angel | +0.003 |
Towards | +0.002 |
Deng | +0.002 |
atum | +0.002 |
Neg logit contributions | |
Story | -0.003 |
ylan | -0.003 |
Brist | -0.003 |
kok | -0.003 |
Kyr | -0.003 |
Token | to |
Token ID | 284 |
Feature activation | -4.89e-03 |
Pos logit contributions | |
Story | +0.036 |
ylan | +0.036 |
Brist | +0.035 |
kok | +0.034 |
Kyr | +0.032 |
Neg logit contributions | |
Pope | -0.040 |
angel | -0.037 |
Towards | -0.031 |
Deng | -0.031 |
Chu | -0.031 |
Token | the |
Token ID | 262 |
Feature activation | +3.16e-03 |
Pos logit contributions | |
Story | +0.004 |
ylan | +0.004 |
Brist | +0.004 |
kok | +0.003 |
Kyr | +0.003 |
Neg logit contributions | |
Pope | -0.004 |
angel | -0.004 |
Towards | -0.003 |
Deng | -0.003 |
Chu | -0.003 |
Token | thoroughly |
Token ID | 13770 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
Pope | +0.054 |
angel | +0.050 |
Towards | +0.043 |
Deng | +0.043 |
Chu | +0.042 |
Neg logit contributions | |
Story | -0.048 |
ylan | -0.047 |
Brist | -0.046 |
kok | -0.045 |
Kyr | -0.043 |
Token | . |
Token ID | 13 |
Feature activation | -3.63e-03 |
Pos logit contributions | |
Story | +0.086 |
ylan | +0.085 |
Brist | +0.083 |
kok | +0.080 |
Kyr | +0.077 |
Neg logit contributions | |
Pope | -0.092 |
angel | -0.085 |
Towards | -0.073 |
Deng | -0.072 |
Chu | -0.070 |
Token | Add |
Token ID | 3060 |
Feature activation | -8.98e-02 |
Pos logit contributions | |
Story | +0.003 |
ylan | +0.003 |
Brist | +0.003 |
kok | +0.002 |
saddle | +0.002 |
Neg logit contributions | |
Pope | -0.003 |
angel | -0.003 |
Towards | -0.002 |
Deng | -0.002 |
Chu | -0.002 |
Token | more |
Token ID | 517 |
Feature activation | -5.84e-02 |
Pos logit contributions | |
Story | +0.066 |
ylan | +0.065 |
Brist | +0.064 |
kok | +0.062 |
Kyr | +0.059 |
Neg logit contributions | |
Pope | -0.073 |
angel | -0.068 |
Towards | -0.058 |
Deng | -0.058 |
Chu | -0.057 |
Token | jun |
Token ID | 10891 |
Feature activation | +1.84e-02 |
Pos logit contributions | |
Story | +0.029 |
ylan | +0.029 |
Brist | +0.028 |
kok | +0.026 |
Kyr | +0.024 |
Neg logit contributions | |
Pope | -0.062 |
angel | -0.058 |
Towards | -0.052 |
Deng | -0.051 |
Chu | -0.051 |
Token | iper |
Token ID | 9346 |
Feature activation | -4.92e-01 |
Pos logit contributions | |
Pope | +0.026 |
angel | +0.025 |
Towards | +0.023 |
Deng | +0.022 |
atum | +0.022 |
Neg logit contributions | |
Story | -0.003 |
ylan | -0.003 |
Brist | -0.002 |
kok | -0.002 |
Kyr | -0.001 |
Token | infusion |
Token ID | 35547 |
Feature activation | -8.28e-02 |
Pos logit contributions | |
Story | +0.363 |
ylan | +0.360 |
Brist | +0.354 |
kok | +0.341 |
Kyr | +0.326 |
Neg logit contributions | |
Pope | -0.400 |
angel | -0.370 |
Towards | -0.316 |
Deng | -0.312 |
Chu | -0.306 |
Token | if |
Token ID | 611 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
Story | +0.062 |
ylan | +0.061 |
Brist | +0.060 |
kok | +0.058 |
Kyr | +0.056 |
Neg logit contributions | |
Pope | -0.066 |
angel | -0.062 |
Towards | -0.052 |
Deng | -0.052 |
Chu | -0.051 |
Token | necessary |
Token ID | 3306 |
Feature activation | +6.13e-03 |
Pos logit contributions | |
Pope | +0.084 |
angel | +0.077 |
Towards | +0.066 |
Deng | +0.065 |
Chu | +0.063 |
Neg logit contributions | |
Story | -0.079 |
ylan | -0.078 |
Brist | -0.077 |
kok | -0.074 |
Kyr | -0.071 |
Token | . |
Token ID | 13 |
Feature activation | -5.39e-03 |
Pos logit contributions | |
Pope | +0.005 |
angel | +0.005 |
Towards | +0.004 |
Deng | +0.004 |
Chu | +0.004 |
Neg logit contributions | |
Story | -0.005 |
ylan | -0.005 |
Brist | -0.004 |
kok | -0.004 |
Kyr | -0.004 |
Token | Leave |
Token ID | 17446 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
Story | +0.004 |
ylan | +0.004 |
Brist | +0.004 |
kok | +0.004 |
Kyr | +0.004 |
Neg logit contributions | |
Pope | -0.004 |
angel | -0.004 |
Towards | -0.004 |
Deng | -0.003 |
Chu | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +1.96e-04 |
Pos logit contributions | |
Pope | +0.003 |
angel | +0.003 |
Towards | +0.002 |
Deng | +0.002 |
Chu | +0.002 |
Neg logit contributions | |
Story | -0.003 |
ylan | -0.003 |
Brist | -0.003 |
kok | -0.003 |
Kyr | -0.003 |
Token | It |
Token ID | 1026 |
Feature activation | -9.98e-03 |
Pos logit contributions | |
Pope | +0.000 |
angel | +0.000 |
Towards | +0.000 |
Deng | +0.000 |
Chu | +0.000 |
Neg logit contributions | |
Story | -0.000 |
ylan | -0.000 |
Brist | -0.000 |
kok | -0.000 |
Kyr | -0.000 |
Token | would |
Token ID | 561 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
Story | +0.007 |
ylan | +0.007 |
Brist | +0.007 |
kok | +0.007 |
Kyr | +0.007 |
Neg logit contributions | |
Pope | -0.008 |
angel | -0.008 |
Towards | -0.006 |
Deng | -0.006 |
Chu | -0.006 |
Token | be |
Token ID | 307 |
Feature activation | -1.48e-03 |
Pos logit contributions | |
Story | +0.011 |
ylan | +0.011 |
Brist | +0.011 |
kok | +0.010 |
Kyr | +0.010 |
Neg logit contributions | |
Pope | -0.012 |
angel | -0.011 |
Towards | -0.009 |
Deng | -0.009 |
Chu | -0.009 |
Token | dis |
Token ID | 595 |
Feature activation | +5.71e-02 |
Pos logit contributions | |
Story | +0.001 |
ylan | +0.001 |
Brist | +0.001 |
kok | +0.001 |
Kyr | +0.001 |
Neg logit contributions | |
Pope | -0.001 |
angel | -0.001 |
Towards | -0.001 |
Deng | -0.001 |
Chu | -0.001 |
Token | pir |
Token ID | 4063 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
Pope | +0.062 |
angel | +0.059 |
Towards | +0.053 |
Deng | +0.052 |
Chu | +0.052 |
Neg logit contributions | |
Story | -0.026 |
ylan | -0.026 |
Brist | -0.025 |
kok | -0.023 |
Kyr | -0.022 |
Token | iting |
Token ID | 1780 |
Feature activation | +3.03e-02 |
Pos logit contributions | |
Story | +0.384 |
ylan | +0.381 |
Brist | +0.375 |
kok | +0.362 |
Kyr | +0.347 |
Neg logit contributions | |
Pope | -0.374 |
angel | -0.345 |
Towards | -0.291 |
Deng | -0.287 |
Chu | -0.281 |
Token | if |
Token ID | 611 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
Pope | +0.023 |
angel | +0.021 |
Towards | +0.018 |
Deng | +0.017 |
Chu | +0.017 |
Neg logit contributions | |
Story | -0.024 |
ylan | -0.024 |
Brist | -0.024 |
kok | -0.023 |
Kyr | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | +6.73e-04 |
Pos logit contributions | |
Pope | +0.082 |
angel | +0.076 |
Towards | +0.064 |
Deng | +0.064 |
Chu | +0.062 |
Neg logit contributions | |
Story | -0.080 |
ylan | -0.079 |
Brist | -0.078 |
kok | -0.075 |
Kyr | -0.072 |
Token | book |
Token ID | 1492 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
Pope | +0.001 |
angel | +0.000 |
Towards | +0.000 |
Deng | +0.000 |
atum | +0.000 |
Neg logit contributions | |
Story | -0.001 |
ylan | -0.001 |
Brist | -0.001 |
kok | -0.000 |
Kyr | -0.000 |
Token | came |
Token ID | 1625 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
Pope | +0.138 |
angel | +0.128 |
Towards | +0.109 |
Deng | +0.108 |
Chu | +0.106 |
Neg logit contributions | |
Story | -0.125 |
ylan | -0.124 |
Brist | -0.122 |
kok | -0.117 |
Kyr | -0.112 |
Token | dip |
Token ID | 19550 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
Story | +0.004 |
ylan | +0.004 |
Brist | +0.004 |
kok | +0.004 |
saddle | +0.003 |
Neg logit contributions | |
Pope | -0.005 |
angel | -0.004 |
Towards | -0.004 |
Deng | -0.004 |
Chu | -0.003 |
Token | these |
Token ID | 777 |
Feature activation | +3.40e-02 |
Pos logit contributions | |
Story | +0.166 |
ylan | +0.165 |
Brist | +0.162 |
kok | +0.156 |
Kyr | +0.149 |
Neg logit contributions | |
Pope | -0.184 |
angel | -0.170 |
Towards | -0.145 |
Deng | -0.144 |
Chu | -0.141 |
Token | in |
Token ID | 287 |
Feature activation | -5.80e-03 |
Pos logit contributions | |
Pope | +0.027 |
angel | +0.025 |
Towards | +0.022 |
Deng | +0.021 |
Chu | +0.021 |
Neg logit contributions | |
Story | -0.025 |
ylan | -0.025 |
Brist | -0.025 |
kok | -0.024 |
Kyr | -0.023 |
Token | boiling |
Token ID | 24372 |
Feature activation | +1.62e-02 |
Pos logit contributions | |
Story | +0.004 |
ylan | +0.004 |
Brist | +0.004 |
kok | +0.004 |
Kyr | +0.004 |
Neg logit contributions | |
Pope | -0.005 |
angel | -0.004 |
Towards | -0.004 |
Deng | -0.004 |
Chu | -0.004 |
Token | jun |
Token ID | 10891 |
Feature activation | +2.05e-02 |
Pos logit contributions | |
Pope | +0.016 |
angel | +0.015 |
Towards | +0.013 |
Deng | +0.013 |
Chu | +0.013 |
Neg logit contributions | |
Story | -0.009 |
ylan | -0.009 |
Brist | -0.009 |
kok | -0.009 |
earch | -0.008 |
Token | iper |
Token ID | 9346 |
Feature activation | -4.88e-01 |
Pos logit contributions | |
Pope | +0.028 |
angel | +0.028 |
Towards | +0.025 |
Deng | +0.025 |
atum | +0.025 |
Neg logit contributions | |
Story | -0.003 |
ylan | -0.003 |
Brist | -0.003 |
kok | -0.002 |
Afgh | -0.002 |
Token | infusion |
Token ID | 35547 |
Feature activation | -7.55e-02 |
Pos logit contributions | |
Story | +0.321 |
ylan | +0.317 |
Brist | +0.310 |
kok | +0.299 |
Kyr | +0.284 |
Neg logit contributions | |
Pope | -0.435 |
angel | -0.408 |
Towards | -0.353 |
Deng | -0.349 |
atum | -0.344 |
Token | first |
Token ID | 717 |
Feature activation | +8.26e-02 |
Pos logit contributions | |
Story | +0.057 |
ylan | +0.056 |
Brist | +0.055 |
kok | +0.054 |
Kyr | +0.051 |
Neg logit contributions | |
Pope | -0.060 |
angel | -0.056 |
Towards | -0.047 |
Deng | -0.047 |
Chu | -0.046 |
Token | .) |
Token ID | 2014 |
Feature activation | +8.37e-02 |
Pos logit contributions | |
Pope | +0.063 |
angel | +0.058 |
Towards | +0.049 |
Deng | +0.048 |
Chu | +0.047 |
Neg logit contributions | |
Story | -0.065 |
ylan | -0.064 |
Brist | -0.063 |
kok | -0.061 |
Kyr | -0.059 |
Token | Transfer |
Token ID | 20558 |
Feature activation | -5.40e-02 |
Pos logit contributions | |
Pope | +0.068 |
angel | +0.063 |
Towards | +0.054 |
Deng | +0.054 |
Chu | +0.053 |
Neg logit contributions | |
Story | -0.061 |
ylan | -0.061 |
Brist | -0.060 |
kok | -0.057 |
Kyr | -0.055 |
Token | the |
Token ID | 262 |
Feature activation | +3.80e-04 |
Pos logit contributions | |
Story | +0.039 |
ylan | +0.039 |
Brist | +0.038 |
kok | +0.037 |
Kyr | +0.035 |
Neg logit contributions | |
Pope | -0.044 |
angel | -0.041 |
Towards | -0.035 |
Deng | -0.035 |
Chu | -0.034 |
Token | chief |
Token ID | 4039 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
Story | +0.001 |
ylan | +0.001 |
Brist | +0.001 |
kok | +0.001 |
Kyr | +0.001 |
Neg logit contributions | |
Pope | -0.001 |
angel | -0.001 |
Towards | -0.001 |
Deng | -0.001 |
atum | -0.001 |
Token | forest |
Token ID | 8222 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
Pope | +0.109 |
angel | +0.101 |
Towards | +0.085 |
Deng | +0.083 |
atum | +0.082 |
Neg logit contributions | |
Story | -0.114 |
ylan | -0.112 |
Brist | -0.111 |
kok | -0.107 |
Kyr | -0.103 |
Token | official |
Token ID | 1743 |
Feature activation | +1.55e-03 |
Pos logit contributions | |
Pope | +0.178 |
angel | +0.164 |
Towards | +0.141 |
Deng | +0.138 |
atum | +0.136 |
Neg logit contributions | |
Story | -0.153 |
ylan | -0.152 |
Brist | -0.149 |
kok | -0.143 |
Kyr | -0.137 |
Token | of |
Token ID | 286 |
Feature activation | +3.99e-03 |
Pos logit contributions | |
Pope | +0.001 |
angel | +0.001 |
Towards | +0.001 |
Deng | +0.001 |
Chu | +0.001 |
Neg logit contributions | |
Story | -0.001 |
ylan | -0.001 |
Brist | -0.001 |
kok | -0.001 |
Kyr | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | -7.38e-04 |
Pos logit contributions | |
Pope | +0.003 |
angel | +0.003 |
Towards | +0.002 |
Deng | +0.002 |
Chu | +0.002 |
Neg logit contributions | |
Story | -0.003 |
ylan | -0.003 |
Brist | -0.003 |
kok | -0.003 |
Kyr | -0.003 |
Token | Sund |
Token ID | 3309 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
Story | +0.001 |
ylan | +0.001 |
Brist | +0.001 |
kok | +0.001 |
Kyr | +0.001 |
Neg logit contributions | |
Pope | -0.001 |
angel | -0.001 |
Towards | -0.000 |
Deng | -0.000 |
atum | -0.000 |
Token | arb |
Token ID | 38039 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
Pope | +0.332 |
angel | +0.314 |
Towards | +0.282 |
Deng | +0.280 |
Chu | +0.276 |
Neg logit contributions | |
Story | -0.121 |
ylan | -0.119 |
Brist | -0.115 |
kok | -0.107 |
Kyr | -0.099 |
Token | ans |
Token ID | 504 |
Feature activation | +5.80e-02 |
Pos logit contributions | |
Story | +0.216 |
ylan | +0.214 |
Brist | +0.210 |
kok | +0.204 |
Kyr | +0.195 |
Neg logit contributions | |
Pope | -0.206 |
angel | -0.188 |
Towards | -0.159 |
Deng | -0.157 |
Chu | -0.154 |
Token | in |
Token ID | 287 |
Feature activation | -3.35e-03 |
Pos logit contributions | |
Pope | +0.045 |
angel | +0.042 |
Towards | +0.035 |
Deng | +0.035 |
atum | +0.034 |
Neg logit contributions | |
Story | -0.045 |
ylan | -0.044 |
Brist | -0.044 |
kok | -0.042 |
Kyr | -0.040 |
Token | Bangladesh |
Token ID | 19483 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
Story | +0.003 |
ylan | +0.003 |
Brist | +0.003 |
kok | +0.002 |
Kyr | +0.002 |
Neg logit contributions | |
Pope | -0.003 |
angel | -0.002 |
Towards | -0.002 |
Deng | -0.002 |
Chu | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | +7.68e-03 |
Pos logit contributions | |
Pope | +0.094 |
angel | +0.087 |
Towards | +0.074 |
Deng | +0.073 |
Chu | +0.072 |
Neg logit contributions | |
Story | -0.086 |
ylan | -0.085 |
Brist | -0.084 |
kok | -0.081 |
Kyr | -0.077 |
Token | poor |
Token ID | 3595 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
Story | +0.002 |
ylan | +0.002 |
Brist | +0.002 |
kok | +0.002 |
Kyr | +0.002 |
Neg logit contributions | |
Pope | -0.002 |
angel | -0.002 |
Towards | -0.002 |
Deng | -0.002 |
Chu | -0.002 |
Token | health |
Token ID | 1535 |
Feature activation | +3.81e-02 |
Pos logit contributions | |
Pope | +0.103 |
angel | +0.095 |
Towards | +0.082 |
Deng | +0.081 |
Chu | +0.079 |
Neg logit contributions | |
Story | -0.090 |
ylan | -0.089 |
Brist | -0.087 |
kok | -0.084 |
Kyr | -0.080 |
Token | or |
Token ID | 393 |
Feature activation | -6.80e-02 |
Pos logit contributions | |
Pope | +0.031 |
angel | +0.028 |
Towards | +0.024 |
Deng | +0.024 |
Chu | +0.023 |
Neg logit contributions | |
Story | -0.028 |
ylan | -0.028 |
Brist | -0.028 |
kok | -0.027 |
Kyr | -0.026 |
Token | suffering |
Token ID | 7195 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
Story | +0.051 |
ylan | +0.050 |
Brist | +0.050 |
kok | +0.048 |
saddle | +0.046 |
Neg logit contributions | |
Pope | -0.054 |
angel | -0.050 |
Towards | -0.043 |
Deng | -0.042 |
atum | -0.041 |
Token | from |
Token ID | 422 |
Feature activation | -9.85e-03 |
Pos logit contributions | |
Story | +0.009 |
ylan | +0.009 |
Brist | +0.009 |
kok | +0.009 |
saddle | +0.008 |
Neg logit contributions | |
Pope | -0.011 |
angel | -0.010 |
Towards | -0.008 |
Deng | -0.008 |
atum | -0.008 |
Token | burn |
Token ID | 4245 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
Story | +0.008 |
ylan | +0.008 |
Brist | +0.008 |
kok | +0.007 |
saddle | +0.007 |
Neg logit contributions | |
Pope | -0.007 |
angel | -0.007 |
Towards | -0.006 |
Deng | -0.006 |
atum | -0.006 |
Token | out |
Token ID | 448 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
Pope | +0.194 |
angel | +0.176 |
Towards | +0.143 |
Deng | +0.140 |
Chu | +0.137 |
Neg logit contributions | |
Story | -0.268 |
ylan | -0.265 |
Brist | -0.261 |
kok | -0.254 |
saddle | -0.245 |
Token | retire |
Token ID | 8058 |
Feature activation | -5.49e-02 |
Pos logit contributions | |
Pope | +0.098 |
angel | +0.091 |
Towards | +0.077 |
Deng | +0.076 |
Chu | +0.075 |
Neg logit contributions | |
Story | -0.091 |
ylan | -0.090 |
Brist | -0.088 |
kok | -0.085 |
saddle | -0.082 |
Token | early |
Token ID | 1903 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
Story | +0.047 |
ylan | +0.046 |
Brist | +0.046 |
kok | +0.044 |
Kyr | +0.042 |
Neg logit contributions | |
Pope | -0.039 |
angel | -0.035 |
Towards | -0.029 |
Deng | -0.029 |
Chu | -0.028 |
Token | while |
Token ID | 981 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
Pope | +0.245 |
angel | +0.228 |
Towards | +0.192 |
Deng | +0.191 |
Chu | +0.186 |
Neg logit contributions | |
Story | -0.240 |
ylan | -0.239 |
Brist | -0.234 |
kok | -0.226 |
Kyr | -0.216 |
Token | those |
Token ID | 883 |
Feature activation | +9.81e-02 |
Pos logit contributions | |
Story | +0.011 |
ylan | +0.011 |
Brist | +0.011 |
kok | +0.010 |
Kyr | +0.010 |
Neg logit contributions | |
Pope | -0.011 |
angel | -0.010 |
Towards | -0.009 |
Deng | -0.009 |
Chu | -0.009 |
Token | up |
Token ID | 510 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
Story | +0.033 |
ylan | +0.032 |
Brist | +0.032 |
kok | +0.030 |
Kyr | +0.028 |
Neg logit contributions | |
Pope | -0.062 |
angel | -0.058 |
Towards | -0.051 |
Deng | -0.051 |
Chu | -0.050 |
Token | more |
Token ID | 517 |
Feature activation | -4.99e-02 |
Pos logit contributions | |
Story | +0.135 |
ylan | +0.133 |
Brist | +0.131 |
kok | +0.126 |
Kyr | +0.121 |
Neg logit contributions | |
Pope | -0.157 |
angel | -0.146 |
Towards | -0.125 |
Deng | -0.123 |
atum | -0.121 |
Token | or |
Token ID | 393 |
Feature activation | -5.86e-02 |
Pos logit contributions | |
Story | +0.035 |
ylan | +0.034 |
Brist | +0.034 |
kok | +0.032 |
Kyr | +0.031 |
Neg logit contributions | |
Pope | -0.043 |
angel | -0.040 |
Towards | -0.034 |
Deng | -0.034 |
atum | -0.033 |
Token | less |
Token ID | 1342 |
Feature activation | +2.81e-02 |
Pos logit contributions | |
Story | +0.045 |
ylan | +0.045 |
Brist | +0.044 |
kok | +0.042 |
Kyr | +0.041 |
Neg logit contributions | |
Pope | -0.046 |
angel | -0.042 |
Towards | -0.036 |
Deng | -0.035 |
Chu | -0.035 |
Token | mirror |
Token ID | 10162 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
Pope | +0.023 |
angel | +0.022 |
Towards | +0.019 |
Deng | +0.018 |
atum | +0.018 |
Neg logit contributions | |
Story | -0.020 |
ylan | -0.020 |
Brist | -0.020 |
kok | -0.019 |
Kyr | -0.018 |
Token | ing |
Token ID | 278 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
Pope | +0.068 |
angel | +0.059 |
Towards | +0.042 |
Deng | +0.041 |
Chu | +0.039 |
Neg logit contributions | |
Story | -0.172 |
ylan | -0.171 |
Brist | -0.169 |
kok | -0.165 |
Kyr | -0.161 |
Token | the |
Token ID | 262 |
Feature activation | +4.07e-03 |
Pos logit contributions | |
Pope | +0.264 |
angel | +0.245 |
Towards | +0.208 |
Deng | +0.206 |
atum | +0.202 |
Neg logit contributions | |
Story | -0.239 |
ylan | -0.237 |
Brist | -0.234 |
kok | -0.224 |
Kyr | -0.216 |
Token | Rab |
Token ID | 28559 |
Feature activation | +5.65e-02 |
Pos logit contributions | |
Pope | +0.003 |
angel | +0.003 |
Towards | +0.003 |
Deng | +0.003 |
atum | +0.002 |
Neg logit contributions | |
Story | -0.003 |
ylan | -0.003 |
Brist | -0.003 |
kok | -0.003 |
Kyr | -0.003 |
Token | id |
Token ID | 312 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
Pope | +0.047 |
angel | +0.044 |
Towards | +0.037 |
Deng | +0.037 |
Chu | +0.036 |
Neg logit contributions | |
Story | -0.041 |
ylan | -0.040 |
Brist | -0.039 |
kok | -0.038 |
Kyr | -0.036 |
Token | Pupp |
Token ID | 20926 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
Story | +0.196 |
ylan | +0.193 |
Brist | +0.189 |
kok | +0.180 |
Kyr | +0.172 |
Neg logit contributions | |
Pope | -0.288 |
angel | -0.269 |
Towards | -0.235 |
Deng | -0.232 |
Chu | -0.228 |
Token | ies |
Token ID | 444 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
Story | +0.105 |
ylan | +0.105 |
Brist | +0.102 |
kok | +0.100 |
saddle | +0.097 |
Neg logit contributions | |
Pope | -0.063 |
angel | -0.056 |
Towards | -0.044 |
Deng | -0.044 |
Chu | -0.041 |
Token | may |
Token ID | 743 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
Pope | +0.064 |
angel | +0.059 |
Towards | +0.050 |
Deng | +0.049 |
atum | +0.049 |
Neg logit contributions | |
Story | -0.060 |
ylan | -0.059 |
Brist | -0.058 |
kok | -0.056 |
Kyr | -0.053 |
Token | not |
Token ID | 407 |
Feature activation | +5.00e-02 |
Pos logit contributions | |
Story | +0.011 |
ylan | +0.010 |
Brist | +0.010 |
kok | +0.010 |
Kyr | +0.009 |
Neg logit contributions | |
Pope | -0.012 |
angel | -0.011 |
Towards | -0.009 |
Deng | -0.009 |
Chu | -0.009 |
Token | be |
Token ID | 307 |
Feature activation | -3.66e-03 |
Pos logit contributions | |
Pope | +0.041 |
angel | +0.038 |
Towards | +0.032 |
Deng | +0.032 |
Chu | +0.031 |
Neg logit contributions | |
Story | -0.037 |
ylan | -0.037 |
Brist | -0.036 |
kok | -0.035 |
Kyr | -0.033 |
Token | that |
Token ID | 326 |
Feature activation | -2.57e-02 |
Pos logit contributions | |
Story | +0.003 |
ylan | +0.003 |
Brist | +0.003 |
kok | +0.003 |
Kyr | +0.002 |
Neg logit contributions | |
Pope | -0.003 |
angel | -0.003 |
Towards | -0.002 |
Deng | -0.002 |
Chu | -0.002 |
Token | young |
Token ID | 1862 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
Story | +0.019 |
ylan | +0.019 |
Brist | +0.018 |
kok | +0.018 |
Kyr | +0.017 |
Neg logit contributions | |
Pope | -0.021 |
angel | -0.020 |
Towards | -0.017 |
Deng | -0.016 |
atum | -0.016 |
Token | evangelicals |
Token ID | 44881 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
Pope | +0.078 |
angel | +0.071 |
Towards | +0.057 |
Deng | +0.056 |
Chu | +0.054 |
Neg logit contributions | |
Story | -0.120 |
ylan | -0.119 |
Brist | -0.117 |
kok | -0.114 |
Kyr | -0.110 |
Token | are |
Token ID | 389 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
Pope | +0.352 |
angel | +0.327 |
Towards | +0.276 |
Deng | +0.273 |
Chu | +0.268 |
Neg logit contributions | |
Story | -0.335 |
ylan | -0.332 |
Brist | -0.327 |
kok | -0.315 |
Kyr | -0.302 |
Token | abandoning |
Token ID | 31309 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
Pope | +0.012 |
angel | +0.011 |
Towards | +0.010 |
Deng | +0.010 |
Chu | +0.009 |
Neg logit contributions | |
Story | -0.011 |
ylan | -0.011 |
Brist | -0.011 |
kok | -0.010 |
Kyr | -0.010 |
Token | their |
Token ID | 511 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
Story | +0.010 |
ylan | +0.010 |
Brist | +0.010 |
kok | +0.010 |
Kyr | +0.009 |
Neg logit contributions | |
Pope | -0.011 |
angel | -0.010 |
Towards | -0.009 |
Deng | -0.008 |
atum | -0.008 |
Token | faith |
Token ID | 4562 |
Feature activation | -4.97e-02 |
Pos logit contributions | |
Pope | +0.013 |
angel | +0.012 |
Towards | +0.010 |
Deng | +0.010 |
Chu | +0.010 |
Neg logit contributions | |
Story | -0.011 |
ylan | -0.011 |
Brist | -0.011 |
kok | -0.010 |
Kyr | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | -3.18e-03 |
Pos logit contributions | |
Story | +0.038 |
ylan | +0.037 |
Brist | +0.037 |
kok | +0.035 |
Kyr | +0.034 |
Neg logit contributions | |
Pope | -0.039 |
angel | -0.036 |
Towards | -0.031 |
Deng | -0.030 |
Chu | -0.030 |
Token | and |
Token ID | 290 |
Feature activation | +1.65e-03 |
Pos logit contributions | |
Story | +0.000 |
ylan | +0.000 |
Brist | +0.000 |
kok | +0.000 |
Kyr | +0.000 |
Neg logit contributions | |
Pope | -0.000 |
angel | -0.000 |
Towards | -0.000 |
Deng | -0.000 |
Chu | -0.000 |
Token | we |
Token ID | 356 |
Feature activation | +8.98e-03 |
Pos logit contributions | |
Pope | +0.001 |
angel | +0.001 |
Towards | +0.001 |
Deng | +0.001 |
Chu | +0.001 |
Neg logit contributions | |
Story | -0.001 |
ylan | -0.001 |
Brist | -0.001 |
kok | -0.001 |
Kyr | -0.001 |
Token | went |
Token ID | 1816 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
Pope | +0.007 |
angel | +0.007 |
Towards | +0.006 |
Deng | +0.006 |
Chu | +0.005 |
Neg logit contributions | |
Story | -0.007 |
ylan | -0.007 |
Brist | -0.007 |
kok | -0.006 |
Kyr | -0.006 |
Token | to |
Token ID | 284 |
Feature activation | -6.27e-03 |
Pos logit contributions | |
Pope | +0.104 |
angel | +0.097 |
Towards | +0.082 |
Deng | +0.081 |
Chu | +0.080 |
Neg logit contributions | |
Story | -0.098 |
ylan | -0.098 |
Brist | -0.096 |
kok | -0.092 |
Kyr | -0.088 |
Token | his |
Token ID | 465 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
Story | +0.005 |
ylan | +0.005 |
Brist | +0.005 |
kok | +0.005 |
Kyr | +0.005 |
Neg logit contributions | |
Pope | -0.005 |
angel | -0.004 |
Towards | -0.004 |
Deng | -0.004 |
Chu | -0.004 |
Token | home |
Token ID | 1363 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
Pope | +0.013 |
angel | +0.012 |
Towards | +0.009 |
Deng | +0.009 |
Chu | +0.009 |
Neg logit contributions | |
Story | -0.016 |
ylan | -0.016 |
Brist | -0.015 |
kok | -0.015 |
Kyr | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -4.53e-03 |
Pos logit contributions | |
Pope | +0.234 |
angel | +0.217 |
Towards | +0.183 |
Deng | +0.181 |
Chu | +0.178 |
Neg logit contributions | |
Story | -0.225 |
ylan | -0.223 |
Brist | -0.219 |
kok | -0.211 |
Kyr | -0.202 |
Token | We |
Token ID | 775 |
Feature activation | +4.79e-02 |
Pos logit contributions | |
Story | +0.003 |
ylan | +0.003 |
Brist | +0.003 |
kok | +0.003 |
Kyr | +0.003 |
Neg logit contributions | |
Pope | -0.004 |
angel | -0.003 |
Towards | -0.003 |
Deng | -0.003 |
Chu | -0.003 |
Token | went |
Token ID | 1816 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
Pope | +0.039 |
angel | +0.036 |
Towards | +0.031 |
Deng | +0.030 |
Chu | +0.030 |
Neg logit contributions | |
Story | -0.035 |
ylan | -0.035 |
Brist | -0.035 |
kok | -0.033 |
Kyr | -0.032 |
Token | to |
Token ID | 284 |
Feature activation | -2.62e-03 |
Pos logit contributions | |
Pope | +0.102 |
angel | +0.095 |
Towards | +0.080 |
Deng | +0.079 |
Chu | +0.078 |
Neg logit contributions | |
Story | -0.099 |
ylan | -0.098 |
Brist | -0.096 |
kok | -0.093 |
Kyr | -0.089 |
Token | a |
Token ID | 257 |
Feature activation | +2.99e-03 |
Pos logit contributions | |
Story | +0.002 |
ylan | +0.002 |
Brist | +0.002 |
kok | +0.002 |
Kyr | +0.002 |
Neg logit contributions | |
Pope | -0.002 |
angel | -0.002 |
Towards | -0.002 |
Deng | -0.002 |
Chu | -0.002 |
Token | oil |
Token ID | 3056 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
Pope | +0.048 |
angel | +0.045 |
Towards | +0.038 |
Deng | +0.037 |
Chu | +0.037 |
Neg logit contributions | |
Story | -0.046 |
ylan | -0.045 |
Brist | -0.044 |
kok | -0.043 |
Kyr | -0.041 |
Token | company |
Token ID | 1664 |
Feature activation | -8.57e-03 |
Pos logit contributions | |
Story | +0.163 |
ylan | +0.161 |
Brist | +0.158 |
kok | +0.152 |
Kyr | +0.145 |
Neg logit contributions | |
Pope | -0.201 |
angel | -0.187 |
Towards | -0.161 |
Deng | -0.159 |
Chu | -0.156 |
Token | Petro |
Token ID | 36863 |
Feature activation | +6.29e-02 |
Pos logit contributions | |
Story | +0.007 |
ylan | +0.007 |
Brist | +0.007 |
kok | +0.006 |
Kyr | +0.006 |
Neg logit contributions | |
Pope | -0.007 |
angel | -0.006 |
Towards | -0.005 |
Deng | -0.005 |
Chu | -0.005 |
Token | br |
Token ID | 1671 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
Pope | +0.061 |
angel | +0.057 |
Towards | +0.050 |
Deng | +0.050 |
Chu | +0.049 |
Neg logit contributions | |
Story | -0.036 |
ylan | -0.036 |
Brist | -0.035 |
kok | -0.034 |
Kyr | -0.032 |
Token | as |
Token ID | 292 |
Feature activation | -1.81e-02 |
Pos logit contributions | |
ylan | +0.099 |
Story | +0.098 |
Brist | +0.094 |
kok | +0.092 |
earch | +0.087 |
Neg logit contributions | |
Pope | -0.122 |
angel | -0.112 |
Towards | -0.099 |
Deng | -0.097 |
Chu | -0.095 |
Token | . |
Token ID | 13 |
Feature activation | -2.61e-03 |
Pos logit contributions | |
Story | +0.014 |
ylan | +0.013 |
Brist | +0.013 |
kok | +0.013 |
Kyr | +0.012 |
Neg logit contributions | |
Pope | -0.014 |
angel | -0.013 |
Towards | -0.011 |
Deng | -0.011 |
Chu | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | +4.03e-03 |
Pos logit contributions | |
Story | +0.002 |
ylan | +0.002 |
Brist | +0.002 |
kok | +0.002 |
Kyr | +0.002 |
Neg logit contributions | |
Pope | -0.002 |
angel | -0.002 |
Towards | -0.002 |
Deng | -0.002 |
Chu | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +4.44e-03 |
Pos logit contributions | |
Pope | +0.003 |
angel | +0.003 |
Towards | +0.003 |
Deng | +0.002 |
Chu | +0.002 |
Neg logit contributions | |
Story | -0.003 |
ylan | -0.003 |
Brist | -0.003 |
kok | -0.003 |
Kyr | -0.003 |
Token | The |
Token ID | 464 |
Feature activation | +1.44e-02 |
Pos logit contributions | |
Pope | +0.004 |
angel | +0.003 |
Towards | +0.003 |
Deng | +0.003 |
Chu | +0.003 |
Neg logit contributions | |
Story | -0.003 |
ylan | -0.003 |
Brist | -0.003 |
kok | -0.003 |
Kyr | -0.003 |
Token | arms |
Token ID | 5101 |
Feature activation | +8.08e-02 |
Pos logit contributions | |
Pope | +0.012 |
angel | +0.011 |
Towards | +0.009 |
Deng | +0.009 |
Chu | +0.009 |
Neg logit contributions | |
Story | -0.011 |
ylan | -0.011 |
Brist | -0.011 |
kok | -0.010 |
Kyr | -0.010 |
Token | dealer |
Token ID | 16456 |
Feature activation | -5.25e-02 |
Pos logit contributions | |
Pope | +0.054 |
angel | +0.049 |
Towards | +0.040 |
Deng | +0.039 |
Chu | +0.038 |
Neg logit contributions | |
Story | -0.072 |
ylan | -0.071 |
Brist | -0.070 |
kok | -0.068 |
Kyr | -0.066 |
Token | 1982 |
Token ID | 14489 |
Feature activation | -9.38e-03 |
Pos logit contributions | |
Pope | +0.041 |
angel | +0.039 |
Towards | +0.034 |
Deng | +0.033 |
Chu | +0.033 |
Neg logit contributions | |
Story | -0.029 |
ylan | -0.028 |
Brist | -0.028 |
kok | -0.026 |
saddle | -0.025 |
Token | V |
Token ID | 569 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
Story | +0.008 |
ylan | +0.008 |
Brist | +0.008 |
kok | +0.008 |
saddle | +0.008 |
Neg logit contributions | |
Pope | -0.006 |
angel | -0.006 |
Towards | -0.005 |
Deng | -0.004 |
Chu | -0.004 |
Token | itus |
Token ID | 17506 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
Pope | +0.085 |
angel | +0.075 |
Towards | +0.058 |
Deng | +0.057 |
Chu | +0.055 |
Neg logit contributions | |
Story | -0.156 |
ylan | -0.155 |
Brist | -0.153 |
kok | -0.149 |
Kyr | -0.144 |
Token | road |
Token ID | 2975 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
Pope | +0.207 |
angel | +0.192 |
Towards | +0.164 |
Deng | +0.162 |
Chu | +0.159 |
Neg logit contributions | |
Story | -0.182 |
ylan | -0.180 |
Brist | -0.177 |
kok | -0.170 |
Kyr | -0.163 |
Token | bike |
Token ID | 7161 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
Pope | +0.172 |
angel | +0.162 |
Towards | +0.142 |
Deng | +0.141 |
Chu | +0.139 |
Neg logit contributions | |
Story | -0.098 |
ylan | -0.097 |
Brist | -0.094 |
kok | -0.090 |
Kyr | -0.084 |
Token | . |
Token ID | 13 |
Feature activation | -3.06e-03 |
Pos logit contributions | |
Story | +0.117 |
ylan | +0.116 |
Brist | +0.114 |
kok | +0.110 |
Kyr | +0.106 |
Neg logit contributions | |
Pope | -0.124 |
angel | -0.115 |
Towards | -0.098 |
Deng | -0.097 |
Chu | -0.095 |
Token |
|
Token ID | 198 |
Feature activation | +5.75e-03 |
Pos logit contributions | |
Story | +0.002 |
ylan | +0.002 |
Brist | +0.002 |
kok | +0.002 |
saddle | +0.002 |
Neg logit contributions | |
Pope | -0.002 |
angel | -0.002 |
Towards | -0.002 |
Deng | -0.002 |
Chu | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +4.66e-03 |
Pos logit contributions | |
Pope | +0.005 |
angel | +0.004 |
Towards | +0.004 |
Deng | +0.003 |
Chu | +0.003 |
Neg logit contributions | |
Story | -0.004 |
ylan | -0.004 |
Brist | -0.004 |
kok | -0.004 |
Kyr | -0.004 |
Token | Gl |
Token ID | 9861 |
Feature activation | -2.78e-02 |
Pos logit contributions | |
Pope | +0.004 |
angel | +0.003 |
Towards | +0.003 |
Deng | +0.003 |
Chu | +0.003 |
Neg logit contributions | |
Story | -0.004 |
ylan | -0.004 |
Brist | -0.003 |
kok | -0.003 |
Kyr | -0.003 |
Token | enn |
Token ID | 1697 |
Feature activation | -9.72e-02 |
Pos logit contributions | |
Story | +0.018 |
ylan | +0.017 |
Brist | +0.017 |
kok | +0.016 |
Kyr | +0.016 |
Neg logit contributions | |
Pope | -0.026 |
angel | -0.024 |
Towards | -0.021 |
Deng | -0.021 |
atum | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | +8.38e-03 |
Pos logit contributions | |
Story | +0.070 |
ylan | +0.070 |
Brist | +0.068 |
kok | +0.066 |
Kyr | +0.063 |
Neg logit contributions | |
Pope | -0.080 |
angel | -0.075 |
Towards | -0.064 |
Deng | -0.063 |
Chu | -0.062 |
Token | beings |
Token ID | 9791 |
Feature activation | -7.38e-02 |
Pos logit contributions | |
Story | +0.028 |
ylan | +0.028 |
Brist | +0.027 |
kok | +0.026 |
Kyr | +0.025 |
Neg logit contributions | |
Pope | -0.032 |
angel | -0.029 |
Towards | -0.025 |
Deng | -0.025 |
Chu | -0.024 |
Token | possess |
Token ID | 8588 |
Feature activation | +6.43e-02 |
Pos logit contributions | |
Story | +0.056 |
ylan | +0.055 |
Brist | +0.054 |
kok | +0.052 |
saddle | +0.050 |
Neg logit contributions | |
Pope | -0.059 |
angel | -0.055 |
Towards | -0.046 |
Deng | -0.046 |
Chu | -0.045 |
Token | reason |
Token ID | 1738 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
Pope | +0.052 |
angel | +0.048 |
Towards | +0.041 |
Deng | +0.040 |
atum | +0.039 |
Neg logit contributions | |
Story | -0.048 |
ylan | -0.048 |
Brist | -0.047 |
kok | -0.045 |
saddle | -0.043 |
Token | in |
Token ID | 287 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
Pope | +0.155 |
angel | +0.143 |
Towards | +0.122 |
Deng | +0.120 |
Chu | +0.118 |
Neg logit contributions | |
Story | -0.144 |
ylan | -0.143 |
Brist | -0.140 |
kok | -0.135 |
Kyr | -0.129 |
Token | equal |
Token ID | 4961 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
Story | +0.009 |
ylan | +0.009 |
Brist | +0.009 |
kok | +0.009 |
Kyr | +0.008 |
Neg logit contributions | |
Pope | -0.009 |
angel | -0.008 |
Towards | -0.007 |
Deng | -0.007 |
atum | -0.006 |
Token | measure |
Token ID | 3953 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
Story | +0.014 |
ylan | +0.014 |
Brist | +0.013 |
kok | +0.013 |
Kyr | +0.013 |
Neg logit contributions | |
Pope | -0.008 |
angel | -0.007 |
Towards | -0.006 |
Deng | -0.006 |
Chu | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | +4.02e-03 |
Pos logit contributions | |
Pope | +0.169 |
angel | +0.156 |
Towards | +0.133 |
Deng | +0.131 |
Chu | +0.128 |
Neg logit contributions | |
Story | -0.159 |
ylan | -0.157 |
Brist | -0.154 |
kok | -0.149 |
Kyr | -0.142 |
Token | Hume |
Token ID | 45485 |
Feature activation | +1.35e-02 |
Pos logit contributions | |
Pope | +0.003 |
angel | +0.003 |
Towards | +0.003 |
Deng | +0.003 |
Chu | +0.002 |
Neg logit contributions | |
Story | -0.003 |
ylan | -0.003 |
Brist | -0.003 |
kok | -0.003 |
saddle | -0.003 |
Token | 's |
Token ID | 338 |
Feature activation | -3.33e-02 |
Pos logit contributions | |
Pope | +0.012 |
angel | +0.011 |
Towards | +0.009 |
Deng | +0.009 |
Chu | +0.009 |
Neg logit contributions | |
Story | -0.009 |
ylan | -0.009 |
Brist | -0.009 |
kok | -0.009 |
Kyr | -0.008 |
Token | endorsement |
Token ID | 17819 |
Feature activation | +7.40e-02 |
Pos logit contributions | |
Story | +0.025 |
ylan | +0.024 |
Brist | +0.024 |
kok | +0.023 |
saddle | +0.022 |
Neg logit contributions | |
Pope | -0.027 |
angel | -0.025 |
Towards | -0.021 |
Deng | -0.021 |
Chu | -0.021 |
Token | of |
Token ID | 286 |
Feature activation | +2.36e-03 |
Pos logit contributions | |
Pope | +0.059 |
angel | +0.054 |
Towards | +0.046 |
Deng | +0.045 |
Chu | +0.044 |
Neg logit contributions | |
Story | -0.056 |
ylan | -0.055 |
Brist | -0.055 |
kok | -0.053 |
Kyr | -0.050 |
Token | we |
Token ID | 356 |
Feature activation | +4.92e-03 |
Pos logit contributions | |
Story | +0.018 |
ylan | +0.018 |
Brist | +0.018 |
kok | +0.017 |
Kyr | +0.017 |
Neg logit contributions | |
Pope | -0.019 |
angel | -0.017 |
Towards | -0.015 |
Deng | -0.014 |
atum | -0.014 |
Token | had |
Token ID | 550 |
Feature activation | +2.45e-02 |
Pos logit contributions | |
Pope | +0.004 |
angel | +0.004 |
Towards | +0.003 |
Deng | +0.003 |
Chu | +0.003 |
Neg logit contributions | |
Story | -0.004 |
ylan | -0.004 |
Brist | -0.003 |
kok | -0.003 |
Kyr | -0.003 |
Token | reached |
Token ID | 4251 |
Feature activation | -1.27e-03 |
Pos logit contributions | |
Pope | +0.020 |
angel | +0.019 |
Towards | +0.016 |
Deng | +0.015 |
atum | +0.015 |
Neg logit contributions | |
Story | -0.018 |
ylan | -0.018 |
Brist | -0.018 |
kok | -0.017 |
Kyr | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | -2.45e-03 |
Pos logit contributions | |
Story | +0.001 |
ylan | +0.001 |
Brist | +0.001 |
kok | +0.001 |
Kyr | +0.001 |
Neg logit contributions | |
Pope | -0.001 |
angel | -0.001 |
Towards | -0.001 |
Deng | -0.001 |
atum | -0.001 |
Token | final |
Token ID | 2457 |
Feature activation | -5.70e-02 |
Pos logit contributions | |
Story | +0.002 |
ylan | +0.002 |
Brist | +0.002 |
kok | +0.002 |
Kyr | +0.002 |
Neg logit contributions | |
Pope | -0.002 |
angel | -0.002 |
Towards | -0.002 |
Deng | -0.002 |
atum | -0.002 |
Token | part |
Token ID | 636 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
Story | +0.044 |
ylan | +0.043 |
Brist | +0.043 |
kok | +0.041 |
saddle | +0.040 |
Neg logit contributions | |
Pope | -0.045 |
angel | -0.041 |
Towards | -0.035 |
Deng | -0.034 |
atum | -0.034 |
Token | of |
Token ID | 286 |
Feature activation | +8.23e-03 |
Pos logit contributions | |
Pope | +0.186 |
angel | +0.172 |
Towards | +0.146 |
Deng | +0.144 |
Chu | +0.141 |
Neg logit contributions | |
Story | -0.180 |
ylan | -0.178 |
Brist | -0.175 |
kok | -0.169 |
Kyr | -0.162 |
Token | the |
Token ID | 262 |
Feature activation | -2.96e-03 |
Pos logit contributions | |
Pope | +0.007 |
angel | +0.006 |
Towards | +0.005 |
Deng | +0.005 |
atum | +0.005 |
Neg logit contributions | |
Story | -0.006 |
ylan | -0.006 |
Brist | -0.006 |
kok | -0.006 |
Kyr | -0.005 |
Token | process |
Token ID | 1429 |
Feature activation | -2.36e-03 |
Pos logit contributions | |
Story | +0.002 |
ylan | +0.002 |
Brist | +0.002 |
kok | +0.002 |
Kyr | +0.002 |
Neg logit contributions | |
Pope | -0.002 |
angel | -0.002 |
Towards | -0.002 |
Deng | -0.002 |
atum | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +1.69e-03 |
Pos logit contributions | |
Story | +0.002 |
ylan | +0.002 |
Brist | +0.002 |
kok | +0.002 |
Kyr | +0.002 |
Neg logit contributions | |
Pope | -0.002 |
angel | -0.002 |
Towards | -0.002 |
Deng | -0.001 |
atum | -0.001 |
Token | She |
Token ID | 1375 |
Feature activation | +3.00e-02 |
Pos logit contributions | |
Pope | +0.001 |
angel | +0.001 |
Towards | +0.001 |
Deng | +0.001 |
atum | +0.001 |
Neg logit contributions | |
Story | -0.001 |
ylan | -0.001 |
Brist | -0.001 |
kok | -0.001 |
Kyr | -0.001 |
Token | if |
Token ID | 611 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
Pope | +0.025 |
angel | +0.023 |
Towards | +0.020 |
Deng | +0.019 |
Chu | +0.019 |
Neg logit contributions | |
Story | -0.026 |
ylan | -0.026 |
Brist | -0.025 |
kok | -0.024 |
Kyr | -0.023 |
Token | I |
Token ID | 314 |
Feature activation | -4.99e-03 |
Pos logit contributions | |
Pope | +0.085 |
angel | +0.079 |
Towards | +0.067 |
Deng | +0.066 |
Chu | +0.065 |
Neg logit contributions | |
Story | -0.079 |
ylan | -0.079 |
Brist | -0.077 |
kok | -0.075 |
Kyr | -0.071 |
Token | 'm |
Token ID | 1101 |
Feature activation | -3.93e-02 |
Pos logit contributions | |
Story | +0.004 |
ylan | +0.004 |
Brist | +0.004 |
kok | +0.003 |
Kyr | +0.003 |
Neg logit contributions | |
Pope | -0.004 |
angel | -0.004 |
Towards | -0.003 |
Deng | -0.003 |
Chu | -0.003 |
Token | making |
Token ID | 1642 |
Feature activation | -2.36e-02 |
Pos logit contributions | |
Story | +0.029 |
ylan | +0.029 |
Brist | +0.029 |
kok | +0.028 |
Kyr | +0.026 |
Neg logit contributions | |
Pope | -0.031 |
angel | -0.029 |
Towards | -0.025 |
Deng | -0.024 |
atum | -0.024 |
Token | news |
Token ID | 1705 |
Feature activation | -8.77e-02 |
Pos logit contributions | |
Story | +0.017 |
ylan | +0.017 |
Brist | +0.017 |
kok | +0.016 |
Kyr | +0.016 |
Neg logit contributions | |
Pope | -0.019 |
angel | -0.018 |
Towards | -0.015 |
Deng | -0.015 |
atum | -0.015 |
Token | here |
Token ID | 994 |
Feature activation | +7.45e-02 |
Pos logit contributions | |
Story | +0.064 |
ylan | +0.063 |
Brist | +0.062 |
kok | +0.060 |
Kyr | +0.057 |
Neg logit contributions | |
Pope | -0.072 |
angel | -0.067 |
Towards | -0.057 |
Deng | -0.056 |
atum | -0.055 |
Token | ," |
Token ID | 553 |
Feature activation | -6.41e-02 |
Pos logit contributions | |
Pope | +0.062 |
angel | +0.058 |
Towards | +0.050 |
Deng | +0.049 |
Chu | +0.048 |
Neg logit contributions | |
Story | -0.053 |
ylan | -0.053 |
Brist | -0.052 |
kok | -0.050 |
Kyr | -0.048 |
Token | National |
Token ID | 2351 |
Feature activation | +5.55e-02 |
Pos logit contributions | |
Story | +0.048 |
ylan | +0.047 |
Brist | +0.047 |
kok | +0.045 |
Kyr | +0.043 |
Neg logit contributions | |
Pope | -0.052 |
angel | -0.048 |
Towards | -0.041 |
Deng | -0.040 |
atum | -0.039 |
Token | Review |
Token ID | 6602 |
Feature activation | +6.30e-02 |
Pos logit contributions | |
Pope | +0.041 |
angel | +0.038 |
Towards | +0.032 |
Deng | +0.031 |
Chu | +0.030 |
Neg logit contributions | |
Story | -0.045 |
ylan | -0.045 |
Brist | -0.044 |
kok | -0.042 |
Kyr | -0.041 |
Token | 's |
Token ID | 338 |
Feature activation | -3.82e-02 |
Pos logit contributions | |
Pope | +0.052 |
angel | +0.048 |
Towards | +0.041 |
Deng | +0.041 |
atum | +0.040 |
Neg logit contributions | |
Story | -0.046 |
ylan | -0.045 |
Brist | -0.045 |
kok | -0.043 |
Kyr | -0.041 |
Token | Jonah |
Token ID | 45447 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
Story | +0.028 |
ylan | +0.028 |
Brist | +0.027 |
kok | +0.026 |
Kyr | +0.025 |
Neg logit contributions | |
Pope | -0.031 |
angel | -0.029 |
Towards | -0.025 |
Deng | -0.025 |
Chu | -0.024 |
Token | run |
Token ID | 1057 |
Feature activation | +7.55e-02 |
Pos logit contributions | |
Pope | +0.013 |
angel | +0.012 |
Towards | +0.010 |
Deng | +0.010 |
Chu | +0.010 |
Neg logit contributions | |
Story | -0.013 |
ylan | -0.012 |
Brist | -0.012 |
kok | -0.012 |
saddle | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | +6.27e-04 |
Pos logit contributions | |
Pope | +0.062 |
angel | +0.057 |
Towards | +0.049 |
Deng | +0.048 |
Chu | +0.047 |
Neg logit contributions | |
Story | -0.055 |
ylan | -0.055 |
Brist | -0.054 |
kok | -0.052 |
Kyr | -0.049 |
Token | sl |
Token ID | 1017 |
Feature activation | -5.84e-02 |
Pos logit contributions | |
Pope | +0.001 |
angel | +0.000 |
Towards | +0.000 |
Deng | +0.000 |
Chu | +0.000 |
Neg logit contributions | |
Story | -0.000 |
ylan | -0.000 |
Brist | -0.000 |
kok | -0.000 |
Kyr | -0.000 |
Token | s |
Token ID | 82 |
Feature activation | +5.17e-03 |
Pos logit contributions | |
Story | +0.043 |
ylan | +0.043 |
Brist | +0.042 |
kok | +0.041 |
Kyr | +0.039 |
Neg logit contributions | |
Pope | -0.047 |
angel | -0.044 |
Towards | -0.037 |
Deng | -0.037 |
Chu | -0.036 |
Token | deploy |
Token ID | 6061 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
Pope | +0.004 |
angel | +0.004 |
Towards | +0.003 |
Deng | +0.003 |
Chu | +0.003 |
Neg logit contributions | |
Story | -0.004 |
ylan | -0.004 |
Brist | -0.004 |
kok | -0.004 |
Kyr | -0.004 |
Token | command |
Token ID | 3141 |
Feature activation | -6.77e-02 |
Pos logit contributions | |
Pope | +0.169 |
angel | +0.158 |
Towards | +0.136 |
Deng | +0.135 |
Chu | +0.132 |
Neg logit contributions | |
Story | -0.132 |
ylan | -0.131 |
Brist | -0.129 |
kok | -0.123 |
Kyr | -0.118 |
Token | , |
Token ID | 11 |
Feature activation | -8.32e-05 |
Pos logit contributions | |
Story | +0.051 |
ylan | +0.051 |
Brist | +0.050 |
kok | +0.048 |
Kyr | +0.046 |
Neg logit contributions | |
Pope | -0.054 |
angel | -0.050 |
Towards | -0.042 |
Deng | -0.042 |
Chu | -0.041 |
Token | the |
Token ID | 262 |
Feature activation | +3.16e-03 |
Pos logit contributions | |
Story | +0.000 |
ylan | +0.000 |
Brist | +0.000 |
kok | +0.000 |
Kyr | +0.000 |
Neg logit contributions | |
Pope | -0.000 |
angel | -0.000 |
Towards | -0.000 |
Deng | -0.000 |
Chu | -0.000 |
Token | following |
Token ID | 1708 |
Feature activation | +5.30e-02 |
Pos logit contributions | |
Pope | +0.003 |
angel | +0.002 |
Towards | +0.002 |
Deng | +0.002 |
Chu | +0.002 |
Neg logit contributions | |
Story | -0.002 |
ylan | -0.002 |
Brist | -0.002 |
kok | -0.002 |
Kyr | -0.002 |
Token | things |
Token ID | 1243 |
Feature activation | -5.64e-02 |
Pos logit contributions | |
Pope | +0.041 |
angel | +0.038 |
Towards | +0.032 |
Deng | +0.031 |
Chu | +0.031 |
Neg logit contributions | |
Story | -0.041 |
ylan | -0.041 |
Brist | -0.040 |
kok | -0.039 |
Kyr | -0.037 |
Token | happen |
Token ID | 1645 |
Feature activation | +2.97e-02 |
Pos logit contributions | |
Story | +0.042 |
ylan | +0.042 |
Brist | +0.041 |
kok | +0.040 |
Kyr | +0.038 |
Neg logit contributions | |
Pope | -0.045 |
angel | -0.042 |
Towards | -0.036 |
Deng | -0.035 |
Chu | -0.034 |
Token | from |
Token ID | 422 |
Feature activation | -6.69e-03 |
Pos logit contributions | |
Pope | +0.125 |
angel | +0.116 |
Towards | +0.099 |
Deng | +0.098 |
Chu | +0.096 |
Neg logit contributions | |
Story | -0.115 |
ylan | -0.114 |
Brist | -0.112 |
kok | -0.108 |
Kyr | -0.103 |
Token | processes |
Token ID | 7767 |
Feature activation | +2.93e-02 |
Pos logit contributions | |
Story | +0.005 |
ylan | +0.005 |
Brist | +0.005 |
kok | +0.005 |
Kyr | +0.005 |
Neg logit contributions | |
Pope | -0.005 |
angel | -0.005 |
Towards | -0.004 |
Deng | -0.004 |
Chu | -0.004 |
Token | in |
Token ID | 287 |
Feature activation | -2.99e-03 |
Pos logit contributions | |
Pope | +0.023 |
angel | +0.021 |
Towards | +0.018 |
Deng | +0.018 |
atum | +0.017 |
Neg logit contributions | |
Story | -0.022 |
ylan | -0.022 |
Brist | -0.022 |
kok | -0.021 |
Kyr | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | +3.04e-03 |
Pos logit contributions | |
Story | +0.002 |
ylan | +0.002 |
Brist | +0.002 |
kok | +0.002 |
Kyr | +0.002 |
Neg logit contributions | |
Pope | -0.002 |
angel | -0.002 |
Towards | -0.002 |
Deng | -0.002 |
atum | -0.002 |
Token | planet |
Token ID | 5440 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
Pope | +0.002 |
angel | +0.002 |
Towards | +0.002 |
Deng | +0.002 |
atum | +0.002 |
Neg logit contributions | |
Story | -0.002 |
ylan | -0.002 |
Brist | -0.002 |
kok | -0.002 |
saddle | -0.002 |
Token | 's |
Token ID | 338 |
Feature activation | -3.46e-02 |
Pos logit contributions | |
Pope | +0.154 |
angel | +0.144 |
Towards | +0.123 |
Deng | +0.122 |
Chu | +0.120 |
Neg logit contributions | |
Story | -0.134 |
ylan | -0.133 |
Brist | -0.131 |
kok | -0.126 |
Kyr | -0.119 |
Token | mantle |
Token ID | 32107 |
Feature activation | +4.39e-02 |
Pos logit contributions | |
Story | +0.027 |
ylan | +0.027 |
Brist | +0.026 |
kok | +0.025 |
saddle | +0.024 |
Neg logit contributions | |
Pope | -0.027 |
angel | -0.025 |
Towards | -0.021 |
Deng | -0.020 |
Chu | -0.020 |
Token | beneath |
Token ID | 11061 |
Feature activation | +5.11e-02 |
Pos logit contributions | |
Pope | +0.036 |
angel | +0.033 |
Towards | +0.028 |
Deng | +0.028 |
Chu | +0.027 |
Neg logit contributions | |
Story | -0.033 |
ylan | -0.032 |
Brist | -0.032 |
kok | -0.030 |
saddle | -0.029 |
Token | the |
Token ID | 262 |
Feature activation | +1.89e-03 |
Pos logit contributions | |
Pope | +0.040 |
angel | +0.037 |
Towards | +0.032 |
Deng | +0.031 |
Chu | +0.031 |
Neg logit contributions | |
Story | -0.039 |
ylan | -0.038 |
Brist | -0.038 |
kok | -0.036 |
Kyr | -0.035 |
Token | crust |
Token ID | 20048 |
Feature activation | -7.64e-02 |
Pos logit contributions | |
Pope | +0.001 |
angel | +0.001 |
Towards | +0.001 |
Deng | +0.001 |
atum | +0.001 |
Neg logit contributions | |
Story | -0.001 |
ylan | -0.001 |
Brist | -0.001 |
kok | -0.001 |
saddle | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | +3.74e-03 |
Pos logit contributions | |
Story | +0.057 |
ylan | +0.056 |
Brist | +0.055 |
kok | +0.053 |
Kyr | +0.051 |
Neg logit contributions | |
Pope | -0.062 |
angel | -0.057 |
Towards | -0.048 |
Deng | -0.048 |
Chu | -0.047 |
Token | future |
Token ID | 2003 |
Feature activation | +9.34e-02 |
Pos logit contributions | |
Story | +0.040 |
ylan | +0.039 |
Brist | +0.039 |
kok | +0.037 |
Kyr | +0.036 |
Neg logit contributions | |
Pope | -0.042 |
angel | -0.038 |
Towards | -0.033 |
Deng | -0.032 |
atum | -0.032 |
Token | husbands |
Token ID | 27742 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
Pope | +0.069 |
angel | +0.063 |
Towards | +0.053 |
Deng | +0.052 |
atum | +0.051 |
Neg logit contributions | |
Story | -0.076 |
ylan | -0.076 |
Brist | -0.074 |
kok | -0.072 |
Kyr | -0.069 |
Token | . |
Token ID | 13 |
Feature activation | -3.49e-03 |
Pos logit contributions | |
Pope | +0.251 |
angel | +0.232 |
Towards | +0.197 |
Deng | +0.195 |
Chu | +0.190 |
Neg logit contributions | |
Story | -0.238 |
ylan | -0.235 |
Brist | -0.231 |
kok | -0.223 |
Kyr | -0.214 |
Token | Then |
Token ID | 3244 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
Story | +0.003 |
ylan | +0.003 |
Brist | +0.003 |
kok | +0.003 |
Kyr | +0.002 |
Neg logit contributions | |
Pope | -0.003 |
angel | -0.003 |
Towards | -0.002 |
Deng | -0.002 |
atum | -0.002 |
Token | we |
Token ID | 356 |
Feature activation | +9.95e-03 |
Pos logit contributions | |
Story | +0.087 |
ylan | +0.086 |
Brist | +0.085 |
kok | +0.081 |
Kyr | +0.078 |
Neg logit contributions | |
Pope | -0.092 |
angel | -0.085 |
Towards | -0.072 |
Deng | -0.071 |
atum | -0.069 |
Token | were |
Token ID | 547 |
Feature activation | -2.52e-02 |
Pos logit contributions | |
Pope | +0.008 |
angel | +0.007 |
Towards | +0.006 |
Deng | +0.006 |
Chu | +0.006 |
Neg logit contributions | |
Story | -0.007 |
ylan | -0.007 |
Brist | -0.007 |
kok | -0.007 |
Kyr | -0.007 |
Token | blind |
Token ID | 7770 |
Feature activation | +5.56e-02 |
Pos logit contributions | |
Story | +0.017 |
ylan | +0.017 |
Brist | +0.016 |
kok | +0.016 |
Kyr | +0.015 |
Neg logit contributions | |
Pope | -0.022 |
angel | -0.021 |
Towards | -0.018 |
Deng | -0.018 |
Chu | -0.018 |
Token | fold |
Token ID | 11379 |
Feature activation | -2.20e-02 |
Pos logit contributions | |
Pope | +0.051 |
angel | +0.048 |
Towards | +0.042 |
Deng | +0.041 |
Chu | +0.041 |
Neg logit contributions | |
Story | -0.035 |
ylan | -0.034 |
Brist | -0.034 |
kok | -0.032 |
Kyr | -0.031 |
Token | ed |
Token ID | 276 |
Feature activation | +3.00e-03 |
Pos logit contributions | |
Story | +0.015 |
ylan | +0.015 |
Brist | +0.015 |
kok | +0.014 |
Kyr | +0.014 |
Neg logit contributions | |
Pope | -0.019 |
angel | -0.017 |
Towards | -0.015 |
Deng | -0.015 |
Chu | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | +1.36e-03 |
Pos logit contributions | |
Pope | +0.002 |
angel | +0.002 |
Towards | +0.002 |
Deng | +0.002 |
Chu | +0.002 |
Neg logit contributions | |
Story | -0.002 |
ylan | -0.002 |
Brist | -0.002 |
kok | -0.002 |
Kyr | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +7.33e-03 |
Pos logit contributions | |
Pope | +0.001 |
angel | +0.001 |
Towards | +0.001 |
Deng | +0.001 |
Chu | +0.001 |
Neg logit contributions | |
Story | -0.001 |
ylan | -0.001 |
Brist | -0.001 |
kok | -0.001 |
Kyr | -0.001 |
Token | he |
Token ID | 339 |
Feature activation | -3.16e-02 |
Pos logit contributions | |
Story | +0.002 |
ylan | +0.002 |
Brist | +0.002 |
kok | +0.002 |
Kyr | +0.002 |
Neg logit contributions | |
Pope | -0.002 |
angel | -0.002 |
Towards | -0.002 |
Deng | -0.002 |
Chu | -0.002 |
Token | thinks |
Token ID | 6834 |
Feature activation | -4.32e-02 |
Pos logit contributions | |
Story | +0.023 |
ylan | +0.022 |
Brist | +0.022 |
kok | +0.021 |
Kyr | +0.020 |
Neg logit contributions | |
Pope | -0.026 |
angel | -0.025 |
Towards | -0.021 |
Deng | -0.021 |
Chu | -0.020 |
Token | interest |
Token ID | 1393 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
Story | +0.032 |
ylan | +0.032 |
Brist | +0.031 |
kok | +0.030 |
Kyr | +0.029 |
Neg logit contributions | |
Pope | -0.035 |
angel | -0.032 |
Towards | -0.027 |
Deng | -0.027 |
Chu | -0.026 |
Token | will |
Token ID | 481 |
Feature activation | +1.68e-03 |
Pos logit contributions | |
Story | +0.115 |
ylan | +0.114 |
Brist | +0.112 |
kok | +0.108 |
Kyr | +0.104 |
Neg logit contributions | |
Pope | -0.124 |
angel | -0.115 |
Towards | -0.098 |
Deng | -0.097 |
Chu | -0.095 |
Token | rapidly |
Token ID | 8902 |
Feature activation | -2.84e-02 |
Pos logit contributions | |
Pope | +0.001 |
angel | +0.001 |
Towards | +0.001 |
Deng | +0.001 |
Chu | +0.001 |
Neg logit contributions | |
Story | -0.001 |
ylan | -0.001 |
Brist | -0.001 |
kok | -0.001 |
saddle | -0.001 |
Token | grow |
Token ID | 1663 |
Feature activation | -3.34e-02 |
Pos logit contributions | |
Story | +0.019 |
ylan | +0.019 |
Brist | +0.019 |
kok | +0.018 |
saddle | +0.017 |
Neg logit contributions | |
Pope | -0.025 |
angel | -0.023 |
Towards | -0.020 |
Deng | -0.020 |
Chu | -0.019 |
Token | in |
Token ID | 287 |
Feature activation | -7.11e-03 |
Pos logit contributions | |
Story | +0.025 |
ylan | +0.025 |
Brist | +0.025 |
kok | +0.024 |
Kyr | +0.023 |
Neg logit contributions | |
Pope | -0.027 |
angel | -0.025 |
Towards | -0.021 |
Deng | -0.021 |
Chu | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | -6.37e-03 |
Pos logit contributions | |
Story | +0.005 |
ylan | +0.005 |
Brist | +0.005 |
kok | +0.005 |
Kyr | +0.005 |
Neg logit contributions | |
Pope | -0.006 |
angel | -0.005 |
Towards | -0.004 |
Deng | -0.004 |
Chu | -0.004 |
Token | mainstream |
Token ID | 8661 |
Feature activation | -3.84e-02 |
Pos logit contributions | |
Story | +0.005 |
ylan | +0.005 |
Brist | +0.005 |
kok | +0.005 |
Kyr | +0.005 |
Neg logit contributions | |
Pope | -0.005 |
angel | -0.004 |
Towards | -0.004 |
Deng | -0.004 |
Chu | -0.004 |
Token | world |
Token ID | 995 |
Feature activation | +8.22e-03 |
Pos logit contributions | |
Story | +0.028 |
ylan | +0.028 |
Brist | +0.028 |
kok | +0.027 |
Kyr | +0.026 |
Neg logit contributions | |
Pope | -0.031 |
angel | -0.029 |
Towards | -0.024 |
Deng | -0.024 |
Chu | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | -5.65e-03 |
Pos logit contributions | |
Pope | +0.007 |
angel | +0.006 |
Towards | +0.005 |
Deng | +0.005 |
Chu | +0.005 |
Neg logit contributions | |
Story | -0.006 |
ylan | -0.006 |
Brist | -0.006 |
kok | -0.006 |
Kyr | -0.006 |
Token | utions |
Token ID | 3508 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
Pope | +0.055 |
angel | +0.051 |
Towards | +0.044 |
Deng | +0.043 |
atum | +0.043 |
Neg logit contributions | |
Story | -0.042 |
ylan | -0.042 |
Brist | -0.041 |
kok | -0.039 |
Kyr | -0.037 |
Token | � |
Token ID | 447 |
Feature activation | +1.94e-03 |
Pos logit contributions | |
Story | +0.084 |
ylan | +0.083 |
Brist | +0.082 |
kok | +0.079 |
Kyr | +0.075 |
Neg logit contributions | |
Pope | -0.088 |
angel | -0.082 |
Towards | -0.069 |
Deng | -0.069 |
Chu | -0.067 |
Token | � |
Token ID | 251 |
Feature activation | -6.18e-03 |
Pos logit contributions | |
Pope | +0.002 |
angel | +0.001 |
Towards | +0.001 |
Deng | +0.001 |
Chu | +0.001 |
Neg logit contributions | |
Story | -0.001 |
ylan | -0.001 |
Brist | -0.001 |
kok | -0.001 |
Kyr | -0.001 |
Token | does |
Token ID | 857 |
Feature activation | +6.97e-04 |
Pos logit contributions | |
Story | +0.005 |
ylan | +0.005 |
Brist | +0.005 |
kok | +0.004 |
Kyr | +0.004 |
Neg logit contributions | |
Pope | -0.005 |
angel | -0.005 |
Towards | -0.004 |
Deng | -0.004 |
Chu | -0.004 |
Token | not |
Token ID | 407 |
Feature activation | +5.85e-02 |
Pos logit contributions | |
Pope | +0.001 |
angel | +0.000 |
Towards | +0.000 |
Deng | +0.000 |
Chu | +0.000 |
Neg logit contributions | |
Story | -0.001 |
ylan | -0.001 |
Brist | -0.001 |
kok | -0.001 |
saddle | -0.001 |
Token | reflect |
Token ID | 4079 |
Feature activation | -6.42e-02 |
Pos logit contributions | |
Pope | +0.048 |
angel | +0.045 |
Towards | +0.038 |
Deng | +0.038 |
Chu | +0.037 |
Neg logit contributions | |
Story | -0.043 |
ylan | -0.042 |
Brist | -0.041 |
kok | -0.040 |
saddle | -0.038 |
Token | a |
Token ID | 257 |
Feature activation | +6.35e-03 |
Pos logit contributions | |
Story | +0.049 |
ylan | +0.049 |
Brist | +0.048 |
kok | +0.046 |
Kyr | +0.044 |
Neg logit contributions | |
Pope | -0.050 |
angel | -0.047 |
Towards | -0.039 |
Deng | -0.039 |
Chu | -0.038 |
Token | belief |
Token ID | 4901 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
Pope | +0.005 |
angel | +0.005 |
Towards | +0.004 |
Deng | +0.004 |
Chu | +0.004 |
Neg logit contributions | |
Story | -0.005 |
ylan | -0.005 |
Brist | -0.005 |
kok | -0.004 |
Kyr | -0.004 |
Token | that |
Token ID | 326 |
Feature activation | -2.56e-02 |
Pos logit contributions | |
Story | +0.082 |
ylan | +0.081 |
Brist | +0.080 |
kok | +0.077 |
Kyr | +0.073 |
Neg logit contributions | |
Pope | -0.090 |
angel | -0.083 |
Towards | -0.071 |
Deng | -0.070 |
Chu | -0.069 |
Token | he |
Token ID | 339 |
Feature activation | -2.36e-02 |
Pos logit contributions | |
Story | +0.019 |
ylan | +0.019 |
Brist | +0.019 |
kok | +0.018 |
Kyr | +0.017 |
Neg logit contributions | |
Pope | -0.021 |
angel | -0.019 |
Towards | -0.016 |
Deng | -0.016 |
Chu | -0.016 |
Token | never |
Token ID | 1239 |
Feature activation | -3.11e-02 |
Pos logit contributions | |
Story | +0.017 |
ylan | +0.017 |
Brist | +0.017 |
kok | +0.016 |
Kyr | +0.015 |
Neg logit contributions | |
Pope | -0.019 |
angel | -0.018 |
Towards | -0.015 |
Deng | -0.015 |
Chu | -0.015 |
Token | - |
Token ID | 12 |
Feature activation | -1.82e-02 |
Pos logit contributions | |
Story | +0.045 |
ylan | +0.045 |
Brist | +0.044 |
kok | +0.043 |
saddle | +0.041 |
Neg logit contributions | |
Pope | -0.052 |
angel | -0.049 |
Towards | -0.042 |
Deng | -0.041 |
Chu | -0.041 |
Token | 150 |
Token ID | 8628 |
Feature activation | +3.57e-02 |
Pos logit contributions | |
Story | +0.014 |
ylan | +0.014 |
Brist | +0.014 |
kok | +0.014 |
Kyr | +0.013 |
Neg logit contributions | |
Pope | -0.014 |
angel | -0.013 |
Towards | -0.011 |
Deng | -0.011 |
Chu | -0.010 |
Token | Eco |
Token ID | 38719 |
Feature activation | -7.00e-02 |
Pos logit contributions | |
Pope | +0.030 |
angel | +0.027 |
Towards | +0.024 |
Deng | +0.023 |
Chu | +0.023 |
Neg logit contributions | |
Story | -0.026 |
ylan | -0.026 |
Brist | -0.025 |
kok | -0.024 |
saddle | -0.023 |
Token | Boost |
Token ID | 45686 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
Story | +0.050 |
ylan | +0.049 |
Brist | +0.048 |
kok | +0.046 |
saddle | +0.044 |
Neg logit contributions | |
Pope | -0.059 |
angel | -0.055 |
Towards | -0.047 |
Deng | -0.046 |
Chu | -0.046 |
Token | Tort |
Token ID | 28467 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
Story | +0.011 |
ylan | +0.011 |
Brist | +0.011 |
kok | +0.011 |
saddle | +0.010 |
Neg logit contributions | |
Pope | -0.012 |
angel | -0.011 |
Towards | -0.009 |
Deng | -0.009 |
Chu | -0.009 |
Token | ure |
Token ID | 495 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
Story | +0.109 |
ylan | +0.108 |
Brist | +0.106 |
kok | +0.101 |
saddle | +0.096 |
Neg logit contributions | |
Pope | -0.138 |
angel | -0.129 |
Towards | -0.111 |
Deng | -0.110 |
Chu | -0.108 |
Token | Test |
Token ID | 6208 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
Story | +0.247 |
ylan | +0.242 |
Brist | +0.240 |
kok | +0.229 |
saddle | +0.223 |
Neg logit contributions | |
Pope | -0.261 |
angel | -0.242 |
Towards | -0.203 |
Deng | -0.201 |
Chu | -0.198 |
Token | truck |
Token ID | 7779 |
Feature activation | +5.18e-03 |
Pos logit contributions | |
Story | +0.108 |
ylan | +0.107 |
Brist | +0.106 |
kok | +0.101 |
saddle | +0.098 |
Neg logit contributions | |
Pope | -0.117 |
angel | -0.108 |
Towards | -0.092 |
Deng | -0.091 |
Chu | -0.089 |
Token | in |
Token ID | 287 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
Pope | +0.004 |
angel | +0.004 |
Towards | +0.003 |
Deng | +0.003 |
Chu | +0.003 |
Neg logit contributions | |
Story | -0.004 |
ylan | -0.004 |
Brist | -0.004 |
kok | -0.004 |
saddle | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | -6.84e-03 |
Pos logit contributions | |
Story | +0.008 |
ylan | +0.008 |
Brist | +0.008 |
kok | +0.007 |
Kyr | +0.007 |
Neg logit contributions | |
Pope | -0.010 |
angel | -0.009 |
Towards | -0.008 |
Deng | -0.008 |
Chu | -0.008 |
Token | 2010 |
Token ID | 3050 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
Story | +0.005 |
ylan | +0.005 |
Brist | +0.005 |
kok | +0.005 |
Kyr | +0.004 |
Neg logit contributions | |
Pope | -0.006 |
angel | -0.005 |
Towards | -0.004 |
Deng | -0.004 |
Chu | -0.004 |
Token | rankings |
Token ID | 16905 |
Feature activation | +3.64e-02 |
Pos logit contributions | |
Story | +0.047 |
ylan | +0.047 |
Brist | +0.046 |
kok | +0.044 |
Kyr | +0.042 |
Neg logit contributions | |
Pope | -0.051 |
angel | -0.048 |
Towards | -0.040 |
Deng | -0.040 |
Chu | -0.039 |
Token | . |
Token ID | 13 |
Feature activation | -3.12e-04 |
Pos logit contributions | |
Pope | +0.029 |
angel | +0.027 |
Towards | +0.023 |
Deng | +0.023 |
Chu | +0.022 |
Neg logit contributions | |
Story | -0.027 |
ylan | -0.027 |
Brist | -0.027 |
kok | -0.026 |
Kyr | -0.024 |
Token |
|
Token ID | 198 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
Story | +0.000 |
ylan | +0.000 |
Brist | +0.000 |
kok | +0.000 |
Kyr | +0.000 |
Neg logit contributions | |
Pope | -0.000 |
angel | -0.000 |
Towards | -0.000 |
Deng | -0.000 |
Chu | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | +5.28e-03 |
Pos logit contributions | |
Pope | +0.010 |
angel | +0.009 |
Towards | +0.008 |
Deng | +0.007 |
Chu | +0.007 |
Neg logit contributions | |
Story | -0.009 |
ylan | -0.009 |
Brist | -0.009 |
kok | -0.009 |
Kyr | -0.008 |
Token | R |
Token ID | 49 |
Feature activation | -5.13e-02 |
Pos logit contributions | |
Pope | +0.004 |
angel | +0.004 |
Towards | +0.003 |
Deng | +0.003 |
Chu | +0.003 |
Neg logit contributions | |
Story | -0.004 |
ylan | -0.004 |
Brist | -0.004 |
kok | -0.004 |
Kyr | -0.004 |
Token | ANK |
Token ID | 15154 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
Story | +0.037 |
ylan | +0.037 |
Brist | +0.036 |
kok | +0.034 |
Kyr | +0.033 |
Neg logit contributions | |
Pope | -0.043 |
angel | -0.040 |
Towards | -0.034 |
Deng | -0.034 |
Chu | -0.033 |
Token | 1 |
Token ID | 352 |
Feature activation | +9.55e-02 |
Pos logit contributions | |
Story | +0.279 |
ylan | +0.277 |
Brist | +0.273 |
kok | +0.263 |
Kyr | +0.253 |
Neg logit contributions | |
Pope | -0.261 |
angel | -0.240 |
Towards | -0.201 |
Deng | -0.199 |
Chu | -0.194 |
Token | Josh |
Token ID | 8518 |
Feature activation | -7.62e-02 |
Pos logit contributions | |
Pope | +0.077 |
angel | +0.071 |
Towards | +0.060 |
Deng | +0.060 |
Chu | +0.058 |
Neg logit contributions | |
Story | -0.072 |
ylan | -0.071 |
Brist | -0.070 |
kok | -0.067 |
Kyr | -0.064 |
Token | Norman |
Token ID | 19636 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
Story | +0.062 |
ylan | +0.062 |
Brist | +0.061 |
kok | +0.059 |
Kyr | +0.057 |
Neg logit contributions | |
Pope | -0.055 |
angel | -0.051 |
Towards | -0.042 |
Deng | -0.042 |
atum | -0.041 |
Token | , |
Token ID | 11 |
Feature activation | +1.48e-03 |
Pos logit contributions | |
Story | +0.084 |
ylan | +0.083 |
Brist | +0.082 |
kok | +0.079 |
Kyr | +0.076 |
Neg logit contributions | |
Pope | -0.089 |
angel | -0.083 |
Towards | -0.070 |
Deng | -0.069 |
Chu | -0.068 |
Token | Redskins |
Token ID | 22038 |
Feature activation | +7.90e-02 |
Pos logit contributions | |
Pope | +0.001 |
angel | +0.001 |
Towards | +0.001 |
Deng | +0.001 |
Chu | +0.001 |
Neg logit contributions | |
Story | -0.001 |
ylan | -0.001 |
Brist | -0.001 |
kok | -0.001 |
Kyr | -0.001 |
Token | Advertisement |
Token ID | 4723 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
Pope | +0.005 |
angel | +0.005 |
Towards | +0.004 |
Deng | +0.004 |
Chu | +0.004 |
Neg logit contributions | |
Story | -0.004 |
ylan | -0.004 |
Brist | -0.004 |
kok | -0.004 |
Kyr | -0.004 |
Token | Continue |
Token ID | 10054 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
Story | +0.076 |
ylan | +0.076 |
Brist | +0.074 |
kok | +0.071 |
Kyr | +0.067 |
Neg logit contributions | |
Pope | -0.124 |
angel | -0.117 |
Towards | -0.102 |
Deng | -0.101 |
Chu | -0.100 |
Token | reading |
Token ID | 3555 |
Feature activation | -1.55e-02 |
Pos logit contributions | |
Story | +0.100 |
ylan | +0.099 |
Brist | +0.098 |
kok | +0.094 |
Kyr | +0.090 |
Neg logit contributions | |
Pope | -0.108 |
angel | -0.100 |
Towards | -0.085 |
Deng | -0.084 |
Chu | -0.082 |
Token | the |
Token ID | 262 |
Feature activation | +1.78e-03 |
Pos logit contributions | |
ylan | +0.012 |
Story | +0.012 |
Brist | +0.012 |
kok | +0.011 |
saddle | +0.011 |
Neg logit contributions | |
Pope | -0.012 |
angel | -0.011 |
Towards | -0.009 |
Deng | -0.009 |
Chu | -0.009 |
Token | main |
Token ID | 1388 |
Feature activation | -1.92e-02 |
Pos logit contributions | |
Pope | +0.001 |
angel | +0.001 |
Towards | +0.001 |
Deng | +0.001 |
Chu | +0.001 |
Neg logit contributions | |
Story | -0.001 |
ylan | -0.001 |
Brist | -0.001 |
kok | -0.001 |
Kyr | -0.001 |
Token | story |
Token ID | 1621 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
ylan | +0.006 |
Brist | +0.006 |
Story | +0.006 |
kok | +0.006 |
Kyr | +0.005 |
Neg logit contributions | |
Pope | -0.023 |
angel | -0.022 |
Deng | -0.020 |
Towards | -0.020 |
Chu | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | +8.93e-03 |
Pos logit contributions | |
Story | +0.267 |
ylan | +0.263 |
Brist | +0.258 |
kok | +0.249 |
Kyr | +0.239 |
Neg logit contributions | |
Pope | -0.281 |
angel | -0.261 |
Towards | -0.221 |
Deng | -0.218 |
atum | -0.215 |
Token |
|
Token ID | 198 |
Feature activation | +7.03e-03 |
Pos logit contributions | |
Pope | +0.007 |
angel | +0.007 |
Towards | +0.006 |
Deng | +0.005 |
Chu | +0.005 |
Neg logit contributions | |
Story | -0.007 |
ylan | -0.007 |
Brist | -0.007 |
kok | -0.006 |
Kyr | -0.006 |
Token | In |
Token ID | 818 |
Feature activation | +2.53e-02 |
Pos logit contributions | |
Pope | +0.006 |
angel | +0.005 |
Towards | +0.004 |
Deng | +0.004 |
Chu | +0.004 |
Neg logit contributions | |
Story | -0.005 |
ylan | -0.005 |
Brist | -0.005 |
kok | -0.005 |
Kyr | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | +5.30e-03 |
Pos logit contributions | |
Pope | +0.021 |
angel | +0.020 |
Towards | +0.017 |
Deng | +0.017 |
Chu | +0.016 |
Neg logit contributions | |
Story | -0.018 |
ylan | -0.018 |
Brist | -0.017 |
kok | -0.017 |
Kyr | -0.016 |
Token | capital |
Token ID | 3139 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
Pope | +0.004 |
angel | +0.004 |
Towards | +0.003 |
Deng | +0.003 |
Chu | +0.003 |
Neg logit contributions | |
Story | -0.004 |
ylan | -0.004 |
Brist | -0.004 |
kok | -0.004 |
Kyr | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | +5.17e-05 |
Pos logit contributions | |
Pope | +0.083 |
angel | +0.077 |
Towards | +0.065 |
Deng | +0.064 |
Chu | +0.063 |
Neg logit contributions | |
Story | -0.078 |
ylan | -0.077 |
Brist | -0.076 |
kok | -0.073 |
Kyr | -0.070 |
Token | he |
Token ID | 339 |
Feature activation | -2.64e-02 |
Pos logit contributions | |
Pope | +0.000 |
angel | +0.000 |
Towards | +0.000 |
Deng | +0.000 |
Chu | +0.000 |
Neg logit contributions | |
Story | -0.000 |
ylan | -0.000 |
Brist | -0.000 |
kok | -0.000 |
Kyr | -0.000 |
Token | is |
Token ID | 318 |
Feature activation | -1.63e-03 |
Pos logit contributions | |
Story | +0.019 |
ylan | +0.019 |
Brist | +0.019 |
kok | +0.018 |
Kyr | +0.017 |
Neg logit contributions | |
Pope | -0.022 |
angel | -0.020 |
Towards | -0.017 |
Deng | -0.017 |
Chu | -0.017 |
Token | an |
Token ID | 281 |
Feature activation | -4.38e-04 |
Pos logit contributions | |
Story | +0.001 |
ylan | +0.001 |
Brist | +0.001 |
kok | +0.001 |
Kyr | +0.001 |
Neg logit contributions | |
Pope | -0.001 |
angel | -0.001 |
Towards | -0.001 |
Deng | -0.001 |
Chu | -0.001 |
Token | instinct |
Token ID | 13311 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
Story | +0.000 |
ylan | +0.000 |
Brist | +0.000 |
kok | +0.000 |
Kyr | +0.000 |
Neg logit contributions | |
Pope | -0.000 |
angel | -0.000 |
Towards | -0.000 |
Deng | -0.000 |
Chu | -0.000 |
Token | ive |
Token ID | 425 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
Pope | +0.144 |
angel | +0.136 |
Towards | +0.123 |
Deng | +0.122 |
Chu | +0.120 |
Neg logit contributions | |
Story | -0.048 |
ylan | -0.047 |
Brist | -0.045 |
kok | -0.042 |
Kyr | -0.039 |
Token | leader |
Token ID | 3554 |
Feature activation | -6.25e-02 |
Pos logit contributions | |
Story | +0.239 |
ylan | +0.236 |
Brist | +0.232 |
kok | +0.222 |
Kyr | +0.213 |
Neg logit contributions | |
Pope | -0.301 |
angel | -0.280 |
Towards | -0.241 |
Deng | -0.238 |
Chu | -0.234 |
Token | and |
Token ID | 290 |
Feature activation | +9.02e-03 |
Pos logit contributions | |
Story | +0.047 |
ylan | +0.047 |
Brist | +0.046 |
kok | +0.045 |
Kyr | +0.043 |
Neg logit contributions | |
Pope | -0.049 |
angel | -0.046 |
Towards | -0.039 |
Deng | -0.038 |
Chu | -0.038 |
Token | a |
Token ID | 257 |
Feature activation | +4.95e-03 |
Pos logit contributions | |
Pope | +0.007 |
angel | +0.007 |
Towards | +0.006 |
Deng | +0.006 |
Chu | +0.006 |
Neg logit contributions | |
Story | -0.007 |
ylan | -0.007 |
Brist | -0.006 |
kok | -0.006 |
Kyr | -0.006 |
Token | perfectly |
Token ID | 7138 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
Pope | +0.004 |
angel | +0.004 |
Towards | +0.003 |
Deng | +0.003 |
Chu | +0.003 |
Neg logit contributions | |
Story | -0.004 |
ylan | -0.004 |
Brist | -0.003 |
kok | -0.003 |
Kyr | -0.003 |
Token | efficient |
Token ID | 6942 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
Pope | +0.110 |
angel | +0.102 |
Towards | +0.087 |
Deng | +0.086 |
Chu | +0.084 |
Neg logit contributions | |
Story | -0.102 |
ylan | -0.102 |
Brist | -0.100 |
kok | -0.096 |
Kyr | -0.092 |
Token | Chin |
Token ID | 22604 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
Story | +0.002 |
ylan | +0.002 |
Brist | +0.002 |
kok | +0.002 |
Kyr | +0.002 |
Neg logit contributions | |
Pope | -0.003 |
angel | -0.003 |
Towards | -0.002 |
Deng | -0.002 |
Chu | -0.002 |
Token | ook |
Token ID | 566 |
Feature activation | -9.26e-02 |
Pos logit contributions | |
Story | +0.072 |
ylan | +0.071 |
Brist | +0.070 |
kok | +0.067 |
Kyr | +0.063 |
Neg logit contributions | |
Pope | -0.110 |
angel | -0.103 |
Towards | -0.090 |
Deng | -0.089 |
Chu | -0.087 |
Token | and |
Token ID | 290 |
Feature activation | +4.74e-04 |
Pos logit contributions | |
Story | +0.049 |
ylan | +0.048 |
Brist | +0.047 |
kok | +0.044 |
Kyr | +0.042 |
Neg logit contributions | |
Pope | -0.095 |
angel | -0.089 |
Towards | -0.079 |
Deng | -0.078 |
Chu | -0.077 |
Token | Cit |
Token ID | 15792 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
Pope | +0.000 |
angel | +0.000 |
Towards | +0.000 |
Deng | +0.000 |
Chu | +0.000 |
Neg logit contributions | |
Story | -0.000 |
ylan | -0.000 |
Brist | -0.000 |
kok | -0.000 |
Kyr | -0.000 |
Token | ra |
Token ID | 430 |
Feature activation | -4.98e-02 |
Pos logit contributions | |
Story | +0.231 |
ylan | +0.230 |
Brist | +0.226 |
kok | +0.216 |
saddle | +0.206 |
Neg logit contributions | |
Pope | -0.285 |
angel | -0.266 |
Towards | -0.228 |
Deng | -0.226 |
Chu | -0.222 |
Token | hops |
Token ID | 29438 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
Story | +0.021 |
ylan | +0.021 |
Brist | +0.020 |
kok | +0.019 |
Kyr | +0.018 |
Neg logit contributions | |
Pope | -0.056 |
angel | -0.053 |
Towards | -0.047 |
Deng | -0.047 |
Chu | -0.046 |
Token | in |
Token ID | 287 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
Story | +0.248 |
ylan | +0.246 |
Brist | +0.242 |
kok | +0.233 |
Kyr | +0.223 |
Neg logit contributions | |
Pope | -0.262 |
angel | -0.243 |
Towards | -0.205 |
Deng | -0.203 |
Chu | -0.199 |
Token | the |
Token ID | 262 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
Story | +0.008 |
ylan | +0.008 |
Brist | +0.008 |
kok | +0.007 |
Kyr | +0.007 |
Neg logit contributions | |
Pope | -0.009 |
angel | -0.008 |
Towards | -0.007 |
Deng | -0.007 |
Chu | -0.007 |
Token | kettle |
Token ID | 40231 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
Story | +0.008 |
ylan | +0.008 |
Brist | +0.008 |
kok | +0.008 |
Kyr | +0.007 |
Neg logit contributions | |
Pope | -0.009 |
angel | -0.009 |
Towards | -0.007 |
Deng | -0.007 |
Chu | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | +1.57e-03 |
Pos logit contributions | |
Story | +0.075 |
ylan | +0.074 |
Brist | +0.073 |
kok | +0.070 |
saddle | +0.067 |
Neg logit contributions | |
Pope | -0.080 |
angel | -0.074 |
Towards | -0.063 |
Deng | -0.063 |
Chu | -0.061 |
Token | dry |
Token ID | 5894 |
Feature activation | +7.55e-03 |
Pos logit contributions | |
Pope | +0.001 |
angel | +0.001 |
Towards | +0.001 |
Deng | +0.001 |
Chu | +0.001 |
Neg logit contributions | |
Story | -0.001 |
ylan | -0.001 |
Brist | -0.001 |
kok | -0.001 |
Kyr | -0.001 |