Token | canned |
Token ID | 32530 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
aney | +0.000 |
of | +0.000 |
hest | +0.000 |
iky | +0.000 |
isy | +0.000 |
Neg logit contributions | |
Sorry | -0.000 |
H | -0.000 |
ulk | -0.000 |
fired | -0.000 |
minded | -0.000 |
Token | and |
Token ID | 290 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
aney | +0.031 |
hest | +0.028 |
iky | +0.027 |
isy | +0.025 |
pole | +0.024 |
Neg logit contributions | |
elbows | -0.019 |
minded | -0.019 |
Sorry | -0.018 |
late | -0.018 |
ulk | -0.018 |
Token | jar |
Token ID | 17379 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
aney | +0.001 |
hest | +0.001 |
of | +0.001 |
iky | +0.001 |
isy | +0.001 |
Neg logit contributions | |
Sorry | -0.001 |
elbows | -0.001 |
ulk | -0.001 |
fired | -0.001 |
H | -0.001 |
Token | red |
Token ID | 445 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
aney | +0.035 |
iky | +0.030 |
hest | +0.029 |
isy | +0.027 |
affe | +0.027 |
Neg logit contributions | |
late | -0.026 |
fired | -0.023 |
ulk | -0.022 |
H | -0.022 |
minded | -0.022 |
Token | and |
Token ID | 290 |
Feature activation | +7.31e-03 |
Pos logit contributions | |
late | +0.099 |
Sorry | +0.096 |
H | +0.095 |
minded | +0.095 |
fired | +0.094 |
Neg logit contributions | |
aney | -0.146 |
hest | -0.132 |
iky | -0.126 |
of | -0.120 |
isy | -0.118 |
Token | bottled |
Token ID | 34123 |
Feature activation | +6.17e+00 |
Pos logit contributions | |
Sorry | +0.001 |
elbows | +0.001 |
ulk | +0.001 |
fired | +0.001 |
H | +0.001 |
Neg logit contributions | |
aney | -0.001 |
hest | -0.001 |
of | -0.001 |
iky | -0.001 |
isy | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | +1.53e-02 |
Pos logit contributions | |
Sorry | +0.420 |
elbows | +0.409 |
ulk | +0.395 |
fired | +0.395 |
H | +0.392 |
Neg logit contributions | |
aney | -0.712 |
hest | -0.655 |
of | -0.627 |
iky | -0.626 |
isy | -0.588 |
Token | vacuum |
Token ID | 17076 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
Sorry | +0.001 |
elbows | +0.001 |
ulk | +0.001 |
fired | +0.001 |
H | +0.001 |
Neg logit contributions | |
aney | -0.002 |
hest | -0.001 |
of | -0.001 |
iky | -0.001 |
isy | -0.001 |
Token | - |
Token ID | 12 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
aney | +0.127 |
hest | +0.114 |
iky | +0.110 |
of | +0.108 |
isy | +0.104 |
Neg logit contributions | |
Sorry | -0.079 |
elbows | -0.077 |
H | -0.075 |
ulk | -0.075 |
late | -0.075 |
Token | se |
Token ID | 325 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
Sorry | +0.224 |
elbows | +0.219 |
ulk | +0.209 |
fired | +0.209 |
H | +0.207 |
Neg logit contributions | |
aney | -0.289 |
hest | -0.262 |
of | -0.255 |
iky | -0.249 |
isy | -0.233 |
Token | aled |
Token ID | 3021 |
Feature activation | -8.31e-01 |
Pos logit contributions | |
elbows | +0.113 |
fired | +0.112 |
H | +0.111 |
late | +0.111 |
minded | +0.110 |
Neg logit contributions | |
aney | -0.170 |
hest | -0.149 |
iky | -0.145 |
isy | -0.136 |
of | -0.132 |
Token | the |
Token ID | 262 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
Sorry | +0.025 |
minded | +0.023 |
elbows | +0.023 |
ulk | +0.022 |
fired | +0.022 |
Neg logit contributions | |
aney | -0.029 |
of | -0.028 |
hest | -0.025 |
iky | -0.023 |
contain | -0.023 |
Token | store |
Token ID | 3650 |
Feature activation | -5.94e-01 |
Pos logit contributions | |
Sorry | +0.028 |
elbows | +0.027 |
ulk | +0.026 |
fired | +0.026 |
H | +0.025 |
Neg logit contributions | |
aney | -0.037 |
of | -0.034 |
hest | -0.034 |
iky | -0.032 |
isy | -0.030 |
Token | and |
Token ID | 290 |
Feature activation | +2.49e-02 |
Pos logit contributions | |
aney | +0.060 |
hest | +0.054 |
iky | +0.052 |
of | +0.050 |
isy | +0.048 |
Neg logit contributions | |
Sorry | -0.049 |
late | -0.049 |
fired | -0.048 |
elbows | -0.048 |
H | -0.048 |
Token | buy |
Token ID | 2822 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
elbows | +0.002 |
ulk | +0.002 |
Sorry | +0.002 |
minded | +0.002 |
fired | +0.002 |
Neg logit contributions | |
aney | -0.002 |
of | -0.002 |
hest | -0.002 |
contain | -0.002 |
isy | -0.002 |
Token | some |
Token ID | 617 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
aney | +0.123 |
hest | +0.113 |
of | +0.110 |
iky | +0.108 |
isy | +0.102 |
Neg logit contributions | |
Sorry | -0.063 |
elbows | -0.061 |
ulk | -0.059 |
fired | -0.059 |
H | -0.058 |
Token | bottled |
Token ID | 34123 |
Feature activation | +5.86e+00 |
Pos logit contributions | |
aney | +0.020 |
hest | +0.017 |
iky | +0.016 |
pole | +0.016 |
aces | +0.016 |
Neg logit contributions | |
late | -0.010 |
H | -0.009 |
something | -0.009 |
Sorry | -0.009 |
heaven | -0.008 |
Token | water |
Token ID | 1660 |
Feature activation | +4.38e-01 |
Pos logit contributions | |
Sorry | +0.459 |
elbows | +0.446 |
ulk | +0.435 |
fired | +0.434 |
H | +0.432 |
Neg logit contributions | |
aney | -0.620 |
hest | -0.561 |
of | -0.541 |
iky | -0.536 |
isy | -0.501 |
Token | . |
Token ID | 13 |
Feature activation | +4.62e-02 |
Pos logit contributions | |
late | +0.031 |
H | +0.030 |
Sorry | +0.030 |
fired | +0.030 |
minded | +0.029 |
Neg logit contributions | |
aney | -0.050 |
hest | -0.045 |
iky | -0.043 |
isy | -0.041 |
of | -0.038 |
Token | Lily |
Token ID | 20037 |
Feature activation | +4.93e-01 |
Pos logit contributions | |
elbows | +0.004 |
fired | +0.003 |
Sorry | +0.003 |
ulk | +0.003 |
minded | +0.003 |
Neg logit contributions | |
aney | -0.005 |
of | -0.005 |
hest | -0.004 |
isy | -0.004 |
iky | -0.004 |
Token | was |
Token ID | 373 |
Feature activation | -7.24e-02 |
Pos logit contributions | |
Sorry | +0.031 |
H | +0.031 |
fired | +0.031 |
elbows | +0.031 |
late | +0.030 |
Neg logit contributions | |
aney | -0.058 |
hest | -0.054 |
iky | -0.052 |
of | -0.050 |
iest | -0.049 |
Token | happy |
Token ID | 3772 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
aney | +0.008 |
hest | +0.008 |
iky | +0.008 |
iest | +0.007 |
arrow | +0.007 |
Neg logit contributions | |
late | -0.006 |
elbows | -0.005 |
H | -0.005 |
ulk | -0.005 |
heaven | -0.005 |
Token | watched |
Token ID | 7342 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
Sorry | +0.016 |
elbows | +0.016 |
H | +0.016 |
fired | +0.016 |
ulk | +0.015 |
Neg logit contributions | |
aney | -0.031 |
hest | -0.029 |
iky | -0.027 |
of | -0.027 |
isy | -0.025 |
Token | , |
Token ID | 11 |
Feature activation | +3.54e-02 |
Pos logit contributions | |
aney | +0.162 |
hest | +0.149 |
iky | +0.144 |
of | +0.140 |
isy | +0.134 |
Neg logit contributions | |
Sorry | -0.077 |
elbows | -0.074 |
H | -0.073 |
ulk | -0.071 |
late | -0.071 |
Token | she |
Token ID | 673 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
elbows | +0.004 |
minded | +0.004 |
Sorry | +0.003 |
fired | +0.003 |
ulk | +0.003 |
Neg logit contributions | |
of | -0.003 |
aney | -0.002 |
iest | -0.002 |
hest | -0.002 |
isy | -0.002 |
Token | realized |
Token ID | 6939 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
Sorry | +0.020 |
elbows | +0.019 |
ulk | +0.019 |
late | +0.019 |
fired | +0.019 |
Neg logit contributions | |
aney | -0.036 |
hest | -0.033 |
of | -0.033 |
iky | -0.032 |
isy | -0.030 |
Token | that |
Token ID | 326 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
Sorry | +0.028 |
elbows | +0.027 |
ulk | +0.026 |
fired | +0.026 |
minded | +0.026 |
Neg logit contributions | |
aney | -0.040 |
of | -0.036 |
hest | -0.036 |
iky | -0.035 |
isy | -0.033 |
Token | Â |
Token ID | 5523 |
Feature activation | +5.04e+00 |
Pos logit contributions | |
Sorry | +0.021 |
elbows | +0.020 |
ulk | +0.020 |
fired | +0.020 |
minded | +0.019 |
Neg logit contributions | |
of | -0.027 |
aney | -0.026 |
hest | -0.024 |
iky | -0.023 |
iest | -0.022 |
Token | |
Token ID | 1849 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
Sorry | +0.362 |
ulk | +0.344 |
elbows | +0.343 |
minded | +0.340 |
fired | +0.334 |
Neg logit contributions | |
aney | -0.576 |
of | -0.536 |
hest | -0.507 |
iky | -0.493 |
isy | -0.475 |
Token | the |
Token ID | 1169 |
Feature activation | -7.66e-01 |
Pos logit contributions | |
Sorry | +0.181 |
elbows | +0.177 |
ulk | +0.174 |
late | +0.173 |
fired | +0.172 |
Neg logit contributions | |
aney | -0.313 |
hest | -0.286 |
iky | -0.276 |
of | -0.274 |
isy | -0.259 |
Token | ground |
Token ID | 2323 |
Feature activation | -6.52e-01 |
Pos logit contributions | |
aney | +0.083 |
hest | +0.074 |
iky | +0.069 |
of | +0.067 |
umbs | +0.064 |
Neg logit contributions | |
Sorry | -0.059 |
elbows | -0.058 |
late | -0.058 |
fired | -0.055 |
H | -0.055 |
Token | was |
Token ID | 373 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
aney | +0.078 |
hest | +0.072 |
iky | +0.065 |
isy | +0.064 |
umbs | +0.063 |
Neg logit contributions | |
fired | -0.043 |
Sorry | -0.041 |
elbows | -0.040 |
H | -0.040 |
late | -0.040 |
Token | alive |
Token ID | 6776 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
aney | +0.018 |
hest | +0.017 |
iky | +0.016 |
umbs | +0.015 |
isy | +0.015 |
Neg logit contributions | |
late | -0.011 |
H | -0.010 |
elbows | -0.009 |
fired | -0.009 |
something | -0.009 |
Token | baby |
Token ID | 5156 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
aney | +0.064 |
hest | +0.058 |
iky | +0.056 |
of | +0.055 |
isy | +0.051 |
Neg logit contributions | |
Sorry | -0.046 |
elbows | -0.044 |
H | -0.044 |
late | -0.043 |
ulk | -0.043 |
Token | thought |
Token ID | 1807 |
Feature activation | -5.18e-01 |
Pos logit contributions | |
aney | +0.120 |
hest | +0.108 |
of | +0.106 |
iky | +0.103 |
isy | +0.097 |
Neg logit contributions | |
Sorry | -0.100 |
elbows | -0.097 |
ulk | -0.096 |
fired | -0.095 |
late | -0.094 |
Token | about |
Token ID | 546 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
aney | +0.056 |
hest | +0.051 |
umbs | +0.049 |
iky | +0.048 |
arrow | +0.044 |
Neg logit contributions | |
H | -0.038 |
late | -0.038 |
Tiny | -0.037 |
fired | -0.037 |
Tina | -0.036 |
Token | the |
Token ID | 262 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
aney | +0.041 |
of | +0.039 |
hest | +0.037 |
iky | +0.036 |
isy | +0.035 |
Neg logit contributions | |
Sorry | -0.029 |
elbows | -0.028 |
late | -0.027 |
fired | -0.027 |
ulk | -0.026 |
Token | night |
Token ID | 1755 |
Feature activation | +7.46e-01 |
Pos logit contributions | |
Sorry | +0.027 |
elbows | +0.026 |
H | +0.026 |
late | +0.026 |
ulk | +0.026 |
Neg logit contributions | |
aney | -0.034 |
hest | -0.030 |
of | -0.029 |
iky | -0.029 |
isy | -0.027 |
Token | Â |
Token ID | 5523 |
Feature activation | +4.99e+00 |
Pos logit contributions | |
Sorry | +0.064 |
late | +0.063 |
elbows | +0.062 |
H | +0.062 |
fired | +0.062 |
Neg logit contributions | |
aney | -0.072 |
hest | -0.064 |
iky | -0.062 |
of | -0.058 |
isy | -0.056 |
Token | ´ |
Token ID | 18265 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
Sorry | +0.377 |
elbows | +0.370 |
ulk | +0.363 |
minded | +0.357 |
fired | +0.352 |
Neg logit contributions | |
aney | -0.553 |
of | -0.500 |
hest | -0.489 |
iky | -0.471 |
isy | -0.450 |
Token | s |
Token ID | 82 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
elbows | +0.173 |
Sorry | +0.168 |
ulk | +0.163 |
fired | +0.159 |
H | +0.157 |
Neg logit contributions | |
aney | -0.225 |
hest | -0.206 |
of | -0.200 |
iky | -0.196 |
isy | -0.182 |
Token | adventure |
Token ID | 8855 |
Feature activation | -6.46e-01 |
Pos logit contributions | |
elbows | +0.123 |
Sorry | +0.121 |
H | +0.120 |
fired | +0.120 |
late | +0.119 |
Neg logit contributions | |
aney | -0.195 |
hest | -0.180 |
iky | -0.168 |
umbs | -0.155 |
of | -0.155 |
Token | as |
Token ID | 355 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
aney | +0.069 |
hest | +0.063 |
iky | +0.061 |
umbs | +0.055 |
isy | +0.054 |
Neg logit contributions | |
late | -0.048 |
H | -0.047 |
fired | -0.047 |
Sorry | -0.046 |
minded | -0.045 |
Token | she |
Token ID | 673 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
Sorry | +0.016 |
elbows | +0.016 |
ulk | +0.016 |
fired | +0.015 |
minded | +0.015 |
Neg logit contributions | |
aney | -0.027 |
of | -0.025 |
hest | -0.025 |
iky | -0.024 |
isy | -0.023 |
Token | floor |
Token ID | 4314 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
elbows | +0.031 |
H | +0.030 |
late | +0.028 |
Sorry | +0.028 |
minded | +0.028 |
Neg logit contributions | |
aney | -0.035 |
hest | -0.028 |
iky | -0.027 |
of | -0.027 |
umbs | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | -8.72e-02 |
Pos logit contributions | |
aney | +0.161 |
hest | +0.147 |
isy | +0.138 |
iky | +0.136 |
iest | +0.132 |
Neg logit contributions | |
late | -0.069 |
elbows | -0.063 |
ulk | -0.062 |
fired | -0.062 |
backward | -0.061 |
Token |
|
Token ID | 198 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
aney | +0.010 |
hest | +0.010 |
iky | +0.009 |
of | +0.009 |
isy | +0.009 |
Neg logit contributions | |
Sorry | -0.006 |
elbows | -0.005 |
late | -0.005 |
H | -0.005 |
ulk | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
Sorry | +0.008 |
late | +0.008 |
H | +0.007 |
ulk | +0.007 |
fired | +0.007 |
Neg logit contributions | |
aney | -0.019 |
hest | -0.018 |
iky | -0.017 |
of | -0.017 |
isy | -0.016 |
Token | " |
Token ID | 1 |
Feature activation | +4.21e-01 |
Pos logit contributions | |
Sorry | +0.008 |
elbows | +0.008 |
ulk | +0.008 |
fired | +0.008 |
H | +0.008 |
Neg logit contributions | |
aney | -0.011 |
hest | -0.010 |
of | -0.010 |
iky | -0.010 |
isy | -0.009 |
Token | Â |
Token ID | 5523 |
Feature activation | +4.76e+00 |
Pos logit contributions | |
Sorry | +0.023 |
elbows | +0.023 |
fired | +0.022 |
ulk | +0.022 |
late | +0.022 |
Neg logit contributions | |
aney | -0.054 |
hest | -0.050 |
of | -0.048 |
iky | -0.048 |
isy | -0.045 |
Token | � |
Token ID | 126 |
Feature activation | +3.54e-02 |
Pos logit contributions | |
elbows | +0.368 |
fired | +0.362 |
ulk | +0.360 |
Sorry | +0.359 |
minded | +0.346 |
Neg logit contributions | |
aney | -0.486 |
of | -0.485 |
hest | -0.451 |
iky | -0.427 |
isy | -0.399 |
Token | � |
Token ID | 94 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
H | +0.003 |
Sorry | +0.003 |
late | +0.002 |
ulk | +0.002 |
elbows | +0.002 |
Neg logit contributions | |
aney | -0.004 |
of | -0.003 |
hest | -0.003 |
iky | -0.003 |
iest | -0.003 |
Token | M |
Token ID | 44 |
Feature activation | +6.29e-01 |
Pos logit contributions | |
elbows | +0.183 |
Sorry | +0.182 |
fired | +0.177 |
H | +0.172 |
minded | +0.169 |
Neg logit contributions | |
aney | -0.217 |
hest | -0.202 |
iky | -0.189 |
of | -0.189 |
isy | -0.170 |
Token | ira |
Token ID | 8704 |
Feature activation | +7.59e-01 |
Pos logit contributions | |
Sorry | +0.070 |
elbows | +0.067 |
ulk | +0.067 |
H | +0.067 |
fired | +0.067 |
Neg logit contributions | |
aney | -0.047 |
hest | -0.040 |
of | -0.038 |
iky | -0.037 |
isy | -0.034 |
Token | mi |
Token ID | 21504 |
Feature activation | -7.27e-02 |
Pos logit contributions | |
Sorry | +0.060 |
H | +0.058 |
elbows | +0.057 |
fired | +0.057 |
minded | +0.056 |
Neg logit contributions | |
aney | -0.080 |
hest | -0.071 |
iky | -0.068 |
of | -0.066 |
isy | -0.062 |
Token | a |
Token ID | 257 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
aney | +0.016 |
hest | +0.015 |
iky | +0.014 |
of | +0.014 |
isy | +0.014 |
Neg logit contributions | |
Sorry | -0.006 |
elbows | -0.006 |
late | -0.006 |
H | -0.006 |
ulk | -0.006 |
Token | loud |
Token ID | 7812 |
Feature activation | +9.95e-02 |
Pos logit contributions | |
Sorry | +0.010 |
elbows | +0.010 |
ulk | +0.010 |
fired | +0.010 |
H | +0.010 |
Neg logit contributions | |
aney | -0.011 |
hest | -0.010 |
of | -0.010 |
iky | -0.010 |
isy | -0.009 |
Token | * |
Token ID | 1635 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
Sorry | +0.007 |
elbows | +0.006 |
ulk | +0.006 |
fired | +0.006 |
H | +0.006 |
Neg logit contributions | |
aney | -0.012 |
hest | -0.011 |
of | -0.010 |
iky | -0.010 |
isy | -0.010 |
Token | be |
Token ID | 1350 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
Sorry | +0.151 |
elbows | +0.147 |
fired | +0.142 |
ulk | +0.142 |
H | +0.141 |
Neg logit contributions | |
aney | -0.204 |
hest | -0.185 |
of | -0.179 |
iky | -0.176 |
isy | -0.163 |
Token | ep |
Token ID | 538 |
Feature activation | +6.87e-01 |
Pos logit contributions | |
elbows | +0.099 |
ulk | +0.097 |
late | +0.097 |
Sorry | +0.095 |
fired | +0.092 |
Neg logit contributions | |
aney | -0.163 |
hest | -0.153 |
iky | -0.145 |
of | -0.136 |
isy | -0.134 |
Token | * |
Token ID | 9 |
Feature activation | +4.59e+00 |
Pos logit contributions | |
Sorry | +0.051 |
late | +0.051 |
fired | +0.050 |
ulk | +0.050 |
elbows | +0.049 |
Neg logit contributions | |
aney | -0.073 |
hest | -0.066 |
iky | -0.064 |
isy | -0.058 |
aces | -0.057 |
Token | from |
Token ID | 422 |
Feature activation | -7.87e-01 |
Pos logit contributions | |
late | +0.357 |
Sorry | +0.347 |
H | +0.327 |
elbows | +0.323 |
ulk | +0.318 |
Neg logit contributions | |
aney | -0.505 |
hest | -0.460 |
iky | -0.438 |
isy | -0.422 |
aces | -0.406 |
Token | the |
Token ID | 262 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
aney | +0.091 |
hest | +0.083 |
of | +0.082 |
iky | +0.080 |
isy | +0.075 |
Neg logit contributions | |
Sorry | -0.054 |
elbows | -0.051 |
ulk | -0.050 |
fired | -0.050 |
H | -0.049 |
Token | oven |
Token ID | 14361 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
Sorry | +0.030 |
late | +0.029 |
elbows | +0.029 |
minded | +0.027 |
heaven | +0.027 |
Neg logit contributions | |
aney | -0.034 |
hest | -0.031 |
iky | -0.030 |
aces | -0.029 |
of | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
aney | +0.193 |
hest | +0.175 |
iky | +0.171 |
isy | +0.159 |
aces | +0.155 |
Neg logit contributions | |
Sorry | -0.133 |
late | -0.132 |
fired | -0.128 |
elbows | -0.127 |
ulk | -0.125 |
Token | The |
Token ID | 383 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
elbows | +0.015 |
Sorry | +0.014 |
fired | +0.014 |
ulk | +0.014 |
minded | +0.014 |
Neg logit contributions | |
aney | -0.021 |
of | -0.019 |
hest | -0.019 |
iky | -0.017 |
umbs | -0.016 |
Token | her |
Token ID | 607 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
aney | +0.169 |
hest | +0.153 |
iky | +0.147 |
of | +0.146 |
isy | +0.137 |
Neg logit contributions | |
elbows | -0.096 |
Sorry | -0.095 |
H | -0.092 |
ulk | -0.091 |
late | -0.090 |
Token | sweater |
Token ID | 35685 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
aney | +0.014 |
hest | +0.013 |
iky | +0.012 |
of | +0.012 |
igator | +0.011 |
Neg logit contributions | |
elbows | -0.008 |
H | -0.007 |
Sorry | -0.007 |
fired | -0.007 |
Tiny | -0.007 |
Token | * |
Token ID | 1635 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
aney | +0.029 |
hest | +0.026 |
iky | +0.025 |
isy | +0.023 |
of | +0.023 |
Neg logit contributions | |
elbows | -0.016 |
fired | -0.016 |
H | -0.016 |
Sorry | -0.016 |
late | -0.015 |
Token | po |
Token ID | 7501 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
Sorry | +0.156 |
elbows | +0.152 |
ulk | +0.149 |
fired | +0.148 |
H | +0.147 |
Neg logit contributions | |
aney | -0.190 |
hest | -0.171 |
of | -0.165 |
iky | -0.163 |
isy | -0.152 |
Token | pped |
Token ID | 1496 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
Sorry | +0.093 |
elbows | +0.090 |
ulk | +0.088 |
fired | +0.087 |
late | +0.087 |
Neg logit contributions | |
aney | -0.097 |
hest | -0.087 |
of | -0.084 |
iky | -0.083 |
isy | -0.077 |
Token | * |
Token ID | 9 |
Feature activation | +4.50e+00 |
Pos logit contributions | |
late | +0.023 |
H | +0.022 |
Sorry | +0.021 |
fired | +0.021 |
elbows | +0.021 |
Neg logit contributions | |
aney | -0.050 |
hest | -0.045 |
iky | -0.043 |
isy | -0.041 |
aces | -0.040 |
Token | ! |
Token ID | 0 |
Feature activation | +5.74e-01 |
Pos logit contributions | |
Sorry | +0.330 |
H | +0.320 |
late | +0.315 |
elbows | +0.303 |
ulk | +0.301 |
Neg logit contributions | |
aney | -0.502 |
hest | -0.450 |
iky | -0.440 |
of | -0.416 |
isy | -0.404 |
Token | Everyone |
Token ID | 11075 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
elbows | +0.042 |
Sorry | +0.042 |
ulk | +0.041 |
fired | +0.041 |
minded | +0.041 |
Neg logit contributions | |
aney | -0.063 |
of | -0.057 |
hest | -0.057 |
iky | -0.053 |
isy | -0.050 |
Token | stopped |
Token ID | 5025 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
Sorry | +0.027 |
fired | +0.027 |
ulk | +0.025 |
late | +0.025 |
elbows | +0.025 |
Neg logit contributions | |
aney | -0.045 |
hest | -0.043 |
iky | -0.041 |
aces | -0.038 |
umbs | -0.038 |
Token | and |
Token ID | 290 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
Sorry | +0.098 |
ulk | +0.089 |
minded | +0.088 |
fired | +0.087 |
elbows | +0.086 |
Neg logit contributions | |
aney | -0.091 |
of | -0.087 |
hest | -0.079 |
iky | -0.078 |
isy | -0.072 |
Token | looked |
Token ID | 3114 |
Feature activation | -1.80e-02 |
Pos logit contributions | |
elbows | +0.013 |
ulk | +0.013 |
Sorry | +0.013 |
late | +0.012 |
fired | +0.012 |
Neg logit contributions | |
aney | -0.014 |
of | -0.013 |
hest | -0.011 |
isy | -0.011 |
contain | -0.011 |
Token | inside |
Token ID | 2641 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
Sorry | +0.025 |
elbows | +0.023 |
minded | +0.023 |
ulk | +0.022 |
Does | +0.021 |
Neg logit contributions | |
aney | -0.032 |
of | -0.032 |
hest | -0.027 |
iky | -0.025 |
iest | -0.025 |
Token | , |
Token ID | 11 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
aney | +0.030 |
hest | +0.028 |
iky | +0.027 |
isy | +0.025 |
aces | +0.024 |
Neg logit contributions | |
Sorry | -0.020 |
fired | -0.020 |
late | -0.020 |
H | -0.020 |
elbows | -0.020 |
Token | Amy |
Token ID | 14235 |
Feature activation | -7.19e-01 |
Pos logit contributions | |
elbows | +0.014 |
Sorry | +0.014 |
ulk | +0.014 |
minded | +0.014 |
H | +0.014 |
Neg logit contributions | |
aney | -0.020 |
of | -0.019 |
hest | -0.018 |
isy | -0.016 |
iky | -0.016 |
Token | saw |
Token ID | 2497 |
Feature activation | +3.63e-03 |
Pos logit contributions | |
aney | +0.085 |
hest | +0.080 |
iky | +0.077 |
of | +0.074 |
iest | +0.070 |
Neg logit contributions | |
fired | -0.045 |
elbows | -0.044 |
H | -0.044 |
Sorry | -0.043 |
late | -0.043 |
Token | snow |
Token ID | 6729 |
Feature activation | +2.50e-02 |
Pos logit contributions | |
Sorry | +0.000 |
elbows | +0.000 |
ulk | +0.000 |
fired | +0.000 |
H | +0.000 |
Neg logit contributions | |
aney | -0.000 |
hest | -0.000 |
iky | -0.000 |
of | -0.000 |
isy | -0.000 |
Token | fl |
Token ID | 2704 |
Feature activation | +4.47e+00 |
Pos logit contributions | |
elbows | +0.002 |
Sorry | +0.002 |
ulk | +0.002 |
H | +0.002 |
late | +0.002 |
Neg logit contributions | |
aney | -0.003 |
hest | -0.003 |
iky | -0.002 |
of | -0.002 |
isy | -0.002 |
Token | akes |
Token ID | 1124 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
elbows | +0.346 |
Sorry | +0.328 |
ulk | +0.321 |
fired | +0.306 |
H | +0.306 |
Neg logit contributions | |
aney | -0.467 |
hest | -0.406 |
isy | -0.398 |
igator | -0.393 |
iky | -0.392 |
Token | falling |
Token ID | 7463 |
Feature activation | -5.74e-01 |
Pos logit contributions | |
late | +0.075 |
elbows | +0.074 |
ulk | +0.071 |
fired | +0.069 |
dreaming | +0.068 |
Neg logit contributions | |
aney | -0.138 |
hest | -0.118 |
iky | -0.113 |
isy | -0.107 |
aces | -0.107 |
Token | from |
Token ID | 422 |
Feature activation | -7.11e-01 |
Pos logit contributions | |
aney | +0.078 |
hest | +0.069 |
isy | +0.066 |
iky | +0.066 |
of | +0.063 |
Neg logit contributions | |
late | -0.031 |
H | -0.030 |
elbows | -0.028 |
fired | -0.028 |
Sorry | -0.028 |
Token | the |
Token ID | 262 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
aney | +0.083 |
hest | +0.076 |
of | +0.075 |
iky | +0.074 |
isy | +0.069 |
Neg logit contributions | |
Sorry | -0.047 |
elbows | -0.045 |
ulk | -0.044 |
fired | -0.044 |
H | -0.044 |
Token | sky |
Token ID | 6766 |
Feature activation | +4.49e-02 |
Pos logit contributions | |
elbows | +0.030 |
Sorry | +0.030 |
H | +0.030 |
late | +0.030 |
fired | +0.028 |
Neg logit contributions | |
aney | -0.037 |
hest | -0.032 |
iky | -0.030 |
of | -0.030 |
isy | -0.028 |
Token | something |
Token ID | 1223 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
aney | +0.000 |
hest | +0.000 |
of | +0.000 |
iky | +0.000 |
isy | +0.000 |
Neg logit contributions | |
Sorry | -0.000 |
elbows | -0.000 |
ulk | -0.000 |
fired | -0.000 |
late | -0.000 |
Token | moving |
Token ID | 3867 |
Feature activation | -6.99e-01 |
Pos logit contributions | |
late | +0.027 |
H | +0.027 |
fired | +0.026 |
elbows | +0.026 |
Sorry | +0.025 |
Neg logit contributions | |
aney | -0.044 |
hest | -0.038 |
umbs | -0.035 |
iky | -0.035 |
aces | -0.035 |
Token | in |
Token ID | 287 |
Feature activation | +7.85e-02 |
Pos logit contributions | |
aney | +0.076 |
hest | +0.069 |
iky | +0.066 |
of | +0.065 |
isy | +0.062 |
Neg logit contributions | |
Sorry | -0.051 |
elbows | -0.051 |
fired | -0.051 |
late | -0.051 |
H | -0.050 |
Token | the |
Token ID | 262 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
Sorry | +0.005 |
elbows | +0.005 |
late | +0.004 |
ulk | +0.004 |
fired | +0.004 |
Neg logit contributions | |
aney | -0.010 |
hest | -0.009 |
iky | -0.009 |
of | -0.009 |
isy | -0.008 |
Token | wild |
Token ID | 4295 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
elbows | +0.021 |
Sorry | +0.021 |
late | +0.021 |
fired | +0.021 |
ulk | +0.020 |
Neg logit contributions | |
aney | -0.028 |
hest | -0.025 |
iky | -0.024 |
of | -0.024 |
isy | -0.022 |
Token | fl |
Token ID | 2704 |
Feature activation | +4.45e+00 |
Pos logit contributions | |
aney | +0.013 |
hest | +0.012 |
iky | +0.011 |
of | +0.011 |
isy | +0.010 |
Neg logit contributions | |
elbows | -0.009 |
fired | -0.009 |
Sorry | -0.009 |
H | -0.009 |
late | -0.009 |
Token | owers |
Token ID | 3618 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
elbows | +0.361 |
Sorry | +0.348 |
ulk | +0.344 |
fired | +0.339 |
late | +0.320 |
Neg logit contributions | |
aney | -0.455 |
hest | -0.394 |
iky | -0.384 |
of | -0.383 |
isy | -0.366 |
Token | . |
Token ID | 13 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
late | +0.067 |
fired | +0.067 |
elbows | +0.065 |
Sorry | +0.063 |
H | +0.062 |
Neg logit contributions | |
aney | -0.121 |
hest | -0.105 |
iky | -0.105 |
aces | -0.096 |
isy | -0.095 |
Token | It |
Token ID | 632 |
Feature activation | -6.47e-01 |
Pos logit contributions | |
aney | +0.016 |
of | +0.014 |
hest | +0.013 |
iky | +0.012 |
isy | +0.012 |
Neg logit contributions | |
elbows | -0.015 |
Sorry | -0.014 |
minded | -0.014 |
ulk | -0.014 |
fired | -0.014 |
Token | was |
Token ID | 373 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
aney | +0.069 |
hest | +0.061 |
iky | +0.059 |
of | +0.058 |
aces | +0.054 |
Neg logit contributions | |
Sorry | -0.051 |
elbows | -0.049 |
H | -0.049 |
fired | -0.049 |
late | -0.048 |
Token | a |
Token ID | 257 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
aney | +0.022 |
hest | +0.021 |
iky | +0.020 |
isy | +0.019 |
iest | +0.019 |
Neg logit contributions | |
late | -0.008 |
H | -0.007 |
elbows | -0.007 |
Tiny | -0.007 |
something | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
aney | +0.156 |
hest | +0.141 |
iky | +0.137 |
isy | +0.129 |
iest | +0.127 |
Neg logit contributions | |
late | -0.078 |
backward | -0.078 |
together | -0.074 |
elbows | -0.073 |
Tiny | -0.072 |
Token | look |
Token ID | 804 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
Sorry | +0.010 |
fired | +0.009 |
late | +0.009 |
H | +0.009 |
ulk | +0.009 |
Neg logit contributions | |
aney | -0.010 |
of | -0.010 |
hest | -0.009 |
iky | -0.009 |
aces | -0.008 |
Token | at |
Token ID | 379 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
Sorry | +0.079 |
late | +0.077 |
H | +0.075 |
minded | +0.075 |
elbows | +0.074 |
Neg logit contributions | |
aney | -0.117 |
hest | -0.106 |
iky | -0.102 |
of | -0.098 |
isy | -0.095 |
Token | their |
Token ID | 511 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
elbows | +0.059 |
Sorry | +0.055 |
H | +0.055 |
fired | +0.054 |
minded | +0.052 |
Neg logit contributions | |
aney | -0.138 |
hest | -0.131 |
iky | -0.121 |
isy | -0.120 |
umbs | -0.117 |
Token | snow |
Token ID | 6729 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
Sorry | +0.011 |
elbows | +0.011 |
ulk | +0.011 |
fired | +0.011 |
H | +0.011 |
Neg logit contributions | |
aney | -0.014 |
hest | -0.013 |
of | -0.012 |
iky | -0.012 |
isy | -0.011 |
Token | fl |
Token ID | 2704 |
Feature activation | +4.44e+00 |
Pos logit contributions | |
Sorry | +0.016 |
elbows | +0.015 |
ulk | +0.015 |
fired | +0.015 |
H | +0.015 |
Neg logit contributions | |
aney | -0.021 |
hest | -0.019 |
of | -0.019 |
iky | -0.018 |
isy | -0.017 |
Token | akes |
Token ID | 1124 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
elbows | +0.374 |
Sorry | +0.370 |
ulk | +0.348 |
fired | +0.334 |
H | +0.325 |
Neg logit contributions | |
aney | -0.455 |
hest | -0.393 |
of | -0.383 |
isy | -0.368 |
iky | -0.365 |
Token | . |
Token ID | 13 |
Feature activation | -2.01e-02 |
Pos logit contributions | |
late | +0.076 |
elbows | +0.074 |
Sorry | +0.072 |
ulk | +0.069 |
backward | +0.068 |
Neg logit contributions | |
aney | -0.141 |
hest | -0.122 |
iky | -0.118 |
isy | -0.112 |
iest | -0.110 |
Token |
|
Token ID | 198 |
Feature activation | +6.69e-02 |
Pos logit contributions | |
aney | +0.002 |
of | +0.002 |
hest | +0.002 |
iky | +0.002 |
aces | +0.002 |
Neg logit contributions | |
elbows | -0.001 |
Sorry | -0.001 |
fired | -0.001 |
ulk | -0.001 |
minded | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
Sorry | +0.003 |
late | +0.003 |
H | +0.003 |
ulk | +0.003 |
elbows | +0.003 |
Neg logit contributions | |
aney | -0.009 |
hest | -0.008 |
iky | -0.008 |
of | -0.008 |
isy | -0.007 |
Token | S |
Token ID | 50 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
Sorry | +0.001 |
elbows | +0.001 |
fired | +0.001 |
minded | +0.001 |
ulk | +0.001 |
Neg logit contributions | |
aney | -0.002 |
hest | -0.001 |
of | -0.001 |
iky | -0.001 |
isy | -0.001 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
aney | +0.002 |
of | +0.002 |
hest | +0.002 |
iky | +0.002 |
isy | +0.002 |
Neg logit contributions | |
elbows | -0.002 |
Sorry | -0.001 |
ulk | -0.001 |
minded | -0.001 |
fired | -0.001 |
Token | Sam |
Token ID | 16305 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
Sorry | +0.013 |
elbows | +0.013 |
minded | +0.012 |
fired | +0.012 |
ulk | +0.012 |
Neg logit contributions | |
aney | -0.025 |
of | -0.023 |
hest | -0.023 |
iky | -0.022 |
isy | -0.020 |
Token | was |
Token ID | 373 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
fired | +0.013 |
H | +0.012 |
Sorry | +0.012 |
late | +0.012 |
elbows | +0.012 |
Neg logit contributions | |
aney | -0.025 |
hest | -0.024 |
iky | -0.023 |
of | -0.022 |
isy | -0.022 |
Token | picking |
Token ID | 10868 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
aney | +0.024 |
hest | +0.022 |
iky | +0.022 |
of | +0.021 |
isy | +0.020 |
Neg logit contributions | |
late | -0.015 |
Sorry | -0.014 |
elbows | -0.014 |
H | -0.014 |
ulk | -0.014 |
Token | wild |
Token ID | 4295 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
aney | +0.165 |
hest | +0.151 |
of | +0.150 |
iky | +0.145 |
isy | +0.136 |
Neg logit contributions | |
Sorry | -0.101 |
elbows | -0.098 |
ulk | -0.095 |
fired | -0.094 |
minded | -0.091 |
Token | fl |
Token ID | 2704 |
Feature activation | +4.43e+00 |
Pos logit contributions | |
aney | +0.012 |
hest | +0.011 |
of | +0.011 |
iky | +0.010 |
isy | +0.010 |
Neg logit contributions | |
Sorry | -0.008 |
elbows | -0.008 |
ulk | -0.008 |
fired | -0.008 |
late | -0.008 |
Token | owers |
Token ID | 3618 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
Sorry | +0.385 |
elbows | +0.374 |
ulk | +0.363 |
fired | +0.361 |
H | +0.352 |
Neg logit contributions | |
aney | -0.424 |
hest | -0.384 |
iky | -0.368 |
of | -0.360 |
isy | -0.354 |
Token | in |
Token ID | 287 |
Feature activation | +4.95e-02 |
Pos logit contributions | |
late | +0.060 |
fired | +0.058 |
H | +0.056 |
something | +0.054 |
elbows | +0.052 |
Neg logit contributions | |
aney | -0.131 |
hest | -0.113 |
iky | -0.112 |
isy | -0.103 |
aces | -0.101 |
Token | the |
Token ID | 262 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
Sorry | +0.003 |
elbows | +0.003 |
H | +0.003 |
late | +0.003 |
fired | +0.002 |
Neg logit contributions | |
aney | -0.006 |
hest | -0.006 |
iky | -0.006 |
isy | -0.006 |
of | -0.006 |
Token | me |
Token ID | 502 |
Feature activation | -7.08e-01 |
Pos logit contributions | |
ulk | +0.021 |
Sorry | +0.021 |
elbows | +0.021 |
fired | +0.020 |
minded | +0.020 |
Neg logit contributions | |
aney | -0.026 |
of | -0.024 |
hest | -0.023 |
iky | -0.022 |
isy | -0.020 |
Token | adow |
Token ID | 4584 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
hest | +0.073 |
aney | +0.072 |
iky | +0.067 |
of | +0.063 |
isy | +0.063 |
Neg logit contributions | |
fired | -0.054 |
elbows | -0.051 |
late | -0.048 |
heaven | -0.046 |
ulk | -0.046 |
Token | a |
Token ID | 257 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
Sorry | +0.002 |
elbows | +0.002 |
fired | +0.002 |
H | +0.002 |
late | +0.002 |
Neg logit contributions | |
aney | -0.004 |
hest | -0.004 |
iky | -0.004 |
of | -0.004 |
isy | -0.003 |
Token | stream |
Token ID | 4269 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
Sorry | +0.001 |
elbows | +0.001 |
ulk | +0.001 |
fired | +0.001 |
H | +0.001 |
Neg logit contributions | |
aney | -0.001 |
hest | -0.001 |
of | -0.001 |
iky | -0.001 |
isy | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
aney | +0.020 |
iky | +0.016 |
hest | +0.016 |
umbs | +0.014 |
isy | +0.013 |
Neg logit contributions | |
late | -0.020 |
fired | -0.019 |
ulk | -0.019 |
minded | -0.018 |
something | -0.018 |
Token | some |
Token ID | 617 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
elbows | +0.012 |
Sorry | +0.012 |
late | +0.012 |
fired | +0.012 |
H | +0.012 |
Neg logit contributions | |
aney | -0.017 |
hest | -0.015 |
iky | -0.015 |
of | -0.014 |
isy | -0.013 |
Token | wild |
Token ID | 4295 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
aney | +0.026 |
hest | +0.022 |
iky | +0.022 |
umbs | +0.020 |
aces | +0.019 |
Neg logit contributions | |
elbows | -0.017 |
late | -0.016 |
fired | -0.016 |
H | -0.016 |
Tiny | -0.015 |
Token | fl |
Token ID | 2704 |
Feature activation | +4.42e+00 |
Pos logit contributions | |
aney | +0.027 |
hest | +0.025 |
of | +0.024 |
iky | +0.024 |
isy | +0.022 |
Neg logit contributions | |
Sorry | -0.016 |
elbows | -0.016 |
ulk | -0.015 |
fired | -0.015 |
late | -0.015 |
Token | owers |
Token ID | 3618 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
elbows | +0.341 |
fired | +0.332 |
ulk | +0.321 |
Sorry | +0.316 |
H | +0.306 |
Neg logit contributions | |
aney | -0.451 |
hest | -0.410 |
iky | -0.396 |
of | -0.381 |
isy | -0.381 |
Token | and |
Token ID | 290 |
Feature activation | +9.35e-02 |
Pos logit contributions | |
fired | +0.075 |
late | +0.068 |
Tiny | +0.065 |
elbows | +0.064 |
dreaming | +0.064 |
Neg logit contributions | |
aney | -0.122 |
iky | -0.109 |
hest | -0.109 |
aces | -0.093 |
umbs | -0.093 |
Token | a |
Token ID | 257 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
Sorry | +0.007 |
elbows | +0.007 |
late | +0.007 |
H | +0.007 |
fired | +0.007 |
Neg logit contributions | |
aney | -0.010 |
hest | -0.009 |
iky | -0.009 |
of | -0.008 |
isy | -0.008 |
Token | huge |
Token ID | 3236 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
aney | +0.001 |
hest | +0.001 |
iky | +0.001 |
of | +0.001 |
aces | +0.001 |
Neg logit contributions | |
Sorry | -0.001 |
elbows | -0.001 |
H | -0.001 |
late | -0.001 |
fired | -0.001 |
Token | old |
Token ID | 1468 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
aney | +0.158 |
hest | +0.145 |
iky | +0.138 |
of | +0.127 |
aces | +0.125 |
Neg logit contributions | |
Sorry | -0.106 |
H | -0.106 |
fired | -0.105 |
elbows | -0.104 |
late | -0.101 |
Token | surrounded |
Token ID | 11191 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
aney | +0.006 |
hest | +0.005 |
iky | +0.005 |
iest | +0.005 |
of | +0.005 |
Neg logit contributions | |
late | -0.004 |
elbows | -0.004 |
ulk | -0.003 |
H | -0.003 |
fired | -0.003 |
Token | by |
Token ID | 416 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
aney | +0.115 |
of | +0.108 |
hest | +0.102 |
iky | +0.099 |
isy | +0.093 |
Neg logit contributions | |
Sorry | -0.085 |
elbows | -0.080 |
ulk | -0.076 |
fired | -0.075 |
minded | -0.072 |
Token | very |
Token ID | 845 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
aney | +0.014 |
hest | +0.013 |
iky | +0.012 |
of | +0.012 |
isy | +0.011 |
Neg logit contributions | |
elbows | -0.009 |
Sorry | -0.009 |
H | -0.009 |
late | -0.008 |
ulk | -0.008 |
Token | large |
Token ID | 1588 |
Feature activation | -9.06e-01 |
Pos logit contributions | |
aney | +0.011 |
of | +0.010 |
hest | +0.010 |
iky | +0.010 |
isy | +0.009 |
Neg logit contributions | |
Sorry | -0.009 |
elbows | -0.008 |
ulk | -0.008 |
H | -0.008 |
fired | -0.008 |
Token | snow |
Token ID | 6729 |
Feature activation | -4.38e-02 |
Pos logit contributions | |
aney | +0.097 |
hest | +0.088 |
iky | +0.082 |
of | +0.080 |
isy | +0.078 |
Neg logit contributions | |
elbows | -0.070 |
Sorry | -0.069 |
H | -0.069 |
fired | -0.068 |
ulk | -0.067 |
Token | fl |
Token ID | 2704 |
Feature activation | +4.42e+00 |
Pos logit contributions | |
aney | +0.005 |
hest | +0.004 |
of | +0.004 |
iky | +0.004 |
isy | +0.004 |
Neg logit contributions | |
Sorry | -0.003 |
elbows | -0.003 |
H | -0.003 |
fired | -0.003 |
ulk | -0.003 |
Token | akes |
Token ID | 1124 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
elbows | +0.349 |
ulk | +0.335 |
Sorry | +0.329 |
H | +0.323 |
late | +0.322 |
Neg logit contributions | |
aney | -0.463 |
hest | -0.394 |
of | -0.378 |
isy | -0.376 |
iky | -0.373 |
Token | , |
Token ID | 11 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
late | +0.071 |
elbows | +0.068 |
fired | +0.067 |
H | +0.065 |
dreaming | +0.065 |
Neg logit contributions | |
aney | -0.137 |
hest | -0.116 |
iky | -0.112 |
isy | -0.105 |
aces | -0.104 |
Token | but |
Token ID | 475 |
Feature activation | -5.88e-01 |
Pos logit contributions | |
late | +0.009 |
elbows | +0.009 |
Sorry | +0.009 |
H | +0.009 |
ulk | +0.008 |
Neg logit contributions | |
aney | -0.010 |
hest | -0.009 |
iky | -0.009 |
of | -0.008 |
isy | -0.008 |
Token | right |
Token ID | 826 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
aney | +0.069 |
hest | +0.063 |
of | +0.061 |
iky | +0.060 |
isy | +0.057 |
Neg logit contributions | |
Sorry | -0.040 |
elbows | -0.039 |
ulk | -0.038 |
fired | -0.037 |
H | -0.037 |
Token | in |
Token ID | 287 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
aney | +0.026 |
of | +0.024 |
hest | +0.023 |
iky | +0.023 |
isy | +0.021 |
Neg logit contributions | |
Sorry | -0.028 |
elbows | -0.027 |
ulk | -0.027 |
H | -0.026 |
fired | -0.025 |
Token | chains |
Token ID | 14659 |
Feature activation | -7.40e-01 |
Pos logit contributions | |
elbows | +0.046 |
H | +0.045 |
Ros | +0.045 |
Tiny | +0.045 |
fired | +0.044 |
Neg logit contributions | |
aney | -0.065 |
hest | -0.060 |
iky | -0.056 |
isy | -0.052 |
contain | -0.051 |
Token | , |
Token ID | 11 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
aney | +0.075 |
iky | +0.063 |
hest | +0.063 |
isy | +0.062 |
contain | +0.060 |
Neg logit contributions | |
late | -0.054 |
Ros | -0.054 |
H | -0.052 |
Tiny | -0.052 |
Snow | -0.050 |
Token | glitter |
Token ID | 31133 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
elbows | +0.017 |
H | +0.016 |
Sorry | +0.016 |
late | +0.016 |
Tiny | +0.016 |
Neg logit contributions | |
aney | -0.023 |
hest | -0.021 |
iky | -0.020 |
of | -0.019 |
isy | -0.018 |
Token | y |
Token ID | 88 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
H | +0.067 |
Snow | +0.064 |
fired | +0.063 |
Tiny | +0.063 |
Ros | +0.063 |
Neg logit contributions | |
aney | -0.144 |
hest | -0.136 |
contain | -0.125 |
isy | -0.124 |
iky | -0.122 |
Token | snow |
Token ID | 6729 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
elbows | +0.107 |
Sorry | +0.102 |
H | +0.099 |
fired | +0.099 |
late | +0.096 |
Neg logit contributions | |
aney | -0.144 |
hest | -0.132 |
iky | -0.121 |
isy | -0.114 |
of | -0.114 |
Token | fl |
Token ID | 2704 |
Feature activation | +4.42e+00 |
Pos logit contributions | |
elbows | +0.008 |
Sorry | +0.008 |
H | +0.008 |
Tiny | +0.008 |
fired | +0.008 |
Neg logit contributions | |
aney | -0.015 |
hest | -0.014 |
of | -0.013 |
iky | -0.013 |
contain | -0.012 |
Token | akes |
Token ID | 1124 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
elbows | +0.320 |
Sorry | +0.319 |
H | +0.293 |
ulk | +0.292 |
fired | +0.284 |
Neg logit contributions | |
aney | -0.476 |
hest | -0.420 |
isy | -0.419 |
contain | -0.406 |
of | -0.399 |
Token | , |
Token ID | 11 |
Feature activation | +8.75e-02 |
Pos logit contributions | |
late | +0.064 |
Snow | +0.056 |
Tiny | +0.056 |
H | +0.055 |
elbows | +0.055 |
Neg logit contributions | |
aney | -0.143 |
hest | -0.124 |
iky | -0.118 |
isy | -0.112 |
contain | -0.111 |
Token | and |
Token ID | 290 |
Feature activation | -3.61e-02 |
Pos logit contributions | |
elbows | +0.007 |
H | +0.007 |
late | +0.007 |
Tiny | +0.007 |
Sorry | +0.007 |
Neg logit contributions | |
aney | -0.009 |
hest | -0.008 |
iky | -0.008 |
of | -0.007 |
isy | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | -3.12e-03 |
Pos logit contributions | |
aney | +0.004 |
hest | +0.004 |
iky | +0.003 |
of | +0.003 |
isy | +0.003 |
Neg logit contributions | |
Sorry | -0.003 |
elbows | -0.003 |
ulk | -0.003 |
H | -0.003 |
late | -0.003 |
Token | picture |
Token ID | 4286 |
Feature activation | +5.47e-01 |
Pos logit contributions | |
aney | +0.000 |
hest | +0.000 |
iky | +0.000 |
of | +0.000 |
isy | +0.000 |
Neg logit contributions | |
Sorry | -0.000 |
elbows | -0.000 |
H | -0.000 |
late | -0.000 |
fired | -0.000 |
Token | friend |
Token ID | 1545 |
Feature activation | -5.67e-01 |
Pos logit contributions | |
late | +0.025 |
H | +0.025 |
fired | +0.025 |
Sorry | +0.024 |
heaven | +0.023 |
Neg logit contributions | |
aney | -0.048 |
hest | -0.045 |
iky | -0.042 |
aces | -0.039 |
isy | -0.039 |
Token | . |
Token ID | 13 |
Feature activation | +9.32e-02 |
Pos logit contributions | |
aney | +0.058 |
hest | +0.053 |
iky | +0.051 |
isy | +0.046 |
of | +0.045 |
Neg logit contributions | |
H | -0.046 |
Sorry | -0.045 |
fired | -0.045 |
late | -0.044 |
minded | -0.044 |
Token | |
Token ID | 220 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
Sorry | +0.006 |
elbows | +0.005 |
ulk | +0.005 |
H | +0.005 |
late | +0.005 |
Neg logit contributions | |
aney | -0.012 |
hest | -0.011 |
iky | -0.010 |
of | -0.010 |
isy | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | +7.44e-02 |
Pos logit contributions | |
aney | +0.014 |
hest | +0.013 |
of | +0.012 |
iky | +0.012 |
isy | +0.011 |
Neg logit contributions | |
Sorry | -0.007 |
elbows | -0.007 |
ulk | -0.007 |
fired | -0.007 |
H | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
Sorry | +0.004 |
ulk | +0.004 |
late | +0.004 |
H | +0.004 |
elbows | +0.004 |
Neg logit contributions | |
aney | -0.010 |
hest | -0.009 |
iky | -0.009 |
of | -0.008 |
isy | -0.008 |
Token | * |
Token ID | 9 |
Feature activation | +4.42e+00 |
Pos logit contributions | |
late | +0.001 |
ulk | +0.001 |
Sorry | +0.001 |
H | +0.001 |
elbows | +0.001 |
Neg logit contributions | |
aney | -0.002 |
hest | -0.001 |
iky | -0.001 |
iest | -0.001 |
aces | -0.001 |
Token | The |
Token ID | 464 |
Feature activation | -7.37e-01 |
Pos logit contributions | |
Sorry | +0.297 |
H | +0.281 |
ulk | +0.278 |
late | +0.277 |
elbows | +0.272 |
Neg logit contributions | |
aney | -0.517 |
hest | -0.476 |
iky | -0.465 |
isy | -0.434 |
of | -0.429 |
Token | End |
Token ID | 5268 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
aney | +0.074 |
hest | +0.068 |
iky | +0.063 |
umbs | +0.060 |
aces | +0.057 |
Neg logit contributions | |
Sorry | -0.065 |
elbows | -0.064 |
late | -0.063 |
What | -0.060 |
H | -0.060 |
Token | * |
Token ID | 9 |
Feature activation | +4.38e+00 |
Pos logit contributions | |
aney | +0.014 |
of | +0.013 |
hest | +0.012 |
iky | +0.012 |
isy | +0.010 |
Neg logit contributions | |
elbows | -0.015 |
Sorry | -0.015 |
fired | -0.014 |
minded | -0.014 |
ulk | -0.014 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.82e-02 |
Pos logit contributions | |
Sorry | +0.313 |
late | +0.300 |
H | +0.295 |
ulk | +0.291 |
fired | +0.278 |
Neg logit contributions | |
aney | -0.495 |
hest | -0.457 |
iky | -0.450 |
isy | -0.420 |
aces | -0.409 |
Token | Once |
Token ID | 7454 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
aney | +0.003 |
of | +0.002 |
hest | +0.002 |
iky | +0.002 |
umbs | +0.002 |
Neg logit contributions | |
Sorry | -0.001 |
elbows | -0.001 |
fired | -0.001 |
minded | -0.001 |
ulk | -0.001 |
Token | me |
Token ID | 502 |
Feature activation | -5.73e-01 |
Pos logit contributions | |
Sorry | +0.005 |
elbows | +0.005 |
ulk | +0.005 |
fired | +0.005 |
minded | +0.005 |
Neg logit contributions | |
aney | -0.007 |
hest | -0.007 |
of | -0.007 |
iky | -0.006 |
isy | -0.006 |
Token | adow |
Token ID | 4584 |
Feature activation | +4.57e-01 |
Pos logit contributions | |
aney | +0.060 |
hest | +0.053 |
iky | +0.052 |
of | +0.047 |
isy | +0.046 |
Neg logit contributions | |
fired | -0.046 |
H | -0.043 |
late | -0.043 |
elbows | -0.042 |
minded | -0.042 |
Token | full |
Token ID | 1336 |
Feature activation | -9.92e-01 |
Pos logit contributions | |
fired | +0.035 |
late | +0.034 |
Sorry | +0.033 |
H | +0.033 |
minded | +0.032 |
Neg logit contributions | |
aney | -0.048 |
hest | -0.044 |
iky | -0.043 |
isy | -0.038 |
of | -0.038 |
Token | of |
Token ID | 286 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
aney | +0.064 |
iky | +0.055 |
hest | +0.048 |
arrow | +0.043 |
aces | +0.039 |
Neg logit contributions | |
late | -0.120 |
H | -0.115 |
heaven | -0.115 |
something | -0.114 |
Tiny | -0.113 |
Token | sun |
Token ID | 4252 |
Feature activation | +4.85e-01 |
Pos logit contributions | |
aney | +0.150 |
hest | +0.135 |
iky | +0.129 |
of | +0.126 |
isy | +0.120 |
Neg logit contributions | |
Sorry | -0.102 |
elbows | -0.102 |
H | -0.099 |
late | -0.099 |
fired | -0.099 |
Token | fl |
Token ID | 2704 |
Feature activation | +4.41e+00 |
Pos logit contributions | |
Sorry | +0.023 |
elbows | +0.022 |
fired | +0.021 |
ulk | +0.021 |
H | +0.021 |
Neg logit contributions | |
aney | -0.066 |
hest | -0.061 |
iky | -0.059 |
of | -0.059 |
isy | -0.056 |
Token | owers |
Token ID | 3618 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
elbows | +0.341 |
Sorry | +0.334 |
fired | +0.329 |
ulk | +0.327 |
H | +0.324 |
Neg logit contributions | |
aney | -0.464 |
hest | -0.399 |
iky | -0.382 |
of | -0.372 |
isy | -0.368 |
Token | and |
Token ID | 290 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
late | +0.073 |
fired | +0.070 |
H | +0.068 |
minded | +0.067 |
Tiny | +0.067 |
Neg logit contributions | |
aney | -0.128 |
iky | -0.112 |
hest | -0.110 |
isy | -0.099 |
arrow | -0.099 |
Token | tall |
Token ID | 7331 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
Sorry | +0.011 |
elbows | +0.011 |
ulk | +0.011 |
fired | +0.011 |
late | +0.010 |
Neg logit contributions | |
aney | -0.014 |
of | -0.013 |
hest | -0.013 |
iky | -0.012 |
isy | -0.012 |
Token | grass |
Token ID | 8701 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
aney | +0.169 |
hest | +0.153 |
iky | +0.145 |
of | +0.135 |
isy | +0.134 |
Neg logit contributions | |
elbows | -0.100 |
H | -0.100 |
fired | -0.099 |
minded | -0.098 |
Sorry | -0.096 |
Token | . |
Token ID | 13 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
fired | +0.019 |
H | +0.018 |
late | +0.017 |
minded | +0.017 |
elbows | +0.017 |
Neg logit contributions | |
aney | -0.032 |
hest | -0.029 |
iky | -0.027 |
of | -0.025 |
isy | -0.025 |
Token | holding |
Token ID | 4769 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
Sorry | +0.010 |
elbows | +0.010 |
late | +0.010 |
H | +0.010 |
fired | +0.010 |
Neg logit contributions | |
aney | -0.011 |
hest | -0.010 |
iky | -0.009 |
of | -0.009 |
isy | -0.009 |
Token | his |
Token ID | 465 |
Feature activation | +2.00e-03 |
Pos logit contributions | |
aney | +0.176 |
of | +0.164 |
hest | +0.160 |
iky | +0.153 |
isy | +0.146 |
Neg logit contributions | |
Sorry | -0.117 |
ulk | -0.113 |
elbows | -0.111 |
late | -0.107 |
fired | -0.106 |
Token | bunch |
Token ID | 7684 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
elbows | +0.000 |
Sorry | +0.000 |
fired | +0.000 |
H | +0.000 |
Fox | +0.000 |
Neg logit contributions | |
aney | -0.000 |
hest | -0.000 |
iky | -0.000 |
of | -0.000 |
ier | -0.000 |
Token | of |
Token ID | 286 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
something | +0.027 |
fired | +0.025 |
late | +0.025 |
elbows | +0.024 |
down | +0.023 |
Neg logit contributions | |
aney | -0.029 |
iky | -0.026 |
hest | -0.024 |
arrow | -0.024 |
oun | -0.023 |
Token | wild |
Token ID | 4295 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
aney | +0.158 |
hest | +0.142 |
iky | +0.134 |
ier | +0.129 |
case | +0.123 |
Neg logit contributions | |
elbows | -0.104 |
H | -0.102 |
Sorry | -0.098 |
Tiny | -0.096 |
Ros | -0.092 |
Token | fl |
Token ID | 2704 |
Feature activation | +4.41e+00 |
Pos logit contributions | |
aney | +0.025 |
hest | +0.023 |
iky | +0.021 |
of | +0.020 |
isy | +0.020 |
Neg logit contributions | |
elbows | -0.015 |
H | -0.014 |
fired | -0.014 |
Sorry | -0.014 |
minded | -0.014 |
Token | owers |
Token ID | 3618 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
elbows | +0.334 |
Sorry | +0.297 |
fired | +0.296 |
ulk | +0.296 |
H | +0.271 |
Neg logit contributions | |
aney | -0.475 |
hest | -0.438 |
of | -0.415 |
contain | -0.413 |
iky | -0.404 |
Token | in |
Token ID | 287 |
Feature activation | +2.41e-02 |
Pos logit contributions | |
fired | +0.059 |
late | +0.057 |
elbows | +0.057 |
H | +0.055 |
Tiny | +0.052 |
Neg logit contributions | |
aney | -0.132 |
hest | -0.118 |
iky | -0.115 |
arrow | -0.104 |
isy | -0.104 |
Token | his |
Token ID | 465 |
Feature activation | -2.93e-02 |
Pos logit contributions | |
elbows | +0.001 |
Sorry | +0.001 |
H | +0.001 |
late | +0.001 |
fired | +0.001 |
Neg logit contributions | |
aney | -0.003 |
hest | -0.003 |
iky | -0.003 |
isy | -0.003 |
of | -0.003 |
Token | hands |
Token ID | 2832 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
aney | +0.003 |
hest | +0.003 |
iky | +0.003 |
of | +0.003 |
isy | +0.003 |
Neg logit contributions | |
Sorry | -0.002 |
elbows | -0.002 |
fired | -0.002 |
H | -0.002 |
late | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
late | +0.016 |
H | +0.015 |
fired | +0.015 |
elbows | +0.014 |
something | +0.013 |
Neg logit contributions | |
aney | -0.039 |
hest | -0.036 |
iky | -0.036 |
arrow | -0.033 |
isy | -0.033 |
Token | get |
Token ID | 651 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
Sorry | +0.014 |
H | +0.014 |
elbows | +0.013 |
ulk | +0.013 |
fired | +0.013 |
Neg logit contributions | |
aney | -0.024 |
hest | -0.021 |
iky | -0.021 |
of | -0.019 |
isy | -0.019 |
Token | to |
Token ID | 284 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
aney | +0.045 |
of | +0.043 |
hest | +0.040 |
iky | +0.038 |
iest | +0.037 |
Neg logit contributions | |
Sorry | -0.034 |
elbows | -0.032 |
fired | -0.031 |
ulk | -0.031 |
H | -0.030 |
Token | feel |
Token ID | 1254 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
Sorry | +0.015 |
elbows | +0.015 |
ulk | +0.015 |
H | +0.015 |
fired | +0.015 |
Neg logit contributions | |
aney | -0.026 |
hest | -0.024 |
of | -0.023 |
iky | -0.023 |
isy | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
late | +0.014 |
Sorry | +0.013 |
H | +0.013 |
ulk | +0.013 |
elbows | +0.013 |
Neg logit contributions | |
aney | -0.026 |
hest | -0.023 |
iky | -0.023 |
isy | -0.021 |
aces | -0.021 |
Token | snow |
Token ID | 6729 |
Feature activation | +2.39e-02 |
Pos logit contributions | |
elbows | +0.018 |
late | +0.018 |
H | +0.017 |
Sorry | +0.016 |
Lightning | +0.016 |
Neg logit contributions | |
aney | -0.034 |
hest | -0.030 |
iky | -0.029 |
aces | -0.028 |
isy | -0.027 |
Token | fl |
Token ID | 2704 |
Feature activation | +4.40e+00 |
Pos logit contributions | |
elbows | +0.002 |
Sorry | +0.002 |
late | +0.002 |
H | +0.001 |
fired | +0.001 |
Neg logit contributions | |
aney | -0.003 |
hest | -0.003 |
iky | -0.002 |
of | -0.002 |
isy | -0.002 |
Token | akes |
Token ID | 1124 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
elbows | +0.315 |
Sorry | +0.296 |
ulk | +0.286 |
late | +0.276 |
bat | +0.275 |
Neg logit contributions | |
aney | -0.499 |
hest | -0.432 |
isy | -0.415 |
contain | -0.407 |
iky | -0.404 |
Token | on |
Token ID | 319 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
late | +0.060 |
elbows | +0.056 |
Sorry | +0.054 |
forth | +0.053 |
dreaming | +0.053 |
Neg logit contributions | |
aney | -0.131 |
iky | -0.113 |
hest | -0.113 |
isy | -0.104 |
aces | -0.104 |
Token | her |
Token ID | 607 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
Sorry | +0.010 |
elbows | +0.010 |
late | +0.009 |
H | +0.009 |
ulk | +0.009 |
Neg logit contributions | |
aney | -0.029 |
hest | -0.027 |
iky | -0.026 |
of | -0.026 |
isy | -0.025 |
Token | face |
Token ID | 1986 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
aney | +0.012 |
hest | +0.011 |
iky | +0.010 |
of | +0.010 |
iest | +0.010 |
Neg logit contributions | |
elbows | -0.009 |
H | -0.007 |
dreaming | -0.007 |
fired | -0.007 |
Tiny | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -8.54e-02 |
Pos logit contributions | |
late | +0.069 |
H | +0.068 |
fired | +0.066 |
elbows | +0.066 |
Sorry | +0.065 |
Neg logit contributions | |
aney | -0.120 |
hest | -0.110 |
iky | -0.105 |
isy | -0.096 |
igator | -0.094 |
Token | amongst |
Token ID | 12077 |
Feature activation | -6.94e-01 |
Pos logit contributions | |
aney | +0.093 |
of | +0.091 |
hest | +0.086 |
iky | +0.085 |
aces | +0.080 |
Neg logit contributions | |
Sorry | -0.101 |
elbows | -0.091 |
ulk | -0.091 |
heaven | -0.086 |
Are | -0.086 |
Token | the |
Token ID | 262 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
aney | +0.093 |
hest | +0.088 |
iky | +0.085 |
isy | +0.081 |
of | +0.081 |
Neg logit contributions | |
H | -0.031 |
elbows | -0.030 |
Sorry | -0.030 |
late | -0.030 |
ulk | -0.029 |
Token | grass |
Token ID | 8701 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
Sorry | +0.022 |
elbows | +0.021 |
ulk | +0.021 |
fired | +0.020 |
late | +0.020 |
Neg logit contributions | |
aney | -0.023 |
hest | -0.021 |
of | -0.020 |
iky | -0.020 |
isy | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | -2.02e-02 |
Pos logit contributions | |
fired | +0.010 |
H | +0.010 |
late | +0.010 |
elbows | +0.010 |
Sorry | +0.009 |
Neg logit contributions | |
aney | -0.018 |
hest | -0.016 |
iky | -0.015 |
isy | -0.014 |
of | -0.014 |
Token | wild |
Token ID | 4295 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
aney | +0.002 |
of | +0.002 |
iky | +0.002 |
hest | +0.002 |
isy | +0.001 |
Neg logit contributions | |
Sorry | -0.002 |
ulk | -0.002 |
late | -0.002 |
fired | -0.002 |
elbows | -0.002 |
Token | fl |
Token ID | 2704 |
Feature activation | +4.39e+00 |
Pos logit contributions | |
aney | +0.020 |
of | +0.019 |
iky | +0.018 |
hest | +0.018 |
aces | +0.016 |
Neg logit contributions | |
Sorry | -0.018 |
ulk | -0.017 |
late | -0.017 |
elbows | -0.017 |
fired | -0.017 |
Token | owers |
Token ID | 3618 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
elbows | +0.385 |
Sorry | +0.375 |
ulk | +0.371 |
fired | +0.368 |
H | +0.354 |
Neg logit contributions | |
aney | -0.423 |
hest | -0.373 |
of | -0.360 |
iky | -0.347 |
isy | -0.339 |
Token | . |
Token ID | 13 |
Feature activation | -6.15e-02 |
Pos logit contributions | |
fired | +0.068 |
elbows | +0.066 |
late | +0.065 |
Sorry | +0.065 |
H | +0.064 |
Neg logit contributions | |
aney | -0.119 |
hest | -0.106 |
iky | -0.101 |
isy | -0.093 |
aces | -0.092 |
Token | Anna |
Token ID | 11735 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
aney | +0.007 |
of | +0.006 |
hest | +0.006 |
iky | +0.005 |
aces | +0.005 |
Neg logit contributions | |
elbows | -0.005 |
fired | -0.005 |
Sorry | -0.005 |
minded | -0.005 |
ulk | -0.005 |
Token | was |
Token ID | 373 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
aney | +0.038 |
hest | +0.035 |
iky | +0.033 |
of | +0.033 |
iest | +0.031 |
Neg logit contributions | |
Sorry | -0.026 |
elbows | -0.025 |
fired | -0.025 |
H | -0.025 |
minded | -0.025 |
Token | so |
Token ID | 523 |
Feature activation | +6.47e-02 |
Pos logit contributions | |
aney | +0.016 |
hest | +0.015 |
iky | +0.014 |
of | +0.013 |
iest | +0.013 |
Neg logit contributions | |
late | -0.012 |
H | -0.012 |
Sorry | -0.012 |
elbows | -0.012 |
fired | -0.011 |
Token | had |
Token ID | 550 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
Sorry | +0.008 |
fired | +0.007 |
ulk | +0.007 |
late | +0.007 |
H | +0.007 |
Neg logit contributions | |
aney | -0.011 |
hest | -0.010 |
iky | -0.010 |
isy | -0.009 |
umbs | -0.009 |
Token | been |
Token ID | 587 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
aney | +0.035 |
hest | +0.032 |
iky | +0.031 |
isy | +0.029 |
of | +0.028 |
Neg logit contributions | |
late | -0.023 |
fired | -0.023 |
H | -0.022 |
Sorry | -0.022 |
ulk | -0.021 |
Token | decorated |
Token ID | 24789 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
aney | +0.141 |
hest | +0.129 |
iky | +0.124 |
of | +0.118 |
isy | +0.117 |
Neg logit contributions | |
late | -0.085 |
fired | -0.082 |
H | -0.081 |
elbows | -0.080 |
ulk | -0.079 |
Token | with |
Token ID | 351 |
Feature activation | +4.71e-01 |
Pos logit contributions | |
aney | +0.156 |
hest | +0.138 |
iky | +0.134 |
of | +0.128 |
isy | +0.128 |
Neg logit contributions | |
late | -0.087 |
Sorry | -0.085 |
H | -0.084 |
fired | -0.083 |
ulk | -0.082 |
Token | snow |
Token ID | 6729 |
Feature activation | -3.85e-02 |
Pos logit contributions | |
Sorry | +0.032 |
elbows | +0.031 |
late | +0.031 |
H | +0.031 |
fired | +0.030 |
Neg logit contributions | |
aney | -0.054 |
hest | -0.050 |
iky | -0.048 |
isy | -0.046 |
of | -0.045 |
Token | fl |
Token ID | 2704 |
Feature activation | +4.39e+00 |
Pos logit contributions | |
aney | +0.004 |
hest | +0.004 |
iky | +0.004 |
of | +0.003 |
isy | +0.003 |
Neg logit contributions | |
Sorry | -0.003 |
elbows | -0.003 |
late | -0.003 |
H | -0.003 |
minded | -0.003 |
Token | akes |
Token ID | 1124 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
Sorry | +0.324 |
elbows | +0.320 |
ulk | +0.311 |
fired | +0.302 |
late | +0.301 |
Neg logit contributions | |
aney | -0.453 |
hest | -0.400 |
isy | -0.399 |
iky | -0.382 |
of | -0.382 |
Token | . |
Token ID | 13 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
late | +0.066 |
fired | +0.058 |
H | +0.057 |
minded | +0.057 |
Sorry | +0.056 |
Neg logit contributions | |
aney | -0.122 |
hest | -0.104 |
iky | -0.103 |
isy | -0.098 |
arrow | -0.093 |
Token | Thomas |
Token ID | 5658 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
aney | +0.013 |
of | +0.012 |
hest | +0.012 |
iky | +0.011 |
aces | +0.010 |
Neg logit contributions | |
elbows | -0.011 |
fired | -0.011 |
Sorry | -0.011 |
minded | -0.010 |
ulk | -0.010 |
Token | couldn |
Token ID | 3521 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
Sorry | +0.026 |
H | +0.026 |
fired | +0.026 |
minded | +0.025 |
late | +0.024 |
Neg logit contributions | |
aney | -0.042 |
hest | -0.039 |
iky | -0.038 |
of | -0.036 |
iest | -0.035 |
Token | 't |
Token ID | 470 |
Feature activation | -9.35e-01 |
Pos logit contributions | |
aney | +0.019 |
isy | +0.016 |
iky | +0.016 |
hest | +0.016 |
aces | +0.015 |
Neg logit contributions | |
Sorry | -0.014 |
late | -0.014 |
H | -0.014 |
ulk | -0.014 |
fired | -0.013 |
Token | take |
Token ID | 1011 |
Feature activation | +5.69e-01 |
Pos logit contributions | |
Sorry | +0.039 |
H | +0.037 |
elbows | +0.035 |
fired | +0.035 |
late | +0.035 |
Neg logit contributions | |
aney | -0.066 |
iky | -0.057 |
hest | -0.057 |
of | -0.053 |
aces | -0.053 |
Token | care |
Token ID | 1337 |
Feature activation | +9.23e-01 |
Pos logit contributions | |
fired | +0.041 |
elbows | +0.041 |
Sorry | +0.041 |
ulk | +0.040 |
minded | +0.038 |
Neg logit contributions | |
of | -0.060 |
aney | -0.056 |
hest | -0.056 |
ion | -0.050 |
iest | -0.049 |
Token | of |
Token ID | 286 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
late | +0.129 |
H | +0.116 |
minded | +0.116 |
fired | +0.115 |
something | +0.114 |
Neg logit contributions | |
aney | -0.050 |
iky | -0.033 |
hest | -0.029 |
arrow | -0.028 |
isy | -0.026 |
Token | the |
Token ID | 262 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
aney | +0.236 |
hest | +0.220 |
of | +0.215 |
iky | +0.210 |
isy | +0.201 |
Neg logit contributions | |
Sorry | -0.102 |
elbows | -0.097 |
ulk | -0.095 |
fired | -0.095 |
late | -0.092 |
Token | all |
Token ID | 477 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
aney | +0.011 |
hest | +0.010 |
iky | +0.010 |
of | +0.009 |
isy | +0.009 |
Neg logit contributions | |
Sorry | -0.008 |
elbows | -0.008 |
H | -0.008 |
late | -0.008 |
fired | -0.008 |
Token | igator |
Token ID | 23823 |
Feature activation | -4.66e+00 |
Pos logit contributions | |
late | +0.040 |
Sorry | +0.037 |
H | +0.036 |
minded | +0.036 |
fired | +0.036 |
Neg logit contributions | |
aney | -0.021 |
iky | -0.015 |
hest | -0.014 |
aces | -0.013 |
umbs | -0.013 |
Token | too |
Token ID | 1165 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
aney | +0.494 |
iky | +0.432 |
hest | +0.430 |
of | +0.398 |
isy | +0.384 |
Neg logit contributions | |
Sorry | -0.366 |
late | -0.358 |
fired | -0.355 |
minded | -0.352 |
H | -0.351 |
Token | ." |
Token ID | 526 |
Feature activation | -6.05e-01 |
Pos logit contributions | |
late | +0.012 |
H | +0.010 |
Sorry | +0.010 |
fired | +0.010 |
Tiny | +0.009 |
Neg logit contributions | |
aney | -0.020 |
iky | -0.017 |
hest | -0.017 |
isy | -0.016 |
arrow | -0.016 |
Token | |
Token ID | 220 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
aney | +0.065 |
of | +0.058 |
hest | +0.053 |
isy | +0.050 |
umbs | +0.049 |
Neg logit contributions | |
elbows | -0.049 |
Sorry | -0.045 |
fired | -0.045 |
ulk | -0.045 |
minded | -0.045 |
Token |
|
Token ID | 198 |
Feature activation | -2.62e-02 |
Pos logit contributions | |
aney | +0.047 |
hest | +0.044 |
iky | +0.043 |
of | +0.041 |
isy | +0.041 |
Neg logit contributions | |
Sorry | -0.017 |
late | -0.016 |
H | -0.016 |
ulk | -0.016 |
fired | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | -7.74e-02 |
Pos logit contributions | |
aney | +0.003 |
hest | +0.003 |
of | +0.003 |
iky | +0.003 |
isy | +0.003 |
Neg logit contributions | |
Sorry | -0.002 |
elbows | -0.002 |
fired | -0.002 |
ulk | -0.002 |
minded | -0.002 |
Token | there |
Token ID | 612 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
aney | +0.066 |
of | +0.061 |
hest | +0.059 |
iky | +0.057 |
isy | +0.055 |
Neg logit contributions | |
elbows | -0.035 |
ulk | -0.034 |
Sorry | -0.034 |
minded | -0.033 |
fired | -0.032 |
Token | was |
Token ID | 373 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
Sorry | +0.010 |
fired | +0.010 |
H | +0.009 |
late | +0.009 |
elbows | +0.009 |
Neg logit contributions | |
aney | -0.020 |
hest | -0.018 |
iky | -0.018 |
isy | -0.017 |
aces | -0.017 |
Token | a |
Token ID | 257 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
aney | +0.070 |
hest | +0.064 |
iky | +0.062 |
of | +0.062 |
isy | +0.059 |
Neg logit contributions | |
Sorry | -0.029 |
elbows | -0.028 |
late | -0.028 |
H | -0.027 |
ulk | -0.027 |
Token | big |
Token ID | 1263 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
aney | +0.016 |
of | +0.014 |
hest | +0.013 |
isy | +0.013 |
iky | +0.013 |
Neg logit contributions | |
ulk | -0.026 |
elbows | -0.026 |
fired | -0.025 |
minded | -0.024 |
Sorry | -0.024 |
Token | all |
Token ID | 477 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
aney | +0.121 |
hest | +0.110 |
of | +0.105 |
iky | +0.104 |
isy | +0.097 |
Neg logit contributions | |
Sorry | -0.097 |
elbows | -0.094 |
H | -0.092 |
fired | -0.092 |
ulk | -0.091 |
Token | igator |
Token ID | 23823 |
Feature activation | -4.62e+00 |
Pos logit contributions | |
late | +0.041 |
Sorry | +0.038 |
Lightning | +0.037 |
H | +0.037 |
fired | +0.037 |
Neg logit contributions | |
aney | -0.018 |
hest | -0.014 |
iky | -0.013 |
umbs | -0.012 |
isy | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -6.24e-01 |
Pos logit contributions | |
aney | +0.494 |
hest | +0.443 |
iky | +0.424 |
of | +0.415 |
isy | +0.392 |
Neg logit contributions | |
Sorry | -0.362 |
elbows | -0.346 |
fired | -0.345 |
H | -0.344 |
late | -0.341 |
Token | He |
Token ID | 679 |
Feature activation | -5.71e-01 |
Pos logit contributions | |
aney | +0.074 |
hest | +0.068 |
iky | +0.066 |
of | +0.064 |
isy | +0.062 |
Neg logit contributions | |
Sorry | -0.041 |
H | -0.040 |
late | -0.039 |
ulk | -0.038 |
elbows | -0.038 |
Token | lived |
Token ID | 5615 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
aney | +0.067 |
hest | +0.061 |
iky | +0.056 |
umbs | +0.056 |
ier | +0.054 |
Neg logit contributions | |
H | -0.040 |
fired | -0.038 |
Sorry | -0.038 |
late | -0.037 |
Tiny | -0.036 |
Token | in |
Token ID | 287 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
aney | +0.012 |
hest | +0.011 |
iky | +0.010 |
of | +0.010 |
isy | +0.009 |
Neg logit contributions | |
Sorry | -0.009 |
late | -0.009 |
elbows | -0.009 |
fired | -0.009 |
ulk | -0.009 |
Token | a |
Token ID | 257 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
aney | +0.017 |
of | +0.016 |
hest | +0.016 |
iky | +0.015 |
iest | +0.014 |
Neg logit contributions | |
Sorry | -0.011 |
elbows | -0.011 |
ulk | -0.010 |
minded | -0.010 |
fired | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
Sorry | +0.017 |
H | +0.017 |
late | +0.016 |
fired | +0.016 |
ulk | +0.016 |
Neg logit contributions | |
aney | -0.022 |
hest | -0.020 |
iky | -0.019 |
of | -0.019 |
isy | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
elbows | +0.008 |
Sorry | +0.007 |
ulk | +0.007 |
fired | +0.007 |
minded | +0.007 |
Neg logit contributions | |
aney | -0.013 |
of | -0.012 |
hest | -0.012 |
iky | -0.011 |
isy | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
Sorry | +0.019 |
elbows | +0.018 |
minded | +0.017 |
fired | +0.017 |
ulk | +0.017 |
Neg logit contributions | |
aney | -0.029 |
of | -0.026 |
hest | -0.026 |
iky | -0.025 |
isy | -0.024 |
Token | The |
Token ID | 464 |
Feature activation | -7.68e-01 |
Pos logit contributions | |
Sorry | +0.015 |
elbows | +0.015 |
fired | +0.015 |
minded | +0.015 |
ulk | +0.015 |
Neg logit contributions | |
aney | -0.020 |
hest | -0.018 |
of | -0.018 |
iky | -0.017 |
isy | -0.016 |
Token | all |
Token ID | 477 |
Feature activation | +5.48e-01 |
Pos logit contributions | |
aney | +0.078 |
hest | +0.070 |
of | +0.067 |
iky | +0.067 |
isy | +0.061 |
Neg logit contributions | |
Sorry | -0.064 |
elbows | -0.062 |
H | -0.060 |
ulk | -0.060 |
late | -0.060 |
Token | igator |
Token ID | 23823 |
Feature activation | -4.54e+00 |
Pos logit contributions | |
Sorry | +0.065 |
late | +0.064 |
fired | +0.062 |
H | +0.061 |
ulk | +0.060 |
Neg logit contributions | |
aney | -0.035 |
hest | -0.031 |
iky | -0.030 |
umbs | -0.025 |
aces | -0.024 |
Token | was |
Token ID | 373 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
aney | +0.487 |
hest | +0.442 |
iky | +0.424 |
of | +0.423 |
isy | +0.392 |
Neg logit contributions | |
Sorry | -0.349 |
elbows | -0.337 |
fired | -0.331 |
ulk | -0.328 |
H | -0.327 |
Token | persistent |
Token ID | 16218 |
Feature activation | -9.53e-01 |
Pos logit contributions | |
aney | +0.027 |
hest | +0.025 |
iky | +0.024 |
iest | +0.022 |
isy | +0.022 |
Neg logit contributions | |
late | -0.017 |
H | -0.015 |
dreaming | -0.014 |
Tiny | -0.014 |
elbows | -0.014 |
Token | though |
Token ID | 996 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
aney | +0.107 |
hest | +0.099 |
iky | +0.094 |
isy | +0.085 |
arrow | +0.084 |
Neg logit contributions | |
late | -0.070 |
H | -0.069 |
fired | -0.068 |
elbows | -0.068 |
minded | -0.067 |
Token | , |
Token ID | 11 |
Feature activation | -5.49e-02 |
Pos logit contributions | |
late | +0.022 |
H | +0.022 |
Sorry | +0.021 |
elbows | +0.021 |
fired | +0.021 |
Neg logit contributions | |
aney | -0.043 |
hest | -0.040 |
iky | -0.038 |
isy | -0.035 |
umbs | -0.035 |
Token | and |
Token ID | 290 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
aney | +0.006 |
hest | +0.006 |
of | +0.006 |
iky | +0.006 |
isy | +0.005 |
Neg logit contributions | |
Sorry | -0.004 |
elbows | -0.003 |
ulk | -0.003 |
fired | -0.003 |
H | -0.003 |
Token | there |
Token ID | 612 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
aney | +0.059 |
hest | +0.053 |
of | +0.052 |
iky | +0.050 |
isy | +0.047 |
Neg logit contributions | |
Sorry | -0.047 |
elbows | -0.046 |
ulk | -0.044 |
minded | -0.044 |
fired | -0.044 |
Token | was |
Token ID | 373 |
Feature activation | -3.97e-01 |
Pos logit contributions | |
Sorry | +0.019 |
fired | +0.018 |
late | +0.018 |
elbows | +0.018 |
H | +0.018 |
Neg logit contributions | |
aney | -0.029 |
hest | -0.027 |
iky | -0.026 |
isy | -0.024 |
aces | -0.024 |
Token | a |
Token ID | 257 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
aney | +0.051 |
hest | +0.047 |
of | +0.045 |
iky | +0.045 |
isy | +0.043 |
Neg logit contributions | |
Sorry | -0.022 |
elbows | -0.022 |
late | -0.021 |
ulk | -0.021 |
H | -0.021 |
Token | white |
Token ID | 2330 |
Feature activation | -6.41e-02 |
Pos logit contributions | |
aney | +0.013 |
of | +0.011 |
hest | +0.011 |
isy | +0.010 |
iky | +0.010 |
Neg logit contributions | |
ulk | -0.020 |
elbows | -0.019 |
fired | -0.019 |
minded | -0.018 |
Sorry | -0.018 |
Token | all |
Token ID | 477 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
aney | +0.007 |
hest | +0.007 |
iky | +0.006 |
of | +0.006 |
aces | +0.006 |
Neg logit contributions | |
Sorry | -0.005 |
H | -0.004 |
elbows | -0.004 |
fired | -0.004 |
late | -0.004 |
Token | igator |
Token ID | 23823 |
Feature activation | -4.51e+00 |
Pos logit contributions | |
late | +0.044 |
Sorry | +0.041 |
H | +0.041 |
Lightning | +0.040 |
Are | +0.039 |
Neg logit contributions | |
aney | -0.024 |
hest | -0.020 |
iky | -0.018 |
umbs | -0.017 |
isy | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -5.95e-01 |
Pos logit contributions | |
aney | +0.496 |
hest | +0.443 |
iky | +0.426 |
of | +0.405 |
isy | +0.389 |
Neg logit contributions | |
Sorry | -0.343 |
H | -0.329 |
fired | -0.328 |
elbows | -0.326 |
late | -0.324 |
Token | He |
Token ID | 679 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
aney | +0.072 |
hest | +0.066 |
iky | +0.065 |
of | +0.062 |
isy | +0.061 |
Neg logit contributions | |
Sorry | -0.038 |
H | -0.037 |
late | -0.035 |
ulk | -0.034 |
elbows | -0.034 |
Token | was |
Token ID | 373 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
aney | +0.056 |
hest | +0.051 |
iky | +0.047 |
umbs | +0.047 |
ier | +0.046 |
Neg logit contributions | |
H | -0.032 |
fired | -0.030 |
Sorry | -0.030 |
Tiny | -0.029 |
late | -0.029 |
Token | very |
Token ID | 845 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
aney | +0.040 |
hest | +0.037 |
iky | +0.035 |
of | +0.032 |
iest | +0.032 |
Neg logit contributions | |
late | -0.030 |
H | -0.029 |
Tiny | -0.028 |
Sorry | -0.028 |
elbows | -0.028 |
Token | big |
Token ID | 1263 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
aney | +0.047 |
hest | +0.043 |
iky | +0.040 |
of | +0.039 |
aces | +0.038 |
Neg logit contributions | |
late | -0.028 |
Sorry | -0.028 |
H | -0.026 |
fired | -0.025 |
minded | -0.025 |
Token | I |
Token ID | 314 |
Feature activation | -2.03e-02 |
Pos logit contributions | |
aney | +0.026 |
hest | +0.024 |
iky | +0.024 |
of | +0.023 |
aces | +0.022 |
Neg logit contributions | |
Sorry | -0.013 |
H | -0.012 |
late | -0.012 |
elbows | -0.012 |
ulk | -0.011 |
Token | am |
Token ID | 716 |
Feature activation | +6.99e-01 |
Pos logit contributions | |
aney | +0.002 |
hest | +0.002 |
of | +0.002 |
iky | +0.002 |
isy | +0.002 |
Neg logit contributions | |
Sorry | -0.002 |
elbows | -0.002 |
ulk | -0.002 |
minded | -0.001 |
fired | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
elbows | +0.051 |
fired | +0.050 |
ulk | +0.049 |
minded | +0.048 |
Sorry | +0.046 |
Neg logit contributions | |
aney | -0.078 |
of | -0.072 |
hest | -0.071 |
iky | -0.066 |
isy | -0.064 |
Token | quiet |
Token ID | 5897 |
Feature activation | +4.80e-01 |
Pos logit contributions | |
Sorry | +0.002 |
elbows | +0.001 |
ulk | +0.001 |
fired | +0.001 |
late | +0.001 |
Neg logit contributions | |
aney | -0.002 |
hest | -0.002 |
of | -0.002 |
iky | -0.002 |
isy | -0.002 |
Token | all |
Token ID | 477 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
Sorry | +0.029 |
H | +0.028 |
late | +0.028 |
elbows | +0.027 |
ulk | +0.027 |
Neg logit contributions | |
aney | -0.060 |
hest | -0.054 |
iky | -0.052 |
of | -0.049 |
aces | -0.048 |
Token | igator |
Token ID | 23823 |
Feature activation | -4.51e+00 |
Pos logit contributions | |
late | +0.055 |
Sorry | +0.054 |
H | +0.053 |
fired | +0.051 |
ulk | +0.051 |
Neg logit contributions | |
aney | -0.023 |
hest | -0.017 |
iky | -0.016 |
isy | -0.013 |
aces | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -4.46e-01 |
Pos logit contributions | |
aney | +0.475 |
hest | +0.422 |
iky | +0.410 |
of | +0.396 |
isy | +0.374 |
Neg logit contributions | |
Sorry | -0.362 |
fired | -0.343 |
late | -0.341 |
elbows | -0.341 |
H | -0.338 |
Token | Why |
Token ID | 4162 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
aney | +0.050 |
of | +0.046 |
hest | +0.046 |
iky | +0.043 |
isy | +0.041 |
Neg logit contributions | |
elbows | -0.032 |
ulk | -0.031 |
fired | -0.030 |
Sorry | -0.030 |
minded | -0.029 |
Token | are |
Token ID | 389 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
Sorry | +0.031 |
H | +0.029 |
elbows | +0.028 |
fired | +0.028 |
Are | +0.027 |
Neg logit contributions | |
aney | -0.029 |
hest | -0.026 |
iky | -0.024 |
of | -0.023 |
isy | -0.022 |
Token | you |
Token ID | 345 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
aney | +0.041 |
of | +0.039 |
hest | +0.038 |
iky | +0.036 |
isy | +0.034 |
Neg logit contributions | |
elbows | -0.023 |
fired | -0.023 |
ulk | -0.022 |
minded | -0.021 |
late | -0.020 |
Token | sad |
Token ID | 6507 |
Feature activation | -6.13e-01 |
Pos logit contributions | |
aney | +0.032 |
hest | +0.030 |
iky | +0.028 |
of | +0.028 |
iest | +0.027 |
Neg logit contributions | |
Sorry | -0.020 |
H | -0.020 |
late | -0.020 |
elbows | -0.019 |
fired | -0.019 |
Token | there |
Token ID | 612 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
aney | +0.065 |
hest | +0.059 |
of | +0.057 |
iky | +0.056 |
isy | +0.053 |
Neg logit contributions | |
Sorry | -0.049 |
elbows | -0.048 |
ulk | -0.047 |
fired | -0.047 |
H | -0.047 |
Token | was |
Token ID | 373 |
Feature activation | -4.23e-01 |
Pos logit contributions | |
Sorry | +0.015 |
fired | +0.015 |
late | +0.015 |
H | +0.015 |
elbows | +0.014 |
Neg logit contributions | |
aney | -0.023 |
hest | -0.022 |
iky | -0.021 |
isy | -0.019 |
of | -0.019 |
Token | an |
Token ID | 281 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
aney | +0.055 |
hest | +0.050 |
iky | +0.049 |
of | +0.049 |
isy | +0.046 |
Neg logit contributions | |
Sorry | -0.023 |
elbows | -0.022 |
late | -0.022 |
H | -0.021 |
ulk | -0.021 |
Token | adventurous |
Token ID | 39770 |
Feature activation | -5.23e-01 |
Pos logit contributions | |
aney | +0.131 |
hest | +0.116 |
umbs | +0.114 |
iky | +0.109 |
of | +0.100 |
Neg logit contributions | |
H | -0.106 |
late | -0.102 |
minded | -0.100 |
afar | -0.096 |
heaven | -0.095 |
Token | all |
Token ID | 477 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
aney | +0.056 |
hest | +0.051 |
iky | +0.049 |
of | +0.048 |
isy | +0.044 |
Neg logit contributions | |
Sorry | -0.040 |
H | -0.039 |
elbows | -0.038 |
late | -0.038 |
fired | -0.038 |
Token | igator |
Token ID | 23823 |
Feature activation | -4.51e+00 |
Pos logit contributions | |
late | +0.040 |
Lightning | +0.038 |
H | +0.038 |
Sorry | +0.037 |
fired | +0.037 |
Neg logit contributions | |
aney | -0.020 |
hest | -0.016 |
iky | -0.015 |
umbs | -0.014 |
isy | -0.012 |
Token | called |
Token ID | 1444 |
Feature activation | -4.09e-02 |
Pos logit contributions | |
aney | +0.506 |
hest | +0.455 |
iky | +0.439 |
of | +0.417 |
isy | +0.399 |
Neg logit contributions | |
Sorry | -0.327 |
H | -0.319 |
fired | -0.316 |
late | -0.312 |
elbows | -0.309 |
Token | Joe |
Token ID | 5689 |
Feature activation | +6.61e-01 |
Pos logit contributions | |
aney | +0.005 |
hest | +0.005 |
iky | +0.004 |
of | +0.004 |
isy | +0.004 |
Neg logit contributions | |
Sorry | -0.003 |
H | -0.002 |
elbows | -0.002 |
fired | -0.002 |
late | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -7.31e-01 |
Pos logit contributions | |
H | +0.041 |
Tiny | +0.038 |
fired | +0.038 |
minded | +0.037 |
Fox | +0.037 |
Neg logit contributions | |
aney | -0.077 |
hest | -0.075 |
iky | -0.071 |
umbs | -0.066 |
contain | -0.064 |
Token | Everywhere |
Token ID | 48201 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
aney | +0.087 |
hest | +0.080 |
iky | +0.078 |
of | +0.074 |
isy | +0.074 |
Neg logit contributions | |
Sorry | -0.048 |
H | -0.047 |
fired | -0.045 |
late | -0.045 |
ulk | -0.045 |
Token | Joe |
Token ID | 5689 |
Feature activation | +7.54e-01 |
Pos logit contributions | |
aney | +0.264 |
of | +0.251 |
hest | +0.242 |
iky | +0.228 |
iest | +0.222 |
Neg logit contributions | |
elbows | -0.194 |
Sorry | -0.187 |
ulk | -0.185 |
fired | -0.176 |
minded | -0.173 |
Token | he |
Token ID | 339 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
ulk | +0.006 |
minded | +0.006 |
elbows | +0.005 |
fired | +0.005 |
Sorry | +0.005 |
Neg logit contributions | |
aney | -0.007 |
of | -0.006 |
hest | -0.006 |
isy | -0.005 |
iest | -0.005 |
Token | saw |
Token ID | 2497 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
Sorry | +0.012 |
elbows | +0.012 |
ulk | +0.012 |
minded | +0.011 |
H | +0.011 |
Neg logit contributions | |
aney | -0.019 |
of | -0.017 |
hest | -0.017 |
iky | -0.016 |
isy | -0.015 |
Token | a |
Token ID | 257 |
Feature activation | -2.48e-02 |
Pos logit contributions | |
aney | +0.017 |
of | +0.016 |
hest | +0.015 |
iky | +0.015 |
isy | +0.014 |
Neg logit contributions | |
Sorry | -0.011 |
elbows | -0.010 |
ulk | -0.010 |
minded | -0.010 |
fired | -0.010 |
Token | big |
Token ID | 1263 |
Feature activation | -9.91e-01 |
Pos logit contributions | |
aney | +0.002 |
of | +0.002 |
hest | +0.002 |
iky | +0.002 |
isy | +0.002 |
Neg logit contributions | |
elbows | -0.003 |
ulk | -0.003 |
minded | -0.003 |
Sorry | -0.003 |
fired | -0.003 |
Token | all |
Token ID | 477 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
aney | +0.091 |
of | +0.082 |
hest | +0.082 |
iky | +0.078 |
isy | +0.073 |
Neg logit contributions | |
Sorry | -0.089 |
elbows | -0.088 |
ulk | -0.087 |
minded | -0.085 |
fired | -0.085 |
Token | igator |
Token ID | 23823 |
Feature activation | -4.50e+00 |
Pos logit contributions | |
late | +0.060 |
Sorry | +0.054 |
H | +0.054 |
Lightning | +0.053 |
Are | +0.053 |
Neg logit contributions | |
aney | -0.030 |
aces | -0.022 |
hest | -0.022 |
umbs | -0.021 |
iky | -0.020 |
Token | in |
Token ID | 287 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
aney | +0.411 |
of | +0.378 |
hest | +0.376 |
iky | +0.355 |
isy | +0.332 |
Neg logit contributions | |
Sorry | -0.405 |
elbows | -0.396 |
ulk | -0.389 |
minded | -0.382 |
H | -0.381 |
Token | the |
Token ID | 262 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
aney | +0.014 |
of | +0.013 |
hest | +0.013 |
iky | +0.012 |
isy | +0.011 |
Neg logit contributions | |
Sorry | -0.009 |
elbows | -0.009 |
minded | -0.009 |
fired | -0.009 |
ulk | -0.008 |
Token | pond |
Token ID | 16723 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
Sorry | +0.008 |
elbows | +0.008 |
late | +0.008 |
ulk | +0.008 |
fired | +0.008 |
Neg logit contributions | |
aney | -0.016 |
hest | -0.014 |
iky | -0.014 |
of | -0.014 |
isy | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
aney | +0.022 |
hest | +0.020 |
iky | +0.019 |
isy | +0.018 |
of | +0.017 |
Neg logit contributions | |
late | -0.014 |
fired | -0.014 |
elbows | -0.013 |
Sorry | -0.013 |
ulk | -0.013 |
Token | The |
Token ID | 383 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
aney | +0.019 |
hest | +0.018 |
of | +0.017 |
iky | +0.017 |
isy | +0.016 |
Neg logit contributions | |
Sorry | -0.012 |
elbows | -0.011 |
ulk | -0.011 |
fired | -0.011 |
H | -0.011 |
Token | there |
Token ID | 612 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
aney | +0.030 |
hest | +0.028 |
of | +0.027 |
iky | +0.027 |
isy | +0.025 |
Neg logit contributions | |
Sorry | -0.012 |
elbows | -0.012 |
ulk | -0.011 |
fired | -0.011 |
H | -0.011 |
Token | was |
Token ID | 373 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
H | +0.020 |
Sorry | +0.020 |
fired | +0.019 |
Are | +0.019 |
late | +0.018 |
Neg logit contributions | |
aney | -0.044 |
hest | -0.041 |
iky | -0.039 |
isy | -0.039 |
aces | -0.038 |
Token | a |
Token ID | 257 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
aney | +0.060 |
hest | +0.056 |
iky | +0.054 |
of | +0.053 |
isy | +0.051 |
Neg logit contributions | |
late | -0.023 |
Sorry | -0.022 |
elbows | -0.022 |
H | -0.022 |
ulk | -0.020 |
Token | poor |
Token ID | 3595 |
Feature activation | -7.63e-02 |
Pos logit contributions | |
aney | +0.009 |
of | +0.007 |
hest | +0.007 |
iky | +0.007 |
isy | +0.007 |
Neg logit contributions | |
ulk | -0.014 |
elbows | -0.014 |
fired | -0.014 |
Sorry | -0.014 |
minded | -0.014 |
Token | all |
Token ID | 477 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
aney | +0.007 |
of | +0.006 |
hest | +0.006 |
iky | +0.006 |
isy | +0.006 |
Neg logit contributions | |
elbows | -0.007 |
Sorry | -0.007 |
ulk | -0.007 |
fired | -0.007 |
minded | -0.007 |
Token | igator |
Token ID | 23823 |
Feature activation | -4.47e+00 |
Pos logit contributions | |
late | +0.052 |
Sorry | +0.051 |
H | +0.050 |
Lightning | +0.048 |
minded | +0.048 |
Neg logit contributions | |
aney | -0.022 |
hest | -0.017 |
iky | -0.014 |
umbs | -0.012 |
isy | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -4.49e-01 |
Pos logit contributions | |
aney | +0.502 |
hest | +0.456 |
of | +0.440 |
iky | +0.437 |
isy | +0.409 |
Neg logit contributions | |
Sorry | -0.323 |
elbows | -0.312 |
fired | -0.304 |
ulk | -0.304 |
H | -0.303 |
Token | He |
Token ID | 679 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
aney | +0.045 |
of | +0.040 |
hest | +0.039 |
iky | +0.037 |
aces | +0.035 |
Neg logit contributions | |
elbows | -0.040 |
fired | -0.038 |
minded | -0.038 |
ulk | -0.038 |
Sorry | -0.037 |
Token | wanted |
Token ID | 2227 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
aney | +0.039 |
hest | +0.035 |
of | +0.035 |
iky | +0.034 |
isy | +0.031 |
Neg logit contributions | |
Sorry | -0.042 |
elbows | -0.041 |
ulk | -0.041 |
fired | -0.040 |
minded | -0.040 |
Token | to |
Token ID | 284 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
aney | +0.054 |
hest | +0.049 |
iky | +0.047 |
isy | +0.045 |
of | +0.044 |
Neg logit contributions | |
late | -0.027 |
H | -0.026 |
elbows | -0.026 |
Sorry | -0.026 |
fired | -0.026 |
Token | read |
Token ID | 1100 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
Sorry | +0.008 |
elbows | +0.008 |
H | +0.008 |
ulk | +0.008 |
fired | +0.007 |
Neg logit contributions | |
aney | -0.014 |
hest | -0.013 |
iky | -0.012 |
of | -0.012 |
isy | -0.012 |
Token | much |
Token ID | 881 |
Feature activation | +4.72e-01 |
Pos logit contributions | |
aney | +0.027 |
hest | +0.024 |
iky | +0.023 |
isy | +0.022 |
of | +0.022 |
Neg logit contributions | |
late | -0.020 |
Sorry | -0.020 |
elbows | -0.020 |
fired | -0.019 |
ulk | -0.019 |
Token | fun |
Token ID | 1257 |
Feature activation | +8.16e-01 |
Pos logit contributions | |
late | +0.031 |
Sorry | +0.028 |
fired | +0.028 |
ulk | +0.027 |
H | +0.027 |
Neg logit contributions | |
aney | -0.059 |
hest | -0.053 |
iky | -0.052 |
isy | -0.048 |
aces | -0.048 |
Token | . |
Token ID | 13 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
Sorry | +0.058 |
ulk | +0.058 |
late | +0.058 |
fired | +0.057 |
elbows | +0.057 |
Neg logit contributions | |
aney | -0.092 |
hest | -0.083 |
iky | -0.079 |
isy | -0.073 |
umbs | -0.072 |
Token | The |
Token ID | 383 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
aney | +0.029 |
hest | +0.026 |
of | +0.026 |
iky | +0.025 |
isy | +0.023 |
Neg logit contributions | |
elbows | -0.017 |
Sorry | -0.017 |
ulk | -0.016 |
fired | -0.016 |
minded | -0.016 |
Token | all |
Token ID | 477 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
aney | +0.018 |
hest | +0.017 |
iky | +0.016 |
of | +0.016 |
isy | +0.014 |
Neg logit contributions | |
Sorry | -0.016 |
elbows | -0.015 |
H | -0.015 |
late | -0.015 |
ulk | -0.015 |
Token | igator |
Token ID | 23823 |
Feature activation | -4.47e+00 |
Pos logit contributions | |
Sorry | +0.044 |
late | +0.042 |
H | +0.042 |
fired | +0.041 |
ulk | +0.040 |
Neg logit contributions | |
aney | -0.041 |
hest | -0.037 |
iky | -0.036 |
isy | -0.032 |
umbs | -0.032 |
Token | and |
Token ID | 290 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
aney | +0.494 |
hest | +0.447 |
iky | +0.433 |
of | +0.412 |
isy | +0.394 |
Neg logit contributions | |
Sorry | -0.333 |
fired | -0.322 |
elbows | -0.316 |
H | -0.313 |
minded | -0.310 |
Token | the |
Token ID | 262 |
Feature activation | +9.21e-02 |
Pos logit contributions | |
aney | +0.036 |
hest | +0.033 |
iky | +0.032 |
of | +0.031 |
isy | +0.029 |
Neg logit contributions | |
Sorry | -0.020 |
elbows | -0.019 |
H | -0.018 |
fired | -0.018 |
late | -0.018 |
Token | bird |
Token ID | 6512 |
Feature activation | -6.71e-02 |
Pos logit contributions | |
Sorry | +0.007 |
H | +0.007 |
elbows | +0.007 |
late | +0.007 |
minded | +0.007 |
Neg logit contributions | |
aney | -0.010 |
hest | -0.009 |
iky | -0.009 |
of | -0.008 |
aces | -0.008 |
Token | were |
Token ID | 547 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
aney | +0.007 |
hest | +0.006 |
iky | +0.006 |
isy | +0.006 |
of | +0.005 |
Neg logit contributions | |
fired | -0.005 |
Sorry | -0.005 |
elbows | -0.005 |
H | -0.005 |
late | -0.005 |
Token | very |
Token ID | 845 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
aney | +0.124 |
hest | +0.115 |
iky | +0.112 |
isy | +0.102 |
aces | +0.099 |
Neg logit contributions | |
late | -0.080 |
H | -0.075 |
elbows | -0.073 |
Tiny | -0.072 |
Sorry | -0.072 |
Token | day |
Token ID | 1110 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
late | +0.047 |
Sorry | +0.041 |
H | +0.040 |
fired | +0.040 |
elbows | +0.039 |
Neg logit contributions | |
aney | -0.080 |
hest | -0.076 |
iky | -0.070 |
aces | -0.069 |
ier | -0.067 |
Token | , |
Token ID | 11 |
Feature activation | -8.17e-02 |
Pos logit contributions | |
aney | +0.021 |
hest | +0.019 |
iky | +0.018 |
of | +0.017 |
isy | +0.017 |
Neg logit contributions | |
Sorry | -0.016 |
late | -0.015 |
fired | -0.015 |
elbows | -0.015 |
H | -0.015 |
Token | a |
Token ID | 257 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
aney | +0.010 |
hest | +0.009 |
of | +0.009 |
iky | +0.009 |
isy | +0.008 |
Neg logit contributions | |
Sorry | -0.005 |
elbows | -0.005 |
ulk | -0.005 |
minded | -0.005 |
fired | -0.005 |
Token | big |
Token ID | 1263 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
aney | +0.009 |
of | +0.008 |
hest | +0.007 |
iky | +0.007 |
isy | +0.007 |
Neg logit contributions | |
ulk | -0.015 |
elbows | -0.015 |
fired | -0.015 |
Sorry | -0.015 |
minded | -0.014 |
Token | all |
Token ID | 477 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
aney | +0.111 |
hest | +0.100 |
of | +0.099 |
iky | +0.097 |
isy | +0.091 |
Neg logit contributions | |
Sorry | -0.080 |
elbows | -0.078 |
ulk | -0.077 |
fired | -0.076 |
late | -0.075 |
Token | igator |
Token ID | 23823 |
Feature activation | -4.47e+00 |
Pos logit contributions | |
late | +0.047 |
Sorry | +0.044 |
Lightning | +0.043 |
H | +0.043 |
fired | +0.041 |
Neg logit contributions | |
aney | -0.035 |
hest | -0.028 |
umbs | -0.026 |
iky | -0.026 |
isy | -0.024 |
Token | was |
Token ID | 373 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
aney | +0.424 |
of | +0.394 |
hest | +0.386 |
iky | +0.371 |
isy | +0.342 |
Neg logit contributions | |
Sorry | -0.381 |
elbows | -0.380 |
ulk | -0.373 |
minded | -0.363 |
late | -0.361 |
Token | near |
Token ID | 1474 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
aney | +0.047 |
hest | +0.041 |
iky | +0.038 |
of | +0.037 |
umbs | +0.037 |
Neg logit contributions | |
late | -0.027 |
H | -0.025 |
elbows | -0.024 |
ulk | -0.024 |
fired | -0.023 |
Token | a |
Token ID | 257 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
aney | +0.135 |
of | +0.133 |
hest | +0.122 |
iky | +0.117 |
isy | +0.110 |
Neg logit contributions | |
Sorry | -0.109 |
elbows | -0.103 |
minded | -0.103 |
fired | -0.103 |
ulk | -0.100 |
Token | small |
Token ID | 1402 |
Feature activation | -5.57e-02 |
Pos logit contributions | |
aney | +0.010 |
hest | +0.009 |
of | +0.009 |
iky | +0.009 |
isy | +0.008 |
Neg logit contributions | |
elbows | -0.013 |
Sorry | -0.012 |
ulk | -0.012 |
fired | -0.012 |
minded | -0.012 |
Token | pond |
Token ID | 16723 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
aney | +0.006 |
hest | +0.006 |
iky | +0.005 |
of | +0.005 |
isy | +0.005 |
Neg logit contributions | |
Sorry | -0.004 |
H | -0.004 |
elbows | -0.004 |
fired | -0.004 |
late | -0.004 |
Token | was |
Token ID | 373 |
Feature activation | -7.43e-02 |
Pos logit contributions | |
H | +0.071 |
Sorry | +0.070 |
fired | +0.070 |
minded | +0.068 |
late | +0.067 |
Neg logit contributions | |
aney | -0.097 |
hest | -0.088 |
iky | -0.084 |
of | -0.082 |
isy | -0.077 |
Token | a |
Token ID | 257 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
aney | +0.008 |
hest | +0.007 |
iky | +0.007 |
of | +0.006 |
isy | +0.006 |
Neg logit contributions | |
late | -0.006 |
H | -0.006 |
Sorry | -0.006 |
elbows | -0.005 |
ulk | -0.005 |
Token | very |
Token ID | 845 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
aney | +0.001 |
hest | +0.001 |
of | +0.001 |
iky | +0.001 |
isy | +0.001 |
Neg logit contributions | |
Sorry | -0.001 |
elbows | -0.001 |
H | -0.001 |
late | -0.001 |
fired | -0.001 |
Token | compassionate |
Token ID | 32533 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
aney | +0.036 |
hest | +0.033 |
iky | +0.031 |
of | +0.031 |
umbs | +0.030 |
Neg logit contributions | |
Sorry | -0.025 |
late | -0.025 |
H | -0.023 |
fired | -0.023 |
minded | -0.022 |
Token | all |
Token ID | 477 |
Feature activation | +5.58e-01 |
Pos logit contributions | |
aney | +0.045 |
hest | +0.043 |
iky | +0.041 |
aces | +0.039 |
umbs | +0.039 |
Neg logit contributions | |
H | -0.020 |
Fox | -0.018 |
Sorry | -0.018 |
late | -0.018 |
Tiny | -0.017 |
Token | igator |
Token ID | 23823 |
Feature activation | -4.44e+00 |
Pos logit contributions | |
late | +0.043 |
H | +0.040 |
Sorry | +0.039 |
fired | +0.039 |
minded | +0.038 |
Neg logit contributions | |
aney | -0.062 |
hest | -0.055 |
iky | -0.053 |
umbs | -0.050 |
isy | -0.048 |
Token | , |
Token ID | 11 |
Feature activation | -3.11e-02 |
Pos logit contributions | |
aney | +0.519 |
hest | +0.460 |
iky | +0.452 |
of | +0.411 |
umbs | +0.408 |
Neg logit contributions | |
Sorry | -0.306 |
H | -0.300 |
fired | -0.298 |
late | -0.292 |
minded | -0.287 |
Token | and |
Token ID | 290 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
aney | +0.003 |
hest | +0.003 |
iky | +0.003 |
of | +0.002 |
iest | +0.002 |
Neg logit contributions | |
H | -0.003 |
late | -0.003 |
Sorry | -0.003 |
fired | -0.003 |
elbows | -0.003 |
Token | all |
Token ID | 477 |
Feature activation | +5.69e-01 |
Pos logit contributions | |
aney | +0.027 |
hest | +0.025 |
of | +0.025 |
iky | +0.024 |
isy | +0.022 |
Neg logit contributions | |
Sorry | -0.019 |
elbows | -0.019 |
ulk | -0.019 |
fired | -0.018 |
late | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
late | +0.040 |
Sorry | +0.040 |
H | +0.039 |
fired | +0.039 |
ulk | +0.038 |
Neg logit contributions | |
aney | -0.063 |
hest | -0.058 |
iky | -0.056 |
umbs | -0.051 |
isy | -0.050 |
Token | animals |
Token ID | 4695 |
Feature activation | -7.17e-01 |
Pos logit contributions | |
late | +0.009 |
Sorry | +0.008 |
H | +0.008 |
elbows | +0.008 |
minded | +0.008 |
Neg logit contributions | |
aney | -0.013 |
hest | -0.012 |
iky | -0.011 |
umbs | -0.010 |
isy | -0.010 |
Token | 't |
Token ID | 470 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
aney | +0.040 |
iky | +0.033 |
hest | +0.032 |
aces | +0.031 |
isy | +0.031 |
Neg logit contributions | |
late | -0.028 |
H | -0.028 |
Sorry | -0.027 |
Tiny | -0.026 |
ulk | -0.026 |
Token | go |
Token ID | 467 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
aney | +0.123 |
of | +0.119 |
hest | +0.112 |
iky | +0.106 |
isy | +0.099 |
Neg logit contributions | |
ulk | -0.101 |
elbows | -0.098 |
minded | -0.098 |
fired | -0.097 |
late | -0.096 |
Token | near |
Token ID | 1474 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
Sorry | +0.018 |
elbows | +0.018 |
fired | +0.017 |
ulk | +0.016 |
Case | +0.016 |
Neg logit contributions | |
of | -0.017 |
aney | -0.016 |
hest | -0.016 |
iky | -0.014 |
iest | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | +6.36e-02 |
Pos logit contributions | |
aney | +0.154 |
hest | +0.141 |
iky | +0.136 |
of | +0.136 |
isy | +0.129 |
Neg logit contributions | |
Sorry | -0.074 |
elbows | -0.072 |
H | -0.070 |
ulk | -0.070 |
late | -0.069 |
Token | all |
Token ID | 477 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
Sorry | +0.005 |
elbows | +0.005 |
H | +0.005 |
late | +0.005 |
ulk | +0.005 |
Neg logit contributions | |
aney | -0.007 |
hest | -0.006 |
iky | -0.006 |
of | -0.006 |
isy | -0.005 |
Token | igator |
Token ID | 23823 |
Feature activation | -4.43e+00 |
Pos logit contributions | |
late | +0.045 |
Sorry | +0.044 |
minded | +0.044 |
fired | +0.043 |
H | +0.042 |
Neg logit contributions | |
aney | -0.041 |
aces | -0.034 |
iky | -0.033 |
hest | -0.033 |
isy | -0.033 |
Token | ." |
Token ID | 526 |
Feature activation | -5.75e-01 |
Pos logit contributions | |
aney | +0.474 |
hest | +0.416 |
iky | +0.409 |
of | +0.387 |
isy | +0.378 |
Neg logit contributions | |
Sorry | -0.348 |
fired | -0.338 |
late | -0.335 |
H | -0.334 |
elbows | -0.332 |
Token | |
Token ID | 220 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
aney | +0.064 |
of | +0.058 |
hest | +0.056 |
iky | +0.052 |
isy | +0.050 |
Neg logit contributions | |
elbows | -0.041 |
Sorry | -0.041 |
minded | -0.040 |
ulk | -0.039 |
fired | -0.039 |
Token |
|
Token ID | 198 |
Feature activation | -2.09e-02 |
Pos logit contributions | |
aney | +0.037 |
hest | +0.034 |
iky | +0.034 |
of | +0.033 |
isy | +0.032 |
Neg logit contributions | |
Sorry | -0.014 |
late | -0.014 |
H | -0.014 |
ulk | -0.013 |
fired | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | -5.09e-02 |
Pos logit contributions | |
aney | +0.003 |
hest | +0.002 |
iky | +0.002 |
of | +0.002 |
isy | +0.002 |
Neg logit contributions | |
Sorry | -0.001 |
elbows | -0.001 |
late | -0.001 |
H | -0.001 |
ulk | -0.001 |
Token | Tim |
Token ID | 14967 |
Feature activation | -9.64e-01 |
Pos logit contributions | |
aney | +0.006 |
hest | +0.005 |
iky | +0.005 |
of | +0.005 |
isy | +0.005 |
Neg logit contributions | |
Sorry | -0.004 |
elbows | -0.003 |
late | -0.003 |
ulk | -0.003 |
H | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
aney | +0.111 |
hest | +0.100 |
iky | +0.097 |
isy | +0.087 |
of | +0.087 |
Neg logit contributions | |
elbows | -0.073 |
Sorry | -0.073 |
fired | -0.070 |
ulk | -0.069 |
late | -0.069 |
Token | He |
Token ID | 679 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
aney | +0.024 |
of | +0.022 |
hest | +0.021 |
iky | +0.020 |
isy | +0.019 |
Neg logit contributions | |
elbows | -0.015 |
ulk | -0.014 |
fired | -0.014 |
minded | -0.014 |
Sorry | -0.014 |
Token | approached |
Token ID | 10448 |
Feature activation | +4.42e-01 |
Pos logit contributions | |
aney | +0.040 |
hest | +0.036 |
iky | +0.035 |
of | +0.034 |
isy | +0.032 |
Neg logit contributions | |
Sorry | -0.025 |
fired | -0.024 |
elbows | -0.024 |
H | -0.024 |
late | -0.024 |
Token | the |
Token ID | 262 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
Sorry | +0.025 |
elbows | +0.025 |
H | +0.025 |
late | +0.024 |
fired | +0.024 |
Neg logit contributions | |
aney | -0.056 |
hest | -0.052 |
iky | -0.050 |
of | -0.049 |
isy | -0.047 |
Token | all |
Token ID | 477 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
Sorry | +0.001 |
elbows | +0.001 |
ulk | +0.001 |
fired | +0.001 |
H | +0.001 |
Neg logit contributions | |
aney | -0.001 |
hest | -0.001 |
of | -0.001 |
iky | -0.001 |
isy | -0.001 |
Token | igator |
Token ID | 23823 |
Feature activation | -4.43e+00 |
Pos logit contributions | |
late | +0.062 |
forth | +0.060 |
minded | +0.059 |
Sorry | +0.058 |
fired | +0.058 |
Neg logit contributions | |
aney | -0.034 |
hest | -0.028 |
iky | -0.028 |
aces | -0.026 |
umbs | -0.024 |
Token | slowly |
Token ID | 6364 |
Feature activation | -9.26e-02 |
Pos logit contributions | |
aney | +0.427 |
hest | +0.382 |
of | +0.368 |
iky | +0.365 |
isy | +0.337 |
Neg logit contributions | |
Sorry | -0.387 |
elbows | -0.378 |
ulk | -0.370 |
fired | -0.369 |
H | -0.367 |
Token | and |
Token ID | 290 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
aney | +0.010 |
hest | +0.009 |
iky | +0.009 |
isy | +0.008 |
of | +0.008 |
Neg logit contributions | |
fired | -0.007 |
elbows | -0.007 |
late | -0.007 |
Sorry | -0.007 |
H | -0.007 |
Token | pet |
Token ID | 4273 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
of | +0.011 |
aney | +0.011 |
isy | +0.009 |
hest | +0.009 |
pole | +0.009 |
Neg logit contributions | |
Sorry | -0.012 |
ulk | -0.012 |
elbows | -0.012 |
late | -0.011 |
fired | -0.011 |
Token | ted |
Token ID | 1513 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
Sorry | +0.017 |
elbows | +0.016 |
fired | +0.016 |
H | +0.016 |
ulk | +0.016 |
Neg logit contributions | |
aney | -0.043 |
hest | -0.040 |
iky | -0.038 |
of | -0.038 |
isy | -0.036 |
Token | it |
Token ID | 340 |
Feature activation | -3.88e-01 |
Pos logit contributions | |
Sorry | +0.082 |
H | +0.081 |
elbows | +0.079 |
late | +0.077 |
fired | +0.075 |
Neg logit contributions | |
aney | -0.207 |
hest | -0.190 |
iky | -0.184 |
of | -0.177 |
isy | -0.170 |
Token | . |
Token ID | 13 |
Feature activation | -3.53e-02 |
Pos logit contributions | |
aney | +0.034 |
hest | +0.031 |
iky | +0.030 |
of | +0.027 |
umbs | +0.027 |
Neg logit contributions | |
minded | -0.022 |
H | -0.022 |
Sorry | -0.021 |
late | -0.021 |
fired | -0.021 |
Token | Finally |
Token ID | 9461 |
Feature activation | +4.11e-01 |
Pos logit contributions | |
aney | +0.004 |
hest | +0.004 |
of | +0.004 |
iky | +0.004 |
isy | +0.003 |
Neg logit contributions | |
Sorry | -0.002 |
elbows | -0.002 |
ulk | -0.002 |
fired | -0.002 |
H | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | +6.48e-03 |
Pos logit contributions | |
Sorry | +0.037 |
elbows | +0.037 |
ulk | +0.036 |
fired | +0.035 |
minded | +0.035 |
Neg logit contributions | |
aney | -0.038 |
hest | -0.034 |
of | -0.034 |
iky | -0.032 |
isy | -0.030 |
Token | another |
Token ID | 1194 |
Feature activation | -5.84e-01 |
Pos logit contributions | |
elbows | +0.001 |
ulk | +0.001 |
Sorry | +0.001 |
fired | +0.001 |
minded | +0.001 |
Neg logit contributions | |
of | -0.001 |
aney | -0.001 |
hest | -0.001 |
iest | -0.000 |
contain | -0.000 |
Token | all |
Token ID | 477 |
Feature activation | +6.26e-01 |
Pos logit contributions | |
aney | +0.064 |
hest | +0.058 |
iky | +0.057 |
aces | +0.056 |
umbs | +0.055 |
Neg logit contributions | |
late | -0.041 |
Fox | -0.039 |
Sorry | -0.039 |
H | -0.038 |
forth | -0.037 |
Token | igator |
Token ID | 23823 |
Feature activation | -4.42e+00 |
Pos logit contributions | |
fired | +0.069 |
late | +0.069 |
Sorry | +0.067 |
minded | +0.066 |
H | +0.064 |
Neg logit contributions | |
aney | -0.046 |
hest | -0.040 |
iky | -0.039 |
umbs | -0.034 |
isy | -0.032 |
Token | said |
Token ID | 531 |
Feature activation | -9.87e-02 |
Pos logit contributions | |
aney | +0.497 |
hest | +0.453 |
iky | +0.442 |
of | +0.415 |
isy | +0.397 |
Neg logit contributions | |
Sorry | -0.320 |
fired | -0.314 |
H | -0.303 |
elbows | -0.302 |
minded | -0.298 |
Token | , |
Token ID | 11 |
Feature activation | -4.33e-02 |
Pos logit contributions | |
aney | +0.011 |
hest | +0.010 |
iky | +0.010 |
umbs | +0.009 |
isy | +0.009 |
Neg logit contributions | |
Sorry | -0.007 |
H | -0.007 |
fired | -0.007 |
late | -0.007 |
minded | -0.006 |
Token | " |
Token ID | 366 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
aney | +0.004 |
hest | +0.004 |
of | +0.003 |
iky | +0.003 |
isy | +0.003 |
Neg logit contributions | |
Sorry | -0.004 |
elbows | -0.004 |
ulk | -0.004 |
H | -0.004 |
fired | -0.004 |
Token | Yes |
Token ID | 5297 |
Feature activation | -8.45e-01 |
Pos logit contributions | |
aney | +0.045 |
hest | +0.041 |
of | +0.040 |
iky | +0.039 |
isy | +0.038 |
Neg logit contributions | |
Sorry | -0.020 |
elbows | -0.020 |
ulk | -0.019 |
fired | -0.019 |
H | -0.018 |
Token | , |
Token ID | 11 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
aney | +0.099 |
hest | +0.093 |
iky | +0.092 |
aces | +0.087 |
umbs | +0.085 |
Neg logit contributions | |
Sorry | -0.058 |
H | -0.054 |
Tiny | -0.048 |
late | -0.046 |
Are | -0.046 |
Token | next |
Token ID | 1306 |
Feature activation | -5.79e-01 |
Pos logit contributions | |
aney | +0.095 |
hest | +0.081 |
iky | +0.079 |
aces | +0.078 |
umbs | +0.077 |
Neg logit contributions | |
Sorry | -0.059 |
late | -0.059 |
Fox | -0.057 |
minded | -0.056 |
What | -0.056 |
Token | day |
Token ID | 1110 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
aney | +0.053 |
hest | +0.047 |
of | +0.046 |
iky | +0.045 |
isy | +0.041 |
Neg logit contributions | |
Sorry | -0.054 |
elbows | -0.054 |
ulk | -0.052 |
fired | -0.052 |
H | -0.052 |
Token | , |
Token ID | 11 |
Feature activation | -9.65e-03 |
Pos logit contributions | |
aney | +0.025 |
of | +0.024 |
hest | +0.022 |
iky | +0.020 |
iest | +0.019 |
Neg logit contributions | |
elbows | -0.032 |
ulk | -0.031 |
Sorry | -0.030 |
minded | -0.030 |
fired | -0.030 |
Token | the |
Token ID | 262 |
Feature activation | +8.91e-02 |
Pos logit contributions | |
of | +0.001 |
aney | +0.001 |
hest | +0.001 |
isy | +0.001 |
iest | +0.001 |
Neg logit contributions | |
elbows | -0.001 |
ulk | -0.001 |
fired | -0.001 |
minded | -0.001 |
Sorry | -0.001 |
Token | all |
Token ID | 477 |
Feature activation | +5.37e-01 |
Pos logit contributions | |
late | +0.006 |
Sorry | +0.006 |
Fox | +0.006 |
H | +0.006 |
minded | +0.006 |
Neg logit contributions | |
aney | -0.010 |
hest | -0.009 |
iky | -0.009 |
aces | -0.008 |
umbs | -0.008 |
Token | igator |
Token ID | 23823 |
Feature activation | -4.42e+00 |
Pos logit contributions | |
Sorry | +0.071 |
late | +0.070 |
fired | +0.069 |
H | +0.067 |
ulk | +0.067 |
Neg logit contributions | |
aney | -0.028 |
hest | -0.024 |
iky | -0.022 |
isy | -0.017 |
aces | -0.017 |
Token | saw |
Token ID | 2497 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
aney | +0.498 |
hest | +0.453 |
iky | +0.436 |
of | +0.432 |
isy | +0.405 |
Neg logit contributions | |
Sorry | -0.316 |
elbows | -0.304 |
fired | -0.301 |
H | -0.296 |
ulk | -0.295 |
Token | a |
Token ID | 257 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
aney | +0.028 |
hest | +0.026 |
iky | +0.025 |
of | +0.024 |
isy | +0.023 |
Neg logit contributions | |
Sorry | -0.011 |
fired | -0.011 |
H | -0.011 |
late | -0.011 |
elbows | -0.011 |
Token | snake |
Token ID | 17522 |
Feature activation | -4.12e-01 |
Pos logit contributions | |
aney | +0.017 |
hest | +0.015 |
of | +0.014 |
iky | +0.014 |
aces | +0.013 |
Neg logit contributions | |
Sorry | -0.015 |
elbows | -0.015 |
H | -0.015 |
late | -0.015 |
fired | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
aney | +0.042 |
hest | +0.038 |
of | +0.036 |
iky | +0.036 |
isy | +0.033 |
Neg logit contributions | |
Sorry | -0.034 |
elbows | -0.033 |
fired | -0.032 |
ulk | -0.032 |
H | -0.032 |
Token | The |
Token ID | 383 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
aney | +0.030 |
hest | +0.028 |
of | +0.027 |
iky | +0.027 |
isy | +0.025 |
Neg logit contributions | |
Sorry | -0.017 |
elbows | -0.017 |
H | -0.016 |
ulk | -0.016 |
fired | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
aney | +0.014 |
of | +0.013 |
hest | +0.013 |
iky | +0.012 |
isy | +0.011 |
Neg logit contributions | |
Sorry | -0.009 |
elbows | -0.009 |
minded | -0.009 |
fired | -0.009 |
ulk | -0.008 |
Token | pond |
Token ID | 16723 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
Sorry | +0.008 |
elbows | +0.008 |
late | +0.008 |
ulk | +0.008 |
fired | +0.008 |
Neg logit contributions | |
aney | -0.016 |
hest | -0.014 |
iky | -0.014 |
of | -0.014 |
isy | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
aney | +0.022 |
hest | +0.020 |
iky | +0.019 |
isy | +0.018 |
of | +0.017 |
Neg logit contributions | |
late | -0.014 |
fired | -0.014 |
elbows | -0.013 |
Sorry | -0.013 |
ulk | -0.013 |
Token | The |
Token ID | 383 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
aney | +0.019 |
hest | +0.018 |
of | +0.017 |
iky | +0.017 |
isy | +0.016 |
Neg logit contributions | |
Sorry | -0.012 |
elbows | -0.011 |
ulk | -0.011 |
fired | -0.011 |
H | -0.011 |
Token | all |
Token ID | 477 |
Feature activation | +5.46e-01 |
Pos logit contributions | |
aney | +0.014 |
hest | +0.012 |
iky | +0.012 |
aces | +0.011 |
ool | +0.011 |
Neg logit contributions | |
Sorry | -0.009 |
What | -0.009 |
late | -0.009 |
Fox | -0.009 |
H | -0.009 |
Token | igator |
Token ID | 23823 |
Feature activation | -4.41e+00 |
Pos logit contributions | |
Sorry | +0.062 |
late | +0.061 |
Lightning | +0.059 |
H | +0.058 |
Are | +0.058 |
Neg logit contributions | |
aney | -0.036 |
hest | -0.031 |
iky | -0.029 |
aces | -0.027 |
umbs | -0.026 |
Token | looked |
Token ID | 3114 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
aney | +0.462 |
hest | +0.417 |
iky | +0.398 |
of | +0.394 |
isy | +0.367 |
Neg logit contributions | |
Sorry | -0.354 |
elbows | -0.342 |
fired | -0.339 |
H | -0.335 |
ulk | -0.331 |
Token | very |
Token ID | 845 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
aney | +0.022 |
hest | +0.020 |
iky | +0.019 |
of | +0.018 |
isy | +0.018 |
Neg logit contributions | |
late | -0.015 |
Sorry | -0.015 |
H | -0.015 |
fired | -0.014 |
elbows | -0.014 |
Token | scary |
Token ID | 14343 |
Feature activation | +7.06e-01 |
Pos logit contributions | |
aney | +0.035 |
hest | +0.032 |
of | +0.030 |
iky | +0.030 |
isy | +0.029 |
Neg logit contributions | |
Sorry | -0.024 |
late | -0.023 |
H | -0.022 |
elbows | -0.022 |
fired | -0.022 |
Token | and |
Token ID | 290 |
Feature activation | -4.72e-02 |
Pos logit contributions | |
elbows | +0.055 |
fired | +0.055 |
H | +0.055 |
Sorry | +0.055 |
late | +0.055 |
Neg logit contributions | |
aney | -0.075 |
hest | -0.067 |
iky | -0.063 |
of | -0.060 |
isy | -0.059 |
Token | Tim |
Token ID | 5045 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
aney | +0.005 |
of | +0.004 |
hest | +0.004 |
iky | +0.004 |
isy | +0.004 |
Neg logit contributions | |
ulk | -0.004 |
Sorry | -0.004 |
elbows | -0.004 |
minded | -0.004 |
fired | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -6.15e-02 |
Pos logit contributions | |
aney | +0.001 |
hest | +0.001 |
iky | +0.001 |
of | +0.001 |
aces | +0.001 |
Neg logit contributions | |
late | -0.000 |
H | -0.000 |
ulk | -0.000 |
Sorry | -0.000 |
elbows | -0.000 |
Token | Soon |
Token ID | 28093 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
aney | +0.008 |
iky | +0.007 |
hest | +0.007 |
aces | +0.006 |
of | +0.006 |
Neg logit contributions | |
late | -0.004 |
Sorry | -0.004 |
ulk | -0.004 |
H | -0.003 |
Case | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | -8.46e-02 |
Pos logit contributions | |
aney | +0.023 |
of | +0.023 |
hest | +0.020 |
iest | +0.019 |
iky | +0.018 |
Neg logit contributions | |
elbows | -0.026 |
Sorry | -0.024 |
ulk | -0.024 |
fired | -0.024 |
minded | -0.023 |
Token | the |
Token ID | 262 |
Feature activation | +8.95e-02 |
Pos logit contributions | |
of | +0.008 |
aney | +0.008 |
hest | +0.007 |
iest | +0.007 |
isy | +0.007 |
Neg logit contributions | |
elbows | -0.007 |
ulk | -0.007 |
fired | -0.007 |
minded | -0.007 |
Sorry | -0.007 |
Token | all |
Token ID | 477 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
Sorry | +0.007 |
late | +0.006 |
Fox | +0.006 |
What | +0.006 |
H | +0.006 |
Neg logit contributions | |
aney | -0.011 |
hest | -0.009 |
iky | -0.009 |
aces | -0.009 |
umbs | -0.008 |
Token | igator |
Token ID | 23823 |
Feature activation | -4.41e+00 |
Pos logit contributions | |
Sorry | +0.053 |
late | +0.052 |
fired | +0.050 |
H | +0.050 |
Tiny | +0.050 |
Neg logit contributions | |
aney | -0.023 |
hest | -0.020 |
iky | -0.019 |
isy | -0.015 |
aces | -0.015 |
Token | 's |
Token ID | 338 |
Feature activation | +6.50e-01 |
Pos logit contributions | |
aney | +0.502 |
hest | +0.454 |
iky | +0.448 |
of | +0.413 |
isy | +0.398 |
Neg logit contributions | |
Sorry | -0.309 |
fired | -0.305 |
H | -0.295 |
late | -0.294 |
elbows | -0.291 |
Token | family |
Token ID | 1641 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
Sorry | +0.046 |
elbows | +0.044 |
H | +0.043 |
late | +0.042 |
fired | +0.042 |
Neg logit contributions | |
aney | -0.076 |
hest | -0.071 |
iky | -0.066 |
of | -0.060 |
aces | -0.059 |
Token | wrote |
Token ID | 2630 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
aney | +0.033 |
iky | +0.031 |
hest | +0.031 |
isy | +0.028 |
aces | +0.027 |
Neg logit contributions | |
fired | -0.019 |
Sorry | -0.018 |
H | -0.018 |
late | -0.018 |
Tiny | -0.017 |
Token | back |
Token ID | 736 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
late | +0.075 |
Sorry | +0.074 |
H | +0.072 |
fired | +0.072 |
minded | +0.072 |
Neg logit contributions | |
aney | -0.126 |
hest | -0.114 |
iky | -0.111 |
of | -0.104 |
isy | -0.102 |
Token | . |
Token ID | 13 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
aney | +0.017 |
of | +0.016 |
hest | +0.015 |
iky | +0.014 |
iest | +0.014 |
Neg logit contributions | |
Sorry | -0.014 |
elbows | -0.014 |
ulk | -0.013 |
late | -0.013 |
H | -0.013 |
Token | sad |
Token ID | 6507 |
Feature activation | -6.13e-01 |
Pos logit contributions | |
aney | +0.032 |
hest | +0.030 |
iky | +0.028 |
of | +0.028 |
iest | +0.027 |
Neg logit contributions | |
Sorry | -0.020 |
H | -0.020 |
late | -0.020 |
elbows | -0.019 |
fired | -0.019 |
Token | ?" |
Token ID | 1701 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
aney | +0.068 |
hest | +0.062 |
of | +0.061 |
iky | +0.059 |
isy | +0.056 |
Neg logit contributions | |
Sorry | -0.045 |
elbows | -0.044 |
ulk | -0.042 |
fired | -0.042 |
H | -0.042 |
Token | asked |
Token ID | 1965 |
Feature activation | -3.10e-02 |
Pos logit contributions | |
of | +0.012 |
aney | +0.011 |
hest | +0.009 |
igator | +0.009 |
isy | +0.009 |
Neg logit contributions | |
elbows | -0.010 |
ulk | -0.010 |
fired | -0.009 |
minded | -0.009 |
icol | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
aney | +0.004 |
hest | +0.003 |
of | +0.003 |
iky | +0.003 |
isy | +0.003 |
Neg logit contributions | |
Sorry | -0.002 |
elbows | -0.002 |
ulk | -0.002 |
fired | -0.002 |
H | -0.002 |
Token | all |
Token ID | 477 |
Feature activation | +5.52e-01 |
Pos logit contributions | |
Sorry | +0.012 |
late | +0.012 |
H | +0.012 |
minded | +0.011 |
elbows | +0.011 |
Neg logit contributions | |
aney | -0.018 |
hest | -0.016 |
iky | -0.015 |
of | -0.014 |
aces | -0.014 |
Token | igator |
Token ID | 23823 |
Feature activation | -4.41e+00 |
Pos logit contributions | |
late | +0.068 |
Sorry | +0.066 |
H | +0.065 |
Lightning | +0.063 |
fired | +0.063 |
Neg logit contributions | |
aney | -0.030 |
hest | -0.030 |
iky | -0.026 |
aces | -0.023 |
umbs | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
aney | +0.402 |
of | +0.360 |
hest | +0.350 |
iky | +0.330 |
isy | +0.321 |
Neg logit contributions | |
Sorry | -0.412 |
elbows | -0.402 |
ulk | -0.396 |
fired | -0.385 |
late | -0.383 |
Token | The |
Token ID | 383 |
Feature activation | -5.61e-02 |
Pos logit contributions | |
Sorry | +0.011 |
elbows | +0.011 |
ulk | +0.011 |
fired | +0.011 |
minded | +0.010 |
Neg logit contributions | |
aney | -0.021 |
hest | -0.019 |
of | -0.019 |
iky | -0.018 |
isy | -0.017 |
Token | girl |
Token ID | 2576 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
aney | +0.006 |
hest | +0.006 |
iky | +0.005 |
of | +0.005 |
umbs | +0.005 |
Neg logit contributions | |
Sorry | -0.004 |
H | -0.004 |
late | -0.004 |
minded | -0.004 |
Fox | -0.004 |
Token | said |
Token ID | 531 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
Sorry | +0.016 |
elbows | +0.015 |
H | +0.015 |
fired | +0.015 |
minded | +0.015 |
Neg logit contributions | |
aney | -0.024 |
hest | -0.023 |
iky | -0.021 |
of | -0.021 |
iest | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
aney | +0.014 |
hest | +0.013 |
iky | +0.012 |
umbs | +0.011 |
of | +0.011 |
Neg logit contributions | |
Sorry | -0.010 |
H | -0.009 |
fired | -0.009 |
late | -0.009 |
minded | -0.009 |
Token | all |
Token ID | 477 |
Feature activation | +6.25e-01 |
Pos logit contributions | |
Sorry | +0.011 |
elbows | +0.011 |
late | +0.011 |
H | +0.010 |
fired | +0.010 |
Neg logit contributions | |
aney | -0.014 |
hest | -0.013 |
iky | -0.012 |
of | -0.012 |
aces | -0.011 |
Token | igator |
Token ID | 23823 |
Feature activation | -4.40e+00 |
Pos logit contributions | |
late | +0.083 |
Sorry | +0.081 |
fired | +0.079 |
ulk | +0.078 |
H | +0.078 |
Neg logit contributions | |
aney | -0.033 |
hest | -0.027 |
iky | -0.024 |
aces | -0.020 |
isy | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | -5.23e-02 |
Pos logit contributions | |
aney | +0.492 |
hest | +0.442 |
iky | +0.430 |
of | +0.398 |
isy | +0.388 |
Neg logit contributions | |
Sorry | -0.330 |
fired | -0.321 |
elbows | -0.318 |
late | -0.312 |
H | -0.306 |
Token | The |
Token ID | 383 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
aney | +0.006 |
of | +0.005 |
hest | +0.005 |
iky | +0.005 |
isy | +0.005 |
Neg logit contributions | |
elbows | -0.004 |
Sorry | -0.004 |
fired | -0.004 |
ulk | -0.004 |
minded | -0.004 |
Token | all |
Token ID | 477 |
Feature activation | +6.22e-01 |
Pos logit contributions | |
aney | +0.012 |
hest | +0.011 |
iky | +0.010 |
of | +0.010 |
aces | +0.010 |
Neg logit contributions | |
Sorry | -0.007 |
late | -0.007 |
H | -0.007 |
elbows | -0.007 |
minded | -0.007 |
Token | igator |
Token ID | 23823 |
Feature activation | -4.41e+00 |
Pos logit contributions | |
late | +0.078 |
Sorry | +0.077 |
fired | +0.075 |
H | +0.073 |
Lightning | +0.073 |
Neg logit contributions | |
aney | -0.036 |
hest | -0.032 |
iky | -0.028 |
umbs | -0.024 |
aces | -0.023 |
Token | was |
Token ID | 373 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
aney | +0.504 |
hest | +0.458 |
iky | +0.442 |
of | +0.425 |
isy | +0.403 |
Neg logit contributions | |
Sorry | -0.315 |
elbows | -0.304 |
fired | -0.303 |
H | -0.291 |
late | -0.290 |
Token | hurt |
Token ID | 5938 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
aney | +0.031 |
hest | +0.029 |
iky | +0.028 |
iest | +0.028 |
ool | +0.026 |
Neg logit contributions | |
late | -0.014 |
elbows | -0.011 |
H | -0.011 |
fired | -0.011 |
barking | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | -2.63e-02 |
Pos logit contributions | |
late | +0.025 |
H | +0.025 |
fired | +0.024 |
elbows | +0.023 |
Tiny | +0.022 |
Neg logit contributions | |
aney | -0.035 |
hest | -0.031 |
iky | -0.029 |
isy | -0.028 |
contain | -0.027 |
Token | could |
Token ID | 714 |
Feature activation | +4.01e-03 |
Pos logit contributions | |
aney | +0.003 |
of | +0.003 |
hest | +0.003 |
iky | +0.002 |
isy | +0.002 |
Neg logit contributions | |
Sorry | -0.002 |
elbows | -0.002 |
ulk | -0.002 |
minded | -0.002 |
fired | -0.002 |
Token | not |
Token ID | 407 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
Sorry | +0.000 |
late | +0.000 |
elbows | +0.000 |
H | +0.000 |
ulk | +0.000 |
Neg logit contributions | |
aney | -0.000 |
hest | -0.000 |
iky | -0.000 |
of | -0.000 |
isy | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
late | +0.061 |
fired | +0.059 |
Sorry | +0.058 |
H | +0.058 |
elbows | +0.057 |
Neg logit contributions | |
aney | -0.089 |
hest | -0.081 |
iky | -0.078 |
of | -0.072 |
isy | -0.072 |
Token |
|
Token ID | 198 |
Feature activation | +8.67e-02 |
Pos logit contributions | |
aney | +0.022 |
hest | +0.020 |
of | +0.020 |
iky | +0.019 |
isy | +0.018 |
Neg logit contributions | |
elbows | -0.013 |
Sorry | -0.013 |
ulk | -0.012 |
fired | -0.012 |
minded | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | +3.21e-02 |
Pos logit contributions | |
Sorry | +0.005 |
late | +0.005 |
H | +0.004 |
ulk | +0.004 |
elbows | +0.004 |
Neg logit contributions | |
aney | -0.011 |
hest | -0.010 |
iky | -0.010 |
of | -0.010 |
isy | -0.009 |
Token | The |
Token ID | 464 |
Feature activation | -8.05e-01 |
Pos logit contributions | |
Sorry | +0.002 |
elbows | +0.002 |
ulk | +0.002 |
fired | +0.002 |
H | +0.002 |
Neg logit contributions | |
aney | -0.004 |
hest | -0.003 |
of | -0.003 |
iky | -0.003 |
isy | -0.003 |
Token | all |
Token ID | 477 |
Feature activation | +5.46e-01 |
Pos logit contributions | |
aney | +0.084 |
hest | +0.077 |
iky | +0.072 |
of | +0.070 |
aces | +0.065 |
Neg logit contributions | |
Sorry | -0.066 |
elbows | -0.064 |
H | -0.062 |
late | -0.062 |
minded | -0.062 |
Token | igator |
Token ID | 23823 |
Feature activation | -4.40e+00 |
Pos logit contributions | |
Sorry | +0.067 |
late | +0.066 |
fired | +0.064 |
Lightning | +0.063 |
Tiny | +0.063 |
Neg logit contributions | |
aney | -0.031 |
hest | -0.029 |
iky | -0.027 |
aces | -0.022 |
umbs | -0.022 |
Token | was |
Token ID | 373 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
aney | +0.479 |
hest | +0.435 |
iky | +0.419 |
of | +0.410 |
isy | +0.380 |
Neg logit contributions | |
Sorry | -0.333 |
elbows | -0.321 |
fired | -0.318 |
H | -0.314 |
late | -0.310 |
Token | so |
Token ID | 523 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
aney | +0.032 |
hest | +0.030 |
iky | +0.029 |
iest | +0.027 |
aces | +0.027 |
Neg logit contributions | |
late | -0.019 |
elbows | -0.016 |
H | -0.016 |
fired | -0.016 |
heaven | -0.016 |
Token | upset |
Token ID | 9247 |
Feature activation | -7.17e-01 |
Pos logit contributions | |
aney | +0.016 |
hest | +0.015 |
iky | +0.014 |
aces | +0.013 |
of | +0.013 |
Neg logit contributions | |
late | -0.008 |
Sorry | -0.008 |
fired | -0.007 |
H | -0.007 |
elbows | -0.007 |
Token | that |
Token ID | 326 |
Feature activation | +9.84e-02 |
Pos logit contributions | |
aney | +0.075 |
hest | +0.067 |
iky | +0.064 |
of | +0.062 |
isy | +0.059 |
Neg logit contributions | |
Sorry | -0.057 |
H | -0.056 |
late | -0.056 |
fired | -0.056 |
elbows | -0.055 |
Token | he |
Token ID | 339 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
elbows | +0.007 |
Sorry | +0.007 |
ulk | +0.007 |
fired | +0.007 |
minded | +0.007 |
Neg logit contributions | |
aney | -0.011 |
of | -0.010 |
hest | -0.010 |
iky | -0.009 |
iest | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | -3.01e-02 |
Pos logit contributions | |
aney | +0.054 |
of | +0.047 |
hest | +0.047 |
iky | +0.045 |
isy | +0.042 |
Neg logit contributions | |
Sorry | -0.060 |
elbows | -0.060 |
ulk | -0.059 |
fired | -0.057 |
minded | -0.057 |
Token | you |
Token ID | 345 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
aney | +0.004 |
hest | +0.003 |
iky | +0.003 |
of | +0.003 |
isy | +0.003 |
Neg logit contributions | |
Sorry | -0.002 |
elbows | -0.002 |
H | -0.002 |
ulk | -0.002 |
fired | -0.002 |
Token | should |
Token ID | 815 |
Feature activation | +7.17e-01 |
Pos logit contributions | |
aney | +0.015 |
hest | +0.013 |
of | +0.013 |
iky | +0.012 |
isy | +0.011 |
Neg logit contributions | |
Sorry | -0.017 |
elbows | -0.017 |
ulk | -0.016 |
fired | -0.016 |
late | -0.016 |
Token | say |
Token ID | 910 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
Sorry | +0.057 |
H | +0.053 |
elbows | +0.053 |
ulk | +0.052 |
fired | +0.052 |
Neg logit contributions | |
aney | -0.078 |
hest | -0.070 |
iky | -0.067 |
of | -0.066 |
isy | -0.062 |
Token | ' |
Token ID | 705 |
Feature activation | +9.79e-01 |
Pos logit contributions | |
aney | +0.029 |
of | +0.027 |
hest | +0.027 |
iky | +0.026 |
isy | +0.025 |
Neg logit contributions | |
elbows | -0.017 |
Sorry | -0.017 |
fired | -0.017 |
ulk | -0.017 |
late | -0.017 |
Token | w |
Token ID | 86 |
Feature activation | +3.58e+00 |
Pos logit contributions | |
Sorry | +0.068 |
elbows | +0.067 |
fired | +0.065 |
ulk | +0.064 |
Tinker | +0.062 |
Neg logit contributions | |
aney | -0.109 |
hest | -0.102 |
of | -0.100 |
iky | -0.097 |
iest | -0.090 |
Token | elcome |
Token ID | 9571 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
Sorry | +0.293 |
elbows | +0.286 |
ulk | +0.279 |
fired | +0.278 |
H | +0.277 |
Neg logit contributions | |
aney | -0.366 |
hest | -0.330 |
of | -0.318 |
iky | -0.315 |
isy | -0.291 |
Token | ' |
Token ID | 6 |
Feature activation | +5.63e-01 |
Pos logit contributions | |
elbows | +0.155 |
Sorry | +0.154 |
ulk | +0.150 |
fired | +0.148 |
H | +0.146 |
Neg logit contributions | |
aney | -0.157 |
hest | -0.140 |
of | -0.139 |
iky | -0.132 |
isy | -0.123 |
Token | and |
Token ID | 290 |
Feature activation | -5.67e-03 |
Pos logit contributions | |
Sorry | +0.047 |
late | +0.046 |
H | +0.045 |
minded | +0.044 |
fired | +0.044 |
Neg logit contributions | |
aney | -0.058 |
hest | -0.051 |
iky | -0.050 |
of | -0.047 |
isy | -0.045 |
Token | share |
Token ID | 2648 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
aney | +0.001 |
of | +0.001 |
hest | +0.000 |
iky | +0.000 |
isy | +0.000 |
Neg logit contributions | |
elbows | -0.000 |
ulk | -0.000 |
Sorry | -0.000 |
fired | -0.000 |
minded | -0.000 |
Token | the |
Token ID | 262 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
aney | +0.024 |
hest | +0.022 |
of | +0.022 |
iky | +0.021 |
isy | +0.020 |
Neg logit contributions | |
Sorry | -0.010 |
elbows | -0.010 |
ulk | -0.009 |
fired | -0.009 |
H | -0.009 |
Token | He |
Token ID | 679 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
elbows | +0.011 |
Sorry | +0.011 |
fired | +0.010 |
minded | +0.010 |
ulk | +0.010 |
Neg logit contributions | |
aney | -0.011 |
of | -0.010 |
hest | -0.009 |
aces | -0.009 |
iky | -0.008 |
Token | saw |
Token ID | 2497 |
Feature activation | -3.35e-02 |
Pos logit contributions | |
aney | +0.014 |
hest | +0.013 |
of | +0.013 |
iky | +0.013 |
isy | +0.012 |
Neg logit contributions | |
Sorry | -0.009 |
elbows | -0.009 |
ulk | -0.009 |
fired | -0.009 |
late | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
aney | +0.004 |
hest | +0.004 |
of | +0.004 |
iky | +0.004 |
isy | +0.003 |
Neg logit contributions | |
Sorry | -0.002 |
elbows | -0.002 |
ulk | -0.002 |
fired | -0.002 |
H | -0.002 |
Token | dog |
Token ID | 3290 |
Feature activation | -3.72e-02 |
Pos logit contributions | |
elbows | +0.025 |
Sorry | +0.024 |
late | +0.024 |
H | +0.023 |
ulk | +0.023 |
Neg logit contributions | |
aney | -0.042 |
hest | -0.037 |
iky | -0.035 |
of | -0.035 |
isy | -0.033 |
Token | sniff |
Token ID | 26300 |
Feature activation | -5.37e-02 |
Pos logit contributions | |
aney | +0.004 |
hest | +0.004 |
iky | +0.003 |
of | +0.003 |
isy | +0.003 |
Neg logit contributions | |
Sorry | -0.003 |
elbows | -0.003 |
fired | -0.003 |
H | -0.003 |
late | -0.003 |
Token | ing |
Token ID | 278 |
Feature activation | +3.48e+00 |
Pos logit contributions | |
aney | +0.007 |
hest | +0.006 |
iky | +0.006 |
isy | +0.006 |
contain | +0.005 |
Neg logit contributions | |
late | -0.003 |
fired | -0.003 |
elbows | -0.003 |
H | -0.003 |
minded | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
elbows | +0.264 |
late | +0.260 |
H | +0.257 |
Sorry | +0.254 |
fired | +0.253 |
Neg logit contributions | |
aney | -0.375 |
hest | -0.344 |
iky | -0.315 |
isy | -0.300 |
of | -0.297 |
Token | box |
Token ID | 3091 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
elbows | +0.025 |
Sorry | +0.025 |
late | +0.024 |
H | +0.023 |
fired | +0.022 |
Neg logit contributions | |
aney | -0.037 |
hest | -0.033 |
iky | -0.031 |
of | -0.031 |
isy | -0.029 |
Token | and |
Token ID | 290 |
Feature activation | +5.11e-02 |
Pos logit contributions | |
late | +0.030 |
backward | +0.026 |
forth | +0.025 |
dreaming | +0.024 |
fired | +0.024 |
Neg logit contributions | |
aney | -0.052 |
hest | -0.043 |
iky | -0.043 |
arrow | -0.041 |
aces | -0.041 |
Token | paw |
Token ID | 41827 |
Feature activation | +3.94e-01 |
Pos logit contributions | |
Sorry | +0.004 |
late | +0.004 |
minded | +0.004 |
ulk | +0.004 |
elbows | +0.004 |
Neg logit contributions | |
aney | -0.005 |
of | -0.005 |
hest | -0.004 |
iky | -0.004 |
isy | -0.004 |
Token | ing |
Token ID | 278 |
Feature activation | +3.48e+00 |
Pos logit contributions | |
elbows | +0.027 |
Sorry | +0.026 |
H | +0.025 |
fired | +0.025 |
late | +0.025 |
Neg logit contributions | |
aney | -0.046 |
hest | -0.042 |
iky | -0.040 |
of | -0.038 |
isy | -0.038 |
Token | fell |
Token ID | 3214 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
H | +0.031 |
fired | +0.031 |
elbows | +0.030 |
check | +0.029 |
Rat | +0.028 |
Neg logit contributions | |
aney | -0.065 |
hest | -0.059 |
iky | -0.053 |
iest | -0.053 |
umbs | -0.052 |
Token | down |
Token ID | 866 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
late | +0.064 |
H | +0.063 |
elbows | +0.061 |
fired | +0.060 |
ulk | +0.059 |
Neg logit contributions | |
aney | -0.196 |
hest | -0.178 |
iky | -0.169 |
isy | -0.169 |
of | -0.164 |
Token | . |
Token ID | 13 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
late | +0.155 |
Sorry | +0.153 |
H | +0.152 |
ulk | +0.151 |
elbows | +0.151 |
Neg logit contributions | |
aney | -0.202 |
hest | -0.180 |
iky | -0.171 |
of | -0.166 |
isy | -0.164 |
Token | She |
Token ID | 1375 |
Feature activation | -2.20e-02 |
Pos logit contributions | |
elbows | +0.021 |
Sorry | +0.021 |
minded | +0.020 |
fired | +0.020 |
ulk | +0.020 |
Neg logit contributions | |
aney | -0.035 |
of | -0.032 |
hest | -0.031 |
iky | -0.030 |
isy | -0.028 |
Token | scrap |
Token ID | 15881 |
Feature activation | -8.43e-02 |
Pos logit contributions | |
aney | +0.003 |
hest | +0.003 |
iky | +0.003 |
of | +0.002 |
isy | +0.002 |
Neg logit contributions | |
elbows | -0.001 |
Sorry | -0.001 |
H | -0.001 |
fired | -0.001 |
ulk | -0.001 |
Token | ed |
Token ID | 276 |
Feature activation | +3.47e+00 |
Pos logit contributions | |
aney | +0.009 |
hest | +0.008 |
of | +0.008 |
iky | +0.008 |
isy | +0.007 |
Neg logit contributions | |
Sorry | -0.006 |
elbows | -0.006 |
ulk | -0.006 |
fired | -0.006 |
minded | -0.006 |
Token | her |
Token ID | 607 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
Sorry | +0.261 |
elbows | +0.231 |
ulk | +0.230 |
fired | +0.230 |
minded | +0.228 |
Neg logit contributions | |
aney | -0.387 |
of | -0.365 |
hest | -0.342 |
iky | -0.330 |
isy | -0.314 |
Token | knee |
Token ID | 10329 |
Feature activation | -5.05e-02 |
Pos logit contributions | |
elbows | +0.001 |
H | +0.001 |
Sorry | +0.001 |
late | +0.001 |
fired | +0.001 |
Neg logit contributions | |
aney | -0.002 |
hest | -0.002 |
iky | -0.002 |
of | -0.001 |
umbs | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
aney | +0.006 |
hest | +0.005 |
iky | +0.004 |
isy | +0.004 |
iest | +0.004 |
Neg logit contributions | |
late | -0.004 |
elbows | -0.004 |
H | -0.004 |
fired | -0.004 |
ulk | -0.004 |
Token | cried |
Token ID | 16896 |
Feature activation | +8.34e-01 |
Pos logit contributions | |
minded | +0.017 |
Sorry | +0.017 |
late | +0.015 |
ulk | +0.015 |
fired | +0.015 |
Neg logit contributions | |
of | -0.020 |
aney | -0.019 |
hest | -0.017 |
aces | -0.017 |
iky | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
Sorry | +0.071 |
elbows | +0.070 |
H | +0.069 |
late | +0.068 |
ulk | +0.068 |
Neg logit contributions | |
aney | -0.083 |
hest | -0.074 |
iky | -0.070 |
of | -0.070 |
isy | -0.065 |
Token | and |
Token ID | 290 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
aney | +0.156 |
hest | +0.141 |
iky | +0.137 |
isy | +0.129 |
iest | +0.127 |
Neg logit contributions | |
late | -0.078 |
backward | -0.078 |
together | -0.074 |
elbows | -0.073 |
Tiny | -0.072 |
Token | look |
Token ID | 804 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
Sorry | +0.010 |
fired | +0.009 |
late | +0.009 |
H | +0.009 |
ulk | +0.009 |
Neg logit contributions | |
aney | -0.010 |
of | -0.010 |
hest | -0.009 |
iky | -0.009 |
aces | -0.008 |
Token | at |
Token ID | 379 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
Sorry | +0.079 |
late | +0.077 |
H | +0.075 |
minded | +0.075 |
elbows | +0.074 |
Neg logit contributions | |
aney | -0.117 |
hest | -0.106 |
iky | -0.102 |
of | -0.098 |
isy | -0.095 |
Token | their |
Token ID | 511 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
elbows | +0.059 |
Sorry | +0.055 |
H | +0.055 |
fired | +0.054 |
minded | +0.052 |
Neg logit contributions | |
aney | -0.138 |
hest | -0.131 |
iky | -0.121 |
isy | -0.120 |
umbs | -0.117 |
Token | snow |
Token ID | 6729 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
Sorry | +0.011 |
elbows | +0.011 |
ulk | +0.011 |
fired | +0.011 |
H | +0.011 |
Neg logit contributions | |
aney | -0.014 |
hest | -0.013 |
of | -0.012 |
iky | -0.012 |
isy | -0.011 |
Token | fl |
Token ID | 2704 |
Feature activation | +4.44e+00 |
Pos logit contributions | |
Sorry | +0.016 |
elbows | +0.015 |
ulk | +0.015 |
fired | +0.015 |
H | +0.015 |
Neg logit contributions | |
aney | -0.021 |
hest | -0.019 |
of | -0.019 |
iky | -0.018 |
isy | -0.017 |
Token | akes |
Token ID | 1124 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
elbows | +0.374 |
Sorry | +0.370 |
ulk | +0.348 |
fired | +0.334 |
H | +0.325 |
Neg logit contributions | |
aney | -0.455 |
hest | -0.393 |
of | -0.383 |
isy | -0.368 |
iky | -0.365 |
Token | . |
Token ID | 13 |
Feature activation | -2.01e-02 |
Pos logit contributions | |
late | +0.076 |
elbows | +0.074 |
Sorry | +0.072 |
ulk | +0.069 |
backward | +0.068 |
Neg logit contributions | |
aney | -0.141 |
hest | -0.122 |
iky | -0.118 |
isy | -0.112 |
iest | -0.110 |
Token |
|
Token ID | 198 |
Feature activation | +6.69e-02 |
Pos logit contributions | |
aney | +0.002 |
of | +0.002 |
hest | +0.002 |
iky | +0.002 |
aces | +0.002 |
Neg logit contributions | |
elbows | -0.001 |
Sorry | -0.001 |
fired | -0.001 |
ulk | -0.001 |
minded | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
Sorry | +0.003 |
late | +0.003 |
H | +0.003 |
ulk | +0.003 |
elbows | +0.003 |
Neg logit contributions | |
aney | -0.009 |
hest | -0.008 |
iky | -0.008 |
of | -0.008 |
isy | -0.007 |
Token | S |
Token ID | 50 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
Sorry | +0.001 |
elbows | +0.001 |
fired | +0.001 |
minded | +0.001 |
ulk | +0.001 |
Neg logit contributions | |
aney | -0.002 |
hest | -0.001 |
of | -0.001 |
iky | -0.001 |
isy | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | -1.77e-02 |
Pos logit contributions | |
aney | +0.018 |
hest | +0.017 |
iky | +0.016 |
of | +0.015 |
iest | +0.015 |
Neg logit contributions | |
late | -0.013 |
elbows | -0.012 |
ulk | -0.011 |
fired | -0.011 |
H | -0.011 |
Token | little |
Token ID | 1310 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
aney | +0.001 |
hest | +0.001 |
of | +0.001 |
iky | +0.001 |
isy | +0.001 |
Neg logit contributions | |
Sorry | -0.002 |
elbows | -0.002 |
ulk | -0.002 |
fired | -0.002 |
H | -0.002 |
Token | girl |
Token ID | 2576 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
Sorry | +0.023 |
ulk | +0.022 |
elbows | +0.022 |
fired | +0.021 |
H | +0.021 |
Neg logit contributions | |
aney | -0.029 |
of | -0.028 |
hest | -0.026 |
iky | -0.025 |
isy | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | -8.94e-02 |
Pos logit contributions | |
Sorry | +0.015 |
elbows | +0.015 |
ulk | +0.015 |
late | +0.014 |
minded | +0.014 |
Neg logit contributions | |
aney | -0.016 |
of | -0.014 |
hest | -0.014 |
iky | -0.013 |
isy | -0.012 |
Token | Inst |
Token ID | 2262 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
aney | +0.010 |
of | +0.009 |
hest | +0.008 |
iky | +0.008 |
aces | +0.007 |
Neg logit contributions | |
elbows | -0.007 |
Sorry | -0.007 |
ulk | -0.007 |
fired | -0.007 |
late | -0.006 |
Token | antly |
Token ID | 3875 |
Feature activation | +4.05e+00 |
Pos logit contributions | |
of | +0.034 |
aney | +0.033 |
iky | +0.031 |
isy | +0.030 |
ier | +0.029 |
Neg logit contributions | |
elbows | -0.035 |
Sorry | -0.033 |
ulk | -0.033 |
Does | -0.032 |
heaven | -0.031 |
Token | , |
Token ID | 11 |
Feature activation | -2.25e-02 |
Pos logit contributions | |
elbows | +0.427 |
Sorry | +0.419 |
minded | +0.414 |
ulk | +0.414 |
fired | +0.407 |
Neg logit contributions | |
aney | -0.320 |
of | -0.296 |
hest | -0.262 |
iky | -0.247 |
isy | -0.244 |
Token | the |
Token ID | 262 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
of | +0.002 |
aney | +0.002 |
hest | +0.002 |
isy | +0.002 |
iest | +0.002 |
Neg logit contributions | |
elbows | -0.002 |
fired | -0.002 |
ulk | -0.002 |
Sorry | -0.002 |
minded | -0.002 |
Token | tart |
Token ID | 35842 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
late | +0.014 |
Sorry | +0.014 |
elbows | +0.014 |
H | +0.014 |
minded | +0.014 |
Neg logit contributions | |
aney | -0.015 |
hest | -0.014 |
iky | -0.013 |
of | -0.012 |
aces | -0.011 |
Token | tasted |
Token ID | 29187 |
Feature activation | -8.62e-01 |
Pos logit contributions | |
aney | +0.147 |
hest | +0.146 |
iky | +0.130 |
aces | +0.127 |
contain | +0.125 |
Neg logit contributions | |
Sorry | -0.082 |
late | -0.080 |
something | -0.077 |
Are | -0.075 |
What | -0.074 |
Token | like |
Token ID | 588 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
aney | +0.095 |
hest | +0.083 |
aces | +0.080 |
iky | +0.080 |
igator | +0.074 |
Neg logit contributions | |
late | -0.066 |
something | -0.062 |
Sorry | -0.060 |
H | -0.058 |
What | -0.057 |
Token |
|
Token ID | 198 |
Feature activation | -6.36e-02 |
Pos logit contributions | |
aney | +0.004 |
hest | +0.003 |
iky | +0.003 |
of | +0.003 |
aces | +0.003 |
Neg logit contributions | |
late | -0.001 |
H | -0.001 |
Sorry | -0.001 |
ulk | -0.001 |
elbows | -0.001 |
Token | One |
Token ID | 3198 |
Feature activation | +7.18e-01 |
Pos logit contributions | |
aney | +0.007 |
hest | +0.006 |
of | +0.006 |
iky | +0.006 |
isy | +0.006 |
Neg logit contributions | |
Sorry | -0.004 |
late | -0.004 |
H | -0.004 |
ulk | -0.004 |
elbows | -0.004 |
Token | day |
Token ID | 1110 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
Sorry | +0.067 |
elbows | +0.066 |
ulk | +0.064 |
fired | +0.064 |
H | +0.063 |
Neg logit contributions | |
aney | -0.066 |
hest | -0.059 |
of | -0.057 |
iky | -0.056 |
isy | -0.052 |
Token | , |
Token ID | 11 |
Feature activation | -5.92e-02 |
Pos logit contributions | |
of | +0.024 |
aney | +0.021 |
iest | +0.017 |
hest | +0.017 |
iky | +0.015 |
Neg logit contributions | |
elbows | -0.043 |
ulk | -0.042 |
minded | -0.042 |
fired | -0.041 |
Sorry | -0.040 |
Token | he |
Token ID | 339 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
of | +0.006 |
aney | +0.005 |
hest | +0.005 |
iest | +0.004 |
iky | +0.004 |
Neg logit contributions | |
ulk | -0.005 |
elbows | -0.005 |
fired | -0.005 |
minded | -0.005 |
Sorry | -0.005 |
Token | decided |
Token ID | 3066 |
Feature activation | +8.38e-01 |
Pos logit contributions | |
Sorry | +0.011 |
elbows | +0.011 |
ulk | +0.011 |
minded | +0.010 |
H | +0.010 |
Neg logit contributions | |
aney | -0.012 |
of | -0.012 |
hest | -0.011 |
iky | -0.010 |
isy | -0.010 |
Token | to |
Token ID | 284 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
elbows | +0.085 |
Sorry | +0.084 |
ulk | +0.079 |
Case | +0.076 |
minded | +0.075 |
Neg logit contributions | |
of | -0.067 |
aney | -0.065 |
hest | -0.057 |
iky | -0.054 |
isy | -0.053 |
Token | take |
Token ID | 1011 |
Feature activation | +7.97e-01 |
Pos logit contributions | |
Sorry | +0.010 |
elbows | +0.010 |
ulk | +0.010 |
fired | +0.010 |
H | +0.010 |
Neg logit contributions | |
aney | -0.014 |
hest | -0.012 |
of | -0.012 |
iky | -0.012 |
isy | -0.011 |
Token | a |
Token ID | 257 |
Feature activation | -7.51e-02 |
Pos logit contributions | |
Sorry | +0.083 |
fired | +0.076 |
elbows | +0.076 |
Fighting | +0.073 |
ulk | +0.072 |
Neg logit contributions | |
of | -0.068 |
hest | -0.057 |
aney | -0.056 |
iest | -0.056 |
aces | -0.053 |
Token | walk |
Token ID | 2513 |
Feature activation | +6.00e-01 |
Pos logit contributions | |
aney | +0.008 |
of | +0.007 |
hest | +0.007 |
iky | +0.007 |
isy | +0.007 |
Neg logit contributions | |
elbows | -0.006 |
ulk | -0.006 |
Sorry | -0.006 |
minded | -0.006 |
fired | -0.006 |
Token | into |
Token ID | 656 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
Sorry | +0.049 |
elbows | +0.048 |
ulk | +0.046 |
fired | +0.046 |
H | +0.046 |
Neg logit contributions | |
aney | -0.062 |
hest | -0.056 |
of | -0.054 |
iky | -0.053 |
isy | -0.050 |
Token | looked |
Token ID | 3114 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
of | +0.000 |
aney | +0.000 |
isy | +0.000 |
igator | +0.000 |
pole | +0.000 |
Neg logit contributions | |
ulk | -0.000 |
minded | -0.000 |
elbows | -0.000 |
late | -0.000 |
unnecessary | -0.000 |
Token | at |
Token ID | 379 |
Feature activation | +9.48e-01 |
Pos logit contributions | |
aney | +0.010 |
of | +0.010 |
hest | +0.009 |
iky | +0.009 |
isy | +0.008 |
Neg logit contributions | |
Sorry | -0.010 |
elbows | -0.010 |
ulk | -0.010 |
fired | -0.009 |
H | -0.009 |
Token | Lily |
Token ID | 20037 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
Sorry | +0.055 |
elbows | +0.053 |
ulk | +0.051 |
fired | +0.051 |
H | +0.050 |
Neg logit contributions | |
aney | -0.120 |
hest | -0.110 |
of | -0.108 |
iky | -0.106 |
isy | -0.101 |
Token | . |
Token ID | 13 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
Sorry | +0.037 |
elbows | +0.036 |
ulk | +0.035 |
fired | +0.035 |
H | +0.035 |
Neg logit contributions | |
aney | -0.045 |
hest | -0.040 |
of | -0.039 |
iky | -0.038 |
isy | -0.036 |
Token | " |
Token ID | 366 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
aney | +0.017 |
of | +0.015 |
hest | +0.015 |
iky | +0.014 |
isy | +0.013 |
Neg logit contributions | |
Sorry | -0.019 |
elbows | -0.019 |
minded | -0.018 |
fired | -0.018 |
ulk | -0.018 |
Token | What |
Token ID | 2061 |
Feature activation | +7.59e-01 |
Pos logit contributions | |
aney | +0.045 |
hest | +0.043 |
of | +0.041 |
iky | +0.039 |
isy | +0.038 |
Neg logit contributions | |
fired | -0.025 |
Sorry | -0.023 |
elbows | -0.023 |
ulk | -0.022 |
icol | -0.022 |
Token | 's |
Token ID | 338 |
Feature activation | +8.17e-01 |
Pos logit contributions | |
Sorry | +0.063 |
H | +0.059 |
elbows | +0.059 |
fired | +0.058 |
late | +0.057 |
Neg logit contributions | |
aney | -0.078 |
hest | -0.071 |
iky | -0.067 |
of | -0.064 |
isy | -0.064 |
Token | that |
Token ID | 326 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
minded | +0.080 |
ulk | +0.080 |
Sorry | +0.077 |
fired | +0.076 |
elbows | +0.076 |
Neg logit contributions | |
of | -0.061 |
aney | -0.061 |
iky | -0.060 |
hest | -0.059 |
isy | -0.056 |
Token | in |
Token ID | 287 |
Feature activation | +3.22e-02 |
Pos logit contributions | |
elbows | +0.015 |
ulk | +0.015 |
Sorry | +0.015 |
fired | +0.014 |
minded | +0.014 |
Neg logit contributions | |
aney | -0.019 |
hest | -0.018 |
of | -0.018 |
iky | -0.017 |
isy | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
Sorry | +0.003 |
ulk | +0.003 |
minded | +0.003 |
elbows | +0.003 |
fired | +0.002 |
Neg logit contributions | |
of | -0.003 |
aney | -0.003 |
hest | -0.003 |
iky | -0.003 |
igator | -0.003 |
Token | water |
Token ID | 1660 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
Sorry | +0.021 |
ulk | +0.020 |
elbows | +0.020 |
H | +0.019 |
fired | +0.019 |
Neg logit contributions | |
aney | -0.022 |
hest | -0.022 |
of | -0.022 |
iky | -0.020 |
isy | -0.018 |
Token | on |
Token ID | 319 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
aney | +0.033 |
hest | +0.030 |
iky | +0.029 |
of | +0.028 |
isy | +0.027 |
Neg logit contributions | |
Sorry | -0.020 |
elbows | -0.020 |
ulk | -0.020 |
H | -0.019 |
late | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
Sorry | +0.015 |
elbows | +0.015 |
ulk | +0.014 |
fired | +0.014 |
H | +0.014 |
Neg logit contributions | |
aney | -0.030 |
hest | -0.027 |
of | -0.027 |
iky | -0.026 |
isy | -0.025 |
Token | swings |
Token ID | 26728 |
Feature activation | -6.38e-01 |
Pos logit contributions | |
elbows | +0.021 |
H | +0.020 |
Sorry | +0.020 |
late | +0.020 |
Tiny | +0.019 |
Neg logit contributions | |
aney | -0.034 |
of | -0.028 |
hest | -0.028 |
umbs | -0.027 |
iky | -0.027 |
Token | and |
Token ID | 290 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
aney | +0.078 |
hest | +0.072 |
iky | +0.070 |
iest | +0.065 |
isy | +0.065 |
Neg logit contributions | |
H | -0.036 |
late | -0.035 |
fired | -0.035 |
down | -0.034 |
together | -0.034 |
Token | went |
Token ID | 1816 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
Sorry | +0.025 |
elbows | +0.024 |
ulk | +0.024 |
fired | +0.024 |
late | +0.023 |
Neg logit contributions | |
aney | -0.031 |
hest | -0.028 |
of | -0.028 |
iky | -0.027 |
isy | -0.025 |
Token | down |
Token ID | 866 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
Sorry | +0.068 |
ulk | +0.067 |
elbows | +0.066 |
late | +0.066 |
fired | +0.066 |
Neg logit contributions | |
aney | -0.119 |
hest | -0.108 |
iky | -0.103 |
of | -0.102 |
isy | -0.098 |
Token | the |
Token ID | 262 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
Sorry | +0.122 |
elbows | +0.118 |
ulk | +0.117 |
late | +0.117 |
H | +0.116 |
Neg logit contributions | |
aney | -0.216 |
hest | -0.198 |
iky | -0.190 |
of | -0.188 |
isy | -0.181 |
Token | slide |
Token ID | 10649 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
elbows | +0.023 |
late | +0.022 |
Sorry | +0.022 |
H | +0.021 |
forth | +0.020 |
Neg logit contributions | |
aney | -0.040 |
hest | -0.034 |
of | -0.033 |
ier | -0.032 |
iky | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
late | +0.022 |
H | +0.021 |
fired | +0.020 |
ulk | +0.019 |
Sorry | +0.019 |
Neg logit contributions | |
aney | -0.048 |
hest | -0.042 |
isy | -0.042 |
iky | -0.041 |
arrow | -0.039 |
Token | But |
Token ID | 887 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
elbows | +0.025 |
Sorry | +0.024 |
fired | +0.024 |
minded | +0.024 |
ulk | +0.024 |
Neg logit contributions | |
aney | -0.040 |
of | -0.036 |
hest | -0.035 |
iky | -0.033 |
umbs | -0.031 |
Token | then |
Token ID | 788 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
aney | +0.021 |
of | +0.020 |
hest | +0.017 |
iky | +0.017 |
isy | +0.017 |
Neg logit contributions | |
ulk | -0.018 |
Sorry | -0.017 |
minded | -0.017 |
elbows | -0.017 |
fired | -0.017 |
Token | â |
Token ID | 22940 |
Feature activation | +9.81e-02 |
Pos logit contributions | |
elbows | +0.118 |
fired | +0.110 |
ulk | +0.108 |
minded | +0.107 |
Sorry | +0.107 |
Neg logit contributions | |
aney | -0.183 |
of | -0.170 |
hest | -0.169 |
iky | -0.153 |
aces | -0.147 |
Token | € |
Token ID | 26391 |
Feature activation | -9.93e-01 |
Pos logit contributions | |
elbows | +0.008 |
Sorry | +0.008 |
fired | +0.008 |
ulk | +0.008 |
late | +0.007 |
Neg logit contributions | |
aney | -0.010 |
hest | -0.009 |
iky | -0.009 |
of | -0.008 |
isy | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
aney | +0.099 |
of | +0.087 |
hest | +0.085 |
case | +0.082 |
iky | +0.081 |
Neg logit contributions | |
elbows | -0.084 |
minded | -0.082 |
ulk | -0.078 |
fired | -0.076 |
Sorry | -0.074 |
Token |
|
Token ID | 198 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
Sorry | +0.014 |
elbows | +0.014 |
ulk | +0.013 |
H | +0.013 |
late | +0.013 |
Neg logit contributions | |
aney | -0.029 |
hest | -0.026 |
of | -0.026 |
iky | -0.025 |
isy | -0.024 |
Token | Emily |
Token ID | 48640 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
Sorry | +0.008 |
elbows | +0.008 |
fired | +0.007 |
ulk | +0.007 |
H | +0.007 |
Neg logit contributions | |
aney | -0.015 |
hest | -0.014 |
of | -0.013 |
iky | -0.013 |
isy | -0.013 |
Token | replied |
Token ID | 8712 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
Sorry | +0.020 |
elbows | +0.019 |
fired | +0.019 |
H | +0.019 |
ulk | +0.019 |
Neg logit contributions | |
aney | -0.026 |
hest | -0.024 |
of | -0.023 |
iky | -0.023 |
isy | -0.021 |
Token | , |
Token ID | 11 |
Feature activation | -7.73e-02 |
Pos logit contributions | |
Sorry | +0.137 |
H | +0.133 |
late | +0.133 |
fired | +0.132 |
ulk | +0.130 |
Neg logit contributions | |
aney | -0.094 |
hest | -0.085 |
iky | -0.078 |
of | -0.071 |
isy | -0.067 |
Token | � |
Token ID | 6184 |
Feature activation | +3.76e-02 |
Pos logit contributions | |
aney | +0.007 |
hest | +0.007 |
iky | +0.006 |
of | +0.006 |
isy | +0.006 |
Neg logit contributions | |
Sorry | -0.007 |
elbows | -0.007 |
H | -0.007 |
late | -0.007 |
ulk | -0.007 |
Token | � |
Token ID | 95 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
elbows | +0.003 |
fired | +0.003 |
late | +0.003 |
Sorry | +0.003 |
ulk | +0.003 |
Neg logit contributions | |
aney | -0.004 |
hest | -0.004 |
iky | -0.003 |
of | -0.003 |
isy | -0.003 |
Token | € |
Token ID | 26391 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
elbows | +0.079 |
Sorry | +0.078 |
fired | +0.074 |
ulk | +0.071 |
late | +0.070 |
Neg logit contributions | |
aney | -0.111 |
hest | -0.106 |
iky | -0.100 |
of | -0.095 |
isy | -0.093 |
Token | � |
Token ID | 129 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
aney | +0.105 |
of | +0.094 |
hest | +0.093 |
case | +0.091 |
iky | +0.090 |
Neg logit contributions | |
elbows | -0.077 |
minded | -0.076 |
ulk | -0.073 |
late | -0.071 |
Sorry | -0.071 |
Token | OK |
Token ID | 7477 |
Feature activation | +5.34e-01 |
Pos logit contributions | |
aney | +0.003 |
of | +0.003 |
hest | +0.003 |
iky | +0.002 |
umbs | +0.002 |
Neg logit contributions | |
elbows | -0.002 |
fired | -0.002 |
ulk | -0.002 |
minded | -0.002 |
Sorry | -0.002 |
Token | ?" |
Token ID | 1701 |
Feature activation | +4.89e-01 |
Pos logit contributions | |
elbows | +0.050 |
ulk | +0.049 |
minded | +0.047 |
Sorry | +0.046 |
Case | +0.045 |
Neg logit contributions | |
aney | -0.049 |
of | -0.047 |
hest | -0.040 |
iky | -0.039 |
isy | -0.038 |
Token |
|
Token ID | 198 |
Feature activation | +1.95e-02 |
Pos logit contributions | |
elbows | +0.039 |
ulk | +0.039 |
minded | +0.039 |
fired | +0.038 |
unnecessary | +0.036 |
Neg logit contributions | |
aney | -0.050 |
of | -0.046 |
hest | -0.039 |
isy | -0.038 |
iky | -0.037 |
Token |
|
Token ID | 198 |
Feature activation | -6.71e-02 |
Pos logit contributions | |
Sorry | +0.001 |
elbows | +0.001 |
minded | +0.001 |
fired | +0.001 |
ulk | +0.001 |
Neg logit contributions | |
aney | -0.002 |
of | -0.002 |
hest | -0.002 |
iky | -0.002 |
isy | -0.002 |
Token | S |
Token ID | 50 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
aney | +0.007 |
of | +0.006 |
hest | +0.006 |
isy | +0.005 |
iky | +0.005 |
Neg logit contributions | |
elbows | -0.006 |
ulk | -0.005 |
fired | -0.005 |
minded | -0.005 |
Sorry | -0.005 |
Token | ara |
Token ID | 3301 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
elbows | +0.093 |
Sorry | +0.092 |
ulk | +0.089 |
late | +0.088 |
H | +0.087 |
Neg logit contributions | |
aney | -0.119 |
hest | -0.102 |
of | -0.101 |
iky | -0.099 |
isy | -0.095 |
Token | said |
Token ID | 531 |
Feature activation | -9.97e-02 |
Pos logit contributions | |
Sorry | +0.124 |
elbows | +0.121 |
ulk | +0.119 |
fired | +0.118 |
H | +0.118 |
Neg logit contributions | |
aney | -0.136 |
hest | -0.122 |
of | -0.118 |
iky | -0.116 |
isy | -0.107 |
Token | , |
Token ID | 11 |
Feature activation | +5.38e-03 |
Pos logit contributions | |
aney | +0.011 |
hest | +0.010 |
iky | +0.010 |
of | +0.009 |
umbs | +0.009 |
Neg logit contributions | |
Sorry | -0.008 |
H | -0.007 |
late | -0.007 |
fired | -0.007 |
elbows | -0.007 |
Token | " |
Token ID | 366 |
Feature activation | -3.97e-01 |
Pos logit contributions | |
Sorry | +0.000 |
H | +0.000 |
late | +0.000 |
elbows | +0.000 |
fired | +0.000 |
Neg logit contributions | |
aney | -0.001 |
hest | -0.001 |
iky | -0.000 |
of | -0.000 |
iest | -0.000 |
Token | OK |
Token ID | 11380 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
aney | +0.044 |
hest | +0.040 |
of | +0.039 |
iky | +0.038 |
isy | +0.036 |
Neg logit contributions | |
fired | -0.029 |
ulk | -0.028 |
elbows | -0.028 |
Sorry | -0.027 |
H | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
Sorry | +0.085 |
H | +0.081 |
late | +0.079 |
elbows | +0.079 |
fired | +0.078 |
Neg logit contributions | |
aney | -0.106 |
hest | -0.096 |
iky | -0.093 |
of | -0.089 |
isy | -0.084 |
Token | lady |
Token ID | 10846 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
Sorry | +0.026 |
elbows | +0.025 |
ulk | +0.025 |
fired | +0.025 |
H | +0.025 |
Neg logit contributions | |
aney | -0.026 |
hest | -0.023 |
of | -0.022 |
iky | -0.022 |
isy | -0.020 |
Token | said |
Token ID | 531 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
aney | +0.021 |
hest | +0.020 |
iky | +0.019 |
of | +0.018 |
isy | +0.017 |
Neg logit contributions | |
Sorry | -0.012 |
H | -0.011 |
minded | -0.011 |
fired | -0.011 |
late | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
aney | +0.027 |
hest | +0.025 |
iky | +0.024 |
of | +0.022 |
isy | +0.022 |
Neg logit contributions | |
Sorry | -0.019 |
late | -0.019 |
H | -0.018 |
elbows | -0.018 |
minded | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
Sorry | +0.011 |
elbows | +0.011 |
ulk | +0.010 |
fired | +0.010 |
H | +0.010 |
Neg logit contributions | |
aney | -0.020 |
hest | -0.018 |
of | -0.018 |
iky | -0.018 |
isy | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
Sorry | +0.017 |
elbows | +0.017 |
ulk | +0.016 |
fired | +0.016 |
H | +0.016 |
Neg logit contributions | |
aney | -0.036 |
hest | -0.033 |
of | -0.032 |
iky | -0.032 |
isy | -0.030 |
Token | " |
Token ID | 1 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
Sorry | +0.018 |
elbows | +0.017 |
fired | +0.016 |
ulk | +0.016 |
H | +0.015 |
Neg logit contributions | |
aney | -0.028 |
hest | -0.026 |
of | -0.025 |
iky | -0.024 |
isy | -0.023 |
Token | Wow |
Token ID | 22017 |
Feature activation | +8.05e-01 |
Pos logit contributions | |
Sorry | +0.027 |
elbows | +0.027 |
fired | +0.026 |
ulk | +0.026 |
H | +0.025 |
Neg logit contributions | |
aney | -0.060 |
hest | -0.056 |
of | -0.054 |
iky | -0.053 |
isy | -0.051 |
Token | , |
Token ID | 11 |
Feature activation | -2.18e-02 |
Pos logit contributions | |
Sorry | +0.073 |
elbows | +0.072 |
ulk | +0.070 |
fired | +0.070 |
late | +0.069 |
Neg logit contributions | |
aney | -0.075 |
hest | -0.067 |
of | -0.065 |
iky | -0.064 |
isy | -0.059 |
Token | that |
Token ID | 326 |
Feature activation | +6.43e-02 |
Pos logit contributions | |
aney | +0.002 |
of | +0.002 |
hest | +0.002 |
isy | +0.002 |
iky | +0.002 |
Neg logit contributions | |
elbows | -0.002 |
ulk | -0.002 |
fired | -0.002 |
late | -0.002 |
minded | -0.002 |
Token | sounds |
Token ID | 5238 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
elbows | +0.006 |
ulk | +0.006 |
Sorry | +0.005 |
fired | +0.005 |
late | +0.005 |
Neg logit contributions | |
aney | -0.006 |
of | -0.006 |
hest | -0.006 |
isy | -0.005 |
iky | -0.005 |
Token | exciting |
Token ID | 7895 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
Sorry | +0.184 |
late | +0.184 |
H | +0.173 |
Are | +0.169 |
minded | +0.163 |
Neg logit contributions | |
aney | -0.250 |
iky | -0.209 |
hest | -0.209 |
of | -0.196 |
umbs | -0.193 |
Token | to |
Token ID | 284 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
aney | +0.039 |
hest | +0.036 |
iky | +0.034 |
of | +0.034 |
isy | +0.032 |
Neg logit contributions | |
Sorry | -0.019 |
H | -0.018 |
elbows | -0.018 |
late | -0.018 |
fired | -0.018 |
Token | climb |
Token ID | 12080 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
Sorry | +0.015 |
elbows | +0.014 |
H | +0.014 |
fired | +0.014 |
ulk | +0.014 |
Neg logit contributions | |
aney | -0.028 |
hest | -0.026 |
iky | -0.025 |
of | -0.024 |
iest | -0.023 |
Token | on |
Token ID | 319 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
aney | +0.037 |
hest | +0.034 |
of | +0.034 |
iky | +0.033 |
isy | +0.031 |
Neg logit contributions | |
Sorry | -0.026 |
elbows | -0.025 |
ulk | -0.024 |
fired | -0.024 |
minded | -0.023 |
Token | its |
Token ID | 663 |
Feature activation | -6.12e-01 |
Pos logit contributions | |
Sorry | +0.015 |
elbows | +0.015 |
H | +0.015 |
fired | +0.015 |
ulk | +0.014 |
Neg logit contributions | |
aney | -0.032 |
hest | -0.029 |
iky | -0.028 |
of | -0.028 |
isy | -0.027 |
Token | branches |
Token ID | 13737 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
aney | +0.078 |
hest | +0.070 |
ier | +0.066 |
iest | +0.064 |
ion | +0.063 |
Neg logit contributions | |
elbows | -0.038 |
fired | -0.036 |
H | -0.036 |
forth | -0.034 |
Tiny | -0.033 |
Token | and |
Token ID | 290 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
aney | +0.018 |
iky | +0.016 |
hest | +0.016 |
isy | +0.015 |
arrow | +0.014 |
Neg logit contributions | |
late | -0.010 |
fired | -0.010 |
H | -0.009 |
backward | -0.009 |
down | -0.008 |
Token | listen |
Token ID | 6004 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
aney | +0.011 |
of | +0.010 |
hest | +0.010 |
iky | +0.009 |
isy | +0.009 |
Neg logit contributions | |
Sorry | -0.008 |
elbows | -0.008 |
ulk | -0.008 |
late | -0.008 |
fired | -0.008 |
Token | to |
Token ID | 284 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
late | +0.064 |
Sorry | +0.062 |
minded | +0.062 |
H | +0.061 |
fired | +0.061 |
Neg logit contributions | |
aney | -0.122 |
hest | -0.110 |
iky | -0.106 |
of | -0.101 |
umbs | -0.098 |
Token | the |
Token ID | 262 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
Sorry | +0.017 |
elbows | +0.016 |
fired | +0.016 |
ulk | +0.016 |
late | +0.016 |
Neg logit contributions | |
aney | -0.034 |
hest | -0.031 |
of | -0.031 |
iky | -0.030 |
isy | -0.029 |
Token | wind |
Token ID | 2344 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
H | +0.027 |
elbows | +0.026 |
Sorry | +0.026 |
late | +0.026 |
fired | +0.025 |
Neg logit contributions | |
aney | -0.042 |
hest | -0.037 |
iky | -0.035 |
of | -0.034 |
aces | -0.032 |
Token | rust |
Token ID | 17000 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
aney | +0.038 |
hest | +0.035 |
iky | +0.033 |
of | +0.031 |
isy | +0.030 |
Neg logit contributions | |
Sorry | -0.027 |
elbows | -0.026 |
fired | -0.026 |
ulk | -0.026 |
late | -0.026 |
Token | saw |
Token ID | 2497 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
aney | +0.012 |
hest | +0.012 |
iky | +0.011 |
iest | +0.010 |
umbs | +0.010 |
Neg logit contributions | |
H | -0.005 |
elbows | -0.005 |
fired | -0.005 |
late | -0.005 |
Case | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
aney | +0.001 |
hest | +0.001 |
iky | +0.001 |
isy | +0.001 |
of | +0.001 |
Neg logit contributions | |
H | -0.001 |
elbows | -0.001 |
late | -0.001 |
Sorry | -0.001 |
ulk | -0.001 |
Token | bee |
Token ID | 20697 |
Feature activation | -2.08e-02 |
Pos logit contributions | |
elbows | +0.029 |
Sorry | +0.029 |
H | +0.027 |
late | +0.027 |
fired | +0.027 |
Neg logit contributions | |
aney | -0.041 |
hest | -0.037 |
of | -0.035 |
iky | -0.034 |
isy | -0.032 |
Token | flying |
Token ID | 7348 |
Feature activation | -8.43e-01 |
Pos logit contributions | |
aney | +0.002 |
hest | +0.002 |
iky | +0.002 |
of | +0.002 |
isy | +0.002 |
Neg logit contributions | |
elbows | -0.002 |
Sorry | -0.002 |
fired | -0.001 |
ulk | -0.001 |
late | -0.001 |
Token | away |
Token ID | 1497 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
aney | +0.097 |
hest | +0.090 |
iky | +0.083 |
isy | +0.080 |
of | +0.080 |
Neg logit contributions | |
late | -0.058 |
fired | -0.056 |
elbows | -0.056 |
H | -0.056 |
Sorry | -0.055 |
Token | from |
Token ID | 422 |
Feature activation | -7.34e-01 |
Pos logit contributions | |
late | +0.078 |
elbows | +0.075 |
fired | +0.075 |
Sorry | +0.074 |
H | +0.072 |
Neg logit contributions | |
aney | -0.116 |
hest | -0.106 |
iky | -0.098 |
isy | -0.094 |
of | -0.092 |
Token | the |
Token ID | 262 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
aney | +0.086 |
hest | +0.078 |
of | +0.077 |
iky | +0.076 |
isy | +0.071 |
Neg logit contributions | |
Sorry | -0.050 |
elbows | -0.046 |
ulk | -0.046 |
fired | -0.045 |
minded | -0.045 |
Token | bush |
Token ID | 24484 |
Feature activation | +4.37e-01 |
Pos logit contributions | |
Sorry | +0.035 |
elbows | +0.034 |
ulk | +0.034 |
fired | +0.034 |
H | +0.033 |
Neg logit contributions | |
aney | -0.038 |
hest | -0.034 |
of | -0.033 |
iky | -0.033 |
isy | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
late | +0.028 |
fired | +0.026 |
heaven | +0.026 |
H | +0.025 |
elbows | +0.025 |
Neg logit contributions | |
aney | -0.054 |
hest | -0.048 |
iky | -0.047 |
iest | -0.046 |
isy | -0.044 |
Token |
|
Token ID | 198 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
Sorry | +0.009 |
elbows | +0.009 |
ulk | +0.009 |
fired | +0.009 |
minded | +0.009 |
Neg logit contributions | |
aney | -0.015 |
of | -0.013 |
hest | -0.013 |
iky | -0.013 |
isy | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
Sorry | +0.015 |
late | +0.015 |
H | +0.015 |
ulk | +0.014 |
elbows | +0.014 |
Neg logit contributions | |
aney | -0.041 |
hest | -0.038 |
iky | -0.036 |
of | -0.035 |
isy | -0.035 |
Token | remembered |
Token ID | 12086 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
Sorry | +0.026 |
fired | +0.024 |
elbows | +0.023 |
H | +0.023 |
ulk | +0.023 |
Neg logit contributions | |
aney | -0.039 |
hest | -0.036 |
iky | -0.035 |
of | -0.032 |
isy | -0.032 |
Token | the |
Token ID | 262 |
Feature activation | +4.58e-02 |
Pos logit contributions | |
Sorry | +0.015 |
elbows | +0.015 |
ulk | +0.014 |
fired | +0.014 |
H | +0.014 |
Neg logit contributions | |
aney | -0.024 |
hest | -0.022 |
of | -0.022 |
iky | -0.021 |
isy | -0.020 |
Token | amazing |
Token ID | 4998 |
Feature activation | -8.03e-01 |
Pos logit contributions | |
Sorry | +0.004 |
elbows | +0.004 |
late | +0.003 |
H | +0.003 |
fired | +0.003 |
Neg logit contributions | |
aney | -0.005 |
hest | -0.004 |
iky | -0.004 |
of | -0.004 |
aces | -0.004 |
Token | things |
Token ID | 1243 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
aney | +0.084 |
hest | +0.076 |
iky | +0.072 |
of | +0.072 |
isy | +0.067 |
Neg logit contributions | |
Sorry | -0.064 |
elbows | -0.062 |
ulk | -0.061 |
fired | -0.061 |
H | -0.060 |
Token | that |
Token ID | 326 |
Feature activation | -4.71e-02 |
Pos logit contributions | |
late | +0.074 |
fired | +0.071 |
Sorry | +0.068 |
H | +0.063 |
heaven | +0.061 |
Neg logit contributions | |
aney | -0.230 |
hest | -0.215 |
iky | -0.211 |
umbs | -0.201 |
isy | -0.193 |
Token | can |
Token ID | 460 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
aney | +0.005 |
hest | +0.005 |
iky | +0.005 |
of | +0.005 |
isy | +0.004 |
Neg logit contributions | |
Sorry | -0.003 |
elbows | -0.003 |
H | -0.003 |
late | -0.003 |
fired | -0.003 |
Token | happen |
Token ID | 1645 |
Feature activation | -9.04e-01 |
Pos logit contributions | |
Sorry | +0.013 |
late | +0.013 |
H | +0.013 |
fired | +0.013 |
Tiny | +0.012 |
Neg logit contributions | |
aney | -0.026 |
iky | -0.022 |
aces | -0.021 |
hest | -0.021 |
umbs | -0.021 |
Token | on |
Token ID | 319 |
Feature activation | +5.72e-02 |
Pos logit contributions | |
aney | +0.100 |
hest | +0.088 |
iky | +0.086 |
of | +0.081 |
isy | +0.080 |
Neg logit contributions | |
late | -0.067 |
Sorry | -0.067 |
fired | -0.066 |
minded | -0.065 |
H | -0.064 |
Token | a |
Token ID | 257 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
Sorry | +0.003 |
elbows | +0.003 |
late | +0.003 |
fired | +0.003 |
H | +0.003 |
Neg logit contributions | |
aney | -0.007 |
hest | -0.006 |
iky | -0.006 |
of | -0.006 |
isy | -0.006 |
Token | gloomy |
Token ID | 46400 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
aney | +0.014 |
hest | +0.012 |
iky | +0.012 |
of | +0.012 |
aces | +0.011 |
Neg logit contributions | |
Sorry | -0.011 |
late | -0.010 |
H | -0.010 |
elbows | -0.010 |
fired | -0.010 |
Token | day |
Token ID | 1110 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
Sorry | +0.032 |
late | +0.031 |
elbows | +0.031 |
H | +0.031 |
fired | +0.031 |
Neg logit contributions | |
aney | -0.044 |
hest | -0.039 |
iky | -0.037 |
of | -0.037 |
aces | -0.034 |
Token | to |
Token ID | 284 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
Sorry | +0.043 |
elbows | +0.042 |
ulk | +0.041 |
fired | +0.041 |
H | +0.041 |
Neg logit contributions | |
aney | -0.067 |
hest | -0.061 |
of | -0.059 |
iky | -0.059 |
isy | -0.055 |
Token | play |
Token ID | 711 |
Feature activation | +6.21e-01 |
Pos logit contributions | |
Sorry | +0.010 |
H | +0.010 |
elbows | +0.009 |
fired | +0.009 |
ulk | +0.009 |
Neg logit contributions | |
aney | -0.019 |
hest | -0.017 |
iky | -0.016 |
of | -0.016 |
isy | -0.015 |
Token | with |
Token ID | 351 |
Feature activation | +4.39e-01 |
Pos logit contributions | |
elbows | +0.049 |
Sorry | +0.048 |
fired | +0.047 |
ulk | +0.045 |
minded | +0.045 |
Neg logit contributions | |
of | -0.063 |
hest | -0.061 |
aney | -0.061 |
iky | -0.056 |
isy | -0.054 |
Token | me |
Token ID | 502 |
Feature activation | -7.72e-01 |
Pos logit contributions | |
Sorry | +0.029 |
elbows | +0.028 |
ulk | +0.028 |
fired | +0.027 |
late | +0.027 |
Neg logit contributions | |
aney | -0.052 |
hest | -0.048 |
of | -0.047 |
iky | -0.046 |
isy | -0.043 |
Token | ?" |
Token ID | 1701 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
aney | +0.095 |
hest | +0.087 |
iky | +0.084 |
of | +0.081 |
isy | +0.079 |
Neg logit contributions | |
Sorry | -0.046 |
H | -0.046 |
late | -0.045 |
fired | -0.045 |
ulk | -0.044 |
Token |
|
Token ID | 198 |
Feature activation | +3.19e-02 |
Pos logit contributions | |
Sorry | +0.030 |
elbows | +0.030 |
fired | +0.028 |
minded | +0.028 |
ulk | +0.027 |
Neg logit contributions | |
aney | -0.039 |
of | -0.037 |
hest | -0.033 |
iky | -0.032 |
isy | -0.030 |
Token |
|
Token ID | 198 |
Feature activation | -8.20e-04 |
Pos logit contributions | |
Sorry | +0.002 |
elbows | +0.002 |
fired | +0.002 |
minded | +0.002 |
ulk | +0.002 |
Neg logit contributions | |
aney | -0.004 |
of | -0.003 |
hest | -0.003 |
iky | -0.003 |
isy | -0.003 |
Token | M |
Token ID | 44 |
Feature activation | +6.11e-01 |
Pos logit contributions | |
aney | +0.000 |
of | +0.000 |
hest | +0.000 |
iky | +0.000 |
isy | +0.000 |
Neg logit contributions | |
Sorry | -0.000 |
elbows | -0.000 |
ulk | -0.000 |
fired | -0.000 |
minded | -0.000 |
Token | ia |
Token ID | 544 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
Sorry | +0.074 |
fired | +0.073 |
elbows | +0.073 |
ulk | +0.072 |
late | +0.072 |
Neg logit contributions | |
aney | -0.036 |
hest | -0.033 |
iky | -0.027 |
of | -0.026 |
contain | -0.025 |
Token | nodded |
Token ID | 14464 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
H | +0.009 |
minded | +0.009 |
Sorry | +0.009 |
fired | +0.009 |
Are | +0.008 |
Neg logit contributions | |
hest | -0.019 |
aney | -0.018 |
iky | -0.018 |
iest | -0.017 |
of | -0.016 |
Token | and |
Token ID | 290 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
Sorry | +0.027 |
elbows | +0.026 |
late | +0.026 |
H | +0.026 |
fired | +0.026 |
Neg logit contributions | |
aney | -0.025 |
hest | -0.023 |
iky | -0.021 |
of | -0.021 |
isy | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | +3.17e-03 |
Pos logit contributions | |
late | +0.037 |
H | +0.031 |
backward | +0.031 |
dreaming | +0.031 |
fired | +0.030 |
Neg logit contributions | |
aney | -0.076 |
hest | -0.065 |
iky | -0.064 |
arrow | -0.062 |
isy | -0.062 |
Token | and |
Token ID | 290 |
Feature activation | -2.92e-02 |
Pos logit contributions | |
Sorry | +0.000 |
H | +0.000 |
elbows | +0.000 |
late | +0.000 |
ulk | +0.000 |
Neg logit contributions | |
aney | -0.000 |
hest | -0.000 |
iky | -0.000 |
of | -0.000 |
isy | -0.000 |
Token | he |
Token ID | 339 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
aney | +0.003 |
of | +0.003 |
hest | +0.003 |
iky | +0.003 |
isy | +0.003 |
Neg logit contributions | |
Sorry | -0.002 |
elbows | -0.002 |
fired | -0.002 |
ulk | -0.002 |
late | -0.002 |
Token | couldn |
Token ID | 3521 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
Sorry | +0.019 |
H | +0.019 |
fired | +0.019 |
minded | +0.018 |
elbows | +0.018 |
Neg logit contributions | |
aney | -0.030 |
hest | -0.027 |
iky | -0.026 |
of | -0.024 |
iest | -0.024 |
Token | 't |
Token ID | 470 |
Feature activation | -9.34e-01 |
Pos logit contributions | |
aney | +0.015 |
iky | +0.012 |
hest | +0.012 |
isy | +0.012 |
aces | +0.011 |
Neg logit contributions | |
Sorry | -0.012 |
H | -0.012 |
late | -0.011 |
ulk | -0.011 |
fired | -0.011 |
Token | contain |
Token ID | 3994 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
aney | +0.102 |
iky | +0.090 |
hest | +0.088 |
of | +0.083 |
umbs | +0.081 |
Neg logit contributions | |
Sorry | -0.069 |
H | -0.069 |
minded | -0.065 |
elbows | -0.065 |
tail | -0.063 |
Token | his |
Token ID | 465 |
Feature activation | -4.16e-02 |
Pos logit contributions | |
aney | +0.272 |
hest | +0.251 |
of | +0.244 |
iky | +0.243 |
isy | +0.223 |
Neg logit contributions | |
Sorry | -0.210 |
elbows | -0.201 |
fired | -0.196 |
ulk | -0.196 |
late | -0.191 |
Token | excitement |
Token ID | 14067 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
aney | +0.004 |
hest | +0.004 |
of | +0.004 |
iky | +0.003 |
isy | +0.003 |
Neg logit contributions | |
Sorry | -0.004 |
elbows | -0.004 |
ulk | -0.003 |
fired | -0.003 |
H | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
aney | +0.034 |
hest | +0.031 |
iky | +0.030 |
isy | +0.028 |
of | +0.028 |
Neg logit contributions | |
Sorry | -0.022 |
late | -0.022 |
elbows | -0.021 |
ulk | -0.021 |
H | -0.021 |
Token | He |
Token ID | 679 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
aney | +0.020 |
hest | +0.018 |
of | +0.018 |
iky | +0.017 |
aces | +0.016 |
Neg logit contributions | |
elbows | -0.013 |
Sorry | -0.013 |
fired | -0.013 |
minded | -0.012 |
ulk | -0.012 |
Token | was |
Token ID | 373 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
aney | +0.034 |
hest | +0.032 |
iky | +0.030 |
of | +0.029 |
iest | +0.029 |
Neg logit contributions | |
H | -0.021 |
Sorry | -0.021 |
fired | -0.020 |
minded | -0.019 |
elbows | -0.019 |
Token | funny |
Token ID | 8258 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
aney | +0.020 |
hest | +0.018 |
iky | +0.018 |
of | +0.017 |
isy | +0.016 |
Neg logit contributions | |
H | -0.013 |
Sorry | -0.013 |
late | -0.013 |
elbows | -0.012 |
Tiny | -0.012 |
Token | to |
Token ID | 284 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
late | +0.044 |
H | +0.044 |
minded | +0.043 |
Sorry | +0.042 |
fired | +0.042 |
Neg logit contributions | |
aney | -0.065 |
hest | -0.059 |
iky | -0.056 |
isy | -0.053 |
arrow | -0.051 |
Token | see |
Token ID | 766 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
H | +0.016 |
Sorry | +0.016 |
elbows | +0.015 |
Tiny | +0.014 |
ulk | +0.014 |
Neg logit contributions | |
aney | -0.032 |
hest | -0.028 |
iky | -0.027 |
of | -0.027 |
umbs | -0.027 |
Token | the |
Token ID | 262 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
Sorry | +0.086 |
H | +0.084 |
late | +0.081 |
minded | +0.080 |
fired | +0.080 |
Neg logit contributions | |
aney | -0.173 |
hest | -0.155 |
iky | -0.152 |
isy | -0.143 |
of | -0.141 |
Token | pink |
Token ID | 11398 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
late | +0.022 |
Sorry | +0.020 |
What | +0.020 |
elbows | +0.019 |
How | +0.019 |
Neg logit contributions | |
aney | -0.027 |
iky | -0.023 |
hest | -0.022 |
contain | -0.021 |
aces | -0.021 |
Token | dough |
Token ID | 15756 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
aney | +0.054 |
hest | +0.047 |
iky | +0.046 |
contain | +0.045 |
isy | +0.041 |
Neg logit contributions | |
Sorry | -0.045 |
late | -0.043 |
elbows | -0.041 |
What | -0.040 |
something | -0.040 |
Token | move |
Token ID | 1445 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
aney | +0.239 |
hest | +0.209 |
iky | +0.207 |
isy | +0.191 |
umbs | +0.184 |
Neg logit contributions | |
Sorry | -0.139 |
elbows | -0.133 |
fired | -0.131 |
late | -0.127 |
ulk | -0.122 |
Token | back |
Token ID | 736 |
Feature activation | +9.74e-02 |
Pos logit contributions | |
late | +0.026 |
H | +0.025 |
fired | +0.025 |
minded | +0.024 |
backward | +0.024 |
Neg logit contributions | |
aney | -0.043 |
hest | -0.038 |
iky | -0.037 |
isy | -0.036 |
umbs | -0.034 |
Token | and |
Token ID | 290 |
Feature activation | -1.80e-02 |
Pos logit contributions | |
fired | +0.006 |
late | +0.006 |
H | +0.006 |
minded | +0.006 |
elbows | +0.006 |
Neg logit contributions | |
aney | -0.012 |
hest | -0.011 |
iky | -0.010 |
isy | -0.010 |
arrow | -0.009 |
Token | forth |
Token ID | 6071 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
aney | +0.002 |
of | +0.002 |
hest | +0.002 |
iky | +0.002 |
isy | +0.002 |
Neg logit contributions | |
Sorry | -0.001 |
elbows | -0.001 |
fired | -0.001 |
ulk | -0.001 |
H | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
late | +0.070 |
H | +0.069 |
Sorry | +0.068 |
elbows | +0.067 |
fired | +0.067 |
Neg logit contributions | |
aney | -0.137 |
hest | -0.120 |
iky | -0.114 |
umbs | -0.110 |
isy | -0.110 |
Token | was |
Token ID | 373 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
fired | +0.001 |
H | +0.001 |
late | +0.001 |
Sorry | +0.001 |
minded | +0.001 |
Neg logit contributions | |
aney | -0.001 |
hest | -0.001 |
iky | -0.001 |
aces | -0.001 |
umbs | -0.001 |
Token | so |
Token ID | 523 |
Feature activation | -4.39e-02 |
Pos logit contributions | |
aney | +0.025 |
hest | +0.023 |
iky | +0.022 |
isy | +0.020 |
iest | +0.020 |
Neg logit contributions | |
late | -0.020 |
H | -0.018 |
elbows | -0.017 |
dreaming | -0.017 |
fired | -0.017 |
Token | happy |
Token ID | 3772 |
Feature activation | +4.29e-02 |
Pos logit contributions | |
aney | +0.005 |
hest | +0.004 |
iky | +0.004 |
aces | +0.004 |
isy | +0.004 |
Neg logit contributions | |
late | -0.003 |
Sorry | -0.003 |
H | -0.003 |
fired | -0.003 |
minded | -0.003 |
Token | it |
Token ID | 340 |
Feature activation | -4.87e-01 |
Pos logit contributions | |
Sorry | +0.004 |
elbows | +0.004 |
ulk | +0.004 |
fired | +0.004 |
H | +0.004 |
Neg logit contributions | |
aney | -0.004 |
of | -0.004 |
hest | -0.004 |
iky | -0.003 |
isy | -0.003 |
Token | could |
Token ID | 714 |
Feature activation | -8.04e-02 |
Pos logit contributions | |
aney | +0.056 |
hest | +0.049 |
iky | +0.048 |
of | +0.046 |
isy | +0.044 |
Neg logit contributions | |
Sorry | -0.034 |
late | -0.034 |
H | -0.033 |
fired | -0.033 |
minded | -0.032 |
Token | hardly |
Token ID | 8941 |
Feature activation | -2.38e+00 |
Pos logit contributions | |
aney | +0.010 |
iky | +0.008 |
hest | +0.008 |
aces | +0.008 |
ement | +0.008 |
Neg logit contributions | |
Sorry | -0.005 |
Tiny | -0.005 |
late | -0.005 |
H | -0.005 |
fired | -0.005 |
Token | believe |
Token ID | 1975 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
aney | +0.234 |
iky | +0.205 |
hest | +0.200 |
aces | +0.184 |
of | +0.178 |
Neg logit contributions | |
Sorry | -0.214 |
H | -0.199 |
late | -0.194 |
elbows | -0.193 |
Are | -0.191 |
Token | it |
Token ID | 340 |
Feature activation | -4.70e-01 |
Pos logit contributions | |
aney | +0.044 |
hest | +0.041 |
iky | +0.039 |
of | +0.039 |
isy | +0.037 |
Neg logit contributions | |
Sorry | -0.023 |
elbows | -0.022 |
ulk | -0.021 |
fired | -0.021 |
H | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | -9.00e-02 |
Pos logit contributions | |
aney | +0.054 |
hest | +0.046 |
iky | +0.045 |
of | +0.043 |
umbs | +0.042 |
Neg logit contributions | |
H | -0.034 |
late | -0.033 |
fired | -0.033 |
Sorry | -0.033 |
minded | -0.032 |
Token | All |
Token ID | 1439 |
Feature activation | +9.96e-01 |
Pos logit contributions | |
aney | +0.011 |
hest | +0.010 |
iky | +0.010 |
of | +0.010 |
isy | +0.009 |
Neg logit contributions | |
Sorry | -0.006 |
H | -0.005 |
late | -0.005 |
ulk | -0.005 |
fired | -0.005 |
Token | its |
Token ID | 663 |
Feature activation | -5.93e-01 |
Pos logit contributions | |
late | +0.067 |
Sorry | +0.066 |
fired | +0.066 |
minded | +0.063 |
H | +0.063 |
Neg logit contributions | |
aney | -0.115 |
hest | -0.108 |
iky | -0.103 |
isy | -0.096 |
aces | -0.095 |
Token | day |
Token ID | 1110 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
aney | +0.021 |
hest | +0.020 |
aces | +0.018 |
iky | +0.018 |
ier | +0.017 |
Neg logit contributions | |
late | -0.014 |
H | -0.013 |
Sorry | -0.013 |
fired | -0.012 |
elbows | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | -8.89e-02 |
Pos logit contributions | |
aney | +0.024 |
of | +0.022 |
hest | +0.021 |
iky | +0.021 |
isy | +0.019 |
Neg logit contributions | |
Sorry | -0.026 |
elbows | -0.026 |
minded | -0.026 |
ulk | -0.026 |
fired | -0.025 |
Token | she |
Token ID | 673 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
aney | +0.010 |
of | +0.009 |
hest | +0.008 |
iky | +0.008 |
isy | +0.008 |
Neg logit contributions | |
minded | -0.007 |
elbows | -0.007 |
fired | -0.007 |
ulk | -0.006 |
Sorry | -0.006 |
Token | saw |
Token ID | 2497 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
Sorry | +0.013 |
ulk | +0.013 |
minded | +0.013 |
elbows | +0.013 |
fired | +0.012 |
Neg logit contributions | |
aney | -0.016 |
of | -0.015 |
hest | -0.014 |
iky | -0.014 |
isy | -0.013 |
Token | her |
Token ID | 607 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
aney | +0.018 |
of | +0.017 |
hest | +0.016 |
iky | +0.015 |
isy | +0.015 |
Neg logit contributions | |
Sorry | -0.011 |
elbows | -0.010 |
minded | -0.010 |
fired | -0.010 |
ulk | -0.010 |
Token | elderly |
Token ID | 13830 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
aney | +0.012 |
hest | +0.011 |
iky | +0.010 |
of | +0.010 |
umbs | +0.010 |
Neg logit contributions | |
H | -0.008 |
Sorry | -0.008 |
elbows | -0.008 |
late | -0.007 |
fired | -0.007 |
Token | neighbor |
Token ID | 4780 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
aney | +0.248 |
hest | +0.233 |
iky | +0.218 |
of | +0.206 |
isy | +0.203 |
Neg logit contributions | |
H | -0.130 |
Sorry | -0.130 |
elbows | -0.128 |
late | -0.125 |
ulk | -0.124 |
Token | , |
Token ID | 11 |
Feature activation | -9.71e-02 |
Pos logit contributions | |
aney | +0.110 |
of | +0.103 |
hest | +0.097 |
iky | +0.092 |
isy | +0.089 |
Neg logit contributions | |
Sorry | -0.088 |
ulk | -0.085 |
elbows | -0.084 |
minded | -0.082 |
fired | -0.082 |
Token | Mrs |
Token ID | 9074 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
aney | +0.012 |
hest | +0.011 |
of | +0.011 |
iky | +0.010 |
isy | +0.010 |
Neg logit contributions | |
Sorry | -0.006 |
elbows | -0.006 |
ulk | -0.006 |
minded | -0.006 |
fired | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
aney | +0.147 |
of | +0.126 |
hest | +0.121 |
iky | +0.118 |
isy | +0.113 |
Neg logit contributions | |
Sorry | -0.169 |
ulk | -0.163 |
elbows | -0.161 |
fired | -0.156 |
late | -0.154 |
Token | Johnson |
Token ID | 5030 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
aney | +0.023 |
umbs | +0.018 |
of | +0.018 |
hest | +0.016 |
cake | +0.015 |
Neg logit contributions | |
elbows | -0.020 |
ulk | -0.020 |
minded | -0.020 |
unnecessary | -0.019 |
fired | -0.019 |
Token | see |
Token ID | 766 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
Sorry | +0.009 |
H | +0.008 |
elbows | +0.008 |
late | +0.008 |
ulk | +0.008 |
Neg logit contributions | |
aney | -0.014 |
iky | -0.013 |
hest | -0.013 |
of | -0.012 |
aces | -0.011 |
Token | how |
Token ID | 703 |
Feature activation | -4.84e-01 |
Pos logit contributions | |
Sorry | +0.073 |
H | +0.071 |
elbows | +0.069 |
fired | +0.068 |
late | +0.068 |
Neg logit contributions | |
aney | -0.159 |
hest | -0.145 |
iky | -0.142 |
of | -0.138 |
isy | -0.133 |
Token | much |
Token ID | 881 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
aney | +0.053 |
hest | +0.048 |
of | +0.047 |
iky | +0.046 |
isy | +0.043 |
Neg logit contributions | |
Sorry | -0.036 |
elbows | -0.035 |
ulk | -0.034 |
fired | -0.034 |
H | -0.034 |
Token | it |
Token ID | 340 |
Feature activation | -6.33e-01 |
Pos logit contributions | |
Sorry | +0.026 |
late | +0.024 |
H | +0.023 |
elbows | +0.022 |
fired | +0.022 |
Neg logit contributions | |
aney | -0.062 |
hest | -0.056 |
iky | -0.056 |
isy | -0.052 |
of | -0.052 |
Token | will |
Token ID | 481 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
aney | +0.073 |
hest | +0.065 |
iky | +0.063 |
of | +0.061 |
isy | +0.060 |
Neg logit contributions | |
Sorry | -0.044 |
fired | -0.042 |
H | -0.042 |
minded | -0.041 |
late | -0.041 |
Token | cost |
Token ID | 1575 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
Sorry | +0.030 |
H | +0.028 |
late | +0.028 |
heaven | +0.026 |
fired | +0.025 |
Neg logit contributions | |
aney | -0.059 |
iky | -0.048 |
aces | -0.048 |
hest | -0.048 |
umbs | -0.047 |
Token | , |
Token ID | 11 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
aney | +0.264 |
iky | +0.226 |
isy | +0.216 |
hest | +0.215 |
arrow | +0.211 |
Neg logit contributions | |
late | -0.170 |
H | -0.154 |
fired | -0.148 |
minded | -0.144 |
ulk | -0.141 |
Token | â |
Token ID | 22940 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
aney | +0.014 |
iky | +0.013 |
hest | +0.013 |
isy | +0.011 |
iest | +0.011 |
Neg logit contributions | |
Sorry | -0.013 |
late | -0.012 |
H | -0.012 |
Are | -0.012 |
minded | -0.012 |
Token | € |
Token ID | 26391 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
Sorry | +0.013 |
elbows | +0.013 |
fired | +0.013 |
ulk | +0.013 |
H | +0.012 |
Neg logit contributions | |
aney | -0.019 |
hest | -0.017 |
of | -0.016 |
iky | -0.016 |
isy | -0.015 |
Token | said |
Token ID | 531 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
aney | +0.110 |
of | +0.098 |
hest | +0.098 |
iky | +0.091 |
case | +0.090 |
Neg logit contributions | |
elbows | -0.073 |
minded | -0.071 |
ulk | -0.070 |
fired | -0.069 |
Sorry | -0.068 |
Token | mummy |
Token ID | 38567 |
Feature activation | +6.32e-01 |
Pos logit contributions | |
aney | +0.033 |
hest | +0.030 |
iky | +0.029 |
of | +0.028 |
isy | +0.026 |
Neg logit contributions | |
Sorry | -0.023 |
H | -0.021 |
elbows | -0.021 |
late | -0.021 |
fired | -0.020 |