Token | and |
Token ID | 290 |
Feature activation | +6.20e-02 |
Pos logit contributions | |
bal | +0.065 |
Seth | +0.063 |
Tyler | +0.062 |
ird | +0.061 |
uka | +0.061 |
Neg logit contributions | |
rog | -0.053 |
acle | -0.051 |
arium | -0.050 |
Buzz | -0.048 |
Buzz | -0.048 |
Token | his |
Token ID | 465 |
Feature activation | -2.96e-02 |
Pos logit contributions | |
rog | +0.094 |
acle | +0.090 |
arium | +0.089 |
Buzz | +0.086 |
Buzz | +0.085 |
Neg logit contributions | |
bal | -0.096 |
Seth | -0.093 |
Tyler | -0.092 |
ird | -0.090 |
uka | -0.090 |
Token | bottle |
Token ID | 9294 |
Feature activation | +2.70e-02 |
Pos logit contributions | |
bal | +0.041 |
Seth | +0.039 |
Tyler | +0.038 |
ird | +0.037 |
isc | +0.037 |
Neg logit contributions | |
rog | -0.051 |
arium | -0.049 |
acle | -0.048 |
Buzz | -0.047 |
Buzz | -0.046 |
Token | of |
Token ID | 286 |
Feature activation | -5.18e-02 |
Pos logit contributions | |
rog | +0.043 |
arium | +0.041 |
acle | +0.041 |
Buzz | +0.039 |
Buzz | +0.039 |
Neg logit contributions | |
bal | -0.040 |
Seth | -0.039 |
Tyler | -0.039 |
ird | -0.038 |
cest | -0.037 |
Token | g |
Token ID | 308 |
Feature activation | -3.29e-02 |
Pos logit contributions | |
bal | +0.080 |
Seth | +0.077 |
Tyler | +0.076 |
ird | +0.075 |
laund | +0.074 |
Neg logit contributions | |
rog | -0.079 |
acle | -0.077 |
arium | -0.076 |
Buzz | -0.072 |
Buzz | -0.071 |
Token | rog |
Token ID | 3828 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
bal | +0.056 |
Seth | +0.054 |
Tyler | +0.053 |
ird | +0.053 |
isc | +0.053 |
Neg logit contributions | |
rog | -0.046 |
acle | -0.044 |
arium | -0.044 |
Buzz | -0.042 |
Buzz | -0.041 |
Token | . |
Token ID | 13 |
Feature activation | -9.42e-04 |
Pos logit contributions | |
rog | +0.656 |
acle | +0.635 |
arium | +0.624 |
Buzz | +0.602 |
Buzz | +0.594 |
Neg logit contributions | |
bal | -0.604 |
Seth | -0.571 |
Tyler | -0.571 |
ird | -0.562 |
cest | -0.558 |
Token | |
Token ID | 220 |
Feature activation | +5.10e-02 |
Pos logit contributions | |
bal | +0.002 |
cest | +0.002 |
Seth | +0.002 |
laund | +0.002 |
ird | +0.002 |
Neg logit contributions | |
rog | -0.001 |
Buzz | -0.001 |
acle | -0.001 |
arium | -0.001 |
Buzz | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -2.36e-02 |
Pos logit contributions | |
rog | +0.077 |
acle | +0.074 |
arium | +0.073 |
Buzz | +0.071 |
Buzz | +0.071 |
Neg logit contributions | |
bal | -0.078 |
Seth | -0.076 |
Tyler | -0.075 |
ird | -0.074 |
cest | -0.073 |
Token |
|
Token ID | 198 |
Feature activation | -2.57e-02 |
Pos logit contributions | |
bal | +0.032 |
Seth | +0.032 |
Tyler | +0.031 |
uka | +0.031 |
ird | +0.030 |
Neg logit contributions | |
acle | -0.040 |
rog | -0.039 |
arium | -0.039 |
atively | -0.037 |
Buzz | -0.036 |
Token | He |
Token ID | 1544 |
Feature activation | -3.55e-02 |
Pos logit contributions | |
bal | +0.039 |
Seth | +0.037 |
Tyler | +0.037 |
ird | +0.036 |
uka | +0.036 |
Neg logit contributions | |
rog | -0.040 |
acle | -0.039 |
arium | -0.039 |
Buzz | -0.037 |
atively | -0.036 |
Token | and |
Token ID | 290 |
Feature activation | +4.91e-03 |
Pos logit contributions | |
acle | +0.168 |
rog | +0.156 |
Buzz | +0.154 |
arium | +0.153 |
atively | +0.149 |
Neg logit contributions | |
ird | -0.282 |
uka | -0.273 |
laund | -0.268 |
Seth | -0.264 |
isc | -0.263 |
Token | said |
Token ID | 531 |
Feature activation | -7.36e-04 |
Pos logit contributions | |
Buzz | +0.006 |
acle | +0.006 |
rog | +0.005 |
Buzz | +0.005 |
arium | +0.005 |
Neg logit contributions | |
ird | -0.009 |
laund | -0.009 |
isc | -0.009 |
uka | -0.009 |
bal | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | -9.54e-03 |
Pos logit contributions | |
bal | +0.001 |
Seth | +0.001 |
Tyler | +0.001 |
ird | +0.001 |
uka | +0.001 |
Neg logit contributions | |
rog | -0.001 |
acle | -0.001 |
arium | -0.001 |
Buzz | -0.001 |
Buzz | -0.001 |
Token | " |
Token ID | 366 |
Feature activation | -6.46e-02 |
Pos logit contributions | |
bal | +0.013 |
Seth | +0.013 |
Tyler | +0.013 |
ird | +0.013 |
uka | +0.013 |
Neg logit contributions | |
rog | -0.016 |
acle | -0.015 |
arium | -0.015 |
Buzz | -0.015 |
Buzz | -0.015 |
Token | F |
Token ID | 37 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
bal | +0.114 |
Tyler | +0.113 |
Seth | +0.113 |
ird | +0.112 |
isc | +0.110 |
Neg logit contributions | |
rog | -0.083 |
Buzz | -0.078 |
acle | -0.077 |
arium | -0.075 |
Buzz | -0.075 |
Token | rog |
Token ID | 3828 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
roller | +0.268 |
ird | +0.267 |
bal | +0.264 |
uka | +0.262 |
Seth | +0.259 |
Neg logit contributions | |
atively | -0.166 |
acle | -0.158 |
Buzz | -0.150 |
rus | -0.147 |
Buzz | -0.146 |
Token | !" |
Token ID | 2474 |
Feature activation | -6.31e-02 |
Pos logit contributions | |
rog | +0.648 |
acle | +0.643 |
arium | +0.622 |
Buzz | +0.612 |
atively | +0.606 |
Neg logit contributions | |
bal | -0.555 |
Tyler | -0.532 |
Seth | -0.529 |
cest | -0.519 |
ird | -0.514 |
Token | He |
Token ID | 679 |
Feature activation | +3.24e-03 |
Pos logit contributions | |
bal | +0.105 |
Seth | +0.101 |
Tyler | +0.101 |
ird | +0.101 |
cest | +0.101 |
Neg logit contributions | |
rog | -0.088 |
acle | -0.085 |
arium | -0.083 |
Buzz | -0.081 |
Buzz | -0.079 |
Token | put |
Token ID | 1234 |
Feature activation | -7.99e-02 |
Pos logit contributions | |
rog | +0.005 |
acle | +0.005 |
arium | +0.004 |
Buzz | +0.004 |
Buzz | +0.004 |
Neg logit contributions | |
bal | -0.005 |
Seth | -0.005 |
Tyler | -0.005 |
ird | -0.005 |
uka | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | -1.93e-02 |
Pos logit contributions | |
bal | +0.117 |
Seth | +0.115 |
Tyler | +0.114 |
uka | +0.111 |
ird | +0.109 |
Neg logit contributions | |
rog | -0.127 |
acle | -0.123 |
arium | -0.122 |
Buzz | -0.117 |
Buzz | -0.116 |
Token | card |
Token ID | 2657 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
sax | +0.025 |
roller | +0.024 |
bal | +0.024 |
ird | +0.024 |
cest | +0.023 |
Neg logit contributions | |
rog | -0.034 |
Buzz | -0.032 |
Buzz | -0.032 |
atively | -0.031 |
arium | -0.031 |
Token | the |
Token ID | 262 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
rog | +0.067 |
acle | +0.064 |
arium | +0.064 |
Buzz | +0.062 |
Buzz | +0.060 |
Neg logit contributions | |
bal | -0.067 |
Seth | -0.065 |
Tyler | -0.064 |
ird | -0.063 |
uka | -0.062 |
Token | bee |
Token ID | 20697 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
rog | +0.023 |
arium | +0.022 |
acle | +0.022 |
Buzz | +0.021 |
Buzz | +0.021 |
Neg logit contributions | |
bal | -0.022 |
Seth | -0.021 |
Tyler | -0.021 |
roller | -0.021 |
ird | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
rog | +0.262 |
acle | +0.259 |
arium | +0.251 |
Buzz | +0.243 |
atively | +0.235 |
Neg logit contributions | |
bal | -0.226 |
Seth | -0.207 |
ird | -0.204 |
cest | -0.204 |
Tyler | -0.203 |
Token | Tim |
Token ID | 5045 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
rog | +0.015 |
acle | +0.014 |
arium | +0.014 |
Buzz | +0.014 |
Buzz | +0.014 |
Neg logit contributions | |
bal | -0.017 |
cest | -0.017 |
Seth | -0.017 |
laund | -0.016 |
Tyler | -0.016 |
Token | and |
Token ID | 290 |
Feature activation | +2.02e-02 |
Pos logit contributions | |
rog | +0.018 |
acle | +0.018 |
arium | +0.017 |
Buzz | +0.017 |
Buzz | +0.017 |
Neg logit contributions | |
bal | -0.018 |
Tyler | -0.018 |
Seth | -0.018 |
ird | -0.017 |
uka | -0.017 |
Token | Buzz |
Token ID | 15753 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
rog | +0.029 |
acle | +0.028 |
arium | +0.028 |
Buzz | +0.027 |
Buzz | +0.027 |
Neg logit contributions | |
bal | -0.033 |
Seth | -0.032 |
Tyler | -0.031 |
ird | -0.031 |
uka | -0.031 |
Token | became |
Token ID | 2627 |
Feature activation | +5.42e-02 |
Pos logit contributions | |
rog | +0.625 |
acle | +0.612 |
arium | +0.597 |
atively | +0.562 |
Buzz | +0.554 |
Neg logit contributions | |
bal | -0.583 |
Seth | -0.559 |
ird | -0.557 |
Tyler | -0.552 |
cest | -0.544 |
Token | friends |
Token ID | 2460 |
Feature activation | +7.76e-04 |
Pos logit contributions | |
Buzz | +0.075 |
rog | +0.072 |
Buzz | +0.072 |
True | +0.066 |
acle | +0.065 |
Neg logit contributions | |
ird | -0.093 |
isc | -0.092 |
Tyler | -0.089 |
bal | -0.088 |
Seth | -0.087 |
Token | . |
Token ID | 13 |
Feature activation | +6.90e-03 |
Pos logit contributions | |
rog | +0.001 |
acle | +0.001 |
arium | +0.001 |
Buzz | +0.001 |
Buzz | +0.001 |
Neg logit contributions | |
bal | -0.001 |
Seth | -0.001 |
Tyler | -0.001 |
ird | -0.001 |
uka | -0.001 |
Token | They |
Token ID | 1119 |
Feature activation | +8.96e-02 |
Pos logit contributions | |
rog | +0.010 |
acle | +0.010 |
arium | +0.010 |
atively | +0.010 |
Buzz | +0.009 |
Neg logit contributions | |
bal | -0.010 |
Seth | -0.010 |
Tyler | -0.010 |
Sel | -0.010 |
Coc | -0.010 |
Token | loved |
Token ID | 6151 |
Feature activation | +3.30e-03 |
Pos logit contributions | |
rog | +0.129 |
acle | +0.124 |
arium | +0.122 |
Buzz | +0.117 |
Buzz | +0.117 |
Neg logit contributions | |
bal | -0.145 |
Seth | -0.141 |
Tyler | -0.140 |
ird | -0.138 |
uka | -0.137 |
Token | name |
Token ID | 1438 |
Feature activation | -2.54e-02 |
Pos logit contributions | |
rog | +0.009 |
acle | +0.009 |
arium | +0.009 |
Buzz | +0.008 |
atively | +0.008 |
Neg logit contributions | |
bal | -0.007 |
Seth | -0.007 |
Tyler | -0.007 |
isc | -0.007 |
Sel | -0.007 |
Token | was |
Token ID | 373 |
Feature activation | +2.50e-03 |
Pos logit contributions | |
bal | +0.044 |
Seth | +0.043 |
Tyler | +0.042 |
laund | +0.042 |
ird | +0.042 |
Neg logit contributions | |
rog | -0.033 |
acle | -0.032 |
Buzz | -0.032 |
arium | -0.032 |
Buzz | -0.031 |
Token | Buzz |
Token ID | 15753 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
rog | +0.003 |
Buzz | +0.003 |
arium | +0.003 |
acle | +0.003 |
Buzz | +0.003 |
Neg logit contributions | |
bal | -0.004 |
ird | -0.004 |
Seth | -0.004 |
laund | -0.004 |
Tyler | -0.004 |
Token | y |
Token ID | 88 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
acle | +0.615 |
rog | +0.605 |
arium | +0.581 |
atively | +0.569 |
Buzz | +0.545 |
Neg logit contributions | |
bal | -0.572 |
cest | -0.554 |
Tyler | -0.524 |
Seth | -0.523 |
uka | -0.513 |
Token | . |
Token ID | 13 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
rog | +0.224 |
acle | +0.217 |
arium | +0.212 |
Buzz | +0.207 |
atively | +0.202 |
Neg logit contributions | |
bal | -0.189 |
Tyler | -0.176 |
Seth | -0.176 |
cest | -0.173 |
Sel | -0.168 |
Token | Buzz |
Token ID | 15753 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
acle | +0.023 |
atively | +0.021 |
rog | +0.021 |
arium | +0.021 |
isy | +0.020 |
Neg logit contributions | |
bal | -0.021 |
Seth | -0.020 |
Tyler | -0.020 |
Coc | -0.020 |
Sel | -0.019 |
Token | y |
Token ID | 88 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
acle | +0.634 |
atively | +0.580 |
rog | +0.568 |
arium | +0.548 |
osis | +0.503 |
Neg logit contributions | |
cest | -0.580 |
bal | -0.562 |
Sel | -0.501 |
Seth | -0.495 |
Tyler | -0.493 |
Token | was |
Token ID | 373 |
Feature activation | +2.02e-04 |
Pos logit contributions | |
rog | +0.230 |
acle | +0.230 |
arium | +0.216 |
atively | +0.211 |
Buzz | +0.206 |
Neg logit contributions | |
bal | -0.178 |
Tyler | -0.163 |
Seth | -0.160 |
cest | -0.158 |
Sel | -0.158 |
Token | a |
Token ID | 257 |
Feature activation | +7.13e-02 |
Pos logit contributions | |
rog | +0.000 |
acle | +0.000 |
arium | +0.000 |
Buzz | +0.000 |
atively | +0.000 |
Neg logit contributions | |
bal | -0.000 |
Seth | -0.000 |
Tyler | -0.000 |
uka | -0.000 |
Sel | -0.000 |
Token | hard |
Token ID | 1327 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
rog | +0.103 |
acle | +0.098 |
arium | +0.097 |
Buzz | +0.094 |
Buzz | +0.094 |
Neg logit contributions | |
bal | -0.115 |
Seth | -0.113 |
Tyler | -0.113 |
ird | -0.111 |
uka | -0.109 |
Token | - |
Token ID | 12 |
Feature activation | -3.35e-02 |
Pos logit contributions | |
rog | +0.156 |
acle | +0.155 |
arium | +0.151 |
Buzz | +0.145 |
Buzz | +0.143 |
Neg logit contributions | |
bal | -0.160 |
cest | -0.148 |
Seth | -0.147 |
Tyler | -0.145 |
uka | -0.143 |
Token | adow |
Token ID | 4584 |
Feature activation | +7.58e-02 |
Pos logit contributions | |
rog | +0.223 |
acle | +0.218 |
Buzz | +0.209 |
atively | +0.208 |
arium | +0.208 |
Neg logit contributions | |
bal | -0.213 |
ird | -0.208 |
cest | -0.196 |
Seth | -0.194 |
uka | -0.193 |
Token | . |
Token ID | 13 |
Feature activation | +8.11e-03 |
Pos logit contributions | |
rog | +0.152 |
Buzz | +0.139 |
acky | +0.138 |
osis | +0.135 |
arium | +0.132 |
Neg logit contributions | |
bal | -0.078 |
cest | -0.071 |
ird | -0.066 |
Seth | -0.063 |
Su | -0.060 |
Token | His |
Token ID | 2399 |
Feature activation | +5.32e-03 |
Pos logit contributions | |
rog | +0.012 |
acle | +0.011 |
arium | +0.011 |
atively | +0.011 |
Buzz | +0.010 |
Neg logit contributions | |
bal | -0.013 |
Seth | -0.013 |
Tyler | -0.013 |
ird | -0.012 |
Sel | -0.012 |
Token | name |
Token ID | 1438 |
Feature activation | -2.54e-02 |
Pos logit contributions | |
rog | +0.009 |
acle | +0.009 |
arium | +0.009 |
Buzz | +0.008 |
atively | +0.008 |
Neg logit contributions | |
bal | -0.007 |
Seth | -0.007 |
Tyler | -0.007 |
isc | -0.007 |
Sel | -0.007 |
Token | was |
Token ID | 373 |
Feature activation | +2.50e-03 |
Pos logit contributions | |
bal | +0.044 |
Seth | +0.043 |
Tyler | +0.042 |
laund | +0.042 |
ird | +0.042 |
Neg logit contributions | |
rog | -0.033 |
acle | -0.032 |
Buzz | -0.032 |
arium | -0.032 |
Buzz | -0.031 |
Token | Buzz |
Token ID | 15753 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
rog | +0.003 |
Buzz | +0.003 |
arium | +0.003 |
acle | +0.003 |
Buzz | +0.003 |
Neg logit contributions | |
bal | -0.004 |
ird | -0.004 |
Seth | -0.004 |
laund | -0.004 |
Tyler | -0.004 |
Token | y |
Token ID | 88 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
acle | +0.615 |
rog | +0.605 |
arium | +0.581 |
atively | +0.569 |
Buzz | +0.545 |
Neg logit contributions | |
bal | -0.572 |
cest | -0.554 |
Tyler | -0.524 |
Seth | -0.523 |
uka | -0.513 |
Token | . |
Token ID | 13 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
rog | +0.224 |
acle | +0.217 |
arium | +0.212 |
Buzz | +0.207 |
atively | +0.202 |
Neg logit contributions | |
bal | -0.189 |
Tyler | -0.176 |
Seth | -0.176 |
cest | -0.173 |
Sel | -0.168 |
Token | Buzz |
Token ID | 15753 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
acle | +0.023 |
atively | +0.021 |
rog | +0.021 |
arium | +0.021 |
isy | +0.020 |
Neg logit contributions | |
bal | -0.021 |
Seth | -0.020 |
Tyler | -0.020 |
Coc | -0.020 |
Sel | -0.019 |
Token | y |
Token ID | 88 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
acle | +0.634 |
atively | +0.580 |
rog | +0.568 |
arium | +0.548 |
osis | +0.503 |
Neg logit contributions | |
cest | -0.580 |
bal | -0.562 |
Sel | -0.501 |
Seth | -0.495 |
Tyler | -0.493 |
Token | was |
Token ID | 373 |
Feature activation | +2.02e-04 |
Pos logit contributions | |
rog | +0.230 |
acle | +0.230 |
arium | +0.216 |
atively | +0.211 |
Buzz | +0.206 |
Neg logit contributions | |
bal | -0.178 |
Tyler | -0.163 |
Seth | -0.160 |
cest | -0.158 |
Sel | -0.158 |
Token | the |
Token ID | 262 |
Feature activation | -6.89e-03 |
Pos logit contributions | |
rog | +0.054 |
acle | +0.052 |
arium | +0.051 |
Buzz | +0.049 |
Buzz | +0.049 |
Neg logit contributions | |
bal | -0.053 |
Seth | -0.051 |
Tyler | -0.051 |
ird | -0.049 |
uka | -0.049 |
Token | bird |
Token ID | 6512 |
Feature activation | +9.41e-02 |
Pos logit contributions | |
bal | +0.010 |
Seth | +0.009 |
roller | +0.009 |
Tyler | +0.009 |
laund | +0.009 |
Neg logit contributions | |
rog | -0.012 |
acle | -0.011 |
arium | -0.011 |
Buzz | -0.011 |
Buzz | -0.011 |
Token | came |
Token ID | 1625 |
Feature activation | -2.22e-02 |
Pos logit contributions | |
rog | +0.152 |
acle | +0.149 |
arium | +0.141 |
atively | +0.136 |
Buzz | +0.136 |
Neg logit contributions | |
bal | -0.138 |
Seth | -0.131 |
Tyler | -0.129 |
ird | -0.128 |
cest | -0.127 |
Token | back |
Token ID | 736 |
Feature activation | +1.73e-02 |
Pos logit contributions | |
bal | +0.030 |
Seth | +0.029 |
Tyler | +0.027 |
Su | +0.026 |
cest | +0.026 |
Neg logit contributions | |
rog | -0.038 |
arium | -0.037 |
acle | -0.036 |
Buzz | -0.035 |
acky | -0.034 |
Token | , |
Token ID | 11 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
rog | +0.026 |
acle | +0.025 |
arium | +0.025 |
Buzz | +0.024 |
Buzz | +0.024 |
Neg logit contributions | |
bal | -0.027 |
Seth | -0.026 |
Tyler | -0.026 |
ird | -0.026 |
uka | -0.026 |
Token | Buzz |
Token ID | 15753 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
bal | +0.021 |
ird | +0.021 |
laund | +0.020 |
Tyler | +0.020 |
isc | +0.020 |
Neg logit contributions | |
rog | -0.019 |
Buzz | -0.018 |
acle | -0.018 |
arium | -0.018 |
Buzz | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | -1.15e-03 |
Pos logit contributions | |
rog | +0.637 |
acle | +0.608 |
arium | +0.586 |
atively | +0.561 |
Buzz | +0.552 |
Neg logit contributions | |
bal | -0.549 |
cest | -0.532 |
Seth | -0.519 |
Tyler | -0.511 |
ird | -0.509 |
Token | his |
Token ID | 465 |
Feature activation | -7.76e-02 |
Pos logit contributions | |
Seth | +0.001 |
bal | +0.001 |
Tyler | +0.001 |
Sel | +0.001 |
cest | +0.001 |
Neg logit contributions | |
rog | -0.002 |
acle | -0.002 |
arium | -0.002 |
agged | -0.002 |
atively | -0.002 |
Token | friends |
Token ID | 2460 |
Feature activation | -1.14e-03 |
Pos logit contributions | |
bal | +0.100 |
roller | +0.091 |
Seth | +0.091 |
isc | +0.089 |
Tyler | +0.088 |
Neg logit contributions | |
rog | -0.141 |
arium | -0.139 |
acle | -0.135 |
Buzz | -0.127 |
atively | -0.126 |
Token | threw |
Token ID | 9617 |
Feature activation | -4.23e-02 |
Pos logit contributions | |
bal | +0.002 |
Seth | +0.002 |
Tyler | +0.002 |
ird | +0.002 |
cest | +0.002 |
Neg logit contributions | |
rog | -0.002 |
acle | -0.002 |
arium | -0.002 |
Buzz | -0.002 |
Buzz | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | -8.54e-03 |
Pos logit contributions | |
bal | +0.055 |
Seth | +0.052 |
Tyler | +0.051 |
Ther | +0.049 |
roller | +0.049 |
Neg logit contributions | |
acle | -0.077 |
rog | -0.075 |
arium | -0.075 |
atively | -0.071 |
isy | -0.068 |
Token | I |
Token ID | 314 |
Feature activation | -4.67e-03 |
Pos logit contributions | |
rog | +0.023 |
acle | +0.022 |
arium | +0.022 |
Buzz | +0.022 |
Buzz | +0.021 |
Neg logit contributions | |
bal | -0.025 |
Seth | -0.025 |
Tyler | -0.024 |
cest | -0.024 |
laund | -0.024 |
Token | like |
Token ID | 588 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
bal | +0.006 |
Seth | +0.006 |
Tyler | +0.006 |
ird | +0.006 |
uka | +0.006 |
Neg logit contributions | |
rog | -0.008 |
acle | -0.008 |
arium | -0.008 |
Buzz | -0.007 |
Buzz | -0.007 |
Token | your |
Token ID | 534 |
Feature activation | -8.79e-02 |
Pos logit contributions | |
bal | +0.231 |
Seth | +0.224 |
Tyler | +0.223 |
ird | +0.220 |
uka | +0.218 |
Neg logit contributions | |
rog | -0.193 |
acle | -0.185 |
arium | -0.183 |
Buzz | -0.177 |
Buzz | -0.175 |
Token | hive |
Token ID | 35881 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
bal | +0.128 |
Seth | +0.121 |
Tyler | +0.120 |
isc | +0.117 |
ird | +0.116 |
Neg logit contributions | |
rog | -0.141 |
acle | -0.137 |
arium | -0.135 |
Buzz | -0.132 |
atively | -0.129 |
Token | ." |
Token ID | 526 |
Feature activation | -5.00e-02 |
Pos logit contributions | |
rog | +0.340 |
acle | +0.329 |
arium | +0.328 |
Buzz | +0.317 |
Buzz | +0.308 |
Neg logit contributions | |
Seth | -0.367 |
bal | -0.365 |
Tyler | -0.364 |
uka | -0.353 |
isc | -0.350 |
Token | Buzz |
Token ID | 15753 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
bal | +0.072 |
Seth | +0.071 |
Tyler | +0.070 |
Sel | +0.067 |
ird | +0.067 |
Neg logit contributions | |
rog | -0.081 |
acle | -0.079 |
arium | -0.077 |
Buzz | -0.074 |
atively | -0.073 |
Token | y |
Token ID | 88 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
rog | +0.673 |
acle | +0.671 |
arium | +0.631 |
alk | +0.605 |
agged | +0.597 |
Neg logit contributions | |
bal | -0.503 |
ird | -0.439 |
Sel | -0.435 |
Seth | -0.434 |
cest | -0.426 |
Token | smiled |
Token ID | 13541 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
rog | +0.224 |
acle | +0.212 |
arium | +0.209 |
agged | +0.199 |
alk | +0.199 |
Neg logit contributions | |
bal | -0.195 |
Seth | -0.176 |
Tyler | -0.174 |
Sel | -0.172 |
ird | -0.169 |
Token | and |
Token ID | 290 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
rog | +0.210 |
acle | +0.206 |
arium | +0.200 |
Buzz | +0.196 |
Buzz | +0.192 |
Neg logit contributions | |
bal | -0.255 |
Seth | -0.253 |
Tyler | -0.252 |
ird | -0.251 |
uka | -0.249 |
Token | said |
Token ID | 531 |
Feature activation | +3.02e-03 |
Pos logit contributions | |
rog | +0.018 |
Buzz | +0.018 |
acle | +0.017 |
arium | +0.017 |
Buzz | +0.017 |
Neg logit contributions | |
bal | -0.024 |
ird | -0.024 |
Seth | -0.024 |
laund | -0.023 |
Tyler | -0.023 |
Token | , |
Token ID | 11 |
Feature activation | -1.86e-03 |
Pos logit contributions | |
rog | +0.005 |
acle | +0.004 |
arium | +0.004 |
Buzz | +0.004 |
Buzz | +0.004 |
Neg logit contributions | |
bal | -0.005 |
Seth | -0.005 |
Tyler | -0.004 |
ird | -0.004 |
uka | -0.004 |
Token | friends |
Token ID | 2460 |
Feature activation | +1.51e-02 |
Pos logit contributions | |
bal | +0.067 |
cest | +0.058 |
isc | +0.058 |
Sel | +0.058 |
Seth | +0.057 |
Neg logit contributions | |
rog | -0.105 |
acle | -0.102 |
arium | -0.101 |
atively | -0.095 |
Buzz | -0.094 |
Token | . |
Token ID | 13 |
Feature activation | +1.55e-02 |
Pos logit contributions | |
rog | +0.025 |
acle | +0.024 |
arium | +0.024 |
Buzz | +0.024 |
atively | +0.023 |
Neg logit contributions | |
bal | -0.021 |
Tyler | -0.020 |
Seth | -0.020 |
ird | -0.020 |
cest | -0.019 |
Token | One |
Token ID | 1881 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
acle | +0.024 |
rog | +0.023 |
atively | +0.023 |
isy | +0.022 |
arium | +0.022 |
Neg logit contributions | |
Seth | -0.022 |
Tyler | -0.021 |
bal | -0.021 |
Sel | -0.020 |
Coc | -0.020 |
Token | day |
Token ID | 1110 |
Feature activation | +3.67e-02 |
Pos logit contributions | |
acle | +0.311 |
atively | +0.283 |
rus | +0.273 |
agged | +0.270 |
beard | +0.269 |
Neg logit contributions | |
bal | -0.151 |
cest | -0.121 |
Su | -0.120 |
North | -0.115 |
uka | -0.113 |
Token | , |
Token ID | 11 |
Feature activation | +9.59e-03 |
Pos logit contributions | |
acle | +0.067 |
rog | +0.066 |
arium | +0.065 |
urious | +0.061 |
isy | +0.058 |
Neg logit contributions | |
bal | -0.048 |
Seth | -0.042 |
Tyler | -0.042 |
ird | -0.041 |
Sel | -0.040 |
Token | Buzz |
Token ID | 15753 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
acle | +0.017 |
agged | +0.016 |
rog | +0.016 |
arium | +0.016 |
urious | +0.016 |
Neg logit contributions | |
bal | -0.012 |
Seth | -0.012 |
Coc | -0.012 |
Su | -0.012 |
Cam | -0.012 |
Token | y |
Token ID | 88 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
acle | +0.529 |
rog | +0.519 |
atively | +0.484 |
arium | +0.459 |
Buzz | +0.442 |
Neg logit contributions | |
bal | -0.647 |
cest | -0.646 |
Seth | -0.612 |
isc | -0.602 |
uka | -0.602 |
Token | wanted |
Token ID | 2227 |
Feature activation | +3.91e-02 |
Pos logit contributions | |
rog | +0.230 |
acle | +0.220 |
Buzz | +0.204 |
arium | +0.203 |
atively | +0.203 |
Neg logit contributions | |
bal | -0.167 |
Seth | -0.156 |
Tyler | -0.156 |
cest | -0.150 |
isc | -0.150 |
Token | to |
Token ID | 284 |
Feature activation | +2.23e-02 |
Pos logit contributions | |
acle | +0.070 |
rog | +0.069 |
atively | +0.065 |
arium | +0.065 |
acky | +0.063 |
Neg logit contributions | |
bal | -0.050 |
Seth | -0.047 |
Tyler | -0.047 |
laund | -0.046 |
uka | -0.045 |
Token | go |
Token ID | 467 |
Feature activation | -9.85e-02 |
Pos logit contributions | |
rog | +0.034 |
acle | +0.033 |
arium | +0.033 |
Buzz | +0.031 |
Buzz | +0.031 |
Neg logit contributions | |
bal | -0.034 |
Seth | -0.033 |
Tyler | -0.033 |
ird | -0.032 |
uka | -0.032 |
Token | outside |
Token ID | 2354 |
Feature activation | +2.45e-02 |
Pos logit contributions | |
bal | +0.134 |
Seth | +0.126 |
Tyler | +0.124 |
uka | +0.121 |
cest | +0.120 |
Neg logit contributions | |
rog | -0.168 |
acle | -0.166 |
arium | -0.160 |
Buzz | -0.156 |
atively | -0.156 |
Token | 't |
Token ID | 470 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
rog | +0.085 |
arium | +0.082 |
Buzz | +0.079 |
Buzz | +0.078 |
acle | +0.078 |
Neg logit contributions | |
Seth | -0.076 |
Tyler | -0.076 |
bal | -0.076 |
isc | -0.073 |
uka | -0.073 |
Token | mean |
Token ID | 1612 |
Feature activation | +8.52e-03 |
Pos logit contributions | |
rog | +0.236 |
acle | +0.230 |
arium | +0.228 |
Buzz | +0.216 |
atively | +0.213 |
Neg logit contributions | |
bal | -0.219 |
Seth | -0.210 |
Tyler | -0.206 |
ird | -0.206 |
cest | -0.204 |
Token | to |
Token ID | 284 |
Feature activation | +3.67e-02 |
Pos logit contributions | |
rog | +0.011 |
acle | +0.010 |
arium | +0.010 |
Buzz | +0.010 |
Buzz | +0.010 |
Neg logit contributions | |
bal | -0.015 |
ird | -0.015 |
Tyler | -0.015 |
uka | -0.015 |
laund | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | +9.53e-03 |
Pos logit contributions | |
arium | +0.057 |
rog | +0.056 |
acle | +0.056 |
atively | +0.052 |
Buzz | +0.051 |
Neg logit contributions | |
Seth | -0.055 |
bal | -0.054 |
Tyler | -0.054 |
ird | -0.051 |
Sel | -0.051 |
Token | but |
Token ID | 475 |
Feature activation | -5.17e-02 |
Pos logit contributions | |
rog | +0.013 |
acle | +0.013 |
Buzz | +0.013 |
arium | +0.013 |
Buzz | +0.012 |
Neg logit contributions | |
bal | -0.016 |
uka | -0.015 |
isc | -0.015 |
ird | -0.015 |
Seth | -0.015 |
Token | Buzz |
Token ID | 15753 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
bal | +0.077 |
Seth | +0.076 |
Tyler | +0.075 |
ird | +0.072 |
Sel | +0.072 |
Neg logit contributions | |
rog | -0.081 |
acle | -0.079 |
arium | -0.078 |
Buzz | -0.074 |
atively | -0.072 |
Token | was |
Token ID | 373 |
Feature activation | -3.78e-03 |
Pos logit contributions | |
rog | +0.601 |
acle | +0.584 |
arium | +0.572 |
atively | +0.544 |
Buzz | +0.543 |
Neg logit contributions | |
bal | -0.565 |
Seth | -0.540 |
Tyler | -0.538 |
cest | -0.536 |
ird | -0.527 |
Token | too |
Token ID | 1165 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
bal | +0.006 |
Seth | +0.005 |
Tyler | +0.005 |
uka | +0.005 |
ird | +0.005 |
Neg logit contributions | |
rog | -0.006 |
arium | -0.006 |
acle | -0.006 |
atively | -0.006 |
Buzz | -0.005 |
Token | small |
Token ID | 1402 |
Feature activation | +7.27e-02 |
Pos logit contributions | |
rog | +0.255 |
acle | +0.248 |
arium | +0.246 |
atively | +0.233 |
Buzz | +0.226 |
Neg logit contributions | |
bal | -0.234 |
Seth | -0.224 |
Tyler | -0.219 |
cest | -0.217 |
uka | -0.213 |
Token | for |
Token ID | 329 |
Feature activation | +2.75e-04 |
Pos logit contributions | |
rog | +0.116 |
acle | +0.111 |
arium | +0.109 |
Buzz | +0.107 |
Buzz | +0.105 |
Neg logit contributions | |
bal | -0.108 |
Tyler | -0.104 |
Seth | -0.103 |
ird | -0.101 |
cest | -0.101 |
Token | her |
Token ID | 607 |
Feature activation | -2.93e-02 |
Pos logit contributions | |
arium | +0.000 |
acle | +0.000 |
rog | +0.000 |
urious | +0.000 |
hog | +0.000 |
Neg logit contributions | |
Seth | -0.000 |
Tyler | -0.000 |
Super | -0.000 |
Sel | -0.000 |
Coc | -0.000 |
Token | little |
Token ID | 1310 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
rog | +0.092 |
acle | +0.087 |
arium | +0.087 |
Buzz | +0.084 |
Buzz | +0.083 |
Neg logit contributions | |
bal | -0.149 |
Seth | -0.146 |
Tyler | -0.145 |
ird | -0.143 |
isc | -0.142 |
Token | bee |
Token ID | 20697 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
acle | +0.172 |
rog | +0.169 |
arium | +0.164 |
atively | +0.160 |
Buzz | +0.152 |
Neg logit contributions | |
bal | -0.179 |
cest | -0.166 |
Seth | -0.166 |
Tyler | -0.165 |
pian | -0.162 |
Token | named |
Token ID | 3706 |
Feature activation | -9.05e-02 |
Pos logit contributions | |
rog | +0.223 |
acle | +0.214 |
arium | +0.214 |
Buzz | +0.207 |
Buzz | +0.207 |
Neg logit contributions | |
bal | -0.169 |
Seth | -0.165 |
Tyler | -0.164 |
ird | -0.159 |
uka | -0.159 |
Token | Buzz |
Token ID | 15753 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
Su | +0.155 |
Sel | +0.154 |
Seth | +0.153 |
bal | +0.152 |
uka | +0.152 |
Neg logit contributions | |
acle | -0.125 |
atively | -0.115 |
arium | -0.113 |
rog | -0.110 |
agged | -0.102 |
Token | . |
Token ID | 13 |
Feature activation | +5.43e-03 |
Pos logit contributions | |
rog | +0.486 |
acle | +0.467 |
arium | +0.458 |
Buzz | +0.437 |
Buzz | +0.436 |
Neg logit contributions | |
bal | -0.677 |
Seth | -0.658 |
Tyler | -0.654 |
ird | -0.644 |
uka | -0.641 |
Token | Buzz |
Token ID | 15753 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
acle | +0.005 |
erie | +0.004 |
atively | +0.004 |
arium | +0.004 |
urious | +0.004 |
Neg logit contributions | |
bal | -0.010 |
Coc | -0.010 |
North | -0.010 |
Stri | -0.010 |
Sel | -0.010 |
Token | lived |
Token ID | 5615 |
Feature activation | +6.66e-02 |
Pos logit contributions | |
acle | +0.611 |
rog | +0.592 |
atively | +0.567 |
arium | +0.562 |
Buzz | +0.531 |
Neg logit contributions | |
bal | -0.572 |
cest | -0.565 |
uka | -0.519 |
Seth | -0.518 |
ird | -0.515 |
Token | in |
Token ID | 287 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
rog | +0.119 |
acle | +0.118 |
atively | +0.111 |
arium | +0.111 |
beard | +0.103 |
Neg logit contributions | |
bal | -0.085 |
uka | -0.074 |
Super | -0.074 |
cest | -0.072 |
Es | -0.071 |
Token | a |
Token ID | 257 |
Feature activation | +7.26e-02 |
Pos logit contributions | |
acle | +0.184 |
rog | +0.182 |
atively | +0.182 |
arium | +0.171 |
ly | +0.160 |
Neg logit contributions | |
North | -0.123 |
bal | -0.120 |
uka | -0.118 |
Super | -0.117 |
Seth | -0.115 |
Token | hive |
Token ID | 35881 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
rog | +0.120 |
acle | +0.119 |
atively | +0.113 |
arium | +0.109 |
Buzz | +0.105 |
Neg logit contributions | |
bal | -0.102 |
laund | -0.095 |
uka | -0.095 |
cest | -0.095 |
Seth | -0.094 |
Token | with |
Token ID | 351 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
rog | +0.423 |
acle | +0.396 |
atively | +0.394 |
Buzz | +0.383 |
beard | +0.370 |
Neg logit contributions | |
bal | -0.270 |
cest | -0.264 |
ird | -0.236 |
North | -0.228 |
Es | -0.219 |
Token | hive |
Token ID | 35881 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
rog | +0.120 |
acle | +0.119 |
atively | +0.113 |
arium | +0.109 |
Buzz | +0.105 |
Neg logit contributions | |
bal | -0.102 |
laund | -0.095 |
uka | -0.095 |
cest | -0.095 |
Seth | -0.094 |
Token | with |
Token ID | 351 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
rog | +0.423 |
acle | +0.396 |
atively | +0.394 |
Buzz | +0.383 |
beard | +0.370 |
Neg logit contributions | |
bal | -0.270 |
cest | -0.264 |
ird | -0.236 |
North | -0.228 |
Es | -0.219 |
Token | his |
Token ID | 465 |
Feature activation | -6.25e-02 |
Pos logit contributions | |
rog | +0.037 |
acle | +0.037 |
arium | +0.036 |
atively | +0.034 |
acky | +0.032 |
Neg logit contributions | |
bal | -0.024 |
North | -0.022 |
Seth | -0.022 |
cest | -0.021 |
Sel | -0.021 |
Token | friends |
Token ID | 2460 |
Feature activation | +6.88e-03 |
Pos logit contributions | |
bal | +0.063 |
North | +0.055 |
cest | +0.055 |
Sel | +0.054 |
isc | +0.054 |
Neg logit contributions | |
acle | -0.126 |
rog | -0.125 |
arium | -0.121 |
atively | -0.119 |
beard | -0.113 |
Token | . |
Token ID | 13 |
Feature activation | +7.97e-03 |
Pos logit contributions | |
rog | +0.012 |
acle | +0.012 |
atively | +0.012 |
Buzz | +0.011 |
arium | +0.011 |
Neg logit contributions | |
bal | -0.009 |
Tyler | -0.008 |
Seth | -0.008 |
ird | -0.008 |
cest | -0.008 |
Token | Buzz |
Token ID | 15753 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
isy | +0.014 |
ly | +0.014 |
acle | +0.014 |
face | +0.014 |
erie | +0.013 |
Neg logit contributions | |
Coc | -0.008 |
Whe | -0.008 |
Ther | -0.007 |
North | -0.007 |
Stri | -0.007 |
Token | liked |
Token ID | 8288 |
Feature activation | +5.24e-02 |
Pos logit contributions | |
acle | +0.650 |
rog | +0.635 |
atively | +0.609 |
arium | +0.584 |
Buzz | +0.561 |
Neg logit contributions | |
bal | -0.526 |
cest | -0.522 |
Tyler | -0.473 |
ird | -0.473 |
Seth | -0.472 |
Token | to |
Token ID | 284 |
Feature activation | +2.25e-02 |
Pos logit contributions | |
acle | +0.108 |
rog | +0.102 |
atively | +0.100 |
arium | +0.096 |
acky | +0.091 |
Neg logit contributions | |
bal | -0.057 |
Coc | -0.052 |
North | -0.052 |
Seth | -0.051 |
Stri | -0.051 |
Token | fly |
Token ID | 6129 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
acle | +0.041 |
arium | +0.040 |
beard | +0.039 |
rus | +0.039 |
atively | +0.039 |
Neg logit contributions | |
bal | -0.025 |
North | -0.022 |
Seth | -0.021 |
Es | -0.021 |
ird | -0.021 |
Token | around |
Token ID | 1088 |
Feature activation | +3.63e-02 |
Pos logit contributions | |
rog | +0.197 |
acle | +0.193 |
atively | +0.181 |
perate | +0.179 |
arium | +0.176 |
Neg logit contributions | |
bal | -0.115 |
cest | -0.112 |
Super | -0.106 |
Seth | -0.097 |
pian | -0.097 |
Token | and |
Token ID | 290 |
Feature activation | +1.91e-02 |
Pos logit contributions | |
acle | +0.067 |
rog | +0.064 |
atively | +0.061 |
arium | +0.059 |
isy | +0.058 |
Neg logit contributions | |
bal | -0.040 |
Super | -0.039 |
cest | -0.037 |
Coc | -0.037 |
North | -0.037 |
Token | Andy |
Token ID | 12382 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
rog | +0.067 |
acle | +0.064 |
arium | +0.064 |
Buzz | +0.062 |
Buzz | +0.060 |
Neg logit contributions | |
bal | -0.067 |
Seth | -0.065 |
Tyler | -0.064 |
ird | -0.063 |
uka | -0.062 |
Token | . |
Token ID | 13 |
Feature activation | +8.80e-03 |
Pos logit contributions | |
rog | +0.222 |
acle | +0.215 |
arium | +0.214 |
Buzz | +0.208 |
Buzz | +0.203 |
Neg logit contributions | |
bal | -0.194 |
Seth | -0.190 |
Tyler | -0.189 |
ird | -0.184 |
cest | -0.180 |
Token | |
Token ID | 220 |
Feature activation | +6.08e-02 |
Pos logit contributions | |
rog | +0.012 |
acle | +0.012 |
Buzz | +0.011 |
arium | +0.011 |
Buzz | +0.011 |
Neg logit contributions | |
bal | -0.015 |
uka | -0.014 |
cest | -0.014 |
ird | -0.014 |
Seth | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | -2.27e-02 |
Pos logit contributions | |
rog | +0.093 |
acle | +0.090 |
arium | +0.089 |
Buzz | +0.086 |
Buzz | +0.086 |
Neg logit contributions | |
bal | -0.092 |
Seth | -0.089 |
Tyler | -0.089 |
ird | -0.087 |
uka | -0.086 |
Token |
|
Token ID | 198 |
Feature activation | -2.57e-02 |
Pos logit contributions | |
bal | +0.032 |
Seth | +0.032 |
Tyler | +0.032 |
ird | +0.031 |
uka | +0.030 |
Neg logit contributions | |
rog | -0.036 |
acle | -0.036 |
arium | -0.035 |
Buzz | -0.033 |
Buzz | -0.033 |
Token | Buzz |
Token ID | 48230 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
bal | +0.041 |
Seth | +0.040 |
Tyler | +0.040 |
ird | +0.039 |
uka | +0.039 |
Neg logit contributions | |
rog | -0.038 |
acle | -0.036 |
arium | -0.035 |
Buzz | -0.034 |
Buzz | -0.034 |
Token | felt |
Token ID | 2936 |
Feature activation | +3.47e-02 |
Pos logit contributions | |
acle | +0.653 |
rog | +0.640 |
arium | +0.624 |
atively | +0.597 |
agged | +0.576 |
Neg logit contributions | |
bal | -0.495 |
cest | -0.456 |
Tyler | -0.455 |
Seth | -0.452 |
Sel | -0.433 |
Token | sorry |
Token ID | 7926 |
Feature activation | +5.93e-02 |
Pos logit contributions | |
rog | +0.051 |
acle | +0.050 |
Buzz | +0.049 |
arium | +0.048 |
Buzz | +0.048 |
Neg logit contributions | |
Seth | -0.053 |
bal | -0.053 |
Tyler | -0.053 |
ird | -0.053 |
isc | -0.052 |
Token | for |
Token ID | 329 |
Feature activation | +3.57e-03 |
Pos logit contributions | |
rog | +0.096 |
arium | +0.093 |
acle | +0.093 |
Buzz | +0.090 |
Buzz | +0.087 |
Neg logit contributions | |
bal | -0.089 |
Tyler | -0.083 |
Seth | -0.083 |
Sel | -0.080 |
cest | -0.080 |
Token | the |
Token ID | 262 |
Feature activation | -3.33e-02 |
Pos logit contributions | |
rog | +0.005 |
arium | +0.005 |
acle | +0.005 |
Buzz | +0.005 |
atively | +0.005 |
Neg logit contributions | |
Tyler | -0.006 |
Seth | -0.006 |
Sel | -0.006 |
bal | -0.005 |
Su | -0.005 |
Token | poor |
Token ID | 3595 |
Feature activation | +2.25e-02 |
Pos logit contributions | |
bal | +0.050 |
roller | +0.046 |
Tyler | +0.046 |
Seth | +0.046 |
laund | +0.045 |
Neg logit contributions | |
rog | -0.053 |
arium | -0.052 |
acle | -0.052 |
atively | -0.048 |
Buzz | -0.048 |
Token | the |
Token ID | 262 |
Feature activation | -7.87e-03 |
Pos logit contributions | |
rog | +0.129 |
acle | +0.125 |
arium | +0.123 |
Buzz | +0.117 |
atively | +0.115 |
Neg logit contributions | |
bal | -0.137 |
Seth | -0.136 |
Tyler | -0.134 |
Sel | -0.130 |
ird | -0.130 |
Token | net |
Token ID | 2010 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
bal | +0.012 |
roller | +0.011 |
Seth | +0.011 |
laund | +0.011 |
cest | +0.011 |
Neg logit contributions | |
rog | -0.012 |
arium | -0.012 |
acle | -0.011 |
atively | -0.011 |
Buzz | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -2.24e-03 |
Pos logit contributions | |
rog | +0.251 |
acle | +0.237 |
arium | +0.236 |
Buzz | +0.232 |
Buzz | +0.227 |
Neg logit contributions | |
bal | -0.225 |
Seth | -0.213 |
Tyler | -0.213 |
ird | -0.211 |
cest | -0.208 |
Token |
|
Token ID | 198 |
Feature activation | -1.80e-02 |
Pos logit contributions | |
bal | +0.004 |
Coc | +0.004 |
Super | +0.003 |
Seth | +0.003 |
Sel | +0.003 |
Neg logit contributions | |
acle | -0.003 |
rog | -0.003 |
arium | -0.003 |
atively | -0.003 |
erie | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -1.89e-02 |
Pos logit contributions | |
uka | +0.013 |
Tyler | +0.013 |
Seth | +0.013 |
Stri | +0.012 |
Coc | +0.012 |
Neg logit contributions | |
acle | -0.041 |
atively | -0.038 |
ly | -0.037 |
rog | -0.037 |
arium | -0.037 |
Token | Buzz |
Token ID | 48230 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
bal | +0.034 |
Cam | +0.032 |
Coc | +0.031 |
laund | +0.031 |
Ron | +0.030 |
Neg logit contributions | |
acle | -0.024 |
work | -0.021 |
arium | -0.020 |
flies | -0.020 |
atively | -0.019 |
Token | told |
Token ID | 1297 |
Feature activation | -5.78e-02 |
Pos logit contributions | |
rog | +0.637 |
acle | +0.631 |
arium | +0.597 |
atively | +0.588 |
Buzz | +0.562 |
Neg logit contributions | |
bal | -0.517 |
cest | -0.506 |
Tyler | -0.478 |
Seth | -0.477 |
ird | -0.474 |
Token | the |
Token ID | 262 |
Feature activation | -7.06e-03 |
Pos logit contributions | |
Seth | +0.036 |
Super | +0.035 |
Gl | +0.034 |
bal | +0.033 |
Roc | +0.033 |
Neg logit contributions | |
ider | -0.133 |
acle | -0.131 |
urious | -0.131 |
arium | -0.127 |
rog | -0.122 |
Token | bird |
Token ID | 6512 |
Feature activation | +7.94e-02 |
Pos logit contributions | |
bal | +0.009 |
North | +0.008 |
Seth | +0.007 |
cest | +0.007 |
roller | +0.007 |
Neg logit contributions | |
acle | -0.013 |
rog | -0.013 |
arium | -0.013 |
atively | -0.013 |
agged | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | -3.72e-03 |
Pos logit contributions | |
acle | +0.168 |
atively | +0.153 |
agged | +0.151 |
rog | +0.149 |
arium | +0.147 |
Neg logit contributions | |
bal | -0.083 |
cest | -0.076 |
Seth | -0.074 |
Su | -0.071 |
Cam | -0.068 |
Token | " |
Token ID | 366 |
Feature activation | -6.08e-02 |
Pos logit contributions | |
bal | +0.004 |
Seth | +0.004 |
Tyler | +0.004 |
Sel | +0.004 |
Es | +0.003 |
Neg logit contributions | |
rog | -0.008 |
arium | -0.007 |
acle | -0.007 |
Buzz | -0.007 |
atively | -0.007 |
Token | was |
Token ID | 373 |
Feature activation | -3.35e-03 |
Pos logit contributions | |
rog | +0.120 |
Buzz | +0.116 |
arium | +0.115 |
acle | +0.110 |
Buzz | +0.109 |
Neg logit contributions | |
bal | -0.225 |
pian | -0.221 |
laund | -0.219 |
Seth | -0.217 |
ird | -0.217 |
Token | a |
Token ID | 257 |
Feature activation | +7.92e-02 |
Pos logit contributions | |
bal | +0.005 |
Tyler | +0.004 |
uka | +0.004 |
roller | +0.004 |
Seth | +0.004 |
Neg logit contributions | |
rog | -0.006 |
acle | -0.006 |
atively | -0.006 |
arium | -0.006 |
flies | -0.005 |
Token | little |
Token ID | 1310 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
rog | +0.092 |
acle | +0.087 |
arium | +0.087 |
Buzz | +0.084 |
Buzz | +0.083 |
Neg logit contributions | |
bal | -0.149 |
Seth | -0.146 |
Tyler | -0.145 |
ird | -0.143 |
isc | -0.142 |
Token | bee |
Token ID | 20697 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
acle | +0.172 |
rog | +0.169 |
arium | +0.164 |
atively | +0.160 |
Buzz | +0.152 |
Neg logit contributions | |
bal | -0.179 |
cest | -0.166 |
Seth | -0.166 |
Tyler | -0.165 |
pian | -0.162 |
Token | named |
Token ID | 3706 |
Feature activation | -9.05e-02 |
Pos logit contributions | |
rog | +0.223 |
acle | +0.214 |
arium | +0.214 |
Buzz | +0.207 |
Buzz | +0.207 |
Neg logit contributions | |
bal | -0.169 |
Seth | -0.165 |
Tyler | -0.164 |
ird | -0.159 |
uka | -0.159 |
Token | Buzz |
Token ID | 15753 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
Su | +0.155 |
Sel | +0.154 |
Seth | +0.153 |
bal | +0.152 |
uka | +0.152 |
Neg logit contributions | |
acle | -0.125 |
atively | -0.115 |
arium | -0.113 |
rog | -0.110 |
agged | -0.102 |
Token | . |
Token ID | 13 |
Feature activation | +5.43e-03 |
Pos logit contributions | |
rog | +0.486 |
acle | +0.467 |
arium | +0.458 |
Buzz | +0.437 |
Buzz | +0.436 |
Neg logit contributions | |
bal | -0.677 |
Seth | -0.658 |
Tyler | -0.654 |
ird | -0.644 |
uka | -0.641 |
Token | Buzz |
Token ID | 15753 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
acle | +0.005 |
erie | +0.004 |
atively | +0.004 |
arium | +0.004 |
urious | +0.004 |
Neg logit contributions | |
bal | -0.010 |
Coc | -0.010 |
North | -0.010 |
Stri | -0.010 |
Sel | -0.010 |
Token | lived |
Token ID | 5615 |
Feature activation | +6.66e-02 |
Pos logit contributions | |
acle | +0.611 |
rog | +0.592 |
atively | +0.567 |
arium | +0.562 |
Buzz | +0.531 |
Neg logit contributions | |
bal | -0.572 |
cest | -0.565 |
uka | -0.519 |
Seth | -0.518 |
ird | -0.515 |
Token | in |
Token ID | 287 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
rog | +0.119 |
acle | +0.118 |
atively | +0.111 |
arium | +0.111 |
beard | +0.103 |
Neg logit contributions | |
bal | -0.085 |
uka | -0.074 |
Super | -0.074 |
cest | -0.072 |
Es | -0.071 |
Token | a |
Token ID | 257 |
Feature activation | +7.26e-02 |
Pos logit contributions | |
acle | +0.184 |
rog | +0.182 |
atively | +0.182 |
arium | +0.171 |
ly | +0.160 |
Neg logit contributions | |
North | -0.123 |
bal | -0.120 |
uka | -0.118 |
Super | -0.117 |
Seth | -0.115 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
acle | +0.006 |
arium | +0.005 |
rus | +0.005 |
beard | +0.005 |
nowhere | +0.005 |
Neg logit contributions | |
bal | -0.004 |
Coc | -0.004 |
Sel | -0.004 |
Super | -0.004 |
Whe | -0.004 |
Token | loved |
Token ID | 6151 |
Feature activation | +3.18e-03 |
Pos logit contributions | |
rog | +0.023 |
acle | +0.022 |
arium | +0.021 |
Buzz | +0.021 |
Buzz | +0.021 |
Neg logit contributions | |
bal | -0.026 |
Seth | -0.025 |
Tyler | -0.025 |
ird | -0.024 |
uka | -0.024 |
Token | Buzz |
Token ID | 15753 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
rog | +0.005 |
acle | +0.005 |
arium | +0.005 |
atively | +0.005 |
Buzz | +0.005 |
Neg logit contributions | |
bal | -0.005 |
Seth | -0.005 |
Tyler | -0.005 |
Sel | -0.004 |
uka | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | +1.76e-03 |
Pos logit contributions | |
acle | +0.706 |
rog | +0.693 |
atively | +0.665 |
arium | +0.655 |
Buzz | +0.636 |
Neg logit contributions | |
bal | -0.482 |
cest | -0.444 |
ird | -0.421 |
Coc | -0.406 |
Tyler | -0.400 |
Token | and |
Token ID | 290 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
rog | +0.003 |
acle | +0.003 |
arium | +0.003 |
Buzz | +0.003 |
Buzz | +0.003 |
Neg logit contributions | |
bal | -0.002 |
Seth | -0.002 |
Tyler | -0.002 |
ird | -0.002 |
cest | -0.002 |
Token | Buzz |
Token ID | 15753 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
acle | +0.026 |
rog | +0.026 |
arium | +0.024 |
agged | +0.023 |
atively | +0.023 |
Neg logit contributions | |
bal | -0.018 |
Seth | -0.017 |
Tyler | -0.017 |
Sel | -0.016 |
Coc | -0.016 |
Token | loved |
Token ID | 6151 |
Feature activation | +3.82e-03 |
Pos logit contributions | |
rog | +0.530 |
arium | +0.509 |
acle | +0.504 |
Buzz | +0.491 |
Buzz | +0.489 |
Neg logit contributions | |
bal | -0.631 |
Seth | -0.622 |
Tyler | -0.617 |
ird | -0.602 |
uka | -0.602 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
rog | +0.006 |
acle | +0.006 |
arium | +0.006 |
atively | +0.005 |
Buzz | +0.005 |
Neg logit contributions | |
bal | -0.006 |
Seth | -0.005 |
Tyler | -0.005 |
Sel | -0.005 |
uka | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +3.59e-03 |
Pos logit contributions | |
rog | +0.031 |
acle | +0.031 |
arium | +0.030 |
atively | +0.029 |
Buzz | +0.029 |
Neg logit contributions | |
bal | -0.022 |
ird | -0.020 |
cest | -0.019 |
Tyler | -0.019 |
Seth | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
acle | +0.007 |
rus | +0.006 |
nowhere | +0.006 |
rog | +0.006 |
arium | +0.006 |
Neg logit contributions | |
bal | -0.004 |
Coc | -0.004 |
isc | -0.004 |
Sel | -0.004 |
Ther | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
uka | +0.011 |
Tyler | +0.011 |
bal | +0.011 |
Seth | +0.010 |
Sel | +0.010 |
Neg logit contributions | |
acle | -0.021 |
rog | -0.020 |
arium | -0.019 |
atively | -0.019 |
flies | -0.019 |
Token | throwing |
Token ID | 9644 |
Feature activation | -5.57e-02 |
Pos logit contributions | |
rog | +0.035 |
acle | +0.034 |
arium | +0.033 |
Buzz | +0.032 |
Buzz | +0.032 |
Neg logit contributions | |
bal | -0.028 |
Seth | -0.027 |
Tyler | -0.027 |
ird | -0.026 |
uka | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
bal | +0.095 |
Tyler | +0.095 |
ird | +0.094 |
Seth | +0.094 |
uka | +0.093 |
Neg logit contributions | |
rog | -0.075 |
acle | -0.070 |
Buzz | -0.069 |
arium | -0.068 |
Buzz | -0.068 |
Token |
|
Token ID | 198 |
Feature activation | -5.43e-03 |
Pos logit contributions | |
rog | +0.018 |
acle | +0.017 |
arium | +0.017 |
Buzz | +0.016 |
Buzz | +0.016 |
Neg logit contributions | |
bal | -0.020 |
Seth | -0.020 |
Tyler | -0.020 |
ird | -0.019 |
uka | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | -5.41e-03 |
Pos logit contributions | |
bal | +0.008 |
Seth | +0.008 |
Tyler | +0.008 |
ird | +0.008 |
uka | +0.008 |
Neg logit contributions | |
rog | -0.009 |
acle | -0.008 |
arium | -0.008 |
Buzz | -0.008 |
Buzz | -0.008 |
Token | " |
Token ID | 1 |
Feature activation | +1.72e-02 |
Pos logit contributions | |
bal | +0.007 |
Seth | +0.007 |
Tyler | +0.007 |
ird | +0.007 |
laund | +0.007 |
Neg logit contributions | |
rog | -0.009 |
acle | -0.009 |
arium | -0.009 |
Buzz | -0.008 |
atively | -0.008 |
Token | Buzz |
Token ID | 48230 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
rog | +0.027 |
Buzz | +0.026 |
acle | +0.025 |
Buzz | +0.025 |
arium | +0.025 |
Neg logit contributions | |
bal | -0.025 |
Tyler | -0.025 |
Seth | -0.025 |
isc | -0.025 |
ird | -0.024 |
Token | ! |
Token ID | 0 |
Feature activation | -9.51e-02 |
Pos logit contributions | |
rog | +0.632 |
acle | +0.619 |
arium | +0.614 |
Buzz | +0.585 |
atively | +0.579 |
Neg logit contributions | |
bal | -0.530 |
Seth | -0.507 |
cest | -0.503 |
Tyler | -0.502 |
ird | -0.494 |
Token | Buzz |
Token ID | 15753 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
bal | +0.147 |
Seth | +0.142 |
Tyler | +0.142 |
laund | +0.142 |
ird | +0.141 |
Neg logit contributions | |
rog | -0.143 |
acle | -0.136 |
Buzz | -0.135 |
arium | -0.132 |
Buzz | -0.131 |
Token | !" |
Token ID | 2474 |
Feature activation | -4.34e-02 |
Pos logit contributions | |
rog | +0.677 |
acle | +0.659 |
arium | +0.652 |
Buzz | +0.622 |
atively | +0.622 |
Neg logit contributions | |
bal | -0.485 |
cest | -0.459 |
Seth | -0.454 |
Tyler | -0.454 |
ird | -0.446 |
Token | a |
Token ID | 257 |
Feature activation | +6.83e-02 |
Pos logit contributions | |
Seth | +0.056 |
Tyler | +0.055 |
bal | +0.053 |
Su | +0.051 |
Sel | +0.051 |
Neg logit contributions | |
rog | -0.079 |
acle | -0.077 |
arium | -0.076 |
atively | -0.070 |
Buzz | -0.069 |
Token | bee |
Token ID | 20697 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
rog | +0.069 |
acle | +0.069 |
arium | +0.069 |
Buzz | +0.060 |
atively | +0.059 |
Neg logit contributions | |
bal | -0.137 |
Seth | -0.135 |
Tyler | -0.133 |
cest | -0.131 |
Sel | -0.130 |
Token | his |
Token ID | 465 |
Feature activation | -7.15e-02 |
Pos logit contributions | |
bal | +0.046 |
ird | +0.046 |
Seth | +0.046 |
laund | +0.045 |
Tyler | +0.045 |
Neg logit contributions | |
acle | -0.036 |
rog | -0.035 |
arium | -0.034 |
Buzz | -0.034 |
atively | -0.033 |
Token | name |
Token ID | 1438 |
Feature activation | -2.86e-02 |
Pos logit contributions | |
bal | +0.111 |
Seth | +0.103 |
Tyler | +0.102 |
isc | +0.101 |
ird | +0.101 |
Neg logit contributions | |
rog | -0.110 |
acle | -0.106 |
arium | -0.105 |
Buzz | -0.103 |
Buzz | -0.101 |
Token | . |
Token ID | 13 |
Feature activation | -2.14e-03 |
Pos logit contributions | |
Seth | +0.048 |
laund | +0.048 |
uka | +0.048 |
Tyler | +0.047 |
isc | +0.047 |
Neg logit contributions | |
acle | -0.038 |
rog | -0.037 |
Buzz | -0.036 |
arium | -0.036 |
atively | -0.034 |
Token | Now |
Token ID | 2735 |
Feature activation | -3.78e-02 |
Pos logit contributions | |
bal | +0.003 |
Coc | +0.002 |
Sel | +0.002 |
isc | +0.002 |
Whe | +0.002 |
Neg logit contributions | |
acle | -0.004 |
rog | -0.004 |
arium | -0.004 |
nowhere | -0.004 |
erie | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | -3.52e-03 |
Pos logit contributions | |
bal | +0.050 |
Seth | +0.046 |
cest | +0.045 |
Tyler | +0.045 |
Sel | +0.044 |
Neg logit contributions | |
rog | -0.067 |
acle | -0.067 |
arium | -0.064 |
Buzz | -0.060 |
atively | -0.059 |
Token | Buzz |
Token ID | 15753 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
bal | +0.004 |
Sel | +0.003 |
Super | +0.003 |
cest | +0.003 |
Coc | +0.003 |
Neg logit contributions | |
acle | -0.007 |
rog | -0.007 |
agged | -0.007 |
arium | -0.006 |
urious | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | -6.06e-03 |
Pos logit contributions | |
rog | +0.524 |
arium | +0.515 |
acle | +0.507 |
Buzz | +0.492 |
Buzz | +0.488 |
Neg logit contributions | |
Seth | -0.625 |
bal | -0.619 |
Tyler | -0.614 |
ird | -0.600 |
laund | -0.599 |
Token | happy |
Token ID | 3772 |
Feature activation | +4.72e-02 |
Pos logit contributions | |
isc | +0.012 |
Seth | +0.011 |
Tyler | +0.011 |
laund | +0.011 |
Coc | +0.011 |
Neg logit contributions | |
Buzz | -0.007 |
acle | -0.007 |
arium | -0.007 |
nowhere | -0.006 |
Marie | -0.006 |
Token | because |
Token ID | 780 |
Feature activation | -5.30e-02 |
Pos logit contributions | |
rog | +0.069 |
acle | +0.066 |
arium | +0.065 |
Buzz | +0.063 |
Buzz | +0.062 |
Neg logit contributions | |
bal | -0.077 |
Seth | -0.074 |
Tyler | -0.074 |
cest | -0.072 |
uka | -0.071 |
Token | he |
Token ID | 339 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
bal | +0.078 |
Seth | +0.076 |
Tyler | +0.076 |
ird | +0.074 |
uka | +0.073 |
Neg logit contributions | |
rog | -0.084 |
acle | -0.081 |
arium | -0.080 |
Buzz | -0.078 |
Buzz | -0.077 |
Token | could |
Token ID | 714 |
Feature activation | -9.10e-02 |
Pos logit contributions | |
Seth | +0.024 |
bal | +0.023 |
Tyler | +0.023 |
laund | +0.023 |
isc | +0.022 |
Neg logit contributions | |
rog | -0.019 |
arium | -0.018 |
acle | -0.018 |
Buzz | -0.018 |
Buzz | -0.017 |
Token | anymore |
Token ID | 7471 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
Seth | +0.013 |
bal | +0.013 |
Tyler | +0.013 |
uka | +0.013 |
ird | +0.013 |
Neg logit contributions | |
rog | -0.008 |
arium | -0.008 |
acle | -0.008 |
Buzz | -0.008 |
Buzz | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +8.36e-03 |
Pos logit contributions | |
rog | +0.142 |
arium | +0.136 |
acle | +0.135 |
Buzz | +0.133 |
Buzz | +0.126 |
Neg logit contributions | |
Seth | -0.169 |
bal | -0.168 |
uka | -0.165 |
Tyler | -0.165 |
laund | -0.164 |
Token | After |
Token ID | 2293 |
Feature activation | +2.72e-02 |
Pos logit contributions | |
acle | +0.014 |
rog | +0.014 |
arium | +0.013 |
atively | +0.013 |
isy | +0.012 |
Neg logit contributions | |
bal | -0.011 |
Sel | -0.011 |
Tyler | -0.011 |
Coc | -0.011 |
Seth | -0.011 |
Token | playing |
Token ID | 2712 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
rog | +0.046 |
acle | +0.045 |
arium | +0.042 |
atively | +0.042 |
Buzz | +0.041 |
Neg logit contributions | |
bal | -0.039 |
Tyler | -0.038 |
Seth | -0.037 |
uka | -0.036 |
Sel | -0.036 |
Token | , |
Token ID | 11 |
Feature activation | +3.05e-03 |
Pos logit contributions | |
bal | +0.026 |
Tyler | +0.024 |
Seth | +0.024 |
ird | +0.024 |
laund | +0.023 |
Neg logit contributions | |
rog | -0.030 |
acle | -0.030 |
arium | -0.029 |
Buzz | -0.028 |
atively | -0.027 |
Token | Buzz |
Token ID | 15753 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
acle | +0.004 |
rog | +0.004 |
agged | +0.004 |
arium | +0.004 |
atively | +0.004 |
Neg logit contributions | |
bal | -0.005 |
Super | -0.005 |
Coc | -0.005 |
Sel | -0.005 |
Stri | -0.005 |
Token | y |
Token ID | 88 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
rog | +0.498 |
acle | +0.490 |
arium | +0.453 |
atively | +0.448 |
Buzz | +0.428 |
Neg logit contributions | |
bal | -0.667 |
cest | -0.646 |
Seth | -0.631 |
Tyler | -0.628 |
ird | -0.617 |
Token | went |
Token ID | 1816 |
Feature activation | -7.18e-02 |
Pos logit contributions | |
rog | +0.203 |
acle | +0.195 |
arium | +0.192 |
Buzz | +0.185 |
Buzz | +0.185 |
Neg logit contributions | |
bal | -0.206 |
Seth | -0.199 |
Tyler | -0.198 |
ird | -0.194 |
uka | -0.193 |
Token | back |
Token ID | 736 |
Feature activation | +1.75e-02 |
Pos logit contributions | |
bal | +0.096 |
Seth | +0.090 |
Tyler | +0.090 |
laund | +0.087 |
uka | +0.086 |
Neg logit contributions | |
rog | -0.126 |
acle | -0.117 |
Buzz | -0.115 |
arium | -0.113 |
atively | -0.111 |
Token | to |
Token ID | 284 |
Feature activation | +2.17e-02 |
Pos logit contributions | |
rog | +0.028 |
acle | +0.027 |
Buzz | +0.026 |
arium | +0.025 |
atively | +0.025 |
Neg logit contributions | |
bal | -0.025 |
Tyler | -0.024 |
Seth | -0.024 |
uka | -0.023 |
laund | -0.023 |
Token | the |
Token ID | 262 |
Feature activation | -4.11e-03 |
Pos logit contributions | |
rog | +0.034 |
acle | +0.033 |
arium | +0.032 |
Buzz | +0.031 |
Buzz | +0.031 |
Neg logit contributions | |
bal | -0.033 |
Seth | -0.032 |
Tyler | -0.031 |
ird | -0.031 |
uka | -0.031 |
Token | she |
Token ID | 673 |
Feature activation | -1.90e-02 |
Pos logit contributions | |
rog | +0.121 |
acle | +0.120 |
arium | +0.115 |
atively | +0.107 |
Buzz | +0.106 |
Neg logit contributions | |
bal | -0.086 |
Seth | -0.081 |
Tyler | -0.080 |
uka | -0.077 |
Sel | -0.077 |
Token | played |
Token ID | 2826 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
bal | +0.030 |
Seth | +0.028 |
Tyler | +0.028 |
ird | +0.028 |
uka | +0.027 |
Neg logit contributions | |
rog | -0.029 |
acle | -0.028 |
arium | -0.027 |
Buzz | -0.026 |
Buzz | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | +3.26e-03 |
Pos logit contributions | |
rog | +0.022 |
acle | +0.021 |
arium | +0.021 |
Buzz | +0.020 |
atively | +0.020 |
Neg logit contributions | |
bal | -0.018 |
Seth | -0.017 |
Tyler | -0.017 |
cest | -0.017 |
ird | -0.016 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
acle | +0.006 |
arium | +0.005 |
rus | +0.005 |
beard | +0.005 |
nowhere | +0.005 |
Neg logit contributions | |
bal | -0.004 |
Coc | -0.004 |
Sel | -0.004 |
Super | -0.004 |
Whe | -0.004 |
Token | loved |
Token ID | 6151 |
Feature activation | +3.18e-03 |
Pos logit contributions | |
rog | +0.023 |
acle | +0.022 |
arium | +0.021 |
Buzz | +0.021 |
Buzz | +0.021 |
Neg logit contributions | |
bal | -0.026 |
Seth | -0.025 |
Tyler | -0.025 |
ird | -0.024 |
uka | -0.024 |
Token | Buzz |
Token ID | 15753 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
rog | +0.005 |
acle | +0.005 |
arium | +0.005 |
atively | +0.005 |
Buzz | +0.005 |
Neg logit contributions | |
bal | -0.005 |
Seth | -0.005 |
Tyler | -0.005 |
Sel | -0.004 |
uka | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | +1.76e-03 |
Pos logit contributions | |
acle | +0.706 |
rog | +0.693 |
atively | +0.665 |
arium | +0.655 |
Buzz | +0.636 |
Neg logit contributions | |
bal | -0.482 |
cest | -0.444 |
ird | -0.421 |
Coc | -0.406 |
Tyler | -0.400 |
Token | and |
Token ID | 290 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
rog | +0.003 |
acle | +0.003 |
arium | +0.003 |
Buzz | +0.003 |
Buzz | +0.003 |
Neg logit contributions | |
bal | -0.002 |
Seth | -0.002 |
Tyler | -0.002 |
ird | -0.002 |
cest | -0.002 |
Token | Buzz |
Token ID | 15753 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
acle | +0.026 |
rog | +0.026 |
arium | +0.024 |
agged | +0.023 |
atively | +0.023 |
Neg logit contributions | |
bal | -0.018 |
Seth | -0.017 |
Tyler | -0.017 |
Sel | -0.016 |
Coc | -0.016 |
Token | loved |
Token ID | 6151 |
Feature activation | +3.82e-03 |
Pos logit contributions | |
rog | +0.530 |
arium | +0.509 |
acle | +0.504 |
Buzz | +0.491 |
Buzz | +0.489 |
Neg logit contributions | |
bal | -0.631 |
Seth | -0.622 |
Tyler | -0.617 |
ird | -0.602 |
uka | -0.602 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
rog | +0.006 |
acle | +0.006 |
arium | +0.006 |
atively | +0.005 |
Buzz | +0.005 |
Neg logit contributions | |
bal | -0.006 |
Seth | -0.005 |
Tyler | -0.005 |
Sel | -0.005 |
uka | -0.005 |
Token | bee |
Token ID | 20697 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
rog | +0.142 |
acle | +0.139 |
arium | +0.135 |
Buzz | +0.128 |
Buzz | +0.128 |
Neg logit contributions | |
bal | -0.162 |
Seth | -0.154 |
Tyler | -0.153 |
ird | -0.151 |
cest | -0.150 |
Token | named |
Token ID | 3706 |
Feature activation | -7.53e-02 |
Pos logit contributions | |
acle | +0.251 |
rog | +0.251 |
atively | +0.238 |
arium | +0.236 |
Buzz | +0.228 |
Neg logit contributions | |
bal | -0.149 |
cest | -0.139 |
ird | -0.134 |
Seth | -0.133 |
Tyler | -0.130 |
Token | Buzz |
Token ID | 15753 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
Su | +0.126 |
Seth | +0.122 |
Sel | +0.122 |
Coc | +0.122 |
bal | +0.120 |
Neg logit contributions | |
acle | -0.108 |
atively | -0.102 |
arium | -0.098 |
rog | -0.096 |
beard | -0.094 |
Token | y |
Token ID | 88 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
acle | +0.612 |
rog | +0.612 |
arium | +0.580 |
atively | +0.567 |
Buzz | +0.558 |
Neg logit contributions | |
bal | -0.544 |
cest | -0.522 |
Seth | -0.514 |
Tyler | -0.506 |
ird | -0.505 |
Token | . |
Token ID | 13 |
Feature activation | +8.81e-03 |
Pos logit contributions | |
acle | +0.235 |
rog | +0.230 |
arium | +0.224 |
atively | +0.221 |
Buzz | +0.215 |
Neg logit contributions | |
bal | -0.160 |
cest | -0.150 |
Seth | -0.150 |
Sel | -0.146 |
Tyler | -0.145 |
Token | Buzz |
Token ID | 15753 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
acle | +0.009 |
erie | +0.009 |
arium | +0.008 |
atively | +0.008 |
work | +0.008 |
Neg logit contributions | |
Coc | -0.016 |
bal | -0.015 |
Whe | -0.015 |
Ther | -0.015 |
Stri | -0.015 |
Token | y |
Token ID | 88 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
acle | +0.548 |
atively | +0.510 |
rog | +0.502 |
arium | +0.466 |
Buzz | +0.439 |
Neg logit contributions | |
cest | -0.643 |
bal | -0.634 |
uka | -0.583 |
isc | -0.576 |
Seth | -0.575 |
Token | loved |
Token ID | 6151 |
Feature activation | +5.28e-03 |
Pos logit contributions | |
acle | +0.229 |
rog | +0.223 |
atively | +0.214 |
arium | +0.212 |
Buzz | +0.199 |
Neg logit contributions | |
bal | -0.175 |
cest | -0.159 |
Sel | -0.157 |
Tyler | -0.155 |
Seth | -0.154 |
Token | to |
Token ID | 284 |
Feature activation | +2.42e-02 |
Pos logit contributions | |
rog | +0.008 |
acle | +0.008 |
arium | +0.008 |
atively | +0.008 |
Buzz | +0.007 |
Neg logit contributions | |
bal | -0.008 |
Seth | -0.008 |
Tyler | -0.008 |
uka | -0.007 |
laund | -0.007 |
Token | rush |
Token ID | 10484 |
Feature activation | -5.06e-02 |
Pos logit contributions | |
acle | +0.037 |
rog | +0.037 |
arium | +0.036 |
atively | +0.034 |
Buzz | +0.032 |
Neg logit contributions | |
bal | -0.037 |
Seth | -0.034 |
ird | -0.033 |
roller | -0.033 |
laund | -0.033 |
Token | from |
Token ID | 422 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
bal | +0.080 |
Seth | +0.075 |
Tyler | +0.075 |
cest | +0.072 |
Sel | +0.072 |
Neg logit contributions | |
rog | -0.077 |
acle | -0.075 |
arium | -0.074 |
Buzz | -0.070 |
Buzz | -0.069 |
Token | ribbon |
Token ID | 29092 |
Feature activation | -4.01e-02 |
Pos logit contributions | |
bal | +0.084 |
Tyler | +0.079 |
Seth | +0.079 |
ird | +0.077 |
laund | +0.076 |
Neg logit contributions | |
rog | -0.092 |
acle | -0.089 |
arium | -0.088 |
Buzz | -0.086 |
Buzz | -0.085 |
Token | for |
Token ID | 329 |
Feature activation | -7.89e-03 |
Pos logit contributions | |
bal | +0.064 |
Seth | +0.061 |
Tyler | +0.061 |
ird | +0.060 |
uka | +0.059 |
Neg logit contributions | |
rog | -0.060 |
acle | -0.057 |
arium | -0.057 |
Buzz | -0.054 |
Buzz | -0.054 |
Token | being |
Token ID | 852 |
Feature activation | +5.68e-02 |
Pos logit contributions | |
bal | +0.011 |
Tyler | +0.011 |
Seth | +0.011 |
uka | +0.011 |
Sel | +0.011 |
Neg logit contributions | |
rog | -0.013 |
arium | -0.012 |
acle | -0.012 |
Buzz | -0.012 |
Buzz | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | -2.32e-02 |
Pos logit contributions | |
rog | +0.068 |
Buzz | +0.068 |
acle | +0.066 |
arium | +0.063 |
Buzz | +0.062 |
Neg logit contributions | |
isc | -0.101 |
bal | -0.099 |
laund | -0.098 |
Seth | -0.097 |
uka | -0.096 |
Token | best |
Token ID | 1266 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
Seth | +0.032 |
Tyler | +0.031 |
bal | +0.031 |
uka | +0.031 |
isc | +0.031 |
Neg logit contributions | |
rog | -0.038 |
acle | -0.036 |
Buzz | -0.035 |
arium | -0.035 |
Buzz | -0.034 |
Token | bal |
Token ID | 3652 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
uka | +0.380 |
Seth | +0.376 |
isc | +0.364 |
laund | +0.363 |
Tyler | +0.362 |
Neg logit contributions | |
rog | -0.265 |
acle | -0.245 |
arium | -0.238 |
True | -0.230 |
Buzz | -0.229 |
Token | ancer |
Token ID | 8250 |
Feature activation | -7.39e-02 |
Pos logit contributions | |
ird | +0.519 |
bal | +0.518 |
uka | +0.501 |
Tyler | +0.487 |
Seth | +0.471 |
Neg logit contributions | |
rog | -0.820 |
acle | -0.815 |
arium | -0.793 |
Buzz | -0.776 |
Buzz | -0.771 |
Token | in |
Token ID | 287 |
Feature activation | +7.69e-02 |
Pos logit contributions | |
bal | +0.113 |
Seth | +0.109 |
Tyler | +0.109 |
ird | +0.107 |
uka | +0.106 |
Neg logit contributions | |
rog | -0.112 |
acle | -0.108 |
arium | -0.107 |
Buzz | -0.103 |
Buzz | -0.103 |
Token | the |
Token ID | 262 |
Feature activation | -2.45e-02 |
Pos logit contributions | |
rog | +0.098 |
Buzz | +0.094 |
arium | +0.094 |
acle | +0.092 |
Buzz | +0.087 |
Neg logit contributions | |
bal | -0.139 |
isc | -0.136 |
ird | -0.132 |
laund | -0.132 |
Seth | -0.130 |
Token | competition |
Token ID | 5449 |
Feature activation | +5.45e-02 |
Pos logit contributions | |
bal | +0.041 |
Seth | +0.041 |
isc | +0.040 |
Tyler | +0.039 |
uka | +0.039 |
Neg logit contributions | |
rog | -0.033 |
arium | -0.032 |
acle | -0.032 |
Buzz | -0.030 |
Buzz | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | -2.30e-02 |
Pos logit contributions | |
rog | +0.070 |
arium | +0.069 |
acle | +0.069 |
Buzz | +0.064 |
atively | +0.062 |
Neg logit contributions | |
uka | -0.093 |
Seth | -0.092 |
bal | -0.092 |
laund | -0.091 |
isc | -0.091 |
Token | made |
Token ID | 925 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
bal | +0.138 |
ird | +0.137 |
uka | +0.136 |
Seth | +0.135 |
Tyler | +0.135 |
Neg logit contributions | |
acle | -0.120 |
rog | -0.119 |
arium | -0.115 |
Buzz | -0.113 |
atively | -0.111 |
Token | him |
Token ID | 683 |
Feature activation | +3.47e-02 |
Pos logit contributions | |
ird | +0.235 |
bal | +0.230 |
cest | +0.228 |
uka | +0.215 |
laund | +0.214 |
Neg logit contributions | |
acle | -0.156 |
rog | -0.152 |
atively | -0.148 |
Buzz | -0.143 |
arium | -0.137 |
Token | squ |
Token ID | 2809 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
rog | +0.054 |
arium | +0.052 |
acle | +0.051 |
Buzz | +0.049 |
Buzz | +0.048 |
Neg logit contributions | |
bal | -0.055 |
Seth | -0.051 |
cest | -0.050 |
Tyler | -0.050 |
Sel | -0.049 |
Token | int |
Token ID | 600 |
Feature activation | +7.98e-02 |
Pos logit contributions | |
bal | +0.017 |
Seth | +0.016 |
Tyler | +0.016 |
ird | +0.016 |
cest | +0.015 |
Neg logit contributions | |
rog | -0.017 |
acle | -0.017 |
arium | -0.017 |
Buzz | -0.016 |
Buzz | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
rog | +0.119 |
acle | +0.115 |
arium | +0.113 |
Buzz | +0.109 |
Buzz | +0.109 |
Neg logit contributions | |
bal | -0.124 |
Seth | -0.120 |
Tyler | -0.120 |
ird | -0.118 |
uka | -0.117 |
Token | Tyler |
Token ID | 14886 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
cest | +0.024 |
bal | +0.021 |
ird | +0.021 |
hairst | +0.020 |
pian | +0.020 |
Neg logit contributions | |
acle | -0.007 |
True | -0.007 |
< | -0.006 |
rog | -0.006 |
upon | -0.006 |
Token | raced |
Token ID | 32897 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
bal | +0.733 |
Seth | +0.714 |
Tyler | +0.708 |
ird | +0.699 |
uka | +0.697 |
Neg logit contributions | |
rog | -0.581 |
acle | -0.557 |
arium | -0.548 |
Buzz | -0.529 |
Buzz | -0.526 |
Token | ahead |
Token ID | 4058 |
Feature activation | -8.00e-03 |
Pos logit contributions | |
ird | +0.248 |
uka | +0.237 |
bal | +0.237 |
cest | +0.236 |
isc | +0.235 |
Neg logit contributions | |
rog | -0.167 |
acle | -0.159 |
Buzz | -0.153 |
atively | -0.148 |
arium | -0.148 |
Token | of |
Token ID | 286 |
Feature activation | -8.45e-02 |
Pos logit contributions | |
isc | +0.015 |
ird | +0.014 |
uka | +0.014 |
bal | +0.014 |
cest | +0.014 |
Neg logit contributions | |
rog | -0.009 |
acle | -0.009 |
Buzz | -0.009 |
arium | -0.008 |
atively | -0.008 |
Token | his |
Token ID | 465 |
Feature activation | -9.15e-02 |
Pos logit contributions | |
bal | +0.168 |
ird | +0.167 |
isc | +0.163 |
cest | +0.159 |
uka | +0.151 |
Neg logit contributions | |
rog | -0.090 |
acle | -0.084 |
Buzz | -0.083 |
arium | -0.079 |
True | -0.075 |
Token | mom |
Token ID | 1995 |
Feature activation | -7.50e-02 |
Pos logit contributions | |
bal | +0.139 |
Seth | +0.136 |
Tyler | +0.134 |
ird | +0.133 |
uka | +0.133 |
Neg logit contributions | |
rog | -0.140 |
acle | -0.136 |
arium | -0.133 |
Buzz | -0.128 |
Buzz | -0.127 |
Token | as |
Token ID | 355 |
Feature activation | +9.09e-02 |
Pos logit contributions | |
cest | +0.109 |
pian | +0.105 |
laund | +0.105 |
ird | +0.105 |
bal | +0.104 |
Neg logit contributions | |
acle | -0.076 |
rog | -0.075 |
Buzz | -0.070 |
arium | -0.070 |
atively | -0.069 |
Token | he |
Token ID | 339 |
Feature activation | -2.85e-02 |
Pos logit contributions | |
first | +0.073 |
next | +0.061 |
upon | +0.059 |
moment | +0.056 |
nowhere | +0.055 |
Neg logit contributions | |
opl | -0.186 |
laund | -0.185 |
hairst | -0.183 |
paramed | -0.182 |
ird | -0.178 |
Token | got |
Token ID | 1392 |
Feature activation | -3.46e-02 |
Pos logit contributions | |
isc | +0.051 |
cest | +0.051 |
bal | +0.051 |
laund | +0.050 |
uka | +0.050 |
Neg logit contributions | |
rog | -0.033 |
acle | -0.031 |
arium | -0.030 |
Buzz | -0.030 |
atively | -0.030 |
Token | closer |
Token ID | 5699 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
bal | +0.067 |
Seth | +0.065 |
Tyler | +0.065 |
uka | +0.063 |
ird | +0.063 |
Neg logit contributions | |
rog | -0.040 |
acle | -0.038 |
arium | -0.038 |
Buzz | -0.035 |
Buzz | -0.035 |
Token | , |
Token ID | 11 |
Feature activation | -1.74e-02 |
Pos logit contributions | |
rog | +0.198 |
acle | +0.191 |
arium | +0.188 |
Buzz | +0.181 |
Buzz | +0.181 |
Neg logit contributions | |
bal | -0.209 |
Seth | -0.203 |
Tyler | -0.202 |
ird | -0.198 |
uka | -0.197 |
Token | Tyler |
Token ID | 14886 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
cest | +0.035 |
ird | +0.034 |
opl | +0.033 |
isc | +0.032 |
bal | +0.032 |
Neg logit contributions | |
nowhere | -0.015 |
acle | -0.014 |
atively | -0.014 |
True | -0.014 |
arium | -0.013 |
Token | felt |
Token ID | 2936 |
Feature activation | +2.05e-02 |
Pos logit contributions | |
bal | +0.726 |
cest | +0.714 |
uka | +0.713 |
laund | +0.708 |
isc | +0.697 |
Neg logit contributions | |
acle | -0.554 |
rog | -0.541 |
atively | -0.511 |
arium | -0.509 |
Buzz | -0.506 |
Token | his |
Token ID | 465 |
Feature activation | -8.51e-02 |
Pos logit contributions | |
rog | +0.023 |
acle | +0.023 |
Buzz | +0.023 |
Buzz | +0.021 |
arium | +0.021 |
Neg logit contributions | |
ird | -0.038 |
isc | -0.038 |
Tyler | -0.037 |
Seth | -0.037 |
laund | -0.037 |
Token | heart |
Token ID | 2612 |
Feature activation | -2.54e-02 |
Pos logit contributions | |
bal | +0.136 |
Tyler | +0.128 |
Seth | +0.128 |
isc | +0.126 |
ird | +0.122 |
Neg logit contributions | |
rog | -0.129 |
arium | -0.128 |
Buzz | -0.123 |
Buzz | -0.119 |
acle | -0.118 |
Token | start |
Token ID | 923 |
Feature activation | -5.18e-02 |
Pos logit contributions | |
bal | +0.036 |
Seth | +0.035 |
Tyler | +0.034 |
ird | +0.034 |
cest | +0.033 |
Neg logit contributions | |
rog | -0.042 |
acle | -0.040 |
arium | -0.040 |
Buzz | -0.039 |
Buzz | -0.038 |
Token | to |
Token ID | 284 |
Feature activation | +6.01e-03 |
Pos logit contributions | |
bal | +0.089 |
uka | +0.088 |
Seth | +0.088 |
Tyler | +0.088 |
ird | +0.087 |
Neg logit contributions | |
rog | -0.067 |
acle | -0.066 |
arium | -0.062 |
Buzz | -0.060 |
atively | -0.060 |
Token | like |
Token ID | 588 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
ird | +0.027 |
uka | +0.026 |
bal | +0.026 |
laund | +0.025 |
isc | +0.025 |
Neg logit contributions | |
acle | -0.021 |
rog | -0.020 |
Buzz | -0.020 |
arium | -0.019 |
atively | -0.018 |
Token | a |
Token ID | 257 |
Feature activation | +5.68e-02 |
Pos logit contributions | |
bal | +0.247 |
ird | +0.244 |
cest | +0.236 |
laund | +0.235 |
isc | +0.235 |
Neg logit contributions | |
rog | -0.182 |
acle | -0.177 |
Buzz | -0.175 |
arium | -0.173 |
Buzz | -0.165 |
Token | giant |
Token ID | 6175 |
Feature activation | -2.29e-02 |
Pos logit contributions | |
rog | +0.076 |
acle | +0.075 |
arium | +0.072 |
Buzz | +0.071 |
Buzz | +0.070 |
Neg logit contributions | |
uka | -0.094 |
Seth | -0.094 |
Tyler | -0.093 |
ird | -0.093 |
isc | -0.093 |
Token | iron |
Token ID | 6953 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
Seth | +0.036 |
bal | +0.036 |
Tyler | +0.036 |
uka | +0.036 |
isc | +0.035 |
Neg logit contributions | |
rog | -0.032 |
acle | -0.031 |
arium | -0.031 |
Buzz | -0.030 |
Buzz | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | -1.55e-02 |
Pos logit contributions | |
Seth | +0.328 |
uka | +0.327 |
Tyler | +0.326 |
bal | +0.325 |
ird | +0.323 |
Neg logit contributions | |
rog | -0.279 |
acle | -0.277 |
arium | -0.258 |
Buzz | -0.254 |
atively | -0.251 |
Token | Tyler |
Token ID | 14886 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
cest | +0.038 |
bal | +0.034 |
ird | +0.033 |
hairst | +0.033 |
pian | +0.033 |
Neg logit contributions | |
True | -0.009 |
acle | -0.008 |
rog | -0.007 |
upon | -0.007 |
< | -0.006 |
Token | couldn |
Token ID | 3521 |
Feature activation | -3.18e-02 |
Pos logit contributions | |
bal | +0.729 |
Seth | +0.708 |
Tyler | +0.702 |
uka | +0.695 |
ird | +0.694 |
Neg logit contributions | |
rog | -0.585 |
acle | -0.562 |
arium | -0.550 |
Buzz | -0.534 |
Buzz | -0.528 |
Token | 't |
Token ID | 470 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
bal | +0.065 |
Seth | +0.064 |
cest | +0.063 |
Tyler | +0.063 |
ird | +0.063 |
Neg logit contributions | |
rog | -0.032 |
acle | -0.030 |
arium | -0.029 |
Buzz | -0.028 |
Buzz | -0.028 |
Token | believe |
Token ID | 1975 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
rog | +0.161 |
acle | +0.154 |
arium | +0.152 |
Buzz | +0.146 |
Buzz | +0.145 |
Neg logit contributions | |
bal | -0.191 |
Seth | -0.186 |
Tyler | -0.185 |
ird | -0.181 |
uka | -0.180 |
Token | his |
Token ID | 465 |
Feature activation | -8.68e-02 |
Pos logit contributions | |
rog | +0.021 |
acle | +0.020 |
Buzz | +0.019 |
arium | +0.019 |
atively | +0.019 |
Neg logit contributions | |
ird | -0.028 |
isc | -0.028 |
bal | -0.028 |
laund | -0.027 |
uka | -0.026 |
Token | eyes |
Token ID | 2951 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
bal | +0.182 |
Seth | +0.178 |
Tyler | +0.177 |
ird | +0.174 |
uka | +0.173 |
Neg logit contributions | |
rog | -0.085 |
acle | -0.079 |
arium | -0.079 |
Buzz | -0.074 |
Buzz | -0.074 |
Token | was |
Token ID | 373 |
Feature activation | -1.73e-02 |
Pos logit contributions | |
rog | +0.120 |
arium | +0.113 |
acle | +0.113 |
Buzz | +0.112 |
Buzz | +0.108 |
Neg logit contributions | |
bal | -0.158 |
Seth | -0.152 |
Tyler | -0.151 |
ird | -0.150 |
laund | -0.150 |
Token | a |
Token ID | 257 |
Feature activation | +5.71e-02 |
Pos logit contributions | |
bal | +0.026 |
Tyler | +0.023 |
Seth | +0.023 |
uka | +0.023 |
ird | +0.022 |
Neg logit contributions | |
acle | -0.030 |
rog | -0.030 |
arium | -0.028 |
atively | -0.028 |
flies | -0.025 |
Token | little |
Token ID | 1310 |
Feature activation | +8.98e-02 |
Pos logit contributions | |
rog | +0.061 |
arium | +0.057 |
acle | +0.056 |
Buzz | +0.056 |
Buzz | +0.055 |
Neg logit contributions | |
bal | -0.112 |
Seth | -0.111 |
Tyler | -0.111 |
ird | -0.109 |
isc | -0.108 |
Token | boy |
Token ID | 2933 |
Feature activation | +2.23e-02 |
Pos logit contributions | |
rog | +0.127 |
acle | +0.125 |
arium | +0.121 |
atively | +0.115 |
Buzz | +0.115 |
Neg logit contributions | |
bal | -0.149 |
Seth | -0.142 |
Tyler | -0.142 |
ird | -0.139 |
cest | -0.139 |
Token | named |
Token ID | 3706 |
Feature activation | -9.72e-02 |
Pos logit contributions | |
rog | +0.036 |
arium | +0.034 |
Buzz | +0.033 |
Buzz | +0.033 |
acle | +0.032 |
Neg logit contributions | |
bal | -0.032 |
Seth | -0.032 |
Tyler | -0.032 |
isc | -0.032 |
uka | -0.031 |
Token | Seth |
Token ID | 20194 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
Tyler | +0.126 |
Seth | +0.124 |
bal | +0.122 |
uka | +0.116 |
Sel | +0.115 |
Neg logit contributions | |
rog | -0.174 |
acle | -0.173 |
arium | -0.169 |
atively | -0.164 |
Buzz | -0.160 |
Token | . |
Token ID | 13 |
Feature activation | -8.49e-03 |
Pos logit contributions | |
bal | +0.635 |
Seth | +0.618 |
Tyler | +0.614 |
ird | +0.603 |
uka | +0.597 |
Neg logit contributions | |
rog | -0.683 |
acle | -0.661 |
arium | -0.654 |
Buzz | -0.629 |
Buzz | -0.628 |
Token | Seth |
Token ID | 20194 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
ird | +0.019 |
bal | +0.018 |
pian | +0.016 |
drummer | +0.016 |
cest | +0.016 |
Neg logit contributions | |
rog | -0.006 |
acle | -0.006 |
One | -0.006 |
agged | -0.006 |
atively | -0.005 |
Token | loved |
Token ID | 6151 |
Feature activation | -7.69e-03 |
Pos logit contributions | |
bal | +0.634 |
Seth | +0.622 |
Tyler | +0.621 |
ird | +0.606 |
uka | +0.604 |
Neg logit contributions | |
rog | -0.675 |
acle | -0.659 |
arium | -0.650 |
Buzz | -0.618 |
Buzz | -0.613 |
Token | watching |
Token ID | 4964 |
Feature activation | -5.44e-02 |
Pos logit contributions | |
ird | +0.014 |
bal | +0.014 |
isc | +0.014 |
Seth | +0.014 |
cest | +0.013 |
Neg logit contributions | |
rog | -0.009 |
Buzz | -0.009 |
arium | -0.009 |
Buzz | -0.008 |
acle | -0.008 |
Token | his |
Token ID | 465 |
Feature activation | -8.18e-02 |
Pos logit contributions | |
ird | +0.097 |
bal | +0.094 |
uka | +0.092 |
isc | +0.092 |
cest | +0.092 |
Neg logit contributions | |
rog | -0.068 |
Buzz | -0.067 |
acle | -0.064 |
arium | -0.063 |
Buzz | -0.062 |
Token | little |
Token ID | 1310 |
Feature activation | +8.98e-02 |
Pos logit contributions | |
rog | +0.061 |
arium | +0.057 |
acle | +0.056 |
Buzz | +0.056 |
Buzz | +0.055 |
Neg logit contributions | |
bal | -0.112 |
Seth | -0.111 |
Tyler | -0.111 |
ird | -0.109 |
isc | -0.108 |
Token | boy |
Token ID | 2933 |
Feature activation | +2.23e-02 |
Pos logit contributions | |
rog | +0.127 |
acle | +0.125 |
arium | +0.121 |
atively | +0.115 |
Buzz | +0.115 |
Neg logit contributions | |
bal | -0.149 |
Seth | -0.142 |
Tyler | -0.142 |
ird | -0.139 |
cest | -0.139 |
Token | named |
Token ID | 3706 |
Feature activation | -9.72e-02 |
Pos logit contributions | |
rog | +0.036 |
arium | +0.034 |
Buzz | +0.033 |
Buzz | +0.033 |
acle | +0.032 |
Neg logit contributions | |
bal | -0.032 |
Seth | -0.032 |
Tyler | -0.032 |
isc | -0.032 |
uka | -0.031 |
Token | Seth |
Token ID | 20194 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
Tyler | +0.126 |
Seth | +0.124 |
bal | +0.122 |
uka | +0.116 |
Sel | +0.115 |
Neg logit contributions | |
rog | -0.174 |
acle | -0.173 |
arium | -0.169 |
atively | -0.164 |
Buzz | -0.160 |
Token | . |
Token ID | 13 |
Feature activation | -8.49e-03 |
Pos logit contributions | |
bal | +0.635 |
Seth | +0.618 |
Tyler | +0.614 |
ird | +0.603 |
uka | +0.597 |
Neg logit contributions | |
rog | -0.683 |
acle | -0.661 |
arium | -0.654 |
Buzz | -0.629 |
Buzz | -0.628 |
Token | Seth |
Token ID | 20194 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
ird | +0.019 |
bal | +0.018 |
pian | +0.016 |
drummer | +0.016 |
cest | +0.016 |
Neg logit contributions | |
rog | -0.006 |
acle | -0.006 |
One | -0.006 |
agged | -0.006 |
atively | -0.005 |
Token | loved |
Token ID | 6151 |
Feature activation | -7.69e-03 |
Pos logit contributions | |
bal | +0.634 |
Seth | +0.622 |
Tyler | +0.621 |
ird | +0.606 |
uka | +0.604 |
Neg logit contributions | |
rog | -0.675 |
acle | -0.659 |
arium | -0.650 |
Buzz | -0.618 |
Buzz | -0.613 |
Token | watching |
Token ID | 4964 |
Feature activation | -5.44e-02 |
Pos logit contributions | |
ird | +0.014 |
bal | +0.014 |
isc | +0.014 |
Seth | +0.014 |
cest | +0.013 |
Neg logit contributions | |
rog | -0.009 |
Buzz | -0.009 |
arium | -0.009 |
Buzz | -0.008 |
acle | -0.008 |
Token | his |
Token ID | 465 |
Feature activation | -8.18e-02 |
Pos logit contributions | |
ird | +0.097 |
bal | +0.094 |
uka | +0.092 |
isc | +0.092 |
cest | +0.092 |
Neg logit contributions | |
rog | -0.068 |
Buzz | -0.067 |
acle | -0.064 |
arium | -0.063 |
Buzz | -0.062 |
Token | favorite |
Token ID | 4004 |
Feature activation | -2.72e-02 |
Pos logit contributions | |
bal | +0.123 |
Seth | +0.121 |
Tyler | +0.119 |
ird | +0.119 |
uka | +0.118 |
Neg logit contributions | |
rog | -0.125 |
acle | -0.120 |
arium | -0.119 |
Buzz | -0.115 |
Buzz | -0.114 |
Token | show |
Token ID | 905 |
Feature activation | -8.47e-02 |
Pos logit contributions | |
bal | +0.042 |
Seth | +0.041 |
Tyler | +0.041 |
ird | +0.040 |
uka | +0.040 |
Neg logit contributions | |
rog | -0.041 |
arium | -0.039 |
acle | -0.039 |
Buzz | -0.038 |
Buzz | -0.037 |
Token | show |
Token ID | 905 |
Feature activation | -8.43e-02 |
Pos logit contributions | |
rog | +0.055 |
Buzz | +0.051 |
arium | +0.051 |
acle | +0.051 |
Buzz | +0.050 |
Neg logit contributions | |
bal | -0.037 |
laund | -0.036 |
Tyler | -0.035 |
pian | -0.035 |
sax | -0.034 |
Token | started |
Token ID | 2067 |
Feature activation | -2.57e-02 |
Pos logit contributions | |
bal | +0.146 |
Seth | +0.144 |
uka | +0.143 |
Tyler | +0.143 |
isc | +0.142 |
Neg logit contributions | |
rog | -0.104 |
arium | -0.103 |
acle | -0.102 |
atively | -0.095 |
Buzz | -0.095 |
Token | to |
Token ID | 284 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
bal | +0.046 |
ird | +0.046 |
uka | +0.045 |
Seth | +0.044 |
isc | +0.044 |
Neg logit contributions | |
rog | -0.031 |
arium | -0.030 |
acle | -0.029 |
Buzz | -0.029 |
Buzz | -0.027 |
Token | freeze |
Token ID | 16611 |
Feature activation | -5.28e-02 |
Pos logit contributions | |
rog | +0.017 |
acle | +0.016 |
arium | +0.016 |
Buzz | +0.015 |
Buzz | +0.015 |
Neg logit contributions | |
bal | -0.018 |
Seth | -0.017 |
Tyler | -0.017 |
ird | -0.017 |
uka | -0.017 |
Token | ! |
Token ID | 0 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
bal | +0.089 |
ird | +0.089 |
uka | +0.086 |
isc | +0.085 |
Seth | +0.085 |
Neg logit contributions | |
rog | -0.072 |
acle | -0.069 |
arium | -0.067 |
Buzz | -0.066 |
atively | -0.064 |
Token | Seth |
Token ID | 20194 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
cest | +0.251 |
pian | +0.239 |
ird | +0.233 |
bal | +0.232 |
hairst | +0.221 |
Neg logit contributions | |
rog | -0.084 |
acle | -0.075 |
One | -0.075 |
< | -0.069 |
agged | -0.067 |
Token | was |
Token ID | 373 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
bal | +0.686 |
Seth | +0.669 |
Tyler | +0.667 |
ird | +0.653 |
uka | +0.647 |
Neg logit contributions | |
rog | -0.631 |
acle | -0.607 |
arium | -0.599 |
Buzz | -0.573 |
Buzz | -0.572 |
Token | very |
Token ID | 845 |
Feature activation | -4.74e-02 |
Pos logit contributions | |
bal | +0.023 |
Seth | +0.022 |
Tyler | +0.022 |
ird | +0.022 |
isc | +0.022 |
Neg logit contributions | |
rog | -0.022 |
acle | -0.021 |
arium | -0.021 |
Buzz | -0.020 |
Buzz | -0.020 |
Token | surprised |
Token ID | 6655 |
Feature activation | -4.28e-02 |
Pos logit contributions | |
bal | +0.078 |
Seth | +0.076 |
Tyler | +0.076 |
ird | +0.074 |
uka | +0.074 |
Neg logit contributions | |
rog | -0.067 |
acle | -0.065 |
arium | -0.063 |
Buzz | -0.061 |
Buzz | -0.061 |
Token | and |
Token ID | 290 |
Feature activation | +6.69e-03 |
Pos logit contributions | |
ird | +0.070 |
bal | +0.070 |
Seth | +0.068 |
uka | +0.068 |
Tyler | +0.068 |
Neg logit contributions | |
rog | -0.060 |
acle | -0.057 |
arium | -0.057 |
Buzz | -0.055 |
Buzz | -0.053 |
Token | felt |
Token ID | 2936 |
Feature activation | +2.39e-02 |
Pos logit contributions | |
rog | +0.010 |
acle | +0.009 |
arium | +0.009 |
Buzz | +0.009 |
Buzz | +0.009 |
Neg logit contributions | |
bal | -0.011 |
Seth | -0.010 |
Tyler | -0.010 |
ird | -0.010 |
uka | -0.010 |
Token | was |
Token ID | 373 |
Feature activation | -1.80e-02 |
Pos logit contributions | |
bal | +0.055 |
Seth | +0.053 |
Tyler | +0.053 |
ird | +0.052 |
uka | +0.051 |
Neg logit contributions | |
rog | -0.053 |
acle | -0.051 |
arium | -0.050 |
Buzz | -0.048 |
Buzz | -0.048 |
Token | a |
Token ID | 257 |
Feature activation | +5.65e-02 |
Pos logit contributions | |
bal | +0.030 |
ird | +0.030 |
uka | +0.029 |
Seth | +0.029 |
isc | +0.029 |
Neg logit contributions | |
rog | -0.024 |
acle | -0.024 |
Buzz | -0.023 |
arium | -0.023 |
Buzz | -0.021 |
Token | giant |
Token ID | 6175 |
Feature activation | -2.09e-02 |
Pos logit contributions | |
rog | +0.077 |
acle | +0.074 |
arium | +0.071 |
Buzz | +0.069 |
Buzz | +0.069 |
Neg logit contributions | |
Seth | -0.094 |
Tyler | -0.093 |
bal | -0.092 |
uka | -0.092 |
ird | -0.091 |
Token | fish |
Token ID | 5916 |
Feature activation | +9.90e-02 |
Pos logit contributions | |
Seth | +0.033 |
uka | +0.032 |
isc | +0.032 |
bal | +0.032 |
Tyler | +0.032 |
Neg logit contributions | |
rog | -0.029 |
acle | -0.029 |
arium | -0.028 |
Buzz | -0.027 |
Buzz | -0.026 |
Token | ! |
Token ID | 0 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
rog | +0.149 |
acle | +0.145 |
arium | +0.142 |
Buzz | +0.137 |
Buzz | +0.134 |
Neg logit contributions | |
bal | -0.150 |
Seth | -0.149 |
Tyler | -0.147 |
uka | -0.146 |
laund | -0.145 |
Token | Tyler |
Token ID | 14886 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
cest | +0.273 |
bal | +0.233 |
pian | +0.232 |
ird | +0.232 |
hairst | +0.222 |
Neg logit contributions | |
True | -0.087 |
acle | -0.085 |
rog | -0.076 |
< | -0.067 |
atively | -0.065 |
Token | gasped |
Token ID | 45236 |
Feature activation | +7.03e-02 |
Pos logit contributions | |
bal | +0.656 |
Seth | +0.642 |
Tyler | +0.640 |
ird | +0.614 |
Sel | +0.613 |
Neg logit contributions | |
rog | -0.658 |
arium | -0.648 |
acle | -0.630 |
Buzz | -0.604 |
Buzz | -0.596 |
Token | with |
Token ID | 351 |
Feature activation | +5.30e-03 |
Pos logit contributions | |
rog | +0.114 |
arium | +0.112 |
Buzz | +0.108 |
acle | +0.108 |
Buzz | +0.102 |
Neg logit contributions | |
bal | -0.103 |
Tyler | -0.100 |
Seth | -0.100 |
Sel | -0.094 |
cest | -0.093 |
Token | delight |
Token ID | 10974 |
Feature activation | -6.88e-02 |
Pos logit contributions | |
rog | +0.008 |
acle | +0.008 |
arium | +0.007 |
Buzz | +0.007 |
Buzz | +0.007 |
Neg logit contributions | |
bal | -0.009 |
Seth | -0.008 |
ird | -0.008 |
uka | -0.008 |
Tyler | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | -3.14e-03 |
Pos logit contributions | |
bal | +0.104 |
Seth | +0.100 |
Tyler | +0.100 |
cest | +0.096 |
Sel | +0.095 |
Neg logit contributions | |
rog | -0.109 |
arium | -0.105 |
Buzz | -0.103 |
acle | -0.103 |
Buzz | -0.100 |
Token | his |
Token ID | 465 |
Feature activation | -8.42e-02 |
Pos logit contributions | |
bal | +0.006 |
laund | +0.006 |
isc | +0.005 |
ird | +0.005 |
uka | +0.005 |
Neg logit contributions | |
acle | -0.004 |
Buzz | -0.004 |
rog | -0.004 |
atively | -0.004 |
arium | -0.004 |
Token | he |
Token ID | 339 |
Feature activation | -3.15e-02 |
Pos logit contributions | |
ird | +0.007 |
bal | +0.007 |
isc | +0.007 |
uka | +0.007 |
laund | +0.007 |
Neg logit contributions | |
acle | -0.006 |
Buzz | -0.006 |
arium | -0.006 |
rog | -0.006 |
atively | -0.005 |
Token | made |
Token ID | 925 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
bal | +0.052 |
Seth | +0.051 |
Tyler | +0.051 |
laund | +0.050 |
ird | +0.050 |
Neg logit contributions | |
acle | -0.041 |
rog | -0.041 |
arium | -0.040 |
Buzz | -0.040 |
Buzz | -0.039 |
Token | a |
Token ID | 257 |
Feature activation | +5.27e-02 |
Pos logit contributions | |
bal | +0.223 |
Seth | +0.217 |
Tyler | +0.216 |
ird | +0.212 |
uka | +0.210 |
Neg logit contributions | |
rog | -0.195 |
acle | -0.188 |
arium | -0.185 |
Buzz | -0.178 |
Buzz | -0.177 |
Token | bridge |
Token ID | 7696 |
Feature activation | -3.99e-02 |
Pos logit contributions | |
rog | +0.074 |
acle | +0.072 |
arium | +0.070 |
Buzz | +0.068 |
Buzz | +0.068 |
Neg logit contributions | |
bal | -0.085 |
Seth | -0.084 |
Tyler | -0.084 |
ird | -0.083 |
uka | -0.083 |
Token | ! |
Token ID | 0 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
bal | +0.062 |
Seth | +0.061 |
Tyler | +0.061 |
ird | +0.059 |
uka | +0.059 |
Neg logit contributions | |
rog | -0.059 |
acle | -0.057 |
arium | -0.056 |
Buzz | -0.054 |
Buzz | -0.053 |
Token | Tyler |
Token ID | 14886 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
cest | +0.229 |
bal | +0.222 |
laund | +0.216 |
pian | +0.216 |
ird | +0.214 |
Neg logit contributions | |
rog | -0.157 |
Buzz | -0.154 |
acle | -0.148 |
Buzz | -0.143 |
arium | -0.141 |
Token | was |
Token ID | 373 |
Feature activation | -2.68e-02 |
Pos logit contributions | |
bal | +0.722 |
Seth | +0.701 |
Tyler | +0.691 |
uka | +0.688 |
isc | +0.681 |
Neg logit contributions | |
rog | -0.583 |
acle | -0.559 |
arium | -0.546 |
Buzz | -0.533 |
Buzz | -0.530 |
Token | so |
Token ID | 523 |
Feature activation | -8.68e-02 |
Pos logit contributions | |
isc | +0.052 |
bal | +0.048 |
ird | +0.048 |
uka | +0.047 |
laund | +0.047 |
Neg logit contributions | |
Buzz | -0.029 |
acle | -0.029 |
rog | -0.026 |
nowhere | -0.025 |
atively | -0.024 |
Token | happy |
Token ID | 3772 |
Feature activation | +3.29e-02 |
Pos logit contributions | |
isc | +0.159 |
Tyler | +0.157 |
laund | +0.156 |
Seth | +0.156 |
pian | +0.155 |
Neg logit contributions | |
acle | -0.097 |
Buzz | -0.096 |
rog | -0.095 |
Buzz | -0.090 |
atively | -0.087 |
Token | . |
Token ID | 13 |
Feature activation | -2.33e-02 |
Pos logit contributions | |
rog | +0.048 |
acle | +0.046 |
arium | +0.046 |
Buzz | +0.044 |
Buzz | +0.043 |
Neg logit contributions | |
bal | -0.052 |
Seth | -0.051 |
ird | -0.050 |
Tyler | -0.050 |
uka | -0.050 |
Token | He |
Token ID | 679 |
Feature activation | -7.91e-03 |
Pos logit contributions | |
cest | +0.058 |
pian | +0.056 |
ird | +0.055 |
bal | +0.054 |
hairst | +0.052 |
Neg logit contributions | |
rog | -0.013 |
True | -0.013 |
Buzz | -0.013 |
acle | -0.011 |
Freddy | -0.011 |
Token | all |
Token ID | 477 |
Feature activation | +3.48e-02 |
Pos logit contributions | |
cest | +0.037 |
opl | +0.034 |
North | +0.033 |
skysc | +0.032 |
isc | +0.031 |
Neg logit contributions | |
upon | -0.014 |
atively | -0.012 |
first | -0.012 |
True | -0.012 |
nowhere | -0.012 |
Token | of |
Token ID | 286 |
Feature activation | -7.64e-02 |
Pos logit contributions | |
arium | +0.041 |
rog | +0.041 |
Buzz | +0.038 |
acle | +0.036 |
atively | +0.035 |
Neg logit contributions | |
bal | -0.060 |
laund | -0.059 |
isc | -0.058 |
ird | -0.058 |
cest | -0.058 |
Token | a |
Token ID | 257 |
Feature activation | +5.60e-02 |
Pos logit contributions | |
bal | +0.132 |
cest | +0.128 |
ird | +0.124 |
isc | +0.122 |
laund | +0.118 |
Neg logit contributions | |
rog | -0.103 |
Buzz | -0.096 |
arium | -0.096 |
acle | -0.092 |
Buzz | -0.089 |
Token | sudden |
Token ID | 4802 |
Feature activation | -2.46e-02 |
Pos logit contributions | |
rog | +0.082 |
acle | +0.079 |
arium | +0.078 |
Buzz | +0.076 |
Buzz | +0.075 |
Neg logit contributions | |
bal | -0.087 |
Seth | -0.086 |
Tyler | -0.085 |
uka | -0.084 |
isc | -0.084 |
Token | , |
Token ID | 11 |
Feature activation | -1.78e-02 |
Pos logit contributions | |
cest | +0.043 |
bal | +0.042 |
uka | +0.042 |
laund | +0.042 |
isc | +0.041 |
Neg logit contributions | |
rog | -0.028 |
Buzz | -0.028 |
arium | -0.028 |
acle | -0.027 |
atively | -0.026 |
Token | Tyler |
Token ID | 14886 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
cest | +0.031 |
opl | +0.028 |
bal | +0.028 |
North | +0.027 |
ird | +0.027 |
Neg logit contributions | |
arium | -0.020 |
nowhere | -0.020 |
rog | -0.019 |
atively | -0.019 |
True | -0.019 |
Token | saw |
Token ID | 2497 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
bal | +0.725 |
Seth | +0.706 |
cest | +0.704 |
uka | +0.700 |
laund | +0.700 |
Neg logit contributions | |
acle | -0.549 |
rog | -0.544 |
arium | -0.533 |
Buzz | -0.517 |
atively | -0.505 |
Token | a |
Token ID | 257 |
Feature activation | +5.50e-02 |
Pos logit contributions | |
rog | +0.013 |
acle | +0.012 |
Buzz | +0.012 |
arium | +0.012 |
atively | +0.011 |
Neg logit contributions | |
bal | -0.023 |
ird | -0.023 |
cest | -0.022 |
isc | -0.022 |
Seth | -0.022 |
Token | big |
Token ID | 1263 |
Feature activation | -7.49e-02 |
Pos logit contributions | |
rog | +0.077 |
acle | +0.075 |
arium | +0.073 |
Buzz | +0.070 |
Buzz | +0.070 |
Neg logit contributions | |
bal | -0.090 |
Seth | -0.088 |
Tyler | -0.087 |
uka | -0.086 |
ird | -0.086 |
Token | black |
Token ID | 2042 |
Feature activation | -4.86e-02 |
Pos logit contributions | |
bal | +0.118 |
Seth | +0.114 |
Tyler | +0.114 |
ird | +0.111 |
cest | +0.110 |
Neg logit contributions | |
rog | -0.111 |
acle | -0.106 |
arium | -0.105 |
Buzz | -0.102 |
Buzz | -0.101 |
Token | cloud |
Token ID | 6279 |
Feature activation | +1.84e-02 |
Pos logit contributions | |
bal | +0.076 |
Tyler | +0.070 |
ird | +0.070 |
Seth | +0.070 |
roller | +0.069 |
Neg logit contributions | |
rog | -0.074 |
arium | -0.072 |
acle | -0.070 |
Buzz | -0.070 |
Buzz | -0.068 |
Token | Next |
Token ID | 7406 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
bal | +0.026 |
Seth | +0.025 |
Tyler | +0.025 |
ird | +0.024 |
uka | +0.024 |
Neg logit contributions | |
rog | -0.021 |
acle | -0.020 |
arium | -0.020 |
Buzz | -0.019 |
Buzz | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | -2.61e-02 |
Pos logit contributions | |
rog | +0.199 |
acle | +0.191 |
arium | +0.190 |
Buzz | +0.182 |
Buzz | +0.179 |
Neg logit contributions | |
bal | -0.223 |
Seth | -0.216 |
Tyler | -0.213 |
ird | -0.211 |
uka | -0.211 |
Token | Bobby |
Token ID | 17155 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
bal | +0.043 |
Seth | +0.042 |
uka | +0.042 |
isc | +0.042 |
cest | +0.042 |
Neg logit contributions | |
rog | -0.036 |
arium | -0.035 |
acle | -0.035 |
Buzz | -0.033 |
Buzz | -0.032 |
Token | and |
Token ID | 290 |
Feature activation | -6.76e-03 |
Pos logit contributions | |
bal | +0.018 |
Seth | +0.017 |
uka | +0.017 |
ird | +0.017 |
laund | +0.017 |
Neg logit contributions | |
rog | -0.014 |
acle | -0.014 |
arium | -0.014 |
Buzz | -0.014 |
Buzz | -0.013 |
Token | then |
Token ID | 788 |
Feature activation | +2.96e-02 |
Pos logit contributions | |
bal | +0.012 |
Seth | +0.011 |
ird | +0.011 |
uka | +0.011 |
isc | +0.011 |
Neg logit contributions | |
rog | -0.009 |
arium | -0.008 |
Buzz | -0.008 |
acle | -0.008 |
Buzz | -0.008 |
Token | Tyler |
Token ID | 14886 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
Buzz | +0.038 |
rog | +0.037 |
arium | +0.037 |
acle | +0.034 |
Buzz | +0.034 |
Neg logit contributions | |
isc | -0.048 |
cest | -0.048 |
uka | -0.047 |
laund | -0.047 |
bal | -0.047 |
Token | . |
Token ID | 13 |
Feature activation | -2.07e-02 |
Pos logit contributions | |
bal | +0.743 |
cest | +0.729 |
uka | +0.725 |
Seth | +0.716 |
laund | +0.702 |
Neg logit contributions | |
rog | -0.515 |
arium | -0.488 |
acle | -0.487 |
Buzz | -0.482 |
Buzz | -0.469 |
Token |
|
Token ID | 198 |
Feature activation | -3.39e-02 |
Pos logit contributions | |
bal | +0.037 |
cest | +0.035 |
Seth | +0.035 |
ird | +0.035 |
uka | +0.035 |
Neg logit contributions | |
rog | -0.027 |
acle | -0.026 |
arium | -0.025 |
Buzz | -0.025 |
Buzz | -0.024 |
Token |
|
Token ID | 198 |
Feature activation | -3.39e-02 |
Pos logit contributions | |
bal | +0.056 |
Seth | +0.054 |
cest | +0.054 |
isc | +0.053 |
ird | +0.053 |
Neg logit contributions | |
rog | -0.048 |
arium | -0.046 |
acle | -0.045 |
Buzz | -0.045 |
Buzz | -0.044 |
Token | When |
Token ID | 2215 |
Feature activation | -3.61e-02 |
Pos logit contributions | |
bal | +0.056 |
Seth | +0.055 |
isc | +0.054 |
Tyler | +0.053 |
cest | +0.053 |
Neg logit contributions | |
rog | -0.047 |
arium | -0.045 |
Buzz | -0.045 |
acle | -0.044 |
Buzz | -0.043 |
Token | it |
Token ID | 340 |
Feature activation | -3.63e-02 |
Pos logit contributions | |
bal | +0.062 |
Seth | +0.060 |
ird | +0.060 |
cest | +0.059 |
uka | +0.059 |
Neg logit contributions | |
rog | -0.048 |
arium | -0.046 |
acle | -0.046 |
Buzz | -0.045 |
Buzz | -0.043 |
Token | so |
Token ID | 523 |
Feature activation | -8.32e-02 |
Pos logit contributions | |
bal | +0.008 |
Seth | +0.008 |
Tyler | +0.007 |
cest | +0.007 |
laund | +0.007 |
Neg logit contributions | |
rog | -0.008 |
arium | -0.008 |
acle | -0.008 |
Buzz | -0.007 |
Buzz | -0.007 |
Token | big |
Token ID | 1263 |
Feature activation | -7.50e-02 |
Pos logit contributions | |
bal | +0.107 |
Seth | +0.101 |
Tyler | +0.099 |
Sel | +0.098 |
cest | +0.098 |
Neg logit contributions | |
rog | -0.153 |
arium | -0.148 |
acle | -0.143 |
atively | -0.133 |
Buzz | -0.132 |
Token | and |
Token ID | 290 |
Feature activation | +4.32e-04 |
Pos logit contributions | |
uka | +0.139 |
ird | +0.138 |
bal | +0.137 |
isc | +0.137 |
Seth | +0.136 |
Neg logit contributions | |
acle | -0.085 |
arium | -0.083 |
Buzz | -0.082 |
rog | -0.082 |
atively | -0.075 |
Token | bright |
Token ID | 6016 |
Feature activation | +8.20e-03 |
Pos logit contributions | |
rog | +0.001 |
acle | +0.001 |
arium | +0.001 |
Buzz | +0.001 |
Buzz | +0.001 |
Neg logit contributions | |
bal | -0.001 |
Seth | -0.001 |
Tyler | -0.001 |
ird | -0.001 |
uka | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | +9.57e-04 |
Pos logit contributions | |
rog | +0.013 |
acle | +0.012 |
arium | +0.012 |
Buzz | +0.011 |
Buzz | +0.011 |
Neg logit contributions | |
bal | -0.013 |
Seth | -0.012 |
Tyler | -0.012 |
ird | -0.012 |
cest | -0.012 |
Token | Tyler |
Token ID | 14886 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
rog | +0.001 |
acle | +0.001 |
arium | +0.001 |
Buzz | +0.001 |
Buzz | +0.001 |
Neg logit contributions | |
bal | -0.001 |
Seth | -0.001 |
Tyler | -0.001 |
ird | -0.001 |
uka | -0.001 |
Token | was |
Token ID | 373 |
Feature activation | -2.46e-02 |
Pos logit contributions | |
bal | +0.673 |
Seth | +0.653 |
Tyler | +0.649 |
ird | +0.638 |
uka | +0.631 |
Neg logit contributions | |
rog | -0.637 |
acle | -0.612 |
arium | -0.606 |
Buzz | -0.579 |
Buzz | -0.579 |
Token | scared |
Token ID | 12008 |
Feature activation | -1.34e-03 |
Pos logit contributions | |
bal | +0.035 |
Seth | +0.033 |
Tyler | +0.033 |
ird | +0.032 |
cest | +0.032 |
Neg logit contributions | |
rog | -0.041 |
arium | -0.040 |
acle | -0.039 |
Buzz | -0.038 |
Buzz | -0.037 |
Token | . |
Token ID | 13 |
Feature activation | -9.41e-03 |
Pos logit contributions | |
uka | +0.002 |
bal | +0.002 |
ird | +0.002 |
isc | +0.002 |
laund | +0.002 |
Neg logit contributions | |
rog | -0.002 |
Buzz | -0.002 |
acle | -0.002 |
arium | -0.001 |
Buzz | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -3.05e-02 |
Pos logit contributions | |
cest | +0.021 |
bal | +0.019 |
ird | +0.019 |
pian | +0.018 |
hairst | +0.018 |
Neg logit contributions | |
rog | -0.009 |
acle | -0.008 |
True | -0.008 |
Buzz | -0.008 |
arium | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -3.17e-02 |
Pos logit contributions | |
cest | +0.065 |
bal | +0.064 |
pian | +0.061 |
laund | +0.059 |
isc | +0.059 |
Neg logit contributions | |
rog | -0.031 |
Buzz | -0.028 |
Buzz | -0.025 |
acle | -0.025 |
arium | -0.024 |
Token | lot |
Token ID | 1256 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
rog | +0.090 |
acle | +0.087 |
arium | +0.087 |
Buzz | +0.084 |
Buzz | +0.083 |
Neg logit contributions | |
Seth | -0.074 |
bal | -0.074 |
Tyler | -0.073 |
uka | -0.071 |
cest | -0.071 |
Token | of |
Token ID | 286 |
Feature activation | -7.22e-02 |
Pos logit contributions | |
bal | +0.147 |
Seth | +0.136 |
ird | +0.136 |
Tyler | +0.134 |
laund | +0.132 |
Neg logit contributions | |
rog | -0.205 |
acle | -0.201 |
arium | -0.196 |
Buzz | -0.190 |
Buzz | -0.190 |
Token | fun |
Token ID | 1257 |
Feature activation | -4.65e-02 |
Pos logit contributions | |
bal | +0.112 |
Seth | +0.109 |
Tyler | +0.109 |
ird | +0.106 |
uka | +0.106 |
Neg logit contributions | |
rog | -0.109 |
acle | -0.104 |
arium | -0.103 |
Buzz | -0.100 |
Buzz | -0.099 |
Token | today |
Token ID | 1909 |
Feature activation | -1.97e-02 |
Pos logit contributions | |
bal | +0.073 |
Seth | +0.071 |
Tyler | +0.070 |
ird | +0.069 |
uka | +0.069 |
Neg logit contributions | |
rog | -0.069 |
acle | -0.067 |
arium | -0.066 |
Buzz | -0.063 |
Buzz | -0.063 |
Token | . |
Token ID | 13 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
uka | +0.036 |
Seth | +0.035 |
bal | +0.035 |
Tyler | +0.035 |
isc | +0.035 |
Neg logit contributions | |
arium | -0.023 |
rog | -0.022 |
acle | -0.022 |
Buzz | -0.021 |
atively | -0.020 |
Token | Tyler |
Token ID | 14886 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
cest | +0.031 |
bal | +0.028 |
hairst | +0.027 |
ird | +0.026 |
laund | +0.026 |
Neg logit contributions | |
rog | -0.010 |
arium | -0.010 |
True | -0.010 |
Buzz | -0.009 |
acle | -0.009 |
Token | wanted |
Token ID | 2227 |
Feature activation | +2.52e-02 |
Pos logit contributions | |
bal | +0.684 |
Seth | +0.665 |
Tyler | +0.662 |
ird | +0.649 |
uka | +0.643 |
Neg logit contributions | |
rog | -0.621 |
acle | -0.597 |
arium | -0.589 |
Buzz | -0.565 |
Buzz | -0.565 |
Token | to |
Token ID | 284 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
rog | +0.028 |
Buzz | +0.026 |
arium | +0.026 |
acle | +0.025 |
Buzz | +0.024 |
Neg logit contributions | |
bal | -0.048 |
cest | -0.048 |
ird | -0.048 |
isc | -0.047 |
Seth | -0.046 |
Token | relax |
Token ID | 8960 |
Feature activation | +6.46e-02 |
Pos logit contributions | |
rog | +0.014 |
Buzz | +0.013 |
acle | +0.013 |
Buzz | +0.013 |
arium | +0.012 |
Neg logit contributions | |
bal | -0.020 |
uka | -0.020 |
isc | -0.020 |
cest | -0.020 |
Tyler | -0.020 |
Token | and |
Token ID | 290 |
Feature activation | -5.10e-03 |
Pos logit contributions | |
rog | +0.085 |
acle | +0.083 |
arium | +0.082 |
Buzz | +0.080 |
Buzz | +0.077 |
Neg logit contributions | |
bal | -0.110 |
Seth | -0.109 |
Tyler | -0.107 |
ird | -0.107 |
isc | -0.107 |
Token | enjoy |
Token ID | 2883 |
Feature activation | -5.75e-03 |
Pos logit contributions | |
bal | +0.008 |
Seth | +0.007 |
ird | +0.007 |
Tyler | +0.007 |
Sel | +0.007 |
Neg logit contributions | |
rog | -0.008 |
acle | -0.008 |
arium | -0.008 |
Buzz | -0.007 |
atively | -0.007 |
Token | dark |
Token ID | 3223 |
Feature activation | -6.50e-03 |
Pos logit contributions | |
bal | +0.004 |
ird | +0.004 |
Seth | +0.004 |
isc | +0.004 |
Tyler | +0.004 |
Neg logit contributions | |
rog | -0.004 |
acle | -0.004 |
arium | -0.004 |
Buzz | -0.004 |
Buzz | -0.004 |
Token | storm |
Token ID | 6388 |
Feature activation | +3.92e-02 |
Pos logit contributions | |
bal | +0.010 |
Seth | +0.009 |
Tyler | +0.009 |
cest | +0.009 |
ird | +0.009 |
Neg logit contributions | |
rog | -0.010 |
acle | -0.010 |
arium | -0.010 |
Buzz | -0.009 |
Buzz | -0.009 |
Token | clouds |
Token ID | 15114 |
Feature activation | +9.50e-03 |
Pos logit contributions | |
rog | +0.061 |
acle | +0.059 |
arium | +0.058 |
Buzz | +0.056 |
Buzz | +0.056 |
Neg logit contributions | |
bal | -0.058 |
Seth | -0.056 |
Tyler | -0.056 |
ird | -0.055 |
uka | -0.055 |
Token | above |
Token ID | 2029 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
rog | +0.015 |
acle | +0.014 |
arium | +0.014 |
Buzz | +0.014 |
Buzz | +0.014 |
Neg logit contributions | |
bal | -0.014 |
Seth | -0.014 |
Tyler | -0.014 |
ird | -0.013 |
uka | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -1.71e-02 |
Pos logit contributions | |
rog | +0.135 |
acle | +0.134 |
Buzz | +0.129 |
atively | +0.127 |
arium | +0.118 |
Neg logit contributions | |
bal | -0.280 |
ird | -0.279 |
cest | -0.270 |
laund | -0.262 |
uka | -0.259 |
Token | Tyler |
Token ID | 14886 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
cest | +0.040 |
bal | +0.034 |
ird | +0.034 |
pian | +0.033 |
North | +0.032 |
Neg logit contributions | |
True | -0.013 |
acle | -0.012 |
rog | -0.012 |
Marie | -0.012 |
Amy | -0.011 |
Token | started |
Token ID | 2067 |
Feature activation | -2.53e-02 |
Pos logit contributions | |
bal | +0.658 |
Seth | +0.640 |
Tyler | +0.637 |
ird | +0.620 |
Sel | +0.612 |
Neg logit contributions | |
rog | -0.655 |
acle | -0.631 |
arium | -0.631 |
Buzz | -0.596 |
Buzz | -0.594 |
Token | to |
Token ID | 284 |
Feature activation | +7.48e-03 |
Pos logit contributions | |
bal | +0.043 |
Seth | +0.041 |
ird | +0.041 |
Tyler | +0.041 |
uka | +0.041 |
Neg logit contributions | |
rog | -0.034 |
acle | -0.033 |
arium | -0.032 |
Buzz | -0.031 |
Buzz | -0.031 |
Token | worry |
Token ID | 5490 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
rog | +0.011 |
acle | +0.010 |
arium | +0.010 |
Buzz | +0.010 |
Buzz | +0.009 |
Neg logit contributions | |
bal | -0.012 |
Seth | -0.012 |
Tyler | -0.012 |
Sel | -0.012 |
laund | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | -1.82e-02 |
Pos logit contributions | |
rog | +0.164 |
acle | +0.158 |
arium | +0.155 |
Buzz | +0.150 |
Buzz | +0.149 |
Neg logit contributions | |
bal | -0.168 |
Seth | -0.163 |
Tyler | -0.162 |
ird | -0.159 |
uka | -0.158 |
Token | because |
Token ID | 780 |
Feature activation | -6.58e-02 |
Pos logit contributions | |
bal | +0.027 |
ird | +0.026 |
Seth | +0.026 |
uka | +0.026 |
Tyler | +0.026 |
Neg logit contributions | |
rog | -0.028 |
acle | -0.027 |
arium | -0.027 |
Buzz | -0.026 |
Buzz | -0.026 |
Token | the |
Token ID | 262 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
rog | +0.014 |
acle | +0.013 |
arium | +0.013 |
Buzz | +0.013 |
Buzz | +0.012 |
Neg logit contributions | |
bal | -0.015 |
Seth | -0.014 |
ird | -0.014 |
cest | -0.014 |
Tyler | -0.014 |
Token | store |
Token ID | 3650 |
Feature activation | -9.38e-02 |
Pos logit contributions | |
isc | +0.025 |
ird | +0.025 |
bal | +0.025 |
cest | +0.025 |
Seth | +0.025 |
Neg logit contributions | |
rog | -0.025 |
acle | -0.024 |
Buzz | -0.023 |
Buzz | -0.023 |
arium | -0.023 |
Token | and |
Token ID | 290 |
Feature activation | -2.42e-03 |
Pos logit contributions | |
bal | +0.129 |
Seth | +0.127 |
Tyler | +0.126 |
laund | +0.123 |
ird | +0.122 |
Neg logit contributions | |
rog | -0.160 |
Buzz | -0.154 |
Buzz | -0.147 |
acle | -0.146 |
arium | -0.145 |
Token | got |
Token ID | 1392 |
Feature activation | -3.23e-02 |
Pos logit contributions | |
cest | +0.004 |
bal | +0.004 |
Seth | +0.004 |
isc | +0.004 |
pian | +0.004 |
Neg logit contributions | |
arium | -0.003 |
rog | -0.003 |
Buzz | -0.003 |
acle | -0.003 |
Buzz | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | -1.86e-02 |
Pos logit contributions | |
bal | +0.055 |
Seth | +0.053 |
Tyler | +0.053 |
cest | +0.052 |
ird | +0.052 |
Neg logit contributions | |
rog | -0.044 |
acle | -0.042 |
arium | -0.042 |
Buzz | -0.041 |
Buzz | -0.040 |
Token | bal |
Token ID | 3652 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
Seth | +0.028 |
cest | +0.028 |
ird | +0.028 |
Tyler | +0.028 |
Cam | +0.027 |
Neg logit contributions | |
rog | -0.026 |
acle | -0.024 |
Buzz | -0.024 |
Buzz | -0.024 |
atively | -0.023 |
Token | m |
Token ID | 76 |
Feature activation | +3.04e-03 |
Pos logit contributions | |
bal | +0.589 |
ird | +0.576 |
uka | +0.568 |
Tyler | +0.558 |
Seth | +0.550 |
Neg logit contributions | |
acle | -0.732 |
rog | -0.730 |
arium | -0.703 |
Buzz | -0.692 |
Buzz | -0.678 |
Token | . |
Token ID | 13 |
Feature activation | -2.10e-02 |
Pos logit contributions | |
rog | +0.005 |
acle | +0.004 |
arium | +0.004 |
Buzz | +0.004 |
Buzz | +0.004 |
Neg logit contributions | |
Tyler | -0.004 |
Seth | -0.004 |
bal | -0.004 |
laund | -0.004 |
ird | -0.004 |
Token | She |
Token ID | 1375 |
Feature activation | +7.17e-03 |
Pos logit contributions | |
cest | +0.040 |
pian | +0.037 |
ird | +0.037 |
sax | +0.037 |
bal | +0.037 |
Neg logit contributions | |
rog | -0.026 |
Buzz | -0.025 |
acle | -0.024 |
arium | -0.024 |
Buzz | -0.023 |
Token | carefully |
Token ID | 7773 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
rog | +0.009 |
Buzz | +0.009 |
arium | +0.009 |
acle | +0.009 |
Buzz | +0.009 |
Neg logit contributions | |
cest | -0.012 |
Seth | -0.012 |
Tyler | -0.011 |
bal | -0.011 |
uka | -0.011 |
Token | rubbed |
Token ID | 31862 |
Feature activation | -4.17e-02 |
Pos logit contributions | |
rog | +0.156 |
acle | +0.155 |
arium | +0.153 |
Buzz | +0.151 |
atively | +0.146 |
Neg logit contributions | |
cest | -0.200 |
Seth | -0.194 |
Tyler | -0.192 |
bal | -0.189 |
isc | -0.189 |
Token | started |
Token ID | 2067 |
Feature activation | -2.43e-02 |
Pos logit contributions | |
bal | +0.084 |
Seth | +0.082 |
Tyler | +0.081 |
ird | +0.079 |
cest | +0.078 |
Neg logit contributions | |
rog | -0.086 |
acle | -0.083 |
arium | -0.082 |
Buzz | -0.079 |
Buzz | -0.079 |
Token | to |
Token ID | 284 |
Feature activation | +8.69e-03 |
Pos logit contributions | |
bal | +0.040 |
Seth | +0.039 |
ird | +0.039 |
Tyler | +0.039 |
uka | +0.039 |
Neg logit contributions | |
rog | -0.033 |
acle | -0.032 |
arium | -0.032 |
Buzz | -0.031 |
Buzz | -0.030 |
Token | come |
Token ID | 1282 |
Feature activation | -4.55e-02 |
Pos logit contributions | |
rog | +0.013 |
arium | +0.013 |
acle | +0.013 |
Buzz | +0.012 |
Buzz | +0.012 |
Neg logit contributions | |
bal | -0.013 |
Seth | -0.013 |
Tyler | -0.013 |
Sel | -0.013 |
laund | -0.013 |
Token | down |
Token ID | 866 |
Feature activation | -6.04e-02 |
Pos logit contributions | |
bal | +0.062 |
Seth | +0.060 |
Tyler | +0.059 |
cest | +0.057 |
Sel | +0.057 |
Neg logit contributions | |
rog | -0.078 |
arium | -0.075 |
acle | -0.074 |
Buzz | -0.073 |
Buzz | -0.072 |
Token | and |
Token ID | 290 |
Feature activation | -1.52e-03 |
Pos logit contributions | |
bal | +0.105 |
ird | +0.104 |
uka | +0.104 |
isc | +0.101 |
cest | +0.100 |
Neg logit contributions | |
acle | -0.078 |
rog | -0.077 |
arium | -0.075 |
Buzz | -0.074 |
atively | -0.073 |
Token | Tyler |
Token ID | 14886 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
ird | +0.003 |
bal | +0.002 |
uka | +0.002 |
cest | +0.002 |
isc | +0.002 |
Neg logit contributions | |
rog | -0.002 |
arium | -0.002 |
acle | -0.002 |
Buzz | -0.002 |
Buzz | -0.002 |
Token | knew |
Token ID | 2993 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
bal | +0.704 |
uka | +0.684 |
Seth | +0.683 |
Tyler | +0.675 |
cest | +0.672 |
Neg logit contributions | |
rog | -0.574 |
acle | -0.561 |
arium | -0.545 |
Buzz | -0.538 |
Buzz | -0.527 |
Token | it |
Token ID | 340 |
Feature activation | -3.16e-02 |
Pos logit contributions | |
bal | +0.226 |
isc | +0.220 |
ird | +0.220 |
cest | +0.219 |
laund | +0.214 |
Neg logit contributions | |
rog | -0.143 |
arium | -0.139 |
acle | -0.138 |
Buzz | -0.137 |
atively | -0.128 |
Token | was |
Token ID | 373 |
Feature activation | -1.79e-02 |
Pos logit contributions | |
bal | +0.049 |
Seth | +0.047 |
Tyler | +0.047 |
ird | +0.046 |
uka | +0.046 |
Neg logit contributions | |
rog | -0.048 |
acle | -0.046 |
arium | -0.046 |
Buzz | -0.044 |
Buzz | -0.044 |
Token | time |
Token ID | 640 |
Feature activation | +1.35e-02 |
Pos logit contributions | |
bal | +0.031 |
uka | +0.031 |
ird | +0.031 |
isc | +0.031 |
Tyler | +0.030 |
Neg logit contributions | |
acle | -0.023 |
rog | -0.022 |
Buzz | -0.022 |
arium | -0.022 |
Buzz | -0.020 |
Token | to |
Token ID | 284 |
Feature activation | +9.57e-03 |
Pos logit contributions | |
rog | +0.020 |
acle | +0.019 |
arium | +0.019 |
Buzz | +0.018 |
Buzz | +0.018 |
Neg logit contributions | |
bal | -0.021 |
Seth | -0.021 |
Tyler | -0.021 |
ird | -0.020 |
uka | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | -3.35e-02 |
Pos logit contributions | |
cest | +0.032 |
bal | +0.029 |
pian | +0.028 |
ird | +0.028 |
hairst | +0.027 |
Neg logit contributions | |
rog | -0.011 |
acle | -0.011 |
True | -0.011 |
Buzz | -0.010 |
atively | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | -3.35e-02 |
Pos logit contributions | |
cest | +0.075 |
bal | +0.073 |
pian | +0.071 |
laund | +0.068 |
ird | +0.067 |
Neg logit contributions | |
rog | -0.030 |
Buzz | -0.026 |
Buzz | -0.024 |
acle | -0.024 |
arium | -0.023 |
Token | The |
Token ID | 464 |
Feature activation | -2.20e-02 |
Pos logit contributions | |
cest | +0.065 |
bal | +0.061 |
isc | +0.060 |
Es | +0.058 |
Jem | +0.058 |
Neg logit contributions | |
rog | -0.031 |
Buzz | -0.030 |
< | -0.028 |
acle | -0.028 |
urious | -0.027 |
Token | monster |
Token ID | 9234 |
Feature activation | +3.90e-02 |
Pos logit contributions | |
bal | +0.026 |
Tyler | +0.024 |
roller | +0.023 |
pian | +0.022 |
North | +0.022 |
Neg logit contributions | |
rog | -0.042 |
acle | -0.041 |
arium | -0.041 |
alk | -0.040 |
agged | -0.039 |
Token | grabbed |
Token ID | 13176 |
Feature activation | -3.55e-02 |
Pos logit contributions | |
rog | +0.060 |
arium | +0.057 |
acle | +0.057 |
Buzz | +0.054 |
Buzz | +0.054 |
Neg logit contributions | |
bal | -0.061 |
Seth | -0.058 |
Tyler | -0.058 |
ird | -0.056 |
Sel | -0.055 |
Token | Tyler |
Token ID | 14886 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
cest | +0.067 |
ird | +0.066 |
bal | +0.066 |
laund | +0.061 |
North | +0.061 |
Neg logit contributions | |
rog | -0.040 |
acle | -0.040 |
True | -0.039 |
Buzz | -0.037 |
atively | -0.036 |
Token | and |
Token ID | 290 |
Feature activation | -1.30e-03 |
Pos logit contributions | |
bal | +0.588 |
Tyler | +0.568 |
Seth | +0.563 |
ird | +0.533 |
Sel | +0.531 |
Neg logit contributions | |
rog | -0.729 |
arium | -0.711 |
Buzz | -0.699 |
acle | -0.692 |
Buzz | -0.668 |
Token | said |
Token ID | 531 |
Feature activation | -8.17e-03 |
Pos logit contributions | |
uka | +0.002 |
cest | +0.002 |
bal | +0.002 |
ird | +0.002 |
opl | +0.002 |
Neg logit contributions | |
Buzz | -0.002 |
acle | -0.002 |
rog | -0.002 |
atively | -0.001 |
arium | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | -1.62e-02 |
Pos logit contributions | |
bal | +0.013 |
Seth | +0.013 |
Tyler | +0.013 |
ird | +0.012 |
uka | +0.012 |
Neg logit contributions | |
rog | -0.012 |
acle | -0.012 |
arium | -0.011 |
Buzz | -0.011 |
Buzz | -0.011 |
Token | " |
Token ID | 366 |
Feature activation | -7.10e-02 |
Pos logit contributions | |
bal | +0.022 |
Seth | +0.021 |
Tyler | +0.021 |
ird | +0.021 |
uka | +0.020 |
Neg logit contributions | |
rog | -0.028 |
acle | -0.027 |
arium | -0.026 |
Buzz | -0.026 |
Buzz | -0.025 |
Token | You |
Token ID | 1639 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
bal | +0.111 |
ird | +0.110 |
cest | +0.107 |
isc | +0.104 |
laund | +0.104 |
Neg logit contributions | |
rog | -0.099 |
Buzz | -0.099 |
acle | -0.092 |
Buzz | -0.090 |
arium | -0.088 |
Token | boy |
Token ID | 2933 |
Feature activation | +2.35e-02 |
Pos logit contributions | |
rog | +0.134 |
acle | +0.131 |
arium | +0.127 |
Buzz | +0.121 |
Buzz | +0.121 |
Neg logit contributions | |
bal | -0.159 |
Seth | -0.152 |
Tyler | -0.152 |
cest | -0.148 |
ird | -0.148 |
Token | . |
Token ID | 13 |
Feature activation | -5.32e-03 |
Pos logit contributions | |
rog | +0.037 |
arium | +0.034 |
Buzz | +0.033 |
Buzz | +0.033 |
acle | +0.032 |
Neg logit contributions | |
Tyler | -0.036 |
bal | -0.035 |
Seth | -0.035 |
isc | -0.035 |
laund | -0.035 |
Token | He |
Token ID | 679 |
Feature activation | +2.79e-03 |
Pos logit contributions | |
bal | +0.008 |
Seth | +0.008 |
Tyler | +0.008 |
ird | +0.008 |
uka | +0.008 |
Neg logit contributions | |
rog | -0.008 |
acle | -0.008 |
arium | -0.007 |
Buzz | -0.007 |
Buzz | -0.007 |
Token | was |
Token ID | 373 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
rog | +0.005 |
acle | +0.004 |
arium | +0.004 |
Buzz | +0.004 |
atively | +0.004 |
Neg logit contributions | |
bal | -0.004 |
Seth | -0.004 |
Tyler | -0.004 |
uka | -0.004 |
cest | -0.004 |
Token | called |
Token ID | 1444 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
bal | +0.019 |
Seth | +0.019 |
Tyler | +0.019 |
ird | +0.019 |
cest | +0.018 |
Neg logit contributions | |
rog | -0.019 |
acle | -0.018 |
arium | -0.018 |
Buzz | -0.018 |
Buzz | -0.017 |
Token | Tyler |
Token ID | 14886 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
Tyler | +0.193 |
Seth | +0.192 |
bal | +0.185 |
roller | +0.179 |
Sel | +0.179 |
Neg logit contributions | |
rog | -0.253 |
arium | -0.246 |
Buzz | -0.245 |
acle | -0.243 |
atively | -0.236 |
Token | . |
Token ID | 13 |
Feature activation | -4.12e-03 |
Pos logit contributions | |
bal | +0.659 |
Seth | +0.638 |
Tyler | +0.633 |
ird | +0.621 |
uka | +0.618 |
Neg logit contributions | |
rog | -0.652 |
acle | -0.628 |
arium | -0.619 |
Buzz | -0.597 |
Buzz | -0.594 |
Token | Tyler |
Token ID | 14886 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
bal | +0.010 |
cest | +0.009 |
ird | +0.009 |
ele | +0.009 |
hairst | +0.008 |
Neg logit contributions | |
One | -0.002 |
acle | -0.002 |
True | -0.002 |
rog | -0.002 |
arium | -0.002 |
Token | liked |
Token ID | 8288 |
Feature activation | +4.15e-02 |
Pos logit contributions | |
bal | +0.664 |
Seth | +0.650 |
Tyler | +0.649 |
ird | +0.634 |
uka | +0.624 |
Neg logit contributions | |
rog | -0.634 |
acle | -0.612 |
arium | -0.602 |
Buzz | -0.580 |
Buzz | -0.573 |
Token | to |
Token ID | 284 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
rog | +0.051 |
arium | +0.050 |
Buzz | +0.049 |
acle | +0.048 |
Buzz | +0.047 |
Neg logit contributions | |
bal | -0.074 |
ird | -0.073 |
Seth | -0.073 |
isc | -0.072 |
Tyler | -0.072 |
Token | explore |
Token ID | 7301 |
Feature activation | +8.66e-03 |
Pos logit contributions | |
rog | +0.018 |
acle | +0.017 |
arium | +0.017 |
Buzz | +0.017 |
Buzz | +0.017 |
Neg logit contributions | |
bal | -0.023 |
Seth | -0.022 |
Tyler | -0.022 |
uka | -0.022 |
ird | -0.021 |
Token | 's |
Token ID | 338 |
Feature activation | -5.49e-02 |
Pos logit contributions | |
rog | +0.020 |
acle | +0.019 |
arium | +0.019 |
atively | +0.018 |
Buzz | +0.018 |
Neg logit contributions | |
bal | -0.015 |
Seth | -0.014 |
Tyler | -0.014 |
ird | -0.014 |
Sel | -0.013 |
Token | good |
Token ID | 922 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
bal | +0.096 |
Seth | +0.094 |
Tyler | +0.093 |
isc | +0.093 |
ird | +0.093 |
Neg logit contributions | |
rog | -0.071 |
Buzz | -0.067 |
acle | -0.067 |
arium | -0.064 |
Buzz | -0.062 |
Token | for |
Token ID | 329 |
Feature activation | -5.68e-03 |
Pos logit contributions | |
Seth | +0.215 |
Tyler | +0.214 |
uka | +0.212 |
bal | +0.212 |
laund | +0.211 |
Neg logit contributions | |
rog | -0.157 |
acle | -0.150 |
arium | -0.147 |
Buzz | -0.146 |
atively | -0.135 |
Token | you |
Token ID | 345 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
bal | +0.011 |
Seth | +0.010 |
Tyler | +0.010 |
ird | +0.010 |
isc | +0.010 |
Neg logit contributions | |
rog | -0.007 |
acle | -0.006 |
arium | -0.006 |
Buzz | -0.006 |
Buzz | -0.006 |
Token | !" |
Token ID | 2474 |
Feature activation | -7.02e-02 |
Pos logit contributions | |
rog | +0.183 |
acle | +0.177 |
arium | +0.175 |
Buzz | +0.169 |
Buzz | +0.168 |
Neg logit contributions | |
bal | -0.160 |
Seth | -0.155 |
Tyler | -0.154 |
ird | -0.152 |
cest | -0.149 |
Token | Tyler |
Token ID | 14886 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
cest | +0.171 |
North | +0.148 |
bal | +0.147 |
ird | +0.145 |
uka | +0.143 |
Neg logit contributions | |
rog | -0.041 |
True | -0.040 |
acle | -0.037 |
Buzz | -0.034 |
atively | -0.034 |
Token | couldn |
Token ID | 3521 |
Feature activation | -2.70e-02 |
Pos logit contributions | |
bal | +0.707 |
Tyler | +0.682 |
Seth | +0.680 |
ird | +0.668 |
Sel | +0.657 |
Neg logit contributions | |
rog | -0.600 |
arium | -0.597 |
acle | -0.582 |
Buzz | -0.556 |
Buzz | -0.542 |
Token | 't |
Token ID | 470 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
bal | +0.058 |
Seth | +0.056 |
cest | +0.056 |
Tyler | +0.056 |
ird | +0.056 |
Neg logit contributions | |
rog | -0.024 |
acle | -0.023 |
arium | -0.022 |
Buzz | -0.022 |
Buzz | -0.021 |
Token | help |
Token ID | 1037 |
Feature activation | +3.92e-02 |
Pos logit contributions | |
arium | +0.190 |
rog | +0.183 |
acle | +0.183 |
Buzz | +0.171 |
Buzz | +0.171 |
Neg logit contributions | |
bal | -0.179 |
ird | -0.172 |
Seth | -0.167 |
Tyler | -0.165 |
Sel | -0.162 |
Token | but |
Token ID | 475 |
Feature activation | -6.30e-02 |
Pos logit contributions | |
rog | +0.044 |
Buzz | +0.038 |
acle | +0.035 |
True | +0.034 |
isy | +0.032 |
Neg logit contributions | |
isc | -0.078 |
ird | -0.075 |
bal | -0.074 |
laund | -0.072 |
uka | -0.072 |
Token | g |
Token ID | 308 |
Feature activation | -4.88e-02 |
Pos logit contributions | |
bal | +0.103 |
Tyler | +0.099 |
Seth | +0.097 |
ird | +0.095 |
Sel | +0.093 |
Neg logit contributions | |
rog | -0.090 |
arium | -0.089 |
acle | -0.088 |
Buzz | -0.085 |
beard | -0.080 |
Token |
|
Token ID | 198 |
Feature activation | -3.43e-02 |
Pos logit contributions | |
cest | +0.075 |
bal | +0.073 |
pian | +0.070 |
laund | +0.067 |
ird | +0.066 |
Neg logit contributions | |
rog | -0.030 |
acle | -0.027 |
Buzz | -0.026 |
Buzz | -0.025 |
arium | -0.025 |
Token | " |
Token ID | 1 |
Feature activation | -6.13e-03 |
Pos logit contributions | |
cest | +0.066 |
bal | +0.063 |
North | +0.063 |
isc | +0.061 |
Es | +0.061 |
Neg logit contributions | |
rog | -0.033 |
acle | -0.032 |
Buzz | -0.029 |
atively | -0.028 |
urious | -0.028 |
Token | We |
Token ID | 1135 |
Feature activation | -2.99e-02 |
Pos logit contributions | |
cest | +0.010 |
bal | +0.010 |
isc | +0.010 |
ird | +0.010 |
Seth | +0.009 |
Neg logit contributions | |
Buzz | -0.008 |
rog | -0.008 |
Buzz | -0.008 |
nowhere | -0.007 |
acle | -0.007 |
Token | must |
Token ID | 1276 |
Feature activation | -4.89e-02 |
Pos logit contributions | |
bal | +0.042 |
ird | +0.041 |
Seth | +0.040 |
Tyler | +0.040 |
isc | +0.039 |
Neg logit contributions | |
rog | -0.050 |
acle | -0.049 |
arium | -0.049 |
Buzz | -0.047 |
atively | -0.046 |
Token | get |
Token ID | 651 |
Feature activation | -4.40e-02 |
Pos logit contributions | |
bal | +0.076 |
Seth | +0.075 |
Tyler | +0.074 |
ird | +0.073 |
laund | +0.071 |
Neg logit contributions | |
rog | -0.073 |
arium | -0.070 |
acle | -0.070 |
Buzz | -0.067 |
Buzz | -0.067 |
Token | Tyler |
Token ID | 14886 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
bal | +0.055 |
Seth | +0.053 |
Tyler | +0.052 |
uka | +0.051 |
Sel | +0.050 |
Neg logit contributions | |
rog | -0.082 |
acle | -0.080 |
arium | -0.079 |
atively | -0.075 |
Buzz | -0.075 |
Token | out |
Token ID | 503 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
bal | +0.654 |
Seth | +0.634 |
Tyler | +0.629 |
ird | +0.625 |
isc | +0.607 |
Neg logit contributions | |
rog | -0.654 |
acle | -0.627 |
arium | -0.627 |
Buzz | -0.604 |
Buzz | -0.596 |
Token | of |
Token ID | 286 |
Feature activation | -8.11e-02 |
Pos logit contributions | |
bal | +0.197 |
Seth | +0.191 |
Tyler | +0.189 |
uka | +0.187 |
laund | +0.186 |
Neg logit contributions | |
rog | -0.194 |
acle | -0.189 |
arium | -0.188 |
Buzz | -0.181 |
Buzz | -0.177 |
Token | the |
Token ID | 262 |
Feature activation | -2.40e-02 |
Pos logit contributions | |
bal | +0.139 |
ird | +0.131 |
Seth | +0.130 |
isc | +0.130 |
uka | +0.129 |
Neg logit contributions | |
rog | -0.111 |
acle | -0.109 |
arium | -0.108 |
Buzz | -0.105 |
Buzz | -0.100 |
Token | fire |
Token ID | 2046 |
Feature activation | +4.08e-02 |
Pos logit contributions | |
bal | +0.035 |
Tyler | +0.034 |
Seth | +0.034 |
ird | +0.033 |
uka | +0.033 |
Neg logit contributions | |
rog | -0.038 |
acle | -0.038 |
arium | -0.038 |
Buzz | -0.036 |
Buzz | -0.036 |
Token | !" |
Token ID | 2474 |
Feature activation | -6.69e-02 |
Pos logit contributions | |
rog | +0.063 |
acle | +0.060 |
arium | +0.060 |
Buzz | +0.058 |
Buzz | +0.058 |
Neg logit contributions | |
bal | -0.062 |
Seth | -0.060 |
Tyler | -0.059 |
ird | -0.058 |
cest | -0.058 |
Token | a |
Token ID | 257 |
Feature activation | +5.44e-02 |
Pos logit contributions | |
rog | +0.454 |
acle | +0.438 |
arium | +0.430 |
flies | +0.409 |
atively | +0.408 |
Neg logit contributions | |
bal | -0.212 |
roller | -0.193 |
Tyler | -0.191 |
ird | -0.190 |
Seth | -0.189 |
Token | time |
Token ID | 640 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
acle | +0.103 |
rog | +0.102 |
atively | +0.100 |
flies | +0.099 |
Buzz | +0.096 |
Neg logit contributions | |
bal | -0.065 |
ird | -0.059 |
roller | -0.057 |
Tyler | -0.055 |
pian | -0.054 |
Token | there |
Token ID | 612 |
Feature activation | +8.76e-02 |
Pos logit contributions | |
acle | +0.019 |
rog | +0.019 |
Buzz | +0.019 |
arium | +0.018 |
atively | +0.018 |
Neg logit contributions | |
bal | -0.013 |
Tyler | -0.012 |
Seth | -0.011 |
ird | -0.011 |
Su | -0.011 |
Token | was |
Token ID | 373 |
Feature activation | -1.89e-02 |
Pos logit contributions | |
rog | +0.110 |
arium | +0.104 |
Buzz | +0.104 |
acle | +0.102 |
Buzz | +0.099 |
Neg logit contributions | |
bal | -0.158 |
Seth | -0.151 |
cest | -0.151 |
ird | -0.151 |
laund | -0.150 |
Token | a |
Token ID | 257 |
Feature activation | +5.57e-02 |
Pos logit contributions | |
bal | +0.028 |
Tyler | +0.026 |
Seth | +0.026 |
uka | +0.025 |
Su | +0.025 |
Neg logit contributions | |
acle | -0.032 |
rog | -0.031 |
arium | -0.030 |
atively | -0.030 |
flies | -0.027 |
Token | True |
Token ID | 6407 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
rog | +0.059 |
arium | +0.055 |
Buzz | +0.054 |
acle | +0.054 |
Buzz | +0.053 |
Neg logit contributions | |
bal | -0.110 |
Seth | -0.109 |
Tyler | -0.108 |
ird | -0.108 |
isc | -0.107 |
Token | who |
Token ID | 508 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
rog | +0.444 |
arium | +0.423 |
acle | +0.413 |
Buzz | +0.410 |
Buzz | +0.405 |
Neg logit contributions | |
bal | -0.507 |
Seth | -0.505 |
Tyler | -0.501 |
ird | -0.490 |
laund | -0.490 |
Token | was |
Token ID | 373 |
Feature activation | -1.83e-02 |
Pos logit contributions | |
rog | +0.024 |
acle | +0.024 |
arium | +0.023 |
atively | +0.022 |
Buzz | +0.022 |
Neg logit contributions | |
bal | -0.022 |
Seth | -0.021 |
Tyler | -0.020 |
isc | -0.020 |
uka | -0.020 |
Token | very |
Token ID | 845 |
Feature activation | -4.90e-02 |
Pos logit contributions | |
bal | +0.027 |
Seth | +0.026 |
Tyler | +0.026 |
ird | +0.026 |
uka | +0.026 |
Neg logit contributions | |
rog | -0.029 |
acle | -0.028 |
arium | -0.027 |
Buzz | -0.027 |
Buzz | -0.026 |
Token | spoiled |
Token ID | 34781 |
Feature activation | -4.33e-02 |
Pos logit contributions | |
bal | +0.070 |
Seth | +0.066 |
uka | +0.065 |
Tyler | +0.065 |
isc | +0.063 |
Neg logit contributions | |
rog | -0.081 |
acle | -0.080 |
arium | -0.079 |
atively | -0.075 |
Buzz | -0.074 |
Token | . |
Token ID | 13 |
Feature activation | -8.09e-03 |
Pos logit contributions | |
uka | +0.081 |
Seth | +0.081 |
ird | +0.080 |
Tyler | +0.080 |
isc | +0.080 |
Neg logit contributions | |
rog | -0.049 |
Buzz | -0.046 |
acle | -0.045 |
arium | -0.045 |
Buzz | -0.040 |
Token | his |
Token ID | 465 |
Feature activation | -7.81e-02 |
Pos logit contributions | |
bal | +0.071 |
Seth | +0.069 |
Tyler | +0.068 |
uka | +0.065 |
cest | +0.065 |
Neg logit contributions | |
rog | -0.084 |
acle | -0.081 |
arium | -0.080 |
Buzz | -0.077 |
Buzz | -0.077 |
Token | paw |
Token ID | 41827 |
Feature activation | -2.32e-02 |
Pos logit contributions | |
bal | +0.110 |
cest | +0.097 |
Tyler | +0.095 |
isc | +0.094 |
sax | +0.094 |
Neg logit contributions | |
arium | -0.132 |
rog | -0.127 |
Buzz | -0.126 |
Buzz | -0.118 |
| | -0.117 |
Token | to |
Token ID | 284 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
bal | +0.035 |
Seth | +0.031 |
Tyler | +0.031 |
cest | +0.030 |
Sel | +0.030 |
Neg logit contributions | |
rog | -0.039 |
arium | -0.037 |
Buzz | -0.036 |
acle | -0.036 |
Buzz | -0.034 |
Token | get |
Token ID | 651 |
Feature activation | -3.71e-02 |
Pos logit contributions | |
rog | +0.023 |
arium | +0.023 |
acle | +0.022 |
Buzz | +0.021 |
acky | +0.021 |
Neg logit contributions | |
Seth | -0.016 |
bal | -0.016 |
Tyler | -0.016 |
cest | -0.015 |
Sel | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
ird | +0.074 |
bal | +0.074 |
Seth | +0.073 |
Tyler | +0.073 |
laund | +0.073 |
Neg logit contributions | |
rog | -0.037 |
Buzz | -0.036 |
acle | -0.035 |
arium | -0.034 |
Buzz | -0.034 |
Token | frog |
Token ID | 21264 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
bal | +0.023 |
cest | +0.021 |
roller | +0.020 |
Super | +0.020 |
Seth | +0.019 |
Neg logit contributions | |
rog | -0.021 |
arium | -0.021 |
acle | -0.021 |
atively | -0.020 |
agged | -0.020 |
Token | 's |
Token ID | 338 |
Feature activation | -4.47e-02 |
Pos logit contributions | |
rog | +0.371 |
acle | +0.356 |
Buzz | +0.351 |
arium | +0.349 |
atively | +0.343 |
Neg logit contributions | |
bal | -0.302 |
Seth | -0.269 |
Tyler | -0.267 |
cest | -0.266 |
ird | -0.254 |
Token | attention |
Token ID | 3241 |
Feature activation | +4.63e-02 |
Pos logit contributions | |
bal | +0.062 |
isc | +0.057 |
cest | +0.056 |
Seth | +0.056 |
roller | +0.053 |
Neg logit contributions | |
arium | -0.076 |
rog | -0.076 |
Buzz | -0.074 |
acle | -0.070 |
Buzz | -0.070 |
Token | . |
Token ID | 13 |
Feature activation | -8.01e-03 |
Pos logit contributions | |
rog | +0.066 |
acle | +0.064 |
arium | +0.063 |
Buzz | +0.060 |
Buzz | +0.059 |
Neg logit contributions | |
bal | -0.075 |
Seth | -0.073 |
Tyler | -0.073 |
ird | -0.072 |
uka | -0.072 |
Token |
|
Token ID | 198 |
Feature activation | -2.47e-02 |
Pos logit contributions | |
bal | +0.013 |
Seth | +0.012 |
Tyler | +0.012 |
ird | +0.012 |
uka | +0.012 |
Neg logit contributions | |
rog | -0.012 |
acle | -0.011 |
arium | -0.011 |
Buzz | -0.011 |
Buzz | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | -2.51e-02 |
Pos logit contributions | |
bal | +0.039 |
Seth | +0.038 |
Tyler | +0.037 |
ird | +0.037 |
cest | +0.037 |
Neg logit contributions | |
rog | -0.037 |
acle | -0.035 |
arium | -0.035 |
Buzz | -0.034 |
Buzz | -0.034 |
Token | ?" |
Token ID | 1701 |
Feature activation | -4.75e-02 |
Pos logit contributions | |
rog | +0.104 |
acle | +0.100 |
atively | +0.097 |
Buzz | +0.097 |
arium | +0.095 |
Neg logit contributions | |
bal | -0.082 |
ird | -0.078 |
Seth | -0.077 |
cest | -0.077 |
Tyler | -0.074 |
Token |
|
Token ID | 198 |
Feature activation | -1.65e-02 |
Pos logit contributions | |
bal | +0.073 |
Seth | +0.071 |
Tyler | +0.071 |
ird | +0.069 |
uka | +0.068 |
Neg logit contributions | |
rog | -0.073 |
acle | -0.071 |
arium | -0.069 |
Buzz | -0.067 |
Buzz | -0.066 |
Token |
|
Token ID | 198 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
bal | +0.028 |
cest | +0.027 |
Seth | +0.026 |
ird | +0.026 |
Tyler | +0.026 |
Neg logit contributions | |
rog | -0.023 |
arium | -0.022 |
acle | -0.022 |
Buzz | -0.022 |
Buzz | -0.021 |
Token | The |
Token ID | 464 |
Feature activation | -8.63e-03 |
Pos logit contributions | |
bal | +0.025 |
Seth | +0.024 |
Tyler | +0.024 |
ird | +0.024 |
laund | +0.023 |
Neg logit contributions | |
rog | -0.028 |
acle | -0.027 |
arium | -0.027 |
Buzz | -0.026 |
Buzz | -0.025 |
Token | j |
Token ID | 474 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
bal | +0.011 |
Seth | +0.011 |
uka | +0.010 |
Tyler | +0.010 |
laund | +0.010 |
Neg logit contributions | |
rog | -0.016 |
arium | -0.015 |
acle | -0.015 |
Buzz | -0.014 |
Buzz | -0.014 |
Token | olly |
Token ID | 5098 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
bal | +0.317 |
uka | +0.291 |
isc | +0.290 |
ird | +0.288 |
Seth | +0.284 |
Neg logit contributions | |
acle | -0.151 |
atively | -0.138 |
Buzz | -0.136 |
rog | -0.136 |
Buzz | -0.132 |
Token | man |
Token ID | 582 |
Feature activation | -2.66e-02 |
Pos logit contributions | |
acle | +0.388 |
arium | +0.383 |
rog | +0.379 |
agged | +0.354 |
Buzz | +0.353 |
Neg logit contributions | |
bal | -0.335 |
Seth | -0.296 |
isc | -0.287 |
Tyler | -0.284 |
ird | -0.283 |
Token | smiled |
Token ID | 13541 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
bal | +0.040 |
ird | +0.037 |
Seth | +0.036 |
Tyler | +0.036 |
Sel | +0.035 |
Neg logit contributions | |
rog | -0.042 |
arium | -0.040 |
acle | -0.040 |
alk | -0.040 |
Buzz | -0.039 |
Token | and |
Token ID | 290 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
rog | +0.222 |
acle | +0.210 |
arium | +0.209 |
Buzz | +0.202 |
Buzz | +0.200 |
Neg logit contributions | |
bal | -0.227 |
Seth | -0.218 |
Tyler | -0.216 |
cest | -0.211 |
ird | -0.209 |
Token | said |
Token ID | 531 |
Feature activation | +1.33e-03 |
Pos logit contributions | |
rog | +0.014 |
acle | +0.014 |
arium | +0.013 |
Buzz | +0.013 |
Buzz | +0.013 |
Neg logit contributions | |
bal | -0.018 |
ird | -0.018 |
Seth | -0.018 |
uka | -0.018 |
Tyler | -0.018 |
Token | , |
Token ID | 11 |
Feature activation | -6.25e-03 |
Pos logit contributions | |
rog | +0.002 |
acle | +0.002 |
arium | +0.002 |
Buzz | +0.002 |
Buzz | +0.002 |
Neg logit contributions | |
bal | -0.002 |
Seth | -0.002 |
Tyler | -0.002 |
ird | -0.002 |
uka | -0.002 |
Token | get |
Token ID | 651 |
Feature activation | -3.17e-02 |
Pos logit contributions | |
bal | +0.089 |
Seth | +0.087 |
cest | +0.086 |
Tyler | +0.085 |
ird | +0.085 |
Neg logit contributions | |
rog | -0.087 |
arium | -0.083 |
acle | -0.082 |
Buzz | -0.080 |
Buzz | -0.080 |
Token | . |
Token ID | 13 |
Feature activation | -5.17e-03 |
Pos logit contributions | |
bal | +0.051 |
Seth | +0.050 |
Tyler | +0.049 |
uka | +0.048 |
ird | +0.048 |
Neg logit contributions | |
rog | -0.046 |
acle | -0.044 |
arium | -0.044 |
Buzz | -0.042 |
Buzz | -0.042 |
Token | |
Token ID | 220 |
Feature activation | +5.15e-02 |
Pos logit contributions | |
cest | +0.011 |
pian | +0.011 |
bal | +0.010 |
ird | +0.010 |
laund | +0.010 |
Neg logit contributions | |
acle | -0.005 |
arium | -0.005 |
rog | -0.005 |
Buzz | -0.005 |
True | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -1.98e-02 |
Pos logit contributions | |
rog | +0.063 |
acle | +0.061 |
Buzz | +0.060 |
arium | +0.058 |
Buzz | +0.057 |
Neg logit contributions | |
cest | -0.092 |
bal | -0.092 |
laund | -0.089 |
pian | -0.089 |
Seth | -0.087 |
Token |
|
Token ID | 198 |
Feature activation | -1.98e-02 |
Pos logit contributions | |
bal | +0.037 |
cest | +0.036 |
ird | +0.036 |
pian | +0.036 |
laund | +0.035 |
Neg logit contributions | |
rog | -0.023 |
Buzz | -0.022 |
Buzz | -0.022 |
acle | -0.022 |
arium | -0.021 |
Token | True |
Token ID | 17821 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
Sel | +0.038 |
isc | +0.038 |
bal | +0.038 |
ird | +0.038 |
cest | +0.038 |
Neg logit contributions | |
rog | -0.019 |
Buzz | -0.019 |
acle | -0.018 |
isy | -0.017 |
arium | -0.016 |
Token | to |
Token ID | 284 |
Feature activation | +1.88e-02 |
Pos logit contributions | |
rog | +0.470 |
acle | +0.440 |
arium | +0.434 |
Buzz | +0.422 |
atively | +0.409 |
Neg logit contributions | |
bal | -0.364 |
Tyler | -0.329 |
Seth | -0.328 |
Sel | -0.316 |
ird | -0.316 |
Token | his |
Token ID | 465 |
Feature activation | -7.09e-02 |
Pos logit contributions | |
rog | +0.032 |
acle | +0.031 |
arium | +0.031 |
Buzz | +0.030 |
Buzz | +0.030 |
Neg logit contributions | |
bal | -0.025 |
Seth | -0.025 |
Tyler | -0.024 |
ird | -0.024 |
uka | -0.024 |
Token | mom |
Token ID | 1995 |
Feature activation | -6.42e-02 |
Pos logit contributions | |
bal | +0.090 |
Tyler | +0.086 |
Seth | +0.085 |
ird | +0.083 |
cest | +0.082 |
Neg logit contributions | |
rog | -0.129 |
acle | -0.123 |
Buzz | -0.121 |
arium | -0.121 |
Buzz | -0.118 |
Token | 's |
Token ID | 338 |
Feature activation | -3.92e-02 |
Pos logit contributions | |
bal | +0.101 |
Seth | +0.098 |
Tyler | +0.098 |
ird | +0.096 |
uka | +0.095 |
Neg logit contributions | |
rog | -0.096 |
acle | -0.092 |
arium | -0.090 |
Buzz | -0.088 |
Buzz | -0.087 |
Token | words |
Token ID | 2456 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
bal | +0.048 |
roller | +0.045 |
ird | +0.044 |
laund | +0.044 |
Tyler | +0.044 |
Neg logit contributions | |
rog | -0.074 |
Buzz | -0.073 |
acle | -0.069 |
arium | -0.068 |
Buzz | -0.067 |
Token |
|
Token ID | 198 |
Feature activation | -3.34e-02 |
Pos logit contributions | |
bal | +0.059 |
cest | +0.057 |
ird | +0.056 |
laund | +0.055 |
pian | +0.055 |
Neg logit contributions | |
rog | -0.042 |
Buzz | -0.039 |
arium | -0.038 |
Buzz | -0.038 |
acle | -0.037 |
Token | Jake |
Token ID | 43930 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
bal | +0.056 |
isc | +0.056 |
cest | +0.056 |
ird | +0.054 |
Es | +0.052 |
Neg logit contributions | |
rog | -0.045 |
Buzz | -0.044 |
arium | -0.038 |
Buzz | -0.037 |
acky | -0.036 |
Token | thought |
Token ID | 1807 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
bal | +0.201 |
Tyler | +0.197 |
Seth | +0.196 |
ird | +0.192 |
Sel | +0.186 |
Neg logit contributions | |
rog | -0.213 |
acle | -0.203 |
arium | -0.202 |
Buzz | -0.194 |
Buzz | -0.193 |
Token | for |
Token ID | 329 |
Feature activation | -5.39e-03 |
Pos logit contributions | |
rog | +0.230 |
acle | +0.219 |
arium | +0.217 |
Buzz | +0.211 |
atively | +0.203 |
Neg logit contributions | |
bal | -0.292 |
cest | -0.281 |
Seth | -0.281 |
ird | -0.278 |
laund | -0.277 |
Token | a |
Token ID | 257 |
Feature activation | +4.77e-02 |
Pos logit contributions | |
Tyler | +0.008 |
Seth | +0.008 |
Sel | +0.007 |
uka | +0.007 |
roller | +0.007 |
Neg logit contributions | |
rog | -0.009 |
arium | -0.009 |
acle | -0.009 |
Buzz | -0.009 |
Buzz | -0.008 |
Token | moment |
Token ID | 2589 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
acle | +0.042 |
rog | +0.040 |
arium | +0.039 |
Buzz | +0.035 |
Buzz | +0.035 |
Neg logit contributions | |
bal | -0.105 |
Tyler | -0.100 |
Seth | -0.099 |
roller | -0.099 |
ird | -0.098 |
Token | and |
Token ID | 290 |
Feature activation | -4.99e-03 |
Pos logit contributions | |
rog | +0.333 |
acle | +0.321 |
arium | +0.314 |
Buzz | +0.302 |
atively | +0.289 |
Neg logit contributions | |
bal | -0.449 |
Seth | -0.445 |
uka | -0.440 |
isc | -0.439 |
laund | -0.438 |
Token | then |
Token ID | 788 |
Feature activation | +2.89e-02 |
Pos logit contributions | |
bal | +0.008 |
Seth | +0.008 |
Tyler | +0.008 |
ird | +0.008 |
uka | +0.008 |
Neg logit contributions | |
rog | -0.007 |
acle | -0.006 |
arium | -0.006 |
Buzz | -0.006 |
Buzz | -0.006 |
Token | he |
Token ID | 339 |
Feature activation | -2.65e-02 |
Pos logit contributions | |
rog | +0.032 |
Buzz | +0.032 |
acle | +0.032 |
arium | +0.032 |
atively | +0.030 |
Neg logit contributions | |
laund | -0.052 |
isc | -0.051 |
cest | -0.050 |
bal | -0.049 |
uka | -0.049 |
Token | decided |
Token ID | 3066 |
Feature activation | -8.48e-02 |
Pos logit contributions | |
bal | +0.043 |
Seth | +0.042 |
Tyler | +0.042 |
cest | +0.041 |
laund | +0.041 |
Neg logit contributions | |
rog | -0.037 |
acle | -0.036 |
arium | -0.035 |
Buzz | -0.034 |
Buzz | -0.034 |
Token | to |
Token ID | 284 |
Feature activation | +5.60e-03 |
Pos logit contributions | |
bal | +0.143 |
Seth | +0.139 |
Tyler | +0.138 |
ird | +0.137 |
uka | +0.136 |
Neg logit contributions | |
rog | -0.116 |
acle | -0.113 |
arium | -0.110 |
Buzz | -0.106 |
Buzz | -0.104 |
Token | because |
Token ID | 780 |
Feature activation | -6.33e-02 |
Pos logit contributions | |
rog | +0.105 |
arium | +0.101 |
acle | +0.101 |
Buzz | +0.098 |
Buzz | +0.094 |
Neg logit contributions | |
bal | -0.131 |
Seth | -0.130 |
ird | -0.128 |
Tyler | -0.128 |
uka | -0.128 |
Token | her |
Token ID | 607 |
Feature activation | -3.83e-02 |
Pos logit contributions | |
bal | +0.095 |
Seth | +0.092 |
Tyler | +0.091 |
ird | +0.090 |
isc | +0.089 |
Neg logit contributions | |
rog | -0.098 |
arium | -0.094 |
acle | -0.094 |
Buzz | -0.092 |
Buzz | -0.090 |
Token | favorite |
Token ID | 4004 |
Feature activation | -2.32e-02 |
Pos logit contributions | |
bal | +0.047 |
Tyler | +0.044 |
Seth | +0.044 |
laund | +0.043 |
ird | +0.042 |
Neg logit contributions | |
rog | -0.073 |
acle | -0.069 |
Buzz | -0.069 |
arium | -0.069 |
Buzz | -0.067 |
Token | toy |
Token ID | 13373 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
bal | +0.031 |
Seth | +0.029 |
ird | +0.029 |
Tyler | +0.029 |
cest | +0.028 |
Neg logit contributions | |
rog | -0.041 |
acle | -0.040 |
arium | -0.039 |
Buzz | -0.038 |
Buzz | -0.038 |
Token | had |
Token ID | 550 |
Feature activation | +6.22e-02 |
Pos logit contributions | |
bal | +0.214 |
Seth | +0.209 |
Tyler | +0.208 |
uka | +0.204 |
ird | +0.203 |
Neg logit contributions | |
rog | -0.191 |
acle | -0.185 |
arium | -0.183 |
Buzz | -0.175 |
Buzz | -0.174 |
Token | been |
Token ID | 587 |
Feature activation | +6.66e-02 |
Pos logit contributions | |
acle | +0.080 |
rog | +0.078 |
arium | +0.077 |
Buzz | +0.074 |
atively | +0.073 |
Neg logit contributions | |
bal | -0.107 |
Tyler | -0.105 |
uka | -0.104 |
Seth | -0.103 |
ird | -0.102 |
Token | ruined |
Token ID | 20484 |
Feature activation | -2.30e-02 |
Pos logit contributions | |
rog | +0.089 |
acle | +0.087 |
arium | +0.086 |
Buzz | +0.082 |
Buzz | +0.080 |
Neg logit contributions | |
bal | -0.113 |
Tyler | -0.110 |
Seth | -0.110 |
uka | -0.108 |
isc | -0.107 |
Token | by |
Token ID | 416 |
Feature activation | +8.35e-02 |
Pos logit contributions | |
bal | +0.039 |
uka | +0.038 |
Seth | +0.038 |
Tyler | +0.038 |
ird | +0.037 |
Neg logit contributions | |
rog | -0.030 |
acle | -0.030 |
arium | -0.029 |
Buzz | -0.029 |
atively | -0.027 |
Token | the |
Token ID | 262 |
Feature activation | -2.51e-02 |
Pos logit contributions | |
rog | +0.131 |
acle | +0.126 |
arium | +0.126 |
Buzz | +0.122 |
Buzz | +0.117 |
Neg logit contributions | |
bal | -0.124 |
Seth | -0.124 |
Tyler | -0.122 |
Sel | -0.118 |
laund | -0.117 |
Token | rain |
Token ID | 6290 |
Feature activation | +2.34e-02 |
Pos logit contributions | |
bal | +0.038 |
Seth | +0.035 |
laund | +0.035 |
roller | +0.035 |
Tyler | +0.034 |
Neg logit contributions | |
rog | -0.041 |
arium | -0.039 |
acle | -0.039 |
Buzz | -0.037 |
Buzz | -0.037 |
Token | . |
Token ID | 13 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
rog | +0.032 |
acle | +0.031 |
arium | +0.030 |
Buzz | +0.029 |
atively | +0.028 |
Neg logit contributions | |
bal | -0.039 |
uka | -0.038 |
Seth | -0.038 |
Tyler | -0.038 |
Sel | -0.037 |
Token | drops |
Token ID | 49253 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
rog | +0.041 |
acle | +0.039 |
arium | +0.039 |
Buzz | +0.038 |
Buzz | +0.037 |
Neg logit contributions | |
bal | -0.038 |
Seth | -0.036 |
Tyler | -0.036 |
laund | -0.035 |
ird | -0.035 |
Token | falling |
Token ID | 7463 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
bal | +0.159 |
Seth | +0.154 |
Tyler | +0.153 |
uka | +0.150 |
ird | +0.150 |
Neg logit contributions | |
rog | -0.205 |
acle | -0.200 |
arium | -0.197 |
Buzz | -0.192 |
Buzz | -0.190 |
Token | from |
Token ID | 422 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
bal | +0.173 |
uka | +0.172 |
ird | +0.172 |
Tyler | +0.170 |
Seth | +0.169 |
Neg logit contributions | |
rog | -0.162 |
acle | -0.159 |
arium | -0.153 |
Buzz | -0.152 |
atively | -0.148 |
Token | the |
Token ID | 262 |
Feature activation | -3.73e-02 |
Pos logit contributions | |
bal | +0.203 |
Seth | +0.198 |
Tyler | +0.196 |
laund | +0.190 |
uka | +0.190 |
Neg logit contributions | |
rog | -0.223 |
acle | -0.216 |
arium | -0.211 |
Buzz | -0.204 |
Buzz | -0.200 |
Token | sky |
Token ID | 6766 |
Feature activation | +3.58e-02 |
Pos logit contributions | |
bal | +0.065 |
Tyler | +0.064 |
Seth | +0.064 |
uka | +0.063 |
ird | +0.063 |
Neg logit contributions | |
rog | -0.048 |
acle | -0.047 |
arium | -0.045 |
Buzz | -0.044 |
Buzz | -0.044 |
Token | and |
Token ID | 290 |
Feature activation | +6.83e-03 |
Pos logit contributions | |
rog | +0.053 |
acle | +0.051 |
arium | +0.050 |
Buzz | +0.048 |
Buzz | +0.048 |
Neg logit contributions | |
bal | -0.056 |
Seth | -0.055 |
Tyler | -0.055 |
ird | -0.054 |
uka | -0.053 |
Token | she |
Token ID | 673 |
Feature activation | -2.59e-02 |
Pos logit contributions | |
rog | +0.012 |
acle | +0.011 |
arium | +0.011 |
Buzz | +0.010 |
atively | +0.010 |
Neg logit contributions | |
bal | -0.010 |
Seth | -0.009 |
Tyler | -0.009 |
Sel | -0.009 |
laund | -0.009 |
Token | wanted |
Token ID | 2227 |
Feature activation | +3.07e-02 |
Pos logit contributions | |
bal | +0.038 |
Seth | +0.035 |
ird | +0.035 |
Tyler | +0.035 |
Sel | +0.034 |
Neg logit contributions | |
rog | -0.043 |
acle | -0.043 |
arium | -0.042 |
Buzz | -0.038 |
Buzz | -0.038 |
Token | to |
Token ID | 284 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
rog | +0.043 |
acle | +0.041 |
arium | +0.041 |
Buzz | +0.039 |
Buzz | +0.039 |
Neg logit contributions | |
bal | -0.051 |
Seth | -0.050 |
Tyler | -0.049 |
ird | -0.048 |
uka | -0.048 |
Token | catch |
Token ID | 4929 |
Feature activation | +9.03e-03 |
Pos logit contributions | |
rog | +0.017 |
acle | +0.017 |
arium | +0.016 |
Buzz | +0.016 |
Buzz | +0.016 |
Neg logit contributions | |
bal | -0.018 |
Seth | -0.017 |
Tyler | -0.017 |
ird | -0.017 |
uka | -0.017 |
Token | one |
Token ID | 530 |
Feature activation | +4.43e-02 |
Pos logit contributions | |
rog | +0.013 |
acle | +0.012 |
arium | +0.012 |
Buzz | +0.012 |
Buzz | +0.012 |
Neg logit contributions | |
bal | -0.015 |
Seth | -0.014 |
Tyler | -0.014 |
ird | -0.014 |
uka | -0.014 |
Token | for |
Token ID | 329 |
Feature activation | -4.17e-04 |
Pos logit contributions | |
Seth | +0.194 |
uka | +0.193 |
bal | +0.193 |
Tyler | +0.192 |
laund | +0.187 |
Neg logit contributions | |
rog | -0.158 |
acle | -0.151 |
arium | -0.151 |
Buzz | -0.146 |
Buzz | -0.137 |
Token | them |
Token ID | 606 |
Feature activation | +7.56e-02 |
Pos logit contributions | |
bal | +0.001 |
Seth | +0.001 |
Tyler | +0.001 |
ird | +0.001 |
uka | +0.001 |
Neg logit contributions | |
rog | -0.001 |
acle | -0.001 |
arium | -0.001 |
Buzz | -0.001 |
Buzz | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -1.37e-03 |
Pos logit contributions | |
rog | +0.114 |
acle | +0.110 |
arium | +0.109 |
Buzz | +0.105 |
Buzz | +0.104 |
Neg logit contributions | |
bal | -0.117 |
Seth | -0.113 |
Tyler | -0.112 |
ird | -0.110 |
uka | -0.110 |
Token | She |
Token ID | 1375 |
Feature activation | +1.77e-02 |
Pos logit contributions | |
cest | +0.003 |
bal | +0.003 |
laund | +0.003 |
ird | +0.002 |
roller | +0.002 |
Neg logit contributions | |
Buzz | -0.002 |
rog | -0.001 |
arium | -0.001 |
acle | -0.001 |
Buzz | -0.001 |
Token | says |
Token ID | 1139 |
Feature activation | -1.91e-02 |
Pos logit contributions | |
rog | +0.029 |
acle | +0.028 |
arium | +0.028 |
Buzz | +0.027 |
Buzz | +0.027 |
Neg logit contributions | |
bal | -0.026 |
Seth | -0.025 |
Tyler | -0.025 |
ird | -0.024 |
uka | -0.024 |
Token | some |
Token ID | 617 |
Feature activation | +8.37e-02 |
Pos logit contributions | |
bal | +0.030 |
Seth | +0.029 |
Tyler | +0.029 |
ird | +0.028 |
uka | +0.028 |
Neg logit contributions | |
rog | -0.029 |
acle | -0.028 |
arium | -0.027 |
Buzz | -0.026 |
Buzz | -0.026 |
Token | dogs |
Token ID | 6844 |
Feature activation | -6.16e-02 |
Pos logit contributions | |
rog | +0.126 |
acle | +0.124 |
arium | +0.122 |
Buzz | +0.115 |
Buzz | +0.115 |
Neg logit contributions | |
bal | -0.131 |
Seth | -0.126 |
Tyler | -0.125 |
ird | -0.123 |
laund | -0.121 |
Token | are |
Token ID | 389 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
bal | +0.084 |
Seth | +0.082 |
Tyler | +0.082 |
ird | +0.079 |
cest | +0.078 |
Neg logit contributions | |
rog | -0.102 |
acle | -0.100 |
arium | -0.098 |
Buzz | -0.095 |
atively | -0.094 |
Token | too |
Token ID | 1165 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
bal | +0.019 |
Seth | +0.018 |
Tyler | +0.018 |
ird | +0.018 |
uka | +0.018 |
Neg logit contributions | |
rog | -0.016 |
acle | -0.015 |
arium | -0.015 |
Buzz | -0.014 |
Buzz | -0.014 |
Token | big |
Token ID | 1263 |
Feature activation | -7.33e-02 |
Pos logit contributions | |
rog | +0.223 |
acle | +0.214 |
arium | +0.212 |
Buzz | +0.204 |
Buzz | +0.203 |
Neg logit contributions | |
bal | -0.239 |
Seth | -0.232 |
Tyler | -0.231 |
ird | -0.227 |
uka | -0.226 |
Token | or |
Token ID | 393 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
Seth | +0.135 |
bal | +0.134 |
uka | +0.133 |
Tyler | +0.132 |
laund | +0.132 |
Neg logit contributions | |
arium | -0.084 |
rog | -0.083 |
acle | -0.081 |
Buzz | -0.079 |
Buzz | -0.071 |
Token | twisted |
Token ID | 19074 |
Feature activation | -6.21e-02 |
Pos logit contributions | |
ird | +0.098 |
bal | +0.096 |
Tyler | +0.091 |
Seth | +0.091 |
Sel | +0.088 |
Neg logit contributions | |
rog | -0.104 |
arium | -0.101 |
acle | -0.095 |
Buzz | -0.095 |
Buzz | -0.094 |
Token | the |
Token ID | 262 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
bal | +0.100 |
Seth | +0.096 |
ird | +0.096 |
Tyler | +0.095 |
uka | +0.095 |
Neg logit contributions | |
rog | -0.091 |
acle | -0.088 |
arium | -0.087 |
Buzz | -0.084 |
Buzz | -0.083 |
Token | balloon |
Token ID | 21190 |
Feature activation | +3.46e-03 |
Pos logit contributions | |
roller | +0.015 |
bal | +0.014 |
cest | +0.014 |
ird | +0.014 |
laund | +0.014 |
Neg logit contributions | |
rog | -0.024 |
Buzz | -0.023 |
acky | -0.023 |
Buzz | -0.022 |
arium | -0.022 |
Token | very |
Token ID | 845 |
Feature activation | -4.39e-02 |
Pos logit contributions | |
rog | +0.005 |
arium | +0.005 |
acle | +0.005 |
Buzz | +0.005 |
Buzz | +0.005 |
Neg logit contributions | |
bal | -0.005 |
Seth | -0.005 |
Tyler | -0.005 |
ird | -0.005 |
cest | -0.005 |
Token | fast |
Token ID | 3049 |
Feature activation | +4.74e-03 |
Pos logit contributions | |
bal | +0.068 |
Seth | +0.061 |
Sel | +0.060 |
Tyler | +0.060 |
Es | +0.060 |
Neg logit contributions | |
arium | -0.066 |
rog | -0.065 |
acle | -0.063 |
Buzz | -0.058 |
Buzz | -0.058 |
Token | and |
Token ID | 290 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
rog | +0.007 |
acle | +0.007 |
arium | +0.007 |
Buzz | +0.006 |
Buzz | +0.006 |
Neg logit contributions | |
bal | -0.008 |
Seth | -0.007 |
Tyler | -0.007 |
uka | -0.007 |
ird | -0.007 |
Token | very |
Token ID | 845 |
Feature activation | -4.39e-02 |
Pos logit contributions | |
acle | +0.015 |
Buzz | +0.014 |
rog | +0.013 |
arium | +0.013 |
atively | +0.013 |
Neg logit contributions | |
uka | -0.020 |
bal | -0.020 |
ird | -0.020 |
isc | -0.020 |
laund | -0.020 |
Token | hard |
Token ID | 1327 |
Feature activation | +9.19e-02 |
Pos logit contributions | |
bal | +0.074 |
Seth | +0.070 |
Tyler | +0.070 |
ird | +0.068 |
cest | +0.068 |
Neg logit contributions | |
rog | -0.062 |
arium | -0.059 |
acle | -0.058 |
Buzz | -0.056 |
Buzz | -0.055 |
Token | . |
Token ID | 13 |
Feature activation | +4.28e-03 |
Pos logit contributions | |
rog | +0.144 |
acle | +0.138 |
arium | +0.137 |
Buzz | +0.132 |
Buzz | +0.132 |
Neg logit contributions | |
bal | -0.138 |
Seth | -0.134 |
Tyler | -0.133 |
ird | -0.130 |
uka | -0.129 |
Token | They |
Token ID | 1119 |
Feature activation | +8.05e-02 |
Pos logit contributions | |
rog | +0.005 |
acle | +0.005 |
arium | +0.005 |
Buzz | +0.005 |
Buzz | +0.004 |
Neg logit contributions | |
bal | -0.008 |
Seth | -0.008 |
Tyler | -0.008 |
ird | -0.008 |
uka | -0.008 |
Token | made |
Token ID | 925 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
rog | +0.101 |
acle | +0.099 |
arium | +0.095 |
Buzz | +0.093 |
Buzz | +0.093 |
Neg logit contributions | |
bal | -0.143 |
Seth | -0.139 |
isc | -0.137 |
Tyler | -0.137 |
cest | -0.137 |
Token | way |
Token ID | 835 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
bal | +0.028 |
Seth | +0.028 |
Tyler | +0.027 |
ird | +0.027 |
uka | +0.027 |
Neg logit contributions | |
rog | -0.027 |
arium | -0.026 |
acle | -0.026 |
Buzz | -0.025 |
Buzz | -0.025 |
Token | , |
Token ID | 11 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
bal | +0.221 |
Seth | +0.215 |
Tyler | +0.213 |
ird | +0.209 |
uka | +0.208 |
Neg logit contributions | |
rog | -0.215 |
acle | -0.207 |
arium | -0.204 |
Buzz | -0.197 |
Buzz | -0.196 |
Token | the |
Token ID | 262 |
Feature activation | -3.39e-02 |
Pos logit contributions | |
bal | +0.026 |
ird | +0.025 |
Seth | +0.025 |
Tyler | +0.025 |
uka | +0.025 |
Neg logit contributions | |
rog | -0.023 |
Buzz | -0.022 |
arium | -0.022 |
acle | -0.022 |
Buzz | -0.021 |
Token | bird |
Token ID | 6512 |
Feature activation | +6.83e-02 |
Pos logit contributions | |
bal | +0.047 |
roller | +0.043 |
laund | +0.042 |
ird | +0.042 |
Seth | +0.041 |
Neg logit contributions | |
rog | -0.062 |
arium | -0.060 |
acle | -0.058 |
beard | -0.056 |
Buzz | -0.056 |
Token | could |
Token ID | 714 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
rog | +0.106 |
acle | +0.102 |
arium | +0.101 |
Buzz | +0.097 |
Buzz | +0.097 |
Neg logit contributions | |
bal | -0.104 |
Seth | -0.099 |
Tyler | -0.098 |
ird | -0.097 |
cest | -0.096 |
Token | stay |
Token ID | 2652 |
Feature activation | +8.74e-03 |
Pos logit contributions | |
bal | +0.150 |
Seth | +0.145 |
Tyler | +0.143 |
ird | +0.142 |
Sel | +0.137 |
Neg logit contributions | |
rog | -0.184 |
arium | -0.177 |
acle | -0.173 |
Buzz | -0.169 |
Buzz | -0.165 |
Token | for |
Token ID | 329 |
Feature activation | -1.00e-02 |
Pos logit contributions | |
rog | +0.012 |
acle | +0.012 |
arium | +0.012 |
Buzz | +0.011 |
Buzz | +0.011 |
Neg logit contributions | |
bal | -0.015 |
Seth | -0.014 |
Tyler | -0.014 |
ird | -0.014 |
uka | -0.014 |
Token | longer |
Token ID | 2392 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
bal | +0.015 |
Seth | +0.014 |
Tyler | +0.014 |
ird | +0.014 |
Sel | +0.014 |
Neg logit contributions | |
rog | -0.016 |
acle | -0.016 |
arium | -0.015 |
Buzz | -0.015 |
atively | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | -1.81e-03 |
Pos logit contributions | |
rog | +0.016 |
acle | +0.015 |
arium | +0.015 |
Buzz | +0.015 |
Buzz | +0.014 |
Neg logit contributions | |
bal | -0.018 |
Seth | -0.018 |
Tyler | -0.017 |
uka | -0.017 |
isc | -0.017 |
Token | have |
Token ID | 423 |
Feature activation | +2.23e-02 |
Pos logit contributions | |
bal | +0.003 |
Seth | +0.003 |
Tyler | +0.003 |
ird | +0.003 |
uka | +0.003 |
Neg logit contributions | |
rog | -0.003 |
acle | -0.003 |
arium | -0.003 |
Buzz | -0.003 |
Buzz | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | +5.27e-02 |
Pos logit contributions | |
rog | +0.036 |
acle | +0.035 |
arium | +0.034 |
Buzz | +0.033 |
atively | +0.032 |
Neg logit contributions | |
bal | -0.032 |
Seth | -0.032 |
Tyler | -0.031 |
ird | -0.031 |
laund | -0.030 |
Token | years |
Token ID | 812 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
rog | +0.035 |
arium | +0.031 |
acle | +0.029 |
Buzz | +0.029 |
Buzz | +0.028 |
Neg logit contributions | |
Seth | -0.096 |
Tyler | -0.096 |
isc | -0.095 |
bal | -0.095 |
uka | -0.094 |
Token | old |
Token ID | 1468 |
Feature activation | +6.96e-02 |
Pos logit contributions | |
rog | +0.140 |
acle | +0.133 |
arium | +0.131 |
Buzz | +0.124 |
Buzz | +0.124 |
Neg logit contributions | |
bal | -0.237 |
Seth | -0.232 |
Tyler | -0.231 |
ird | -0.227 |
uka | -0.226 |
Token | . |
Token ID | 13 |
Feature activation | -2.16e-03 |
Pos logit contributions | |
rog | +0.078 |
Buzz | +0.069 |
acle | +0.068 |
arium | +0.066 |
Buzz | +0.064 |
Neg logit contributions | |
bal | -0.129 |
uka | -0.129 |
Seth | -0.129 |
isc | -0.128 |
ird | -0.128 |
Token | One |
Token ID | 1881 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
bal | +0.004 |
cest | +0.004 |
ird | +0.004 |
laund | +0.004 |
Seth | +0.004 |
Neg logit contributions | |
rog | -0.003 |
acle | -0.003 |
arium | -0.003 |
Buzz | -0.002 |
Buzz | -0.002 |
Token | day |
Token ID | 1110 |
Feature activation | +3.03e-02 |
Pos logit contributions | |
rog | +0.159 |
acle | +0.154 |
arium | +0.151 |
Buzz | +0.145 |
Buzz | +0.145 |
Neg logit contributions | |
bal | -0.183 |
Seth | -0.177 |
Tyler | -0.176 |
ird | -0.173 |
uka | -0.172 |
Token | he |
Token ID | 339 |
Feature activation | -2.28e-02 |
Pos logit contributions | |
rog | +0.031 |
acle | +0.029 |
arium | +0.029 |
Buzz | +0.028 |
atively | +0.028 |
Neg logit contributions | |
isc | -0.059 |
laund | -0.059 |
North | -0.058 |
cest | -0.058 |
pian | -0.058 |
Token | was |
Token ID | 373 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
bal | +0.036 |
Seth | +0.036 |
Tyler | +0.035 |
ird | +0.035 |
Sel | +0.035 |
Neg logit contributions | |
rog | -0.032 |
arium | -0.032 |
acle | -0.031 |
Buzz | -0.030 |
Buzz | -0.030 |
Token | walking |
Token ID | 6155 |
Feature activation | +8.52e-02 |
Pos logit contributions | |
bal | +0.020 |
Seth | +0.020 |
Tyler | +0.020 |
cest | +0.020 |
isc | +0.020 |
Neg logit contributions | |
rog | -0.018 |
acle | -0.017 |
arium | -0.017 |
Buzz | -0.017 |
Buzz | -0.016 |
Token | around |
Token ID | 1088 |
Feature activation | +3.27e-02 |
Pos logit contributions | |
acle | +0.139 |
rog | +0.136 |
arium | +0.134 |
Buzz | +0.128 |
atively | +0.125 |
Neg logit contributions | |
bal | -0.126 |
Seth | -0.117 |
Tyler | -0.115 |
cest | -0.113 |
Sel | -0.112 |
Token | the |
Token ID | 262 |
Feature activation | -1.55e-02 |
Pos logit contributions | |
rog | +0.058 |
acle | +0.058 |
Buzz | +0.055 |
arium | +0.054 |
atively | +0.054 |
Neg logit contributions | |
Tyler | -0.041 |
bal | -0.041 |
Seth | -0.040 |
Sel | -0.039 |
uka | -0.039 |
Token | city |
Token ID | 1748 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
bal | +0.026 |
ird | +0.026 |
Seth | +0.026 |
Tyler | +0.026 |
isc | +0.025 |
Neg logit contributions | |
rog | -0.021 |
arium | -0.021 |
acle | -0.020 |
Buzz | -0.019 |
Buzz | -0.019 |
Token | told |
Token ID | 1297 |
Feature activation | -6.19e-02 |
Pos logit contributions | |
bal | +0.093 |
Seth | +0.090 |
isc | +0.090 |
uka | +0.089 |
Tyler | +0.089 |
Neg logit contributions | |
rog | -0.064 |
acle | -0.060 |
Buzz | -0.060 |
arium | -0.060 |
Buzz | -0.057 |
Token | everyone |
Token ID | 2506 |
Feature activation | -4.51e-02 |
Pos logit contributions | |
bal | +0.095 |
Seth | +0.092 |
Tyler | +0.090 |
Sel | +0.089 |
laund | +0.087 |
Neg logit contributions | |
rog | -0.096 |
acle | -0.096 |
arium | -0.095 |
Buzz | -0.087 |
atively | -0.086 |
Token | what |
Token ID | 644 |
Feature activation | +5.33e-02 |
Pos logit contributions | |
bal | +0.068 |
Tyler | +0.065 |
Seth | +0.065 |
Sel | +0.063 |
cest | +0.063 |
Neg logit contributions | |
acle | -0.070 |
rog | -0.070 |
arium | -0.066 |
Buzz | -0.065 |
atively | -0.064 |
Token | to |
Token ID | 284 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
rog | +0.066 |
Buzz | +0.065 |
Buzz | +0.062 |
arium | +0.062 |
True | +0.058 |
Neg logit contributions | |
isc | -0.095 |
Seth | -0.094 |
bal | -0.094 |
Tyler | -0.093 |
cest | -0.092 |
Token | do |
Token ID | 466 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
rog | +0.019 |
acle | +0.018 |
arium | +0.018 |
Buzz | +0.017 |
Buzz | +0.017 |
Neg logit contributions | |
bal | -0.020 |
Seth | -0.020 |
Tyler | -0.020 |
ird | -0.019 |
uka | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | -8.91e-03 |
Pos logit contributions | |
Seth | +0.023 |
bal | +0.023 |
Tyler | +0.022 |
isc | +0.022 |
uka | +0.022 |
Neg logit contributions | |
rog | -0.017 |
arium | -0.017 |
acle | -0.016 |
Buzz | -0.015 |
Buzz | -0.015 |
Token | One |
Token ID | 1881 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
Sel | +0.013 |
Seth | +0.012 |
Tyler | +0.012 |
bal | +0.012 |
Es | +0.012 |
Neg logit contributions | |
acle | -0.014 |
rog | -0.014 |
arium | -0.013 |
atively | -0.013 |
Buzz | -0.013 |
Token | day |
Token ID | 1110 |
Feature activation | +2.58e-02 |
Pos logit contributions | |
acle | +0.206 |
atively | +0.193 |
rog | +0.191 |
arium | +0.182 |
Buzz | +0.178 |
Neg logit contributions | |
bal | -0.147 |
cest | -0.128 |
uka | -0.124 |
ird | -0.124 |
Seth | -0.122 |
Token | , |
Token ID | 11 |
Feature activation | -5.80e-03 |
Pos logit contributions | |
rog | +0.033 |
Buzz | +0.031 |
arium | +0.031 |
acle | +0.030 |
Buzz | +0.030 |
Neg logit contributions | |
Seth | -0.045 |
bal | -0.044 |
Tyler | -0.044 |
cest | -0.044 |
uka | -0.044 |
Token | she |
Token ID | 673 |
Feature activation | -2.74e-02 |
Pos logit contributions | |
bal | +0.007 |
Sel | +0.007 |
Seth | +0.006 |
Es | +0.006 |
Tyler | +0.006 |
Neg logit contributions | |
acle | -0.011 |
rog | -0.011 |
arium | -0.010 |
beard | -0.010 |
alk | -0.010 |
Token | decided |
Token ID | 3066 |
Feature activation | -8.69e-02 |
Pos logit contributions | |
bal | +0.048 |
Seth | +0.047 |
Tyler | +0.047 |
Sel | +0.046 |
isc | +0.046 |
Neg logit contributions | |
arium | -0.035 |
rog | -0.035 |
acle | -0.033 |
Buzz | -0.033 |
Buzz | -0.032 |
Token | stories |
Token ID | 3923 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
bal | +0.042 |
pian | +0.038 |
laund | +0.038 |
cest | +0.037 |
roller | +0.037 |
Neg logit contributions | |
acle | -0.046 |
rog | -0.045 |
arium | -0.043 |
Buzz | -0.042 |
atively | -0.042 |
Token | with |
Token ID | 351 |
Feature activation | -1.75e-03 |
Pos logit contributions | |
acle | +0.153 |
rog | +0.151 |
arium | +0.149 |
Buzz | +0.140 |
atively | +0.139 |
Neg logit contributions | |
Seth | -0.203 |
bal | -0.201 |
uka | -0.199 |
Tyler | -0.199 |
laund | -0.195 |
Token | her |
Token ID | 607 |
Feature activation | -3.55e-02 |
Pos logit contributions | |
bal | +0.003 |
Seth | +0.003 |
cest | +0.003 |
ird | +0.003 |
Tyler | +0.003 |
Neg logit contributions | |
rog | -0.002 |
acle | -0.002 |
arium | -0.002 |
Buzz | -0.002 |
Buzz | -0.002 |
Token | mom |
Token ID | 1995 |
Feature activation | -7.08e-02 |
Pos logit contributions | |
bal | +0.052 |
Tyler | +0.050 |
Seth | +0.049 |
ird | +0.048 |
Sel | +0.048 |
Neg logit contributions | |
rog | -0.057 |
acle | -0.055 |
arium | -0.054 |
Buzz | -0.053 |
Buzz | -0.052 |
Token | and |
Token ID | 290 |
Feature activation | +1.92e-04 |
Pos logit contributions | |
bal | +0.123 |
Seth | +0.120 |
uka | +0.118 |
laund | +0.118 |
Tyler | +0.117 |
Neg logit contributions | |
rog | -0.091 |
arium | -0.088 |
acle | -0.088 |
Buzz | -0.084 |
Buzz | -0.078 |
Token | dad |
Token ID | 9955 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
Buzz | +0.000 |
arium | +0.000 |
rog | +0.000 |
acle | +0.000 |
Marie | +0.000 |
Neg logit contributions | |
bal | -0.000 |
ird | -0.000 |
isc | -0.000 |
uka | -0.000 |
Seth | -0.000 |
Token | and |
Token ID | 290 |
Feature activation | +1.12e-03 |
Pos logit contributions | |
bal | +0.162 |
Seth | +0.158 |
Tyler | +0.157 |
ird | +0.153 |
uka | +0.153 |
Neg logit contributions | |
rog | -0.152 |
acle | -0.147 |
arium | -0.145 |
Buzz | -0.139 |
Buzz | -0.138 |
Token | they |
Token ID | 484 |
Feature activation | +2.99e-02 |
Pos logit contributions | |
Buzz | +0.001 |
rog | +0.001 |
arium | +0.001 |
acle | +0.001 |
atively | +0.001 |
Neg logit contributions | |
bal | -0.002 |
uka | -0.002 |
isc | -0.002 |
Seth | -0.002 |
laund | -0.002 |
Token | praised |
Token ID | 15342 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
rog | +0.036 |
acle | +0.035 |
arium | +0.035 |
Buzz | +0.034 |
Buzz | +0.033 |
Neg logit contributions | |
bal | -0.055 |
Seth | -0.053 |
Tyler | -0.052 |
uka | -0.052 |
cest | -0.052 |
Token | her |
Token ID | 607 |
Feature activation | -3.25e-02 |
Pos logit contributions | |
Tyler | +0.159 |
bal | +0.157 |
Seth | +0.157 |
Sel | +0.154 |
Es | +0.147 |
Neg logit contributions | |
rog | -0.198 |
acle | -0.196 |
arium | -0.195 |
Buzz | -0.185 |
atively | -0.176 |
Token | for |
Token ID | 329 |
Feature activation | -6.12e-03 |
Pos logit contributions | |
bal | +0.051 |
Seth | +0.049 |
Tyler | +0.049 |
ird | +0.048 |
uka | +0.048 |
Neg logit contributions | |
rog | -0.049 |
acle | -0.047 |
arium | -0.046 |
Buzz | -0.045 |
Buzz | -0.044 |
Token | day |
Token ID | 1110 |
Feature activation | +3.50e-02 |
Pos logit contributions | |
rog | +0.150 |
arium | +0.140 |
acle | +0.134 |
Buzz | +0.132 |
Buzz | +0.132 |
Neg logit contributions | |
Seth | -0.217 |
Tyler | -0.217 |
bal | -0.214 |
ird | -0.210 |
uka | -0.209 |
Token | , |
Token ID | 11 |
Feature activation | +2.35e-03 |
Pos logit contributions | |
rog | +0.042 |
Buzz | +0.040 |
arium | +0.039 |
acle | +0.038 |
Buzz | +0.037 |
Neg logit contributions | |
Seth | -0.063 |
isc | -0.062 |
bal | -0.062 |
Tyler | -0.062 |
uka | -0.062 |
Token | a |
Token ID | 257 |
Feature activation | +6.55e-02 |
Pos logit contributions | |
rog | +0.004 |
acle | +0.004 |
arium | +0.004 |
Buzz | +0.004 |
Buzz | +0.003 |
Neg logit contributions | |
bal | -0.003 |
Seth | -0.003 |
Tyler | -0.003 |
uka | -0.003 |
Sel | -0.003 |
Token | man |
Token ID | 582 |
Feature activation | -2.48e-02 |
Pos logit contributions | |
rog | +0.065 |
arium | +0.060 |
Buzz | +0.058 |
acle | +0.058 |
Buzz | +0.057 |
Neg logit contributions | |
Seth | -0.134 |
Tyler | -0.132 |
isc | -0.131 |
ird | -0.128 |
bal | -0.128 |
Token | with |
Token ID | 351 |
Feature activation | +2.02e-02 |
Pos logit contributions | |
bal | +0.040 |
Tyler | +0.040 |
Seth | +0.040 |
isc | +0.039 |
uka | +0.039 |
Neg logit contributions | |
rog | -0.034 |
arium | -0.034 |
acle | -0.032 |
Buzz | -0.032 |
Buzz | -0.032 |
Token | an |
Token ID | 281 |
Feature activation | -4.07e-02 |
Pos logit contributions | |
rog | +0.025 |
acle | +0.024 |
arium | +0.023 |
Buzz | +0.023 |
Buzz | +0.023 |
Neg logit contributions | |
bal | -0.036 |
Seth | -0.035 |
Tyler | -0.035 |
ird | -0.035 |
laund | -0.035 |
Token | ugly |
Token ID | 13400 |
Feature activation | +1.90e-02 |
Pos logit contributions | |
Tyler | +0.069 |
bal | +0.069 |
Seth | +0.069 |
uka | +0.067 |
ird | +0.066 |
Neg logit contributions | |
rog | -0.054 |
acle | -0.051 |
arium | -0.049 |
Buzz | -0.048 |
atively | -0.046 |
Token | face |
Token ID | 1986 |
Feature activation | +9.81e-02 |
Pos logit contributions | |
rog | +0.029 |
acle | +0.028 |
arium | +0.027 |
Buzz | +0.026 |
atively | +0.026 |
Neg logit contributions | |
Seth | -0.028 |
Tyler | -0.028 |
bal | -0.028 |
uka | -0.027 |
isc | -0.027 |
Token | came |
Token ID | 1625 |
Feature activation | -1.95e-02 |
Pos logit contributions | |
rog | +0.109 |
acle | +0.105 |
Buzz | +0.102 |
arium | +0.101 |
atively | +0.098 |
Neg logit contributions | |
Tyler | -0.181 |
uka | -0.177 |
Seth | -0.176 |
isc | -0.175 |
laund | -0.170 |
Token | to |
Token ID | 284 |
Feature activation | +2.32e-02 |
Pos logit contributions | |
bal | +0.031 |
Seth | +0.030 |
Tyler | +0.030 |
ird | +0.029 |
uka | +0.029 |
Neg logit contributions | |
rog | -0.029 |
acle | -0.028 |
arium | -0.027 |
Buzz | -0.026 |
Buzz | -0.026 |
Token | the |
Token ID | 262 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
rog | +0.035 |
acle | +0.034 |
arium | +0.033 |
Buzz | +0.032 |
Buzz | +0.032 |
Neg logit contributions | |
bal | -0.036 |
Seth | -0.035 |
Tyler | -0.035 |
ird | -0.034 |
uka | -0.034 |
Token | him |
Token ID | 683 |
Feature activation | +2.86e-02 |
Pos logit contributions | |
bal | +0.016 |
uka | +0.016 |
Tyler | +0.016 |
laund | +0.016 |
Seth | +0.016 |
Neg logit contributions | |
rog | -0.012 |
acle | -0.011 |
Buzz | -0.011 |
arium | -0.010 |
Buzz | -0.010 |
Token | to |
Token ID | 284 |
Feature activation | +1.30e-03 |
Pos logit contributions | |
rog | +0.042 |
acle | +0.040 |
arium | +0.040 |
Buzz | +0.038 |
Buzz | +0.038 |
Neg logit contributions | |
bal | -0.045 |
Seth | -0.044 |
Tyler | -0.044 |
ird | -0.043 |
uka | -0.042 |
Token | wipe |
Token ID | 19916 |
Feature activation | -3.21e-02 |
Pos logit contributions | |
rog | +0.002 |
Buzz | +0.002 |
arium | +0.002 |
acle | +0.001 |
Buzz | +0.001 |
Neg logit contributions | |
bal | -0.002 |
isc | -0.002 |
uka | -0.002 |
laund | -0.002 |
ird | -0.002 |
Token | it |
Token ID | 340 |
Feature activation | -3.90e-02 |
Pos logit contributions | |
ird | +0.067 |
pian | +0.064 |
bal | +0.063 |
laund | +0.063 |
isc | +0.062 |
Neg logit contributions | |
rog | -0.031 |
Buzz | -0.028 |
acle | -0.027 |
ly | -0.027 |
itself | -0.027 |
Token | off |
Token ID | 572 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
bal | +0.063 |
Seth | +0.063 |
Tyler | +0.063 |
uka | +0.062 |
ird | +0.061 |
Neg logit contributions | |
rog | -0.054 |
acle | -0.053 |
arium | -0.051 |
Buzz | -0.050 |
Buzz | -0.049 |
Token | . |
Token ID | 13 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
bal | +0.332 |
uka | +0.326 |
Seth | +0.324 |
ird | +0.323 |
Tyler | +0.322 |
Neg logit contributions | |
rog | -0.255 |
acle | -0.253 |
arium | -0.244 |
Buzz | -0.242 |
Buzz | -0.228 |
Token |
|
Token ID | 198 |
Feature activation | -3.15e-02 |
Pos logit contributions | |
cest | +0.025 |
bal | +0.025 |
ird | +0.024 |
laund | +0.024 |
Seth | +0.024 |
Neg logit contributions | |
rog | -0.017 |
Buzz | -0.016 |
acle | -0.016 |
arium | -0.016 |
Buzz | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | -3.08e-02 |
Pos logit contributions | |
bal | +0.052 |
Seth | +0.051 |
Tyler | +0.050 |
ird | +0.050 |
cest | +0.049 |
Neg logit contributions | |
rog | -0.044 |
acle | -0.042 |
arium | -0.042 |
Buzz | -0.040 |
Buzz | -0.040 |
Token | The |
Token ID | 464 |
Feature activation | -1.88e-02 |
Pos logit contributions | |
bal | +0.049 |
Seth | +0.048 |
Tyler | +0.048 |
ird | +0.047 |
uka | +0.046 |
Neg logit contributions | |
rog | -0.045 |
acle | -0.043 |
arium | -0.043 |
Buzz | -0.042 |
Buzz | -0.041 |
Token | little |
Token ID | 1310 |
Feature activation | +8.38e-02 |
Pos logit contributions | |
bal | +0.032 |
roller | +0.029 |
Seth | +0.029 |
laund | +0.029 |
isc | +0.028 |
Neg logit contributions | |
rog | -0.028 |
arium | -0.027 |
acle | -0.027 |
Buzz | -0.026 |
Buzz | -0.025 |
Token | boy |
Token ID | 2933 |
Feature activation | +2.23e-02 |
Pos logit contributions | |
acle | +0.159 |
rog | +0.156 |
arium | +0.154 |
atively | +0.150 |
Buzz | +0.148 |
Neg logit contributions | |
bal | -0.108 |
Seth | -0.098 |
cest | -0.097 |
Ther | -0.093 |
roller | -0.092 |
Token | could |
Token ID | 714 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
bal | +0.041 |
Seth | +0.039 |
Tyler | +0.039 |
ird | +0.039 |
uka | +0.038 |
Neg logit contributions | |
rog | -0.054 |
acle | -0.052 |
arium | -0.052 |
Buzz | -0.050 |
Buzz | -0.050 |
Token | talk |
Token ID | 1561 |
Feature activation | +9.55e-02 |
Pos logit contributions | |
bal | +0.170 |
Seth | +0.165 |
Tyler | +0.165 |
uka | +0.163 |
cest | +0.162 |
Neg logit contributions | |
rog | -0.154 |
acle | -0.150 |
arium | -0.143 |
Buzz | -0.142 |
Buzz | -0.140 |
Token | to |
Token ID | 284 |
Feature activation | +7.94e-03 |
Pos logit contributions | |
rog | +0.110 |
acle | +0.108 |
arium | +0.107 |
Buzz | +0.103 |
atively | +0.098 |
Neg logit contributions | |
uka | -0.175 |
bal | -0.174 |
isc | -0.173 |
Seth | -0.173 |
Tyler | -0.171 |
Token | her |
Token ID | 607 |
Feature activation | -4.05e-02 |
Pos logit contributions | |
rog | +0.010 |
Buzz | +0.010 |
arium | +0.010 |
acle | +0.009 |
Buzz | +0.009 |
Neg logit contributions | |
bal | -0.014 |
isc | -0.013 |
cest | -0.013 |
laund | -0.013 |
uka | -0.013 |
Token | friends |
Token ID | 2460 |
Feature activation | -2.53e-03 |
Pos logit contributions | |
bal | +0.064 |
uka | +0.064 |
Seth | +0.063 |
ird | +0.062 |
Tyler | +0.061 |
Neg logit contributions | |
rog | -0.056 |
arium | -0.055 |
acle | -0.054 |
Buzz | -0.053 |
atively | -0.050 |
Token | even |
Token ID | 772 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
bal | +0.004 |
Seth | +0.004 |
Tyler | +0.004 |
uka | +0.004 |
isc | +0.004 |
Neg logit contributions | |
rog | -0.004 |
acle | -0.003 |
arium | -0.003 |
Buzz | -0.003 |
Buzz | -0.003 |
Token | longer |
Token ID | 2392 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
bal | +0.345 |
Seth | +0.336 |
Tyler | +0.334 |
ird | +0.327 |
uka | +0.325 |
Neg logit contributions | |
rog | -0.336 |
acle | -0.323 |
arium | -0.320 |
Buzz | -0.308 |
Buzz | -0.307 |
Token | . |
Token ID | 13 |
Feature activation | -1.48e-02 |
Pos logit contributions | |
rog | +0.021 |
acle | +0.020 |
arium | +0.020 |
Buzz | +0.019 |
Buzz | +0.019 |
Neg logit contributions | |
bal | -0.021 |
Seth | -0.021 |
Tyler | -0.021 |
uka | -0.020 |
ird | -0.020 |
Token | So |
Token ID | 1406 |
Feature activation | +2.20e-02 |
Pos logit contributions | |
bal | +0.020 |
Tyler | +0.020 |
Seth | +0.020 |
Sel | +0.019 |
ird | +0.019 |
Neg logit contributions | |
rog | -0.025 |
acle | -0.025 |
arium | -0.023 |
Buzz | -0.023 |
atively | -0.022 |
Token | she |
Token ID | 673 |
Feature activation | -3.12e-02 |
Pos logit contributions | |
rog | +0.032 |
acle | +0.031 |
arium | +0.031 |
Buzz | +0.030 |
Buzz | +0.029 |
Neg logit contributions | |
bal | -0.035 |
Seth | -0.034 |
Tyler | -0.034 |
ird | -0.034 |
uka | -0.034 |
Token | decided |
Token ID | 3066 |
Feature activation | -8.90e-02 |
Pos logit contributions | |
bal | +0.047 |
Seth | +0.046 |
Tyler | +0.046 |
uka | +0.045 |
ird | +0.045 |
Neg logit contributions | |
rog | -0.048 |
acle | -0.046 |
arium | -0.046 |
Buzz | -0.044 |
Buzz | -0.044 |
Token | agreed |
Token ID | 4987 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
bal | +0.057 |
Seth | +0.055 |
Tyler | +0.055 |
ird | +0.055 |
Sel | +0.053 |
Neg logit contributions | |
rog | -0.059 |
acle | -0.056 |
arium | -0.055 |
Buzz | -0.053 |
Buzz | -0.053 |
Token | and |
Token ID | 290 |
Feature activation | -5.04e-03 |
Pos logit contributions | |
rog | +0.226 |
acle | +0.217 |
arium | +0.215 |
Buzz | +0.207 |
Buzz | +0.206 |
Neg logit contributions | |
bal | -0.244 |
Seth | -0.237 |
Tyler | -0.236 |
ird | -0.230 |
uka | -0.228 |
Token | kindly |
Token ID | 26820 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
bal | +0.009 |
cest | +0.009 |
pian | +0.009 |
laund | +0.009 |
uka | +0.009 |
Neg logit contributions | |
Buzz | -0.006 |
rog | -0.006 |
arium | -0.006 |
acle | -0.006 |
atively | -0.005 |
Token | gave |
Token ID | 2921 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
acle | +0.250 |
rog | +0.249 |
arium | +0.237 |
atively | +0.233 |
Buzz | +0.232 |
Neg logit contributions | |
bal | -0.301 |
uka | -0.293 |
Seth | -0.291 |
Tyler | -0.288 |
isc | -0.287 |
Token | Little |
Token ID | 7703 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
bal | +0.172 |
cest | +0.170 |
ird | +0.165 |
pian | +0.157 |
laund | +0.155 |
Neg logit contributions | |
rog | -0.170 |
arium | -0.157 |
Buzz | -0.156 |
acle | -0.152 |
beard | -0.148 |
Token | Johnny |
Token ID | 15470 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
bal | +0.162 |
ird | +0.148 |
Seth | +0.145 |
cest | +0.144 |
uka | +0.143 |
Neg logit contributions | |
rog | -0.442 |
acle | -0.429 |
arium | -0.423 |
Buzz | -0.413 |
Buzz | -0.409 |
Token | the |
Token ID | 262 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
bal | +0.415 |
Seth | +0.401 |
Tyler | +0.400 |
isc | +0.387 |
uka | +0.387 |
Neg logit contributions | |
rog | -0.375 |
acle | -0.363 |
arium | -0.357 |
Buzz | -0.345 |
Buzz | -0.340 |
Token | zipper |
Token ID | 48992 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
bal | +0.023 |
Seth | +0.022 |
Tyler | +0.022 |
uka | +0.022 |
ird | +0.022 |
Neg logit contributions | |
rog | -0.033 |
acle | -0.032 |
arium | -0.031 |
atively | -0.030 |
Buzz | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | -2.33e-02 |
Pos logit contributions | |
bal | +0.388 |
Seth | +0.375 |
Tyler | +0.373 |
ird | +0.367 |
uka | +0.362 |
Neg logit contributions | |
rog | -0.372 |
acle | -0.355 |
arium | -0.353 |
Buzz | -0.341 |
Buzz | -0.340 |
Token | |
Token ID | 220 |
Feature activation | +3.99e-02 |
Pos logit contributions | |
cest | +0.048 |
bal | +0.046 |
pian | +0.044 |
hairst | +0.043 |
sax | +0.043 |
Neg logit contributions | |
Buzz | -0.021 |
rog | -0.021 |
acle | -0.021 |
arium | -0.020 |
Freddie | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | -3.47e-02 |
Pos logit contributions | |
rog | +0.047 |
acle | +0.045 |
Buzz | +0.044 |
arium | +0.043 |
Buzz | +0.041 |
Neg logit contributions | |
bal | -0.074 |
cest | -0.073 |
pian | -0.072 |
laund | -0.071 |
roller | -0.069 |
Token | Grand |
Token ID | 5675 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
bal | +0.031 |
cest | +0.031 |
isc | +0.031 |
ird | +0.031 |
uka | +0.030 |
Neg logit contributions | |
Buzz | -0.024 |
rog | -0.024 |
arium | -0.023 |
acle | -0.023 |
Buzz | -0.022 |
Token | ma |
Token ID | 2611 |
Feature activation | +3.77e-02 |
Pos logit contributions | |
ird | +0.376 |
uka | +0.349 |
Tyler | +0.349 |
Su | +0.333 |
Seth | +0.330 |
Neg logit contributions | |
acle | -0.623 |
Buzz | -0.604 |
rog | -0.597 |
Buzz | -0.590 |
arium | -0.580 |
Token | got |
Token ID | 1392 |
Feature activation | -3.71e-02 |
Pos logit contributions | |
rog | +0.055 |
acle | +0.053 |
arium | +0.052 |
Buzz | +0.051 |
Buzz | +0.050 |
Neg logit contributions | |
bal | -0.059 |
Seth | -0.058 |
Tyler | -0.057 |
laund | -0.056 |
uka | -0.056 |
Token | out |
Token ID | 503 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
cest | +0.058 |
bal | +0.057 |
Seth | +0.056 |
Tyler | +0.056 |
ird | +0.056 |
Neg logit contributions | |
rog | -0.053 |
Buzz | -0.052 |
acle | -0.051 |
arium | -0.050 |
Buzz | -0.049 |
Token | three |
Token ID | 1115 |
Feature activation | +3.68e-02 |
Pos logit contributions | |
bal | +0.186 |
Seth | +0.180 |
Tyler | +0.179 |
ird | +0.174 |
uka | +0.174 |
Neg logit contributions | |
rog | -0.225 |
acle | -0.217 |
arium | -0.214 |
Buzz | -0.207 |
Buzz | -0.205 |
Token | m |
Token ID | 285 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
rog | +0.053 |
acle | +0.050 |
arium | +0.050 |
Buzz | +0.048 |
Buzz | +0.048 |
Neg logit contributions | |
bal | -0.060 |
Seth | -0.058 |
Tyler | -0.058 |
uka | -0.056 |
isc | -0.056 |
Token | ugs |
Token ID | 10339 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
bal | +0.331 |
Seth | +0.317 |
ird | +0.316 |
Tyler | +0.313 |
uka | +0.308 |
Neg logit contributions | |
rog | -0.449 |
arium | -0.441 |
acle | -0.440 |
Buzz | -0.421 |
Buzz | -0.420 |
Token | and |
Token ID | 290 |
Feature activation | -3.09e-03 |
Pos logit contributions | |
bal | +0.159 |
Seth | +0.155 |
Tyler | +0.154 |
uka | +0.150 |
ird | +0.150 |
Neg logit contributions | |
rog | -0.167 |
acle | -0.162 |
arium | -0.160 |
Buzz | -0.155 |
Buzz | -0.153 |
Token | poured |
Token ID | 19036 |
Feature activation | +1.95e-02 |
Pos logit contributions | |
cest | +0.005 |
bal | +0.005 |
isc | +0.005 |
uka | +0.005 |
laund | +0.005 |
Neg logit contributions | |
Buzz | -0.004 |
rog | -0.004 |
Buzz | -0.004 |
arium | -0.003 |
atively | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | +4.84e-02 |
Pos logit contributions | |
rog | +0.025 |
acle | +0.024 |
Buzz | +0.023 |
arium | +0.023 |
Buzz | +0.023 |
Neg logit contributions | |
bal | -0.034 |
Seth | -0.033 |
Tyler | -0.033 |
ird | -0.033 |
cest | -0.033 |
Token | big |
Token ID | 1263 |
Feature activation | -7.93e-02 |
Pos logit contributions | |
rog | +0.074 |
acle | +0.071 |
arium | +0.070 |
Buzz | +0.068 |
Buzz | +0.068 |
Neg logit contributions | |
bal | -0.073 |
Seth | -0.072 |
Tyler | -0.072 |
uka | -0.070 |
ird | -0.070 |
Token | Her |
Token ID | 2332 |
Feature activation | +8.53e-03 |
Pos logit contributions | |
bal | +0.020 |
Seth | +0.020 |
Tyler | +0.020 |
ird | +0.019 |
Sel | +0.019 |
Neg logit contributions | |
rog | -0.022 |
arium | -0.021 |
acle | -0.021 |
Buzz | -0.020 |
atively | -0.019 |
Token | nos |
Token ID | 43630 |
Feature activation | +3.27e-02 |
Pos logit contributions | |
rog | +0.015 |
acle | +0.014 |
arium | +0.014 |
Buzz | +0.014 |
Buzz | +0.014 |
Neg logit contributions | |
bal | -0.012 |
Seth | -0.011 |
Tyler | -0.011 |
ird | -0.011 |
laund | -0.011 |
Token | y |
Token ID | 88 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
acle | +0.042 |
rog | +0.042 |
arium | +0.042 |
Buzz | +0.039 |
Buzz | +0.039 |
Neg logit contributions | |
bal | -0.058 |
Seth | -0.058 |
Tyler | -0.057 |
cest | -0.056 |
isc | -0.055 |
Token | cat |
Token ID | 3797 |
Feature activation | -4.20e-02 |
Pos logit contributions | |
rog | +0.190 |
arium | +0.188 |
acle | +0.186 |
Buzz | +0.177 |
Buzz | +0.174 |
Neg logit contributions | |
bal | -0.191 |
Seth | -0.180 |
Tyler | -0.178 |
isc | -0.172 |
Sel | -0.172 |
Token | , |
Token ID | 11 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
bal | +0.064 |
Seth | +0.062 |
Tyler | +0.062 |
Sel | +0.059 |
ird | +0.059 |
Neg logit contributions | |
rog | -0.066 |
arium | -0.064 |
acle | -0.063 |
Buzz | -0.060 |
Buzz | -0.058 |
Token | Mitt |
Token ID | 16627 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
bal | +0.023 |
Seth | +0.022 |
Tyler | +0.022 |
ird | +0.022 |
uka | +0.022 |
Neg logit contributions | |
rog | -0.023 |
acle | -0.022 |
arium | -0.022 |
Buzz | -0.021 |
Buzz | -0.021 |
Token | ens |
Token ID | 641 |
Feature activation | +3.88e-02 |
Pos logit contributions | |
bal | +0.451 |
Seth | +0.436 |
Tyler | +0.435 |
isc | +0.422 |
ird | +0.422 |
Neg logit contributions | |
rog | -0.401 |
acle | -0.394 |
arium | -0.387 |
Buzz | -0.367 |
Buzz | -0.363 |
Token | , |
Token ID | 11 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
rog | +0.061 |
arium | +0.058 |
acle | +0.058 |
Buzz | +0.055 |
Buzz | +0.054 |
Neg logit contributions | |
bal | -0.058 |
Tyler | -0.057 |
Seth | -0.057 |
ird | -0.055 |
Sel | -0.054 |
Token | was |
Token ID | 373 |
Feature activation | -1.86e-02 |
Pos logit contributions | |
bal | +0.025 |
Seth | +0.025 |
Tyler | +0.024 |
ird | +0.024 |
uka | +0.024 |
Neg logit contributions | |
rog | -0.024 |
acle | -0.023 |
arium | -0.023 |
Buzz | -0.022 |
Buzz | -0.022 |
Token | following |
Token ID | 1708 |
Feature activation | +4.81e-02 |
Pos logit contributions | |
bal | +0.030 |
Seth | +0.029 |
ird | +0.028 |
isc | +0.028 |
Tyler | +0.028 |
Neg logit contributions | |
rog | -0.027 |
acle | -0.026 |
Buzz | -0.026 |
arium | -0.026 |
Buzz | -0.025 |
Token | her |
Token ID | 607 |
Feature activation | -4.04e-02 |
Pos logit contributions | |
acle | +0.081 |
arium | +0.081 |
rog | +0.080 |
Buzz | +0.077 |
atively | +0.075 |
Neg logit contributions | |
Tyler | -0.065 |
bal | -0.064 |
Seth | -0.064 |
Sel | -0.061 |
laund | -0.060 |
Token | help |
Token ID | 1037 |
Feature activation | +4.02e-02 |
Pos logit contributions | |
rog | +0.007 |
acle | +0.007 |
arium | +0.007 |
Buzz | +0.006 |
Buzz | +0.006 |
Neg logit contributions | |
bal | -0.007 |
Seth | -0.007 |
Tyler | -0.007 |
ird | -0.007 |
uka | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | -2.45e-02 |
Pos logit contributions | |
rog | +0.046 |
Buzz | +0.043 |
Buzz | +0.041 |
acle | +0.037 |
True | +0.037 |
Neg logit contributions | |
bal | -0.077 |
laund | -0.075 |
cest | -0.075 |
pian | -0.074 |
isc | -0.073 |
Token | cut |
Token ID | 2005 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
bal | +0.033 |
Seth | +0.032 |
Tyler | +0.032 |
ird | +0.031 |
uka | +0.031 |
Neg logit contributions | |
rog | -0.042 |
acle | -0.041 |
arium | -0.040 |
Buzz | -0.039 |
Buzz | -0.039 |
Token | heal |
Token ID | 12035 |
Feature activation | +5.03e-02 |
Pos logit contributions | |
bal | +0.205 |
Tyler | +0.201 |
Seth | +0.201 |
laund | +0.197 |
uka | +0.196 |
Neg logit contributions | |
rog | -0.191 |
acle | -0.181 |
Buzz | -0.176 |
arium | -0.176 |
Buzz | -0.174 |
Token | . |
Token ID | 13 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
rog | +0.071 |
acle | +0.067 |
Buzz | +0.066 |
arium | +0.066 |
Buzz | +0.065 |
Neg logit contributions | |
bal | -0.082 |
Seth | -0.080 |
Tyler | -0.080 |
laund | -0.079 |
uka | -0.079 |
Token | Cand |
Token ID | 15518 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
cest | +0.021 |
bal | +0.019 |
laund | +0.019 |
uka | +0.019 |
ird | +0.019 |
Neg logit contributions | |
Buzz | -0.014 |
rog | -0.014 |
acle | -0.013 |
True | -0.013 |
Buzz | -0.013 |
Token | ace |
Token ID | 558 |
Feature activation | +7.76e-02 |
Pos logit contributions | |
bal | +0.385 |
Seth | +0.367 |
uka | +0.366 |
isc | +0.364 |
ird | +0.362 |
Neg logit contributions | |
acle | -0.365 |
arium | -0.349 |
rog | -0.340 |
Buzz | -0.330 |
Buzz | -0.320 |
Token | was |
Token ID | 373 |
Feature activation | -2.07e-02 |
Pos logit contributions | |
rog | +0.136 |
acle | +0.135 |
arium | +0.131 |
Buzz | +0.119 |
atively | +0.118 |
Neg logit contributions | |
bal | -0.108 |
ird | -0.101 |
Seth | -0.096 |
Tyler | -0.095 |
Sel | -0.095 |
Token | so |
Token ID | 523 |
Feature activation | -8.74e-02 |
Pos logit contributions | |
bal | +0.032 |
Seth | +0.032 |
Tyler | +0.031 |
isc | +0.031 |
uka | +0.031 |
Neg logit contributions | |
rog | -0.031 |
acle | -0.030 |
arium | -0.029 |
Buzz | -0.029 |
Buzz | -0.028 |
Token | proud |
Token ID | 6613 |
Feature activation | -8.65e-02 |
Pos logit contributions | |
bal | +0.117 |
ird | +0.109 |
cest | +0.104 |
uka | +0.103 |
Seth | +0.103 |
Neg logit contributions | |
rog | -0.160 |
arium | -0.155 |
acle | -0.153 |
atively | -0.142 |
Buzz | -0.139 |
Token | of |
Token ID | 286 |
Feature activation | -8.11e-02 |
Pos logit contributions | |
uka | +0.158 |
laund | +0.157 |
Seth | +0.157 |
ird | +0.156 |
isc | +0.155 |
Neg logit contributions | |
Buzz | -0.099 |
rog | -0.099 |
arium | -0.098 |
acle | -0.091 |
Buzz | -0.087 |