Token | and |
Token ID | 290 |
Feature activation | -8.30e-01 |
Pos logit contributions | |
zed | +0.012 |
ar | +0.011 |
z | +0.011 |
rd | +0.011 |
da | +0.011 |
Neg logit contributions | |
iring | -0.008 |
efully | -0.007 |
nam | -0.007 |
rad | -0.006 |
ble | -0.006 |
Token | wondered |
Token ID | 14028 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
ar | +0.026 |
zed | +0.026 |
t | +0.025 |
dreaming | +0.025 |
minutes | +0.024 |
Neg logit contributions | |
nam | -0.021 |
iring | -0.020 |
ble | -0.019 |
efully | -0.019 |
ishes | -0.019 |
Token | how |
Token ID | 703 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
ar | +0.009 |
zed | +0.009 |
t | +0.009 |
rd | +0.009 |
dreaming | +0.009 |
Neg logit contributions | |
nam | -0.009 |
iring | -0.009 |
efully | -0.009 |
ble | -0.009 |
ishes | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
nam | +0.030 |
iring | +0.027 |
efully | +0.026 |
rad | +0.026 |
av | +0.025 |
Neg logit contributions | |
ar | -0.034 |
ake | -0.033 |
rd | -0.032 |
stand | -0.032 |
zed | -0.032 |
Token | all |
Token ID | 477 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
nam | +0.040 |
ishes | +0.037 |
ble | +0.035 |
bles | +0.035 |
ins | +0.034 |
Neg logit contributions | |
t | -0.044 |
moment | -0.044 |
ever | -0.043 |
minute | -0.042 |
rd | -0.041 |
Token | igator |
Token ID | 23823 |
Feature activation | +5.23e+00 |
Pos logit contributions | |
ble | +0.026 |
nam | +0.026 |
bles | +0.024 |
iring | +0.023 |
uted | +0.022 |
Neg logit contributions | |
t | -0.069 |
ever | -0.069 |
zed | -0.067 |
moment | -0.066 |
ar | -0.065 |
Token | could |
Token ID | 714 |
Feature activation | +9.60e-01 |
Pos logit contributions | |
nam | +0.162 |
iring | +0.150 |
ble | +0.147 |
efully | +0.145 |
uted | +0.143 |
Neg logit contributions | |
ar | -0.139 |
zed | -0.133 |
t | -0.132 |
ever | -0.129 |
rd | -0.126 |
Token | talk |
Token ID | 1561 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
nam | +0.032 |
iring | +0.030 |
ble | +0.029 |
efully | +0.029 |
uted | +0.029 |
Neg logit contributions | |
ar | -0.023 |
zed | -0.022 |
t | -0.022 |
ake | -0.021 |
rd | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | -5.24e-02 |
Pos logit contributions | |
nam | +0.009 |
iring | +0.008 |
uted | +0.008 |
efully | +0.008 |
ble | +0.008 |
Neg logit contributions | |
ar | -0.009 |
zed | -0.009 |
ake | -0.009 |
rd | -0.009 |
minutes | -0.009 |
Token | She |
Token ID | 1375 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
ar | +0.002 |
zed | +0.002 |
t | +0.002 |
rd | +0.002 |
ake | +0.002 |
Neg logit contributions | |
nam | -0.001 |
iring | -0.001 |
ble | -0.001 |
efully | -0.001 |
uted | -0.001 |
Token | stopped |
Token ID | 5025 |
Feature activation | -5.45e-01 |
Pos logit contributions | |
nam | +0.011 |
iring | +0.011 |
ble | +0.010 |
efully | +0.010 |
uted | +0.010 |
Neg logit contributions | |
ar | -0.013 |
zed | -0.013 |
t | -0.013 |
minutes | -0.012 |
rd | -0.012 |
Token | Thank |
Token ID | 10449 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
zed | +0.004 |
ar | +0.004 |
rd | +0.004 |
t | +0.004 |
minutes | +0.004 |
Neg logit contributions | |
nam | -0.003 |
efully | -0.003 |
iring | -0.003 |
uted | -0.003 |
ble | -0.003 |
Token | you |
Token ID | 345 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
nam | +0.008 |
efully | +0.008 |
iring | +0.008 |
ble | +0.008 |
av | +0.007 |
Neg logit contributions | |
zed | -0.011 |
dreaming | -0.011 |
t | -0.011 |
minutes | -0.011 |
ar | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
nam | +0.029 |
iring | +0.028 |
efully | +0.028 |
ble | +0.027 |
bles | +0.026 |
Neg logit contributions | |
zed | -0.030 |
ar | -0.028 |
seek | -0.028 |
t | -0.027 |
rd | -0.027 |
Token | quiet |
Token ID | 5897 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
nam | +0.034 |
ishes | +0.033 |
efully | +0.033 |
ins | +0.033 |
ble | +0.033 |
Neg logit contributions | |
ever | -0.033 |
t | -0.030 |
ar | -0.030 |
minute | -0.029 |
dreaming | -0.028 |
Token | all |
Token ID | 477 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
ar | +0.006 |
zed | +0.005 |
t | +0.005 |
rd | +0.005 |
ake | +0.005 |
Neg logit contributions | |
nam | -0.004 |
iring | -0.004 |
ble | -0.004 |
efully | -0.004 |
uted | -0.004 |
Token | igator |
Token ID | 23823 |
Feature activation | +5.21e+00 |
Pos logit contributions | |
nam | +0.042 |
iring | +0.039 |
ble | +0.038 |
efully | +0.038 |
uted | +0.036 |
Neg logit contributions | |
ar | -0.062 |
t | -0.060 |
zed | -0.060 |
rd | -0.060 |
ever | -0.060 |
Token | ! |
Token ID | 0 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
iring | +0.142 |
nam | +0.141 |
ble | +0.141 |
efully | +0.139 |
ot | +0.137 |
Neg logit contributions | |
zed | -0.140 |
t | -0.132 |
ar | -0.131 |
minutes | -0.131 |
rd | -0.130 |
Token | Let |
Token ID | 3914 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
ar | +0.007 |
zed | +0.007 |
t | +0.007 |
minutes | +0.007 |
rd | +0.007 |
Neg logit contributions | |
nam | -0.009 |
iring | -0.008 |
efully | -0.008 |
ble | -0.008 |
uted | -0.008 |
Token | me |
Token ID | 502 |
Feature activation | +3.09e+00 |
Pos logit contributions | |
ar | +0.006 |
zed | +0.005 |
t | +0.005 |
ake | +0.005 |
rd | +0.005 |
Neg logit contributions | |
nam | -0.009 |
iring | -0.008 |
ble | -0.008 |
efully | -0.008 |
uted | -0.008 |
Token | give |
Token ID | 1577 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
nam | +0.106 |
iring | +0.101 |
ble | +0.100 |
efully | +0.099 |
uted | +0.096 |
Neg logit contributions | |
ar | -0.068 |
zed | -0.066 |
t | -0.065 |
rd | -0.063 |
ake | -0.063 |
Token | you |
Token ID | 345 |
Feature activation | +9.96e-01 |
Pos logit contributions | |
nam | +0.041 |
iring | +0.038 |
ble | +0.038 |
efully | +0.037 |
uted | +0.036 |
Neg logit contributions | |
ar | -0.033 |
zed | -0.032 |
t | -0.032 |
rd | -0.031 |
ake | -0.031 |
Token | lake |
Token ID | 13546 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
nam | +0.029 |
iring | +0.027 |
ble | +0.026 |
efully | +0.026 |
ishes | +0.025 |
Neg logit contributions | |
ar | -0.032 |
zed | -0.031 |
t | -0.030 |
ake | -0.030 |
rd | -0.030 |
Token | to |
Token ID | 284 |
Feature activation | +5.27e-02 |
Pos logit contributions | |
iring | +0.034 |
nam | +0.034 |
ble | +0.033 |
rad | +0.030 |
ot | +0.030 |
Neg logit contributions | |
ar | -0.040 |
zed | -0.040 |
minutes | -0.039 |
da | -0.039 |
payoff | -0.038 |
Token | see |
Token ID | 766 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
nam | +0.002 |
iring | +0.002 |
efully | +0.002 |
ble | +0.002 |
uted | +0.002 |
Neg logit contributions | |
ar | -0.001 |
zed | -0.001 |
t | -0.001 |
ake | -0.001 |
rd | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
ailed | +0.005 |
nam | +0.005 |
efully | +0.005 |
asure | +0.005 |
outed | +0.005 |
Neg logit contributions | |
dreaming | -0.001 |
one | -0.001 |
this | -0.001 |
Halloween | -0.001 |
ever | -0.001 |
Token | all |
Token ID | 477 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
nam | +0.040 |
efully | +0.035 |
ishes | +0.034 |
gladly | +0.034 |
asure | +0.033 |
Neg logit contributions | |
moment | -0.028 |
ever | -0.028 |
t | -0.028 |
dreaming | -0.027 |
ake | -0.027 |
Token | igators |
Token ID | 25975 |
Feature activation | +5.17e+00 |
Pos logit contributions | |
nam | +0.061 |
ble | +0.059 |
efully | +0.059 |
uted | +0.058 |
iring | +0.057 |
Neg logit contributions | |
ever | -0.045 |
t | -0.045 |
moment | -0.043 |
dreaming | -0.043 |
zed | -0.042 |
Token | . |
Token ID | 13 |
Feature activation | +5.19e-01 |
Pos logit contributions | |
nam | +0.189 |
efully | +0.178 |
iring | +0.174 |
uted | +0.174 |
ishes | +0.170 |
Neg logit contributions | |
ever | -0.102 |
ar | -0.099 |
t | -0.097 |
dreaming | -0.096 |
ake | -0.093 |
Token | One |
Token ID | 1881 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
nam | +0.019 |
ble | +0.018 |
efully | +0.018 |
iring | +0.018 |
uted | +0.018 |
Neg logit contributions | |
t | -0.011 |
ar | -0.010 |
dreaming | -0.010 |
zed | -0.010 |
moment | -0.010 |
Token | day |
Token ID | 1110 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
ar | +0.006 |
zed | +0.005 |
t | +0.005 |
rd | +0.005 |
dreaming | +0.005 |
Neg logit contributions | |
nam | -0.008 |
iring | -0.008 |
ble | -0.008 |
efully | -0.008 |
ot | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
ar | +0.011 |
zed | +0.010 |
t | +0.010 |
rd | +0.010 |
ake | +0.010 |
Neg logit contributions | |
nam | -0.015 |
iring | -0.014 |
ble | -0.014 |
efully | -0.014 |
uted | -0.014 |
Token | Tim |
Token ID | 5045 |
Feature activation | +5.24e-01 |
Pos logit contributions | |
efully | +0.006 |
nam | +0.006 |
iring | +0.006 |
uted | +0.006 |
ishes | +0.006 |
Neg logit contributions | |
t | -0.005 |
ar | -0.005 |
zed | -0.005 |
dreaming | -0.005 |
ever | -0.004 |
Token | No |
Token ID | 2949 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
ar | +0.005 |
zed | +0.005 |
t | +0.005 |
rd | +0.005 |
ake | +0.005 |
Neg logit contributions | |
nam | -0.005 |
iring | -0.005 |
ble | -0.005 |
efully | -0.005 |
uted | -0.005 |
Token | way |
Token ID | 835 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
zed | +0.004 |
ar | +0.004 |
t | +0.003 |
seek | +0.003 |
z | +0.003 |
Neg logit contributions | |
ot | -0.003 |
nam | -0.003 |
rad | -0.003 |
iring | -0.003 |
ble | -0.003 |
Token | ! |
Token ID | 0 |
Feature activation | -6.58e-01 |
Pos logit contributions | |
nam | +0.051 |
iring | +0.050 |
ble | +0.049 |
efully | +0.047 |
ot | +0.047 |
Neg logit contributions | |
zed | -0.045 |
ar | -0.045 |
rd | -0.042 |
minutes | -0.042 |
ake | -0.041 |
Token | That |
Token ID | 1320 |
Feature activation | +8.26e-01 |
Pos logit contributions | |
ar | +0.015 |
zed | +0.015 |
t | +0.015 |
rd | +0.014 |
ake | +0.014 |
Neg logit contributions | |
nam | -0.022 |
iring | -0.021 |
ble | -0.020 |
efully | -0.020 |
uted | -0.020 |
Token | all |
Token ID | 477 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
nam | +0.026 |
iring | +0.025 |
ble | +0.024 |
bles | +0.024 |
efully | +0.024 |
Neg logit contributions | |
t | -0.021 |
ever | -0.020 |
ar | -0.019 |
zed | -0.019 |
rd | -0.019 |
Token | igator |
Token ID | 23823 |
Feature activation | +5.16e+00 |
Pos logit contributions | |
nam | +0.042 |
iring | +0.038 |
ble | +0.038 |
efully | +0.038 |
uted | +0.036 |
Neg logit contributions | |
t | -0.066 |
ar | -0.066 |
zed | -0.065 |
ever | -0.065 |
rd | -0.064 |
Token | is |
Token ID | 318 |
Feature activation | +5.63e-01 |
Pos logit contributions | |
nam | +0.149 |
iring | +0.144 |
ble | +0.142 |
efully | +0.140 |
ishes | +0.138 |
Neg logit contributions | |
ar | -0.134 |
zed | -0.134 |
t | -0.131 |
rd | -0.130 |
ake | -0.129 |
Token | too |
Token ID | 1165 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
nam | +0.015 |
iring | +0.014 |
ble | +0.014 |
efully | +0.014 |
uted | +0.014 |
Neg logit contributions | |
ar | -0.017 |
zed | -0.016 |
rd | -0.016 |
t | -0.016 |
ake | -0.016 |
Token | deep |
Token ID | 2769 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
ar | +0.004 |
zed | +0.004 |
t | +0.004 |
ake | +0.004 |
rd | +0.004 |
Neg logit contributions | |
nam | -0.004 |
iring | -0.004 |
ble | -0.004 |
efully | -0.004 |
uted | -0.004 |
Token | in |
Token ID | 287 |
Feature activation | +6.49e-01 |
Pos logit contributions | |
iring | +0.030 |
ble | +0.028 |
uted | +0.028 |
ishes | +0.027 |
efully | +0.027 |
Neg logit contributions | |
zed | -0.046 |
ar | -0.046 |
rd | -0.044 |
t | -0.043 |
gh | -0.042 |
Token | the |
Token ID | 262 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
nam | +0.014 |
rad | +0.013 |
ble | +0.013 |
ot | +0.013 |
iring | +0.013 |
Neg logit contributions | |
ar | -0.024 |
zed | -0.024 |
t | -0.023 |
seek | -0.023 |
rd | -0.023 |
Token | we |
Token ID | 356 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
nam | +0.012 |
ble | +0.010 |
rad | +0.010 |
iring | +0.010 |
ot | +0.010 |
Neg logit contributions | |
minutes | -0.009 |
ake | -0.009 |
ar | -0.009 |
rd | -0.009 |
zed | -0.009 |
Token | take |
Token ID | 1011 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
ar | +0.008 |
t | +0.007 |
ever | +0.007 |
ake | +0.007 |
zed | +0.007 |
Neg logit contributions | |
nam | -0.011 |
iring | -0.010 |
ble | -0.010 |
efully | -0.010 |
uted | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
zed | +0.013 |
t | +0.013 |
ar | +0.013 |
rd | +0.013 |
dreaming | +0.012 |
Neg logit contributions | |
nam | -0.012 |
efully | -0.012 |
rad | -0.011 |
ishes | -0.011 |
ot | -0.011 |
Token | cute |
Token ID | 13779 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
nam | +0.006 |
ble | +0.005 |
efully | +0.005 |
iring | +0.005 |
ins | +0.005 |
Neg logit contributions | |
t | -0.007 |
ever | -0.007 |
moment | -0.006 |
minute | -0.006 |
ar | -0.006 |
Token | all |
Token ID | 477 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
nam | +0.039 |
ble | +0.033 |
iring | +0.033 |
efully | +0.033 |
uted | +0.031 |
Neg logit contributions | |
ar | -0.043 |
t | -0.041 |
ever | -0.041 |
ake | -0.040 |
rd | -0.039 |
Token | igator |
Token ID | 23823 |
Feature activation | +5.07e+00 |
Pos logit contributions | |
nam | +0.041 |
iring | +0.039 |
ble | +0.038 |
efully | +0.037 |
uted | +0.036 |
Neg logit contributions | |
ar | -0.039 |
zed | -0.038 |
t | -0.037 |
rd | -0.036 |
ake | -0.036 |
Token | home |
Token ID | 1363 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
nam | +0.125 |
iring | +0.116 |
ble | +0.113 |
efully | +0.112 |
uted | +0.108 |
Neg logit contributions | |
ar | -0.163 |
zed | -0.158 |
t | -0.157 |
ake | -0.154 |
rd | -0.154 |
Token | with |
Token ID | 351 |
Feature activation | +6.02e-01 |
Pos logit contributions | |
iring | +0.003 |
nam | +0.003 |
ble | +0.003 |
efully | +0.003 |
ishes | +0.002 |
Neg logit contributions | |
zed | -0.009 |
ar | -0.009 |
minutes | -0.009 |
t | -0.009 |
rd | -0.009 |
Token | us |
Token ID | 514 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
nam | +0.015 |
iring | +0.014 |
ble | +0.014 |
efully | +0.014 |
ishes | +0.013 |
Neg logit contributions | |
ar | -0.019 |
zed | -0.019 |
t | -0.019 |
rd | -0.018 |
minutes | -0.018 |
Token | ?" |
Token ID | 1701 |
Feature activation | -6.16e-02 |
Pos logit contributions | |
ar | +0.011 |
t | +0.010 |
ake | +0.010 |
zed | +0.010 |
ever | +0.010 |
Neg logit contributions | |
nam | -0.006 |
iring | -0.005 |
efully | -0.005 |
ble | -0.005 |
uted | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
ar | +0.002 |
zed | +0.002 |
t | +0.002 |
ake | +0.002 |
rd | +0.002 |
Neg logit contributions | |
nam | -0.001 |
iring | -0.001 |
ble | -0.001 |
efully | -0.001 |
uted | -0.001 |
Token | Everyday |
Token ID | 48154 |
Feature activation | +6.36e-01 |
Pos logit contributions | |
ever | +0.023 |
ar | +0.023 |
zed | +0.023 |
t | +0.023 |
dreaming | +0.022 |
Neg logit contributions | |
nam | -0.024 |
iring | -0.024 |
ble | -0.023 |
efully | -0.022 |
ishes | -0.021 |
Token | he |
Token ID | 339 |
Feature activation | -6.52e-01 |
Pos logit contributions | |
nam | +0.018 |
iring | +0.016 |
rad | +0.016 |
efully | +0.016 |
ot | +0.016 |
Neg logit contributions | |
ar | -0.017 |
zed | -0.017 |
t | -0.017 |
ake | -0.016 |
rd | -0.016 |
Token | would |
Token ID | 561 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
ar | +0.018 |
zed | +0.017 |
t | +0.017 |
rd | +0.017 |
ake | +0.017 |
Neg logit contributions | |
nam | -0.019 |
iring | -0.018 |
ble | -0.017 |
efully | -0.017 |
uted | -0.017 |
Token | take |
Token ID | 1011 |
Feature activation | -6.76e-01 |
Pos logit contributions | |
ar | +0.032 |
t | +0.030 |
ake | +0.030 |
rd | +0.030 |
minutes | +0.030 |
Neg logit contributions | |
nam | -0.031 |
ble | -0.029 |
efully | -0.028 |
iring | -0.027 |
rad | -0.027 |
Token | the |
Token ID | 262 |
Feature activation | -3.77e-02 |
Pos logit contributions | |
t | +0.024 |
storm | +0.022 |
rd | +0.022 |
ar | +0.022 |
ake | +0.022 |
Neg logit contributions | |
nam | -0.014 |
efully | -0.013 |
rad | -0.013 |
av | -0.013 |
ishes | -0.012 |
Token | av |
Token ID | 1196 |
Feature activation | +5.00e+00 |
Pos logit contributions | |
ar | +0.001 |
zed | +0.001 |
t | +0.001 |
ake | +0.001 |
rd | +0.001 |
Neg logit contributions | |
nam | -0.001 |
iring | -0.001 |
ble | -0.001 |
efully | -0.001 |
ishes | -0.001 |
Token | oc |
Token ID | 420 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
nam | +0.200 |
ble | +0.193 |
iring | +0.192 |
uted | +0.187 |
ot | +0.179 |
Neg logit contributions | |
ar | -0.090 |
ake | -0.088 |
t | -0.081 |
z | -0.079 |
rd | -0.075 |
Token | ados |
Token ID | 22484 |
Feature activation | +3.53e+00 |
Pos logit contributions | |
ar | +0.058 |
ake | +0.057 |
t | +0.054 |
rd | +0.054 |
zed | +0.054 |
Neg logit contributions | |
nam | -0.031 |
ble | -0.026 |
iring | -0.026 |
efully | -0.025 |
uted | -0.024 |
Token | and |
Token ID | 290 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
nam | +0.133 |
iring | +0.128 |
efully | +0.126 |
ble | +0.125 |
uted | +0.124 |
Neg logit contributions | |
ar | -0.065 |
t | -0.065 |
ever | -0.060 |
zed | -0.059 |
ake | -0.059 |
Token | scatter |
Token ID | 41058 |
Feature activation | +8.40e-01 |
Pos logit contributions | |
nam | +0.027 |
iring | +0.026 |
ble | +0.026 |
efully | +0.025 |
uted | +0.025 |
Neg logit contributions | |
ar | -0.029 |
zed | -0.028 |
t | -0.028 |
ever | -0.027 |
minutes | -0.027 |
Token | them |
Token ID | 606 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
nam | +0.025 |
iring | +0.024 |
ble | +0.023 |
efully | +0.023 |
uted | +0.022 |
Neg logit contributions | |
ar | -0.023 |
t | -0.022 |
zed | -0.021 |
ake | -0.021 |
minutes | -0.021 |
Token | I |
Token ID | 314 |
Feature activation | +3.98e-02 |
Pos logit contributions | |
nam | +0.023 |
iring | +0.022 |
efully | +0.022 |
ble | +0.021 |
uted | +0.021 |
Neg logit contributions | |
ar | -0.018 |
t | -0.017 |
ever | -0.017 |
zed | -0.017 |
rd | -0.017 |
Token | am |
Token ID | 716 |
Feature activation | -7.69e-02 |
Pos logit contributions | |
ble | +0.001 |
ot | +0.001 |
efully | +0.001 |
nam | +0.001 |
bles | +0.001 |
Neg logit contributions | |
zed | -0.001 |
ar | -0.001 |
minutes | -0.001 |
side | -0.001 |
seek | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
ar | +0.002 |
zed | +0.002 |
t | +0.002 |
ake | +0.002 |
rd | +0.002 |
Neg logit contributions | |
nam | -0.003 |
iring | -0.002 |
ble | -0.002 |
efully | -0.002 |
uted | -0.002 |
Token | quiet |
Token ID | 5897 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
nam | +0.003 |
iring | +0.003 |
efully | +0.002 |
ble | +0.002 |
uted | +0.002 |
Neg logit contributions | |
ar | -0.003 |
t | -0.003 |
zed | -0.003 |
rd | -0.003 |
ake | -0.003 |
Token | all |
Token ID | 477 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
zed | +0.035 |
ar | +0.034 |
t | +0.033 |
ake | +0.033 |
seek | +0.032 |
Neg logit contributions | |
nam | -0.022 |
iring | -0.022 |
ot | -0.022 |
ble | -0.022 |
rad | -0.022 |
Token | igator |
Token ID | 23823 |
Feature activation | +4.98e+00 |
Pos logit contributions | |
nam | +0.007 |
iring | +0.005 |
efully | +0.004 |
ble | +0.004 |
ot | +0.004 |
Neg logit contributions | |
ar | -0.057 |
zed | -0.056 |
ake | -0.055 |
t | -0.054 |
rd | -0.054 |
Token | . |
Token ID | 13 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
nam | +0.123 |
iring | +0.115 |
ble | +0.112 |
efully | +0.111 |
uted | +0.107 |
Neg logit contributions | |
ar | -0.159 |
zed | -0.155 |
t | -0.154 |
rd | -0.150 |
ake | -0.150 |
Token | Why |
Token ID | 4162 |
Feature activation | +5.44e-01 |
Pos logit contributions | |
zed | +0.008 |
ar | +0.008 |
ake | +0.008 |
gh | +0.008 |
t | +0.008 |
Neg logit contributions | |
nam | -0.008 |
iring | -0.008 |
efully | -0.007 |
ot | -0.007 |
ble | -0.007 |
Token | are |
Token ID | 389 |
Feature activation | +8.25e-01 |
Pos logit contributions | |
nam | +0.013 |
iring | +0.012 |
efully | +0.011 |
ble | +0.011 |
uted | +0.011 |
Neg logit contributions | |
ar | -0.018 |
zed | -0.018 |
t | -0.018 |
rd | -0.017 |
ever | -0.017 |
Token | you |
Token ID | 345 |
Feature activation | +7.11e-01 |
Pos logit contributions | |
nam | +0.027 |
iring | +0.027 |
ble | +0.027 |
efully | +0.026 |
uted | +0.026 |
Neg logit contributions | |
ar | -0.018 |
t | -0.018 |
zed | -0.017 |
ever | -0.017 |
rd | -0.017 |
Token | sad |
Token ID | 6507 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
nam | +0.020 |
iring | +0.019 |
ble | +0.019 |
efully | +0.018 |
uted | +0.018 |
Neg logit contributions | |
ar | -0.020 |
zed | -0.020 |
t | -0.019 |
rd | -0.019 |
minutes | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
ar | +0.011 |
t | +0.011 |
zed | +0.011 |
rd | +0.011 |
ake | +0.010 |
Neg logit contributions | |
nam | -0.010 |
iring | -0.009 |
ble | -0.009 |
efully | -0.009 |
uted | -0.009 |
Token | ground |
Token ID | 2323 |
Feature activation | +8.29e-01 |
Pos logit contributions | |
nam | +0.010 |
iring | +0.010 |
ins | +0.010 |
ishes | +0.009 |
efully | +0.009 |
Neg logit contributions | |
ever | -0.011 |
zed | -0.011 |
t | -0.011 |
minutes | -0.011 |
ar | -0.011 |
Token | so |
Token ID | 523 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
iring | +0.019 |
nam | +0.019 |
ble | +0.019 |
bles | +0.018 |
uted | +0.018 |
Neg logit contributions | |
zed | -0.028 |
ar | -0.026 |
rd | -0.025 |
ake | -0.025 |
gh | -0.024 |
Token | the |
Token ID | 262 |
Feature activation | +9.05e-01 |
Pos logit contributions | |
nam | +0.056 |
iring | +0.053 |
ble | +0.052 |
efully | +0.048 |
uted | +0.047 |
Neg logit contributions | |
rd | -0.039 |
ar | -0.039 |
zed | -0.039 |
ake | -0.039 |
dreaming | -0.037 |
Token | all |
Token ID | 477 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
nam | +0.022 |
ishes | +0.021 |
iring | +0.021 |
efully | +0.021 |
ble | +0.020 |
Neg logit contributions | |
t | -0.028 |
ever | -0.027 |
moment | -0.026 |
minutes | -0.026 |
minute | -0.026 |
Token | igator |
Token ID | 23823 |
Feature activation | +4.97e+00 |
Pos logit contributions | |
nam | +0.025 |
iring | +0.023 |
ble | +0.022 |
efully | +0.022 |
uted | +0.020 |
Neg logit contributions | |
ever | -0.066 |
t | -0.066 |
ar | -0.065 |
zed | -0.065 |
minutes | -0.064 |
Token | can |
Token ID | 460 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
nam | +0.159 |
iring | +0.148 |
efully | +0.143 |
ble | +0.143 |
uted | +0.140 |
Neg logit contributions | |
ar | -0.128 |
t | -0.124 |
zed | -0.122 |
ever | -0.119 |
ake | -0.117 |
Token | 't |
Token ID | 470 |
Feature activation | +8.04e-01 |
Pos logit contributions | |
nam | +0.004 |
iring | +0.004 |
ble | +0.003 |
efully | +0.003 |
uted | +0.003 |
Neg logit contributions | |
ar | -0.003 |
zed | -0.003 |
t | -0.003 |
rd | -0.003 |
ake | -0.003 |
Token | see |
Token ID | 766 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
nam | +0.028 |
ishes | +0.026 |
efully | +0.026 |
iring | +0.026 |
uted | +0.025 |
Neg logit contributions | |
ever | -0.020 |
t | -0.020 |
ar | -0.018 |
zed | -0.018 |
ake | -0.017 |
Token | us |
Token ID | 514 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
ar | +0.012 |
zed | +0.012 |
t | +0.012 |
rd | +0.012 |
ake | +0.012 |
Neg logit contributions | |
nam | -0.015 |
iring | -0.014 |
ble | -0.014 |
efully | -0.014 |
uted | -0.013 |
Token | ." |
Token ID | 526 |
Feature activation | +3.00e-01 |
Pos logit contributions | |
nam | +0.008 |
iring | +0.007 |
efully | +0.007 |
ble | +0.007 |
uted | +0.007 |
Neg logit contributions | |
ar | -0.007 |
zed | -0.007 |
t | -0.007 |
ake | -0.007 |
rd | -0.007 |
Token | wanted |
Token ID | 2227 |
Feature activation | +9.90e-01 |
Pos logit contributions | |
nam | +0.024 |
iring | +0.024 |
ying | +0.023 |
ble | +0.023 |
ishes | +0.022 |
Neg logit contributions | |
zed | -0.014 |
ar | -0.013 |
t | -0.013 |
ever | -0.013 |
minutes | -0.011 |
Token | to |
Token ID | 284 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
rad | +0.032 |
nam | +0.031 |
ot | +0.030 |
av | +0.029 |
iring | +0.029 |
Neg logit contributions | |
rd | -0.025 |
ar | -0.024 |
zed | -0.024 |
z | -0.023 |
ake | -0.023 |
Token | help |
Token ID | 1037 |
Feature activation | +8.76e-01 |
Pos logit contributions | |
nam | +0.016 |
iring | +0.015 |
ins | +0.015 |
ishes | +0.015 |
efully | +0.015 |
Neg logit contributions | |
ever | -0.007 |
ar | -0.007 |
t | -0.007 |
zed | -0.007 |
arrest | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
nam | +0.030 |
efully | +0.029 |
iring | +0.028 |
ishes | +0.027 |
uted | +0.027 |
Neg logit contributions | |
ar | -0.020 |
t | -0.020 |
ever | -0.020 |
zed | -0.019 |
ake | -0.019 |
Token | all |
Token ID | 477 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
nam | +0.061 |
ishes | +0.052 |
asure | +0.051 |
ey | +0.050 |
ble | +0.048 |
Neg logit contributions | |
t | -0.056 |
ever | -0.055 |
moment | -0.053 |
minute | -0.051 |
storm | -0.049 |
Token | igator |
Token ID | 23823 |
Feature activation | +4.90e+00 |
Pos logit contributions | |
nam | +0.045 |
uted | +0.038 |
ble | +0.038 |
iring | +0.038 |
efully | +0.037 |
Neg logit contributions | |
t | -0.076 |
ever | -0.075 |
minute | -0.073 |
moment | -0.072 |
ar | -0.072 |
Token | , |
Token ID | 11 |
Feature activation | +5.18e-01 |
Pos logit contributions | |
nam | +0.184 |
efully | +0.172 |
uted | +0.168 |
iring | +0.168 |
ins | +0.166 |
Neg logit contributions | |
t | -0.096 |
ever | -0.096 |
ar | -0.093 |
dreaming | -0.091 |
ake | -0.089 |
Token | so |
Token ID | 523 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
nam | +0.017 |
iring | +0.017 |
efully | +0.017 |
ble | +0.017 |
uted | +0.016 |
Neg logit contributions | |
t | -0.012 |
ar | -0.011 |
minutes | -0.011 |
dreaming | -0.011 |
zed | -0.011 |
Token | he |
Token ID | 339 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
nam | +0.070 |
iring | +0.067 |
efully | +0.066 |
ble | +0.066 |
uted | +0.064 |
Neg logit contributions | |
ar | -0.047 |
zed | -0.046 |
t | -0.045 |
rd | -0.044 |
ake | -0.044 |
Token | asked |
Token ID | 1965 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
nam | +0.057 |
iring | +0.055 |
uted | +0.052 |
ble | +0.050 |
ying | +0.049 |
Neg logit contributions | |
ar | -0.042 |
t | -0.039 |
ever | -0.038 |
zed | -0.038 |
minutes | -0.037 |
Token | his |
Token ID | 465 |
Feature activation | +5.84e-01 |
Pos logit contributions | |
nam | +0.005 |
iring | +0.005 |
efully | +0.005 |
ble | +0.005 |
uted | +0.004 |
Neg logit contributions | |
ar | -0.005 |
zed | -0.005 |
t | -0.005 |
ever | -0.005 |
ake | -0.005 |
Token | girl |
Token ID | 2576 |
Feature activation | +5.13e-01 |
Pos logit contributions | |
ble | +0.049 |
nam | +0.048 |
iring | +0.047 |
uted | +0.047 |
bles | +0.044 |
Neg logit contributions | |
moment | -0.051 |
ar | -0.049 |
minute | -0.049 |
ever | -0.048 |
minutes | -0.048 |
Token | thought |
Token ID | 1807 |
Feature activation | +5.74e-01 |
Pos logit contributions | |
nam | +0.013 |
iring | +0.012 |
efully | +0.012 |
ble | +0.012 |
uted | +0.012 |
Neg logit contributions | |
ar | -0.015 |
zed | -0.015 |
t | -0.015 |
ake | -0.015 |
rd | -0.015 |
Token | maybe |
Token ID | 3863 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
nam | +0.014 |
rad | +0.014 |
av | +0.014 |
iring | +0.014 |
ble | +0.014 |
Neg logit contributions | |
ar | -0.017 |
rd | -0.017 |
ake | -0.017 |
seek | -0.017 |
z | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
ake | +0.041 |
ar | +0.040 |
rd | +0.039 |
t | +0.039 |
z | +0.039 |
Neg logit contributions | |
nam | -0.035 |
av | -0.031 |
rad | -0.031 |
ot | -0.029 |
iring | -0.028 |
Token | all |
Token ID | 477 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
nam | +0.011 |
ishes | +0.010 |
ins | +0.009 |
iring | +0.009 |
asure | +0.009 |
Neg logit contributions | |
moment | -0.011 |
minute | -0.010 |
t | -0.010 |
ever | -0.010 |
payoff | -0.009 |
Token | igator |
Token ID | 23823 |
Feature activation | +4.81e+00 |
Pos logit contributions | |
nam | +0.024 |
ble | +0.023 |
iring | +0.022 |
bles | +0.021 |
efully | +0.019 |
Neg logit contributions | |
ever | -0.067 |
zed | -0.066 |
t | -0.066 |
ar | -0.065 |
rd | -0.064 |
Token | was |
Token ID | 373 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
nam | +0.138 |
iring | +0.129 |
ble | +0.126 |
efully | +0.124 |
uted | +0.121 |
Neg logit contributions | |
ar | -0.136 |
zed | -0.132 |
t | -0.131 |
rd | -0.126 |
ake | -0.126 |
Token | too |
Token ID | 1165 |
Feature activation | -6.29e-01 |
Pos logit contributions | |
nam | +0.030 |
iring | +0.029 |
ble | +0.028 |
efully | +0.028 |
uted | +0.027 |
Neg logit contributions | |
ar | -0.032 |
zed | -0.031 |
t | -0.031 |
ake | -0.030 |
rd | -0.030 |
Token | stubborn |
Token ID | 24444 |
Feature activation | +5.16e-01 |
Pos logit contributions | |
ar | +0.019 |
zed | +0.019 |
t | +0.019 |
rd | +0.018 |
ake | +0.018 |
Neg logit contributions | |
nam | -0.016 |
iring | -0.015 |
ble | -0.015 |
efully | -0.015 |
uted | -0.014 |
Token | to |
Token ID | 284 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
iring | +0.011 |
ying | +0.011 |
uted | +0.010 |
ishes | +0.010 |
ins | +0.010 |
Neg logit contributions | |
zed | -0.018 |
ar | -0.017 |
rd | -0.017 |
da | -0.016 |
z | -0.016 |
Token | talk |
Token ID | 1561 |
Feature activation | +7.65e-02 |
Pos logit contributions | |
ar | +0.007 |
zed | +0.007 |
t | +0.007 |
rd | +0.007 |
minutes | +0.007 |
Neg logit contributions | |
nam | -0.007 |
ble | -0.007 |
iring | -0.007 |
efully | -0.007 |
uted | -0.007 |
Token | wanted |
Token ID | 2227 |
Feature activation | +5.47e-01 |
Pos logit contributions | |
ar | +0.010 |
zed | +0.010 |
t | +0.009 |
ever | +0.009 |
minutes | +0.009 |
Neg logit contributions | |
nam | -0.010 |
iring | -0.010 |
ble | -0.010 |
efully | -0.009 |
uted | -0.009 |
Token | to |
Token ID | 284 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
rad | +0.017 |
nam | +0.017 |
iring | +0.016 |
ducks | +0.016 |
ot | +0.016 |
Neg logit contributions | |
ar | -0.014 |
zed | -0.014 |
rd | -0.014 |
z | -0.014 |
ake | -0.013 |
Token | see |
Token ID | 766 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
ar | +0.005 |
zed | +0.004 |
ever | +0.004 |
t | +0.004 |
rd | +0.004 |
Neg logit contributions | |
nam | -0.007 |
iring | -0.007 |
ishes | -0.007 |
efully | -0.007 |
uted | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
ar | +0.004 |
ever | +0.004 |
minutes | +0.004 |
zed | +0.004 |
dreaming | +0.004 |
Neg logit contributions | |
nam | -0.006 |
iring | -0.006 |
ble | -0.006 |
efully | -0.006 |
uted | -0.005 |
Token | all |
Token ID | 477 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
nam | +0.006 |
ble | +0.005 |
efully | +0.005 |
asure | +0.005 |
uted | +0.005 |
Neg logit contributions | |
ar | -0.007 |
t | -0.007 |
ever | -0.007 |
moment | -0.007 |
minutes | -0.007 |
Token | igators |
Token ID | 25975 |
Feature activation | +4.81e+00 |
Pos logit contributions | |
nam | +0.015 |
ble | +0.012 |
iring | +0.012 |
efully | +0.011 |
uted | +0.010 |
Neg logit contributions | |
ar | -0.057 |
t | -0.056 |
ever | -0.056 |
zed | -0.056 |
minutes | -0.055 |
Token | so |
Token ID | 523 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
nam | +0.147 |
iring | +0.141 |
ble | +0.139 |
efully | +0.136 |
uted | +0.132 |
Neg logit contributions | |
ar | -0.123 |
zed | -0.122 |
t | -0.119 |
rd | -0.116 |
ake | -0.116 |
Token | badly |
Token ID | 11234 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
nam | +0.059 |
iring | +0.058 |
ble | +0.054 |
uted | +0.052 |
efully | +0.052 |
Neg logit contributions | |
ar | -0.051 |
ake | -0.050 |
basis | -0.049 |
rd | -0.049 |
zed | -0.049 |
Token | . |
Token ID | 13 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
iring | +0.046 |
ble | +0.045 |
uted | +0.041 |
nam | +0.041 |
ot | +0.041 |
Neg logit contributions | |
rd | -0.063 |
zed | -0.062 |
ake | -0.060 |
z | -0.058 |
basis | -0.058 |
Token | They |
Token ID | 1119 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
nam | +0.003 |
iring | +0.003 |
efully | +0.002 |
ble | +0.002 |
uted | +0.002 |
Neg logit contributions | |
ar | -0.003 |
zed | -0.003 |
t | -0.003 |
ake | -0.003 |
rd | -0.003 |
Token | looked |
Token ID | 3114 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
ar | +0.003 |
zed | +0.003 |
t | +0.003 |
ever | +0.003 |
minutes | +0.003 |
Neg logit contributions | |
iring | -0.004 |
nam | -0.004 |
ble | -0.004 |
uted | -0.003 |
efully | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
seek | +0.042 |
zed | +0.041 |
rd | +0.041 |
t | +0.041 |
gh | +0.040 |
Neg logit contributions | |
iring | -0.016 |
ot | -0.016 |
rad | -0.016 |
efully | -0.015 |
ble | -0.014 |
Token | saw |
Token ID | 2497 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
nam | +0.004 |
efully | +0.003 |
iring | +0.003 |
ble | +0.003 |
uted | +0.003 |
Neg logit contributions | |
ake | -0.003 |
ar | -0.003 |
rd | -0.003 |
zed | -0.003 |
t | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | +6.95e-01 |
Pos logit contributions | |
ar | +0.008 |
zed | +0.008 |
t | +0.008 |
ake | +0.007 |
rd | +0.007 |
Neg logit contributions | |
nam | -0.009 |
iring | -0.009 |
ble | -0.008 |
efully | -0.008 |
uted | -0.008 |
Token | huge |
Token ID | 3236 |
Feature activation | +9.93e-01 |
Pos logit contributions | |
nam | +0.021 |
iring | +0.020 |
efully | +0.020 |
uted | +0.019 |
ishes | +0.019 |
Neg logit contributions | |
ar | -0.019 |
t | -0.018 |
zed | -0.017 |
minutes | -0.017 |
ake | -0.017 |
Token | all |
Token ID | 477 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
nam | +0.026 |
iring | +0.025 |
ble | +0.024 |
efully | +0.024 |
uted | +0.023 |
Neg logit contributions | |
ar | -0.029 |
zed | -0.029 |
t | -0.029 |
rd | -0.028 |
ake | -0.028 |
Token | igator |
Token ID | 23823 |
Feature activation | +4.81e+00 |
Pos logit contributions | |
nam | +0.024 |
efully | +0.020 |
ishes | +0.019 |
ble | +0.019 |
iring | +0.019 |
Neg logit contributions | |
t | -0.071 |
ever | -0.071 |
minutes | -0.070 |
ar | -0.070 |
rd | -0.069 |
Token | . |
Token ID | 13 |
Feature activation | -2.98e-02 |
Pos logit contributions | |
nam | +0.145 |
iring | +0.139 |
ble | +0.137 |
efully | +0.134 |
uted | +0.131 |
Neg logit contributions | |
ar | -0.125 |
zed | -0.122 |
t | -0.120 |
rd | -0.118 |
ake | -0.117 |
Token | It |
Token ID | 632 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
ar | +0.001 |
t | +0.001 |
zed | +0.001 |
minutes | +0.001 |
rd | +0.001 |
Neg logit contributions | |
nam | -0.001 |
iring | -0.001 |
ble | -0.001 |
efully | -0.001 |
ishes | -0.001 |
Token | had |
Token ID | 550 |
Feature activation | +7.29e-02 |
Pos logit contributions | |
ar | +0.003 |
zed | +0.003 |
ake | +0.003 |
rd | +0.003 |
t | +0.003 |
Neg logit contributions | |
nam | -0.004 |
iring | -0.003 |
ble | -0.003 |
efully | -0.003 |
uted | -0.003 |
Token | big |
Token ID | 1263 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
nam | +0.002 |
efully | +0.002 |
iring | +0.002 |
rad | +0.002 |
ble | +0.002 |
Neg logit contributions | |
ar | -0.002 |
rd | -0.002 |
ake | -0.002 |
t | -0.002 |
zed | -0.002 |
Token | teeth |
Token ID | 9941 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
ar | +0.012 |
t | +0.012 |
zed | +0.012 |
ake | +0.012 |
rd | +0.012 |
Neg logit contributions | |
nam | -0.008 |
iring | -0.008 |
ble | -0.007 |
efully | -0.007 |
uted | -0.007 |
Token | find |
Token ID | 1064 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
nam | +0.082 |
efully | +0.076 |
iring | +0.076 |
uted | +0.073 |
ble | +0.071 |
Neg logit contributions | |
ar | -0.086 |
t | -0.083 |
zed | -0.082 |
ake | -0.082 |
dreaming | -0.081 |
Token | it |
Token ID | 340 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
nam | +0.035 |
iring | +0.033 |
ble | +0.032 |
efully | +0.032 |
ishes | +0.031 |
Neg logit contributions | |
ar | -0.033 |
zed | -0.032 |
t | -0.032 |
rd | -0.031 |
ake | -0.031 |
Token | ?" |
Token ID | 1701 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
ar | +0.010 |
t | +0.010 |
zed | +0.010 |
ake | +0.009 |
rd | +0.009 |
Neg logit contributions | |
nam | -0.005 |
iring | -0.004 |
efully | -0.004 |
ble | -0.004 |
uted | -0.004 |
Token | The |
Token ID | 383 |
Feature activation | +6.46e-01 |
Pos logit contributions | |
nam | +0.004 |
iring | +0.004 |
ble | +0.004 |
ishes | +0.004 |
bles | +0.004 |
Neg logit contributions | |
ar | -0.003 |
t | -0.003 |
ever | -0.002 |
zed | -0.002 |
dreaming | -0.002 |
Token | all |
Token ID | 477 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
ishes | +0.019 |
nam | +0.019 |
ins | +0.019 |
asure | +0.018 |
ants | +0.018 |
Neg logit contributions | |
moment | -0.015 |
minute | -0.015 |
single | -0.014 |
next | -0.013 |
ever | -0.013 |
Token | igator |
Token ID | 23823 |
Feature activation | +4.79e+00 |
Pos logit contributions | |
ble | +0.039 |
iring | +0.039 |
nam | +0.038 |
bles | +0.035 |
ishes | +0.034 |
Neg logit contributions | |
t | -0.097 |
ever | -0.095 |
zed | -0.094 |
ar | -0.093 |
moment | -0.092 |
Token | said |
Token ID | 531 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
nam | +0.121 |
iring | +0.113 |
ble | +0.109 |
efully | +0.107 |
uted | +0.104 |
Neg logit contributions | |
ar | -0.153 |
zed | -0.147 |
t | -0.146 |
rd | -0.142 |
ake | -0.142 |
Token | , |
Token ID | 11 |
Feature activation | -4.24e-02 |
Pos logit contributions | |
ble | +0.003 |
nam | +0.003 |
iring | +0.003 |
bles | +0.003 |
rad | +0.003 |
Neg logit contributions | |
basis | -0.004 |
rd | -0.004 |
ake | -0.004 |
storm | -0.004 |
ital | -0.004 |
Token | " |
Token ID | 366 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
ar | +0.002 |
rd | +0.002 |
ake | +0.002 |
t | +0.002 |
zed | +0.002 |
Neg logit contributions | |
nam | -0.001 |
ble | -0.001 |
uted | -0.001 |
iring | -0.001 |
rad | -0.001 |
Token | Yes |
Token ID | 5297 |
Feature activation | +7.49e-01 |
Pos logit contributions | |
zed | +0.011 |
ar | +0.011 |
rd | +0.010 |
ake | +0.010 |
minutes | +0.010 |
Neg logit contributions | |
nam | -0.011 |
iring | -0.010 |
efully | -0.010 |
ble | -0.010 |
uted | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
ble | +0.019 |
nam | +0.018 |
iring | +0.018 |
rad | +0.018 |
bles | +0.017 |
Neg logit contributions | |
seek | -0.023 |
zed | -0.022 |
rd | -0.022 |
ake | -0.021 |
dreaming | -0.021 |
Token | and |
Token ID | 290 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
nam | +0.015 |
ble | +0.015 |
iring | +0.015 |
efully | +0.014 |
uted | +0.014 |
Neg logit contributions | |
zed | -0.020 |
ar | -0.020 |
rd | -0.019 |
minutes | -0.018 |
ake | -0.018 |
Token | try |
Token ID | 1949 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
nam | +0.009 |
ble | +0.008 |
efully | +0.008 |
iring | +0.008 |
ishes | +0.008 |
Neg logit contributions | |
ar | -0.008 |
t | -0.008 |
zed | -0.008 |
ake | -0.008 |
rd | -0.008 |
Token | to |
Token ID | 284 |
Feature activation | +9.18e-01 |
Pos logit contributions | |
nam | +0.007 |
ble | +0.007 |
iring | +0.007 |
rad | +0.007 |
bles | +0.007 |
Neg logit contributions | |
ar | -0.005 |
rd | -0.005 |
t | -0.004 |
zed | -0.004 |
ake | -0.004 |
Token | grab |
Token ID | 5552 |
Feature activation | +9.64e-01 |
Pos logit contributions | |
iring | +0.033 |
nam | +0.033 |
ins | +0.032 |
efully | +0.032 |
ishes | +0.032 |
Neg logit contributions | |
ar | -0.018 |
ever | -0.018 |
t | -0.017 |
zed | -0.017 |
bite | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
nam | +0.029 |
iring | +0.027 |
ble | +0.027 |
efully | +0.027 |
uted | +0.026 |
Neg logit contributions | |
ar | -0.026 |
zed | -0.025 |
t | -0.025 |
rd | -0.024 |
ake | -0.024 |
Token | av |
Token ID | 1196 |
Feature activation | +4.76e+00 |
Pos logit contributions | |
efully | +0.000 |
uted | +0.000 |
iring | +0.000 |
nam | +0.000 |
ins | +0.000 |
Neg logit contributions | |
ever | -0.000 |
t | -0.000 |
moment | -0.000 |
bite | -0.000 |
payoff | -0.000 |
Token | oc |
Token ID | 420 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
nam | +0.172 |
iring | +0.164 |
ble | +0.161 |
efully | +0.158 |
uted | +0.157 |
Neg logit contributions | |
ar | -0.101 |
t | -0.095 |
ake | -0.093 |
zed | -0.092 |
rd | -0.090 |
Token | ados |
Token ID | 22484 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
ar | +0.082 |
ake | +0.078 |
t | +0.076 |
zed | +0.076 |
rd | +0.075 |
Neg logit contributions | |
nam | -0.037 |
iring | -0.030 |
efully | -0.029 |
ble | -0.029 |
uted | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
nam | +0.085 |
iring | +0.080 |
efully | +0.079 |
ble | +0.077 |
uted | +0.076 |
Neg logit contributions | |
ar | -0.073 |
t | -0.071 |
zed | -0.069 |
ever | -0.068 |
ake | -0.068 |
Token | But |
Token ID | 887 |
Feature activation | -8.57e-01 |
Pos logit contributions | |
nam | +0.004 |
iring | +0.003 |
ble | +0.003 |
efully | +0.003 |
uted | +0.003 |
Neg logit contributions | |
ar | -0.005 |
zed | -0.005 |
t | -0.004 |
rd | -0.004 |
ake | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
ar | +0.020 |
zed | +0.020 |
t | +0.019 |
ake | +0.019 |
rd | +0.019 |
Neg logit contributions | |
nam | -0.028 |
iring | -0.027 |
ble | -0.026 |
efully | -0.026 |
uted | -0.026 |
Token | Please |
Token ID | 5492 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
nam | +0.022 |
iring | +0.021 |
ble | +0.020 |
efully | +0.020 |
uted | +0.020 |
Neg logit contributions | |
ar | -0.020 |
zed | -0.019 |
t | -0.019 |
ake | -0.019 |
rd | -0.019 |
Token | help |
Token ID | 1037 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
nam | +0.036 |
ble | +0.034 |
iring | +0.033 |
efully | +0.032 |
uted | +0.032 |
Neg logit contributions | |
ar | -0.032 |
zed | -0.032 |
rd | -0.031 |
ake | -0.031 |
minutes | -0.031 |
Token | me |
Token ID | 502 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
nam | +0.042 |
iring | +0.040 |
ble | +0.039 |
efully | +0.039 |
uted | +0.038 |
Neg logit contributions | |
ar | -0.039 |
zed | -0.038 |
t | -0.037 |
rd | -0.037 |
ake | -0.036 |
Token | shake |
Token ID | 13279 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
nam | +0.084 |
ble | +0.080 |
iring | +0.080 |
efully | +0.078 |
uted | +0.076 |
Neg logit contributions | |
ar | -0.077 |
zed | -0.075 |
t | -0.074 |
rd | -0.073 |
ake | -0.072 |
Token | this |
Token ID | 428 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
nam | +0.009 |
iring | +0.008 |
ble | +0.008 |
efully | +0.008 |
ishes | +0.008 |
Neg logit contributions | |
ar | -0.009 |
zed | -0.009 |
t | -0.009 |
rd | -0.009 |
ake | -0.009 |
Token | rad |
Token ID | 2511 |
Feature activation | +4.76e+00 |
Pos logit contributions | |
nam | +0.006 |
iring | +0.006 |
efully | +0.006 |
ble | +0.006 |
uted | +0.006 |
Neg logit contributions | |
ar | -0.006 |
t | -0.006 |
zed | -0.006 |
minutes | -0.005 |
ake | -0.005 |
Token | ish |
Token ID | 680 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
uted | +0.090 |
nam | +0.084 |
iring | +0.073 |
blamed | +0.068 |
ble | +0.066 |
Neg logit contributions | |
ar | -0.185 |
ake | -0.173 |
z | -0.172 |
t | -0.164 |
ever | -0.164 |
Token | , |
Token ID | 11 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
nam | +0.064 |
iring | +0.061 |
ble | +0.060 |
efully | +0.059 |
uted | +0.057 |
Neg logit contributions | |
ar | -0.055 |
zed | -0.054 |
t | -0.053 |
rd | -0.052 |
ake | -0.052 |
Token | it |
Token ID | 340 |
Feature activation | -3.34e-02 |
Pos logit contributions | |
nam | +0.042 |
iring | +0.040 |
ble | +0.039 |
efully | +0.039 |
uted | +0.038 |
Neg logit contributions | |
ar | -0.031 |
zed | -0.030 |
t | -0.029 |
ake | -0.028 |
rd | -0.028 |
Token | 's |
Token ID | 338 |
Feature activation | +7.17e-01 |
Pos logit contributions | |
ar | +0.001 |
zed | +0.001 |
t | +0.001 |
ake | +0.001 |
rd | +0.001 |
Neg logit contributions | |
nam | -0.001 |
iring | -0.001 |
ble | -0.001 |
efully | -0.001 |
uted | -0.001 |
Token | too |
Token ID | 1165 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
nam | +0.022 |
iring | +0.021 |
ble | +0.020 |
efully | +0.020 |
uted | +0.020 |
Neg logit contributions | |
ar | -0.018 |
zed | -0.018 |
t | -0.018 |
minutes | -0.017 |
ake | -0.017 |
Token | I |
Token ID | 40 |
Feature activation | +5.16e-01 |
Pos logit contributions | |
zed | +0.008 |
ar | +0.008 |
ake | +0.008 |
rd | +0.007 |
dreaming | +0.007 |
Neg logit contributions | |
nam | -0.007 |
efully | -0.006 |
iring | -0.006 |
ble | -0.005 |
uted | -0.005 |
Token | saw |
Token ID | 2497 |
Feature activation | -6.23e-01 |
Pos logit contributions | |
ot | +0.009 |
ish | +0.008 |
ble | +0.008 |
efully | +0.008 |
nam | +0.008 |
Neg logit contributions | |
zed | -0.019 |
stand | -0.018 |
seek | -0.018 |
rd | -0.018 |
side | -0.018 |
Token | a |
Token ID | 257 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
ever | +0.013 |
ar | +0.013 |
dreaming | +0.012 |
t | +0.012 |
zed | +0.012 |
Neg logit contributions | |
nam | -0.022 |
ble | -0.021 |
iring | -0.020 |
efully | -0.020 |
bles | -0.019 |
Token | big |
Token ID | 1263 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
nam | +0.012 |
efully | +0.011 |
iring | +0.011 |
ishes | +0.011 |
uted | +0.011 |
Neg logit contributions | |
ar | -0.010 |
t | -0.010 |
ever | -0.009 |
moment | -0.009 |
dreaming | -0.009 |
Token | all |
Token ID | 477 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
nam | +0.008 |
iring | +0.008 |
efully | +0.008 |
uted | +0.007 |
ble | +0.007 |
Neg logit contributions | |
ar | -0.008 |
t | -0.008 |
minutes | -0.008 |
ake | -0.008 |
ever | -0.008 |
Token | igator |
Token ID | 23823 |
Feature activation | +4.72e+00 |
Pos logit contributions | |
nam | +0.019 |
efully | +0.017 |
ble | +0.016 |
iring | +0.016 |
ishes | +0.015 |
Neg logit contributions | |
t | -0.064 |
ar | -0.063 |
ever | -0.063 |
minutes | -0.062 |
rd | -0.061 |
Token | there |
Token ID | 612 |
Feature activation | -7.32e-01 |
Pos logit contributions | |
nam | +0.142 |
iring | +0.136 |
ble | +0.134 |
efully | +0.131 |
uted | +0.128 |
Neg logit contributions | |
ar | -0.123 |
zed | -0.122 |
t | -0.118 |
rd | -0.116 |
ake | -0.115 |
Token | !" |
Token ID | 2474 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
ar | +0.020 |
t | +0.020 |
ever | +0.019 |
ake | +0.019 |
rd | +0.019 |
Neg logit contributions | |
nam | -0.021 |
iring | -0.020 |
efully | -0.019 |
ble | -0.019 |
ishes | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | +4.83e-02 |
Pos logit contributions | |
ble | +0.012 |
iring | +0.012 |
nam | +0.012 |
efully | +0.011 |
bles | +0.011 |
Neg logit contributions | |
t | -0.007 |
dreaming | -0.006 |
ar | -0.006 |
stand | -0.006 |
zed | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
nam | +0.002 |
ishes | +0.002 |
efully | +0.002 |
ble | +0.002 |
iring | +0.002 |
Neg logit contributions | |
t | -0.001 |
zed | -0.001 |
ar | -0.001 |
ake | -0.001 |
z | -0.001 |
Token | Tim |
Token ID | 14967 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
t | +0.004 |
ar | +0.004 |
rd | +0.004 |
z | +0.003 |
zed | +0.003 |
Neg logit contributions | |
nam | -0.008 |
ishes | -0.008 |
ble | -0.008 |
iring | -0.007 |
efully | -0.007 |
Token | mom |
Token ID | 1995 |
Feature activation | -7.37e-01 |
Pos logit contributions | |
ar | +0.003 |
zed | +0.003 |
t | +0.003 |
rd | +0.003 |
ake | +0.003 |
Neg logit contributions | |
nam | -0.003 |
iring | -0.003 |
ble | -0.003 |
efully | -0.003 |
uted | -0.003 |
Token | said |
Token ID | 531 |
Feature activation | -7.14e-01 |
Pos logit contributions | |
ar | +0.022 |
zed | +0.022 |
t | +0.022 |
rd | +0.021 |
ake | +0.021 |
Neg logit contributions | |
nam | -0.019 |
iring | -0.018 |
ble | -0.018 |
efully | -0.018 |
uted | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | -7.90e-01 |
Pos logit contributions | |
seek | +0.020 |
rd | +0.020 |
ar | +0.019 |
basis | +0.019 |
ake | +0.019 |
Neg logit contributions | |
nam | -0.020 |
rad | -0.019 |
ble | -0.019 |
av | -0.018 |
ot | -0.018 |
Token | " |
Token ID | 366 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
ar | +0.028 |
rd | +0.027 |
zed | +0.027 |
ake | +0.026 |
t | +0.026 |
Neg logit contributions | |
nam | -0.017 |
iring | -0.015 |
ble | -0.015 |
efully | -0.014 |
uted | -0.014 |
Token | All |
Token ID | 3237 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
ar | +0.010 |
t | +0.010 |
zed | +0.009 |
ake | +0.009 |
rd | +0.009 |
Neg logit contributions | |
nam | -0.013 |
iring | -0.012 |
ble | -0.012 |
efully | -0.012 |
uted | -0.011 |
Token | igators |
Token ID | 25975 |
Feature activation | +4.71e+00 |
Pos logit contributions | |
ar | +0.010 |
zed | +0.010 |
t | +0.010 |
ake | +0.009 |
rd | +0.009 |
Neg logit contributions | |
nam | -0.010 |
iring | -0.009 |
ble | -0.009 |
efully | -0.009 |
uted | -0.009 |
Token | are |
Token ID | 389 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
nam | +0.121 |
iring | +0.112 |
ble | +0.110 |
efully | +0.109 |
uted | +0.105 |
Neg logit contributions | |
ar | -0.146 |
zed | -0.142 |
t | -0.141 |
ake | -0.138 |
rd | -0.137 |
Token | not |
Token ID | 407 |
Feature activation | -7.03e-01 |
Pos logit contributions | |
ar | +0.007 |
zed | +0.007 |
rd | +0.007 |
t | +0.007 |
ake | +0.007 |
Neg logit contributions | |
nam | -0.006 |
iring | -0.005 |
ble | -0.005 |
ishes | -0.005 |
efully | -0.005 |
Token | nice |
Token ID | 3621 |
Feature activation | +5.18e-03 |
Pos logit contributions | |
ever | +0.017 |
dreaming | +0.017 |
minutes | +0.016 |
ar | +0.016 |
t | +0.016 |
Neg logit contributions | |
nam | -0.022 |
efully | -0.021 |
iring | -0.021 |
ble | -0.021 |
uted | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
nam | +0.000 |
iring | +0.000 |
ishes | +0.000 |
ble | +0.000 |
uted | +0.000 |
Neg logit contributions | |
zed | -0.000 |
ar | -0.000 |
t | -0.000 |
rd | -0.000 |
ake | -0.000 |
Token | They |
Token ID | 1119 |
Feature activation | -9.56e-02 |
Pos logit contributions | |
ar | +0.029 |
t | +0.028 |
zed | +0.027 |
rd | +0.027 |
ake | +0.027 |
Neg logit contributions | |
nam | -0.032 |
iring | -0.030 |
ble | -0.030 |
efully | -0.029 |
uted | -0.028 |
Token | help |
Token ID | 1037 |
Feature activation | +8.72e-01 |
Pos logit contributions | |
ar | +0.015 |
t | +0.014 |
zed | +0.014 |
ake | +0.014 |
rd | +0.014 |
Neg logit contributions | |
nam | -0.019 |
ble | -0.018 |
iring | -0.018 |
efully | -0.018 |
uted | -0.017 |
Token | her |
Token ID | 607 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
efully | +0.031 |
nam | +0.031 |
uted | +0.030 |
bles | +0.030 |
iring | +0.030 |
Neg logit contributions | |
ake | -0.016 |
Halloween | -0.014 |
ever | -0.014 |
gh | -0.014 |
stand | -0.013 |
Token | mom |
Token ID | 1995 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
iring | +0.045 |
efully | +0.044 |
uted | +0.044 |
nam | +0.044 |
ble | +0.041 |
Neg logit contributions | |
zed | -0.034 |
dreaming | -0.033 |
ar | -0.032 |
rd | -0.032 |
t | -0.031 |
Token | put |
Token ID | 1234 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
nam | +0.010 |
efully | +0.009 |
iring | +0.009 |
uted | +0.009 |
ble | +0.009 |
Neg logit contributions | |
ake | -0.005 |
t | -0.005 |
ar | -0.005 |
dreaming | -0.005 |
ever | -0.005 |
Token | or |
Token ID | 393 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
nam | +0.003 |
iring | +0.003 |
ble | +0.003 |
efully | +0.003 |
uted | +0.003 |
Neg logit contributions | |
ar | -0.003 |
zed | -0.003 |
t | -0.003 |
ake | -0.003 |
minutes | -0.003 |
Token | nam |
Token ID | 7402 |
Feature activation | +4.70e+00 |
Pos logit contributions | |
ar | +0.006 |
zed | +0.006 |
dreaming | +0.006 |
t | +0.006 |
minutes | +0.006 |
Neg logit contributions | |
iring | -0.007 |
efully | -0.007 |
nam | -0.007 |
uted | -0.007 |
ble | -0.007 |
Token | ents |
Token ID | 658 |
Feature activation | +9.75e-01 |
Pos logit contributions | |
nam | +0.096 |
ot | +0.091 |
ble | +0.091 |
efully | +0.089 |
uted | +0.089 |
Neg logit contributions | |
t | -0.163 |
ake | -0.161 |
z | -0.153 |
ever | -0.152 |
ar | -0.151 |
Token | on |
Token ID | 319 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
nam | +0.030 |
iring | +0.029 |
efully | +0.028 |
ble | +0.028 |
uted | +0.027 |
Neg logit contributions | |
ar | -0.025 |
t | -0.024 |
zed | -0.024 |
ake | -0.023 |
ever | -0.023 |
Token | the |
Token ID | 262 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
ar | +0.007 |
t | +0.006 |
zed | +0.006 |
ake | +0.006 |
rd | +0.006 |
Neg logit contributions | |
nam | -0.006 |
av | -0.005 |
rad | -0.005 |
efully | -0.005 |
iring | -0.004 |
Token | tree |
Token ID | 5509 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
efully | +0.006 |
iring | +0.006 |
uted | +0.005 |
ins | +0.005 |
ble | +0.005 |
Neg logit contributions | |
dreaming | -0.005 |
t | -0.005 |
ever | -0.005 |
zed | -0.005 |
stand | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +6.26e-01 |
Pos logit contributions | |
ar | +0.006 |
t | +0.006 |
ake | +0.005 |
zed | +0.005 |
rd | +0.005 |
Neg logit contributions | |
nam | -0.010 |
iring | -0.010 |
efully | -0.010 |
ble | -0.009 |
uted | -0.009 |
Token | got |
Token ID | 1392 |
Feature activation | +3.17e-02 |
Pos logit contributions | |
ar | +0.015 |
zed | +0.015 |
rd | +0.015 |
ake | +0.015 |
t | +0.015 |
Neg logit contributions | |
nam | -0.012 |
iring | -0.011 |
ble | -0.011 |
efully | -0.011 |
uted | -0.011 |
Token | to |
Token ID | 284 |
Feature activation | -5.34e-01 |
Pos logit contributions | |
nam | +0.001 |
iring | +0.001 |
ble | +0.001 |
efully | +0.001 |
uted | +0.001 |
Neg logit contributions | |
ar | -0.001 |
t | -0.001 |
zed | -0.001 |
ever | -0.001 |
dreaming | -0.001 |
Token | hold |
Token ID | 1745 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
ar | +0.012 |
zed | +0.012 |
t | +0.011 |
ake | +0.011 |
rd | +0.011 |
Neg logit contributions | |
nam | -0.018 |
iring | -0.018 |
ble | -0.017 |
efully | -0.017 |
uted | -0.016 |
Token | an |
Token ID | 281 |
Feature activation | +5.39e-01 |
Pos logit contributions | |
ar | +0.008 |
zed | +0.008 |
t | +0.008 |
ake | +0.008 |
rd | +0.008 |
Neg logit contributions | |
nam | -0.008 |
iring | -0.007 |
ble | -0.007 |
efully | -0.007 |
uted | -0.007 |
Token | all |
Token ID | 477 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
nam | +0.013 |
iring | +0.010 |
ishes | +0.010 |
bles | +0.010 |
ins | +0.009 |
Neg logit contributions | |
ever | -0.018 |
minutes | -0.018 |
rd | -0.018 |
basis | -0.018 |
ake | -0.017 |
Token | igator |
Token ID | 23823 |
Feature activation | +4.69e+00 |
Pos logit contributions | |
nam | +0.030 |
iring | +0.027 |
ble | +0.027 |
efully | +0.026 |
uted | +0.025 |
Neg logit contributions | |
ar | -0.049 |
zed | -0.048 |
t | -0.048 |
rd | -0.047 |
ake | -0.047 |
Token | toy |
Token ID | 13373 |
Feature activation | +9.40e-01 |
Pos logit contributions | |
nam | +0.136 |
iring | +0.126 |
ble | +0.124 |
efully | +0.122 |
ishes | +0.120 |
Neg logit contributions | |
ar | -0.131 |
zed | -0.130 |
t | -0.125 |
rd | -0.122 |
ake | -0.122 |
Token | . |
Token ID | 13 |
Feature activation | +3.05e-02 |
Pos logit contributions | |
nam | +0.030 |
iring | +0.028 |
ble | +0.027 |
efully | +0.027 |
uted | +0.027 |
Neg logit contributions | |
ar | -0.024 |
t | -0.023 |
ever | -0.022 |
zed | -0.022 |
ake | -0.022 |
Token | But |
Token ID | 887 |
Feature activation | -7.74e-01 |
Pos logit contributions | |
nam | +0.001 |
iring | +0.001 |
efully | +0.001 |
ble | +0.001 |
ishes | +0.001 |
Neg logit contributions | |
ar | -0.001 |
zed | -0.001 |
t | -0.001 |
ake | -0.001 |
rd | -0.001 |
Token | M |
Token ID | 337 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
ake | +0.025 |
rd | +0.025 |
seek | +0.024 |
t | +0.024 |
gh | +0.024 |
Neg logit contributions | |
nam | -0.021 |
iring | -0.017 |
rad | -0.017 |
ot | -0.017 |
ble | -0.016 |
Token | omm |
Token ID | 2002 |
Feature activation | +8.18e-01 |
Pos logit contributions | |
ar | +0.012 |
ake | +0.012 |
t | +0.012 |
rd | +0.012 |
zed | +0.011 |
Neg logit contributions | |
nam | -0.013 |
efully | -0.011 |
ble | -0.011 |
uted | -0.010 |
iring | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
zed | +0.037 |
ar | +0.037 |
rd | +0.034 |
t | +0.034 |
minutes | +0.034 |
Neg logit contributions | |
nam | -0.023 |
ishes | -0.021 |
iring | -0.021 |
rad | -0.020 |
ot | -0.020 |
Token | saw |
Token ID | 2497 |
Feature activation | -7.66e-01 |
Pos logit contributions | |
dreaming | +0.005 |
zed | +0.004 |
t | +0.004 |
ever | +0.004 |
ar | +0.004 |
Neg logit contributions | |
iring | -0.007 |
ble | -0.007 |
efully | -0.007 |
uted | -0.007 |
nam | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
zed | +0.012 |
dreaming | +0.012 |
ar | +0.012 |
ever | +0.011 |
minutes | +0.011 |
Neg logit contributions | |
nam | -0.029 |
iring | -0.028 |
ble | -0.028 |
efully | -0.028 |
ishes | -0.028 |
Token | cute |
Token ID | 13779 |
Feature activation | +6.00e-01 |
Pos logit contributions | |
efully | +0.006 |
nam | +0.006 |
ishes | +0.006 |
iring | +0.006 |
uted | +0.006 |
Neg logit contributions | |
ar | -0.005 |
t | -0.004 |
ake | -0.004 |
dreaming | -0.004 |
minutes | -0.004 |
Token | all |
Token ID | 477 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
nam | +0.016 |
iring | +0.015 |
ble | +0.014 |
efully | +0.014 |
uted | +0.014 |
Neg logit contributions | |
ar | -0.018 |
zed | -0.018 |
t | -0.018 |
ake | -0.017 |
rd | -0.017 |
Token | igator |
Token ID | 23823 |
Feature activation | +4.68e+00 |
Pos logit contributions | |
efully | +0.024 |
nam | +0.024 |
ble | +0.023 |
iring | +0.022 |
bles | +0.021 |
Neg logit contributions | |
t | -0.068 |
ever | -0.068 |
dreaming | -0.067 |
ar | -0.067 |
rd | -0.067 |
Token | . |
Token ID | 13 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
nam | +0.148 |
iring | +0.138 |
efully | +0.137 |
ble | +0.135 |
uted | +0.133 |
Neg logit contributions | |
ar | -0.117 |
zed | -0.113 |
t | -0.112 |
ake | -0.110 |
ever | -0.109 |
Token | |
Token ID | 220 |
Feature activation | +5.13e-01 |
Pos logit contributions | |
ble | +0.010 |
nam | +0.010 |
iring | +0.010 |
efully | +0.010 |
uted | +0.010 |
Neg logit contributions | |
t | -0.007 |
ar | -0.007 |
stand | -0.006 |
zed | -0.006 |
dreaming | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -6.34e-01 |
Pos logit contributions | |
nam | +0.020 |
ishes | +0.019 |
ot | +0.019 |
rad | +0.018 |
efully | +0.018 |
Neg logit contributions | |
t | -0.011 |
ake | -0.009 |
zed | -0.009 |
rd | -0.009 |
ar | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | -9.46e-01 |
Pos logit contributions | |
ar | +0.020 |
zed | +0.019 |
t | +0.019 |
rd | +0.019 |
ake | +0.019 |
Neg logit contributions | |
nam | -0.016 |
iring | -0.015 |
ble | -0.015 |
efully | -0.014 |
uted | -0.014 |
Token | L |
Token ID | 43 |
Feature activation | -6.42e-01 |
Pos logit contributions | |
ar | +0.025 |
zed | +0.025 |
ake | +0.023 |
ever | +0.023 |
rd | +0.023 |
Neg logit contributions | |
nam | -0.029 |
iring | -0.027 |
efully | -0.026 |
ble | -0.025 |
uted | -0.025 |
Token | start |
Token ID | 923 |
Feature activation | -5.65e-01 |
Pos logit contributions | |
nam | +0.010 |
iring | +0.009 |
ble | +0.009 |
efully | +0.009 |
uted | +0.009 |
Neg logit contributions | |
ar | -0.009 |
t | -0.009 |
zed | -0.009 |
ake | -0.008 |
rd | -0.008 |
Token | with |
Token ID | 351 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
ar | +0.016 |
zed | +0.016 |
rd | +0.015 |
t | +0.015 |
ake | +0.014 |
Neg logit contributions | |
nam | -0.017 |
ble | -0.015 |
iring | -0.015 |
efully | -0.015 |
ishes | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | -6.74e-01 |
Pos logit contributions | |
nam | +0.005 |
ble | +0.005 |
iring | +0.005 |
efully | +0.005 |
ishes | +0.005 |
Neg logit contributions | |
ar | -0.006 |
t | -0.006 |
zed | -0.006 |
rd | -0.006 |
ake | -0.006 |
Token | roller |
Token ID | 24471 |
Feature activation | -3.32e+00 |
Pos logit contributions | |
zed | +0.022 |
ar | +0.022 |
ake | +0.022 |
rd | +0.020 |
t | +0.020 |
Neg logit contributions | |
nam | -0.017 |
iring | -0.015 |
ot | -0.015 |
ble | -0.014 |
bles | -0.014 |
Token | co |
Token ID | 1073 |
Feature activation | -2.94e+00 |
Pos logit contributions | |
t | +0.076 |
ever | +0.075 |
zed | +0.075 |
ake | +0.074 |
ar | +0.074 |
Neg logit contributions | |
ble | -0.096 |
nam | -0.091 |
bles | -0.089 |
av | -0.088 |
uted | -0.088 |
Token | aster |
Token ID | 1603 |
Feature activation | -5.05e+00 |
Pos logit contributions | |
ar | +0.081 |
dreaming | +0.080 |
zed | +0.079 |
injuries | +0.078 |
payoff | +0.076 |
Neg logit contributions | |
nam | -0.075 |
ins | -0.070 |
ble | -0.070 |
ishes | -0.069 |
uted | -0.069 |
Token | ? |
Token ID | 30 |
Feature activation | -8.36e-01 |
Pos logit contributions | |
ar | +0.156 |
zed | +0.154 |
ake | +0.146 |
t | +0.145 |
rd | +0.144 |
Neg logit contributions | |
nam | -0.123 |
ble | -0.114 |
iring | -0.112 |
efully | -0.111 |
ishes | -0.109 |
Token | â |
Token ID | 22940 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
ar | +0.020 |
t | +0.020 |
zed | +0.019 |
rd | +0.019 |
ake | +0.019 |
Neg logit contributions | |
nam | -0.027 |
iring | -0.025 |
ble | -0.025 |
efully | -0.024 |
uted | -0.024 |
Token | € |
Token ID | 26391 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
nam | +0.032 |
ble | +0.030 |
iring | +0.030 |
efully | +0.030 |
uted | +0.029 |
Neg logit contributions | |
ar | -0.040 |
t | -0.039 |
zed | -0.039 |
minutes | -0.038 |
ever | -0.038 |
Token | his |
Token ID | 465 |
Feature activation | -5.65e-01 |
Pos logit contributions | |
nam | +0.005 |
ble | +0.005 |
iring | +0.005 |
uted | +0.005 |
efully | +0.005 |
Neg logit contributions | |
ar | -0.008 |
ever | -0.007 |
zed | -0.007 |
minutes | -0.007 |
payoff | -0.007 |
Token | dad |
Token ID | 9955 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
ar | +0.021 |
t | +0.020 |
ake | +0.020 |
rd | +0.019 |
seek | +0.019 |
Neg logit contributions | |
nam | -0.011 |
ble | -0.010 |
iring | -0.010 |
efully | -0.010 |
rad | -0.009 |
Token | puts |
Token ID | 7584 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
nam | +0.017 |
ble | +0.016 |
efully | +0.016 |
iring | +0.016 |
ishes | +0.016 |
Neg logit contributions | |
ar | -0.017 |
rd | -0.016 |
t | -0.016 |
ake | -0.016 |
zed | -0.016 |
Token | bread |
Token ID | 8509 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
ar | +0.048 |
rd | +0.048 |
t | +0.047 |
seek | +0.046 |
zed | +0.045 |
Neg logit contributions | |
nam | -0.043 |
ble | -0.037 |
ishes | -0.037 |
av | -0.036 |
efully | -0.036 |
Token | in |
Token ID | 287 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
nam | +0.037 |
iring | +0.035 |
ble | +0.034 |
efully | +0.034 |
uted | +0.033 |
Neg logit contributions | |
ar | -0.037 |
zed | -0.036 |
t | -0.035 |
ake | -0.035 |
rd | -0.034 |
Token | the |
Token ID | 262 |
Feature activation | +7.88e-03 |
Pos logit contributions | |
nam | +0.037 |
iring | +0.033 |
ble | +0.033 |
efully | +0.032 |
rad | +0.031 |
Neg logit contributions | |
ar | -0.047 |
t | -0.045 |
zed | -0.044 |
rd | -0.043 |
ake | -0.043 |
Token | to |
Token ID | 284 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
nam | +0.000 |
iring | +0.000 |
ble | +0.000 |
efully | +0.000 |
uted | +0.000 |
Neg logit contributions | |
ar | -0.000 |
zed | -0.000 |
t | -0.000 |
ake | -0.000 |
rd | -0.000 |
Token | aster |
Token ID | 1603 |
Feature activation | -5.01e+00 |
Pos logit contributions | |
ar | +0.007 |
t | +0.007 |
rd | +0.007 |
ake | +0.007 |
zed | +0.007 |
Neg logit contributions | |
nam | -0.017 |
ble | -0.016 |
iring | -0.015 |
efully | -0.015 |
rad | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
ar | +0.159 |
t | +0.152 |
zed | +0.148 |
rd | +0.147 |
da | +0.147 |
Neg logit contributions | |
nam | -0.110 |
ble | -0.106 |
ishes | -0.105 |
ins | -0.105 |
av | -0.101 |
Token | waits |
Token ID | 28364 |
Feature activation | -9.89e-01 |
Pos logit contributions | |
nam | +0.003 |
iring | +0.003 |
ble | +0.003 |
efully | +0.003 |
ishes | +0.003 |
Neg logit contributions | |
ar | -0.003 |
t | -0.003 |
zed | -0.003 |
rd | -0.003 |
ake | -0.003 |
Token | for |
Token ID | 329 |
Feature activation | +6.47e-01 |
Pos logit contributions | |
ar | +0.027 |
rd | +0.025 |
t | +0.025 |
zed | +0.025 |
ake | +0.025 |
Neg logit contributions | |
nam | -0.029 |
ble | -0.029 |
iring | -0.028 |
uted | -0.026 |
efully | -0.026 |
Token | it |
Token ID | 340 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
nam | +0.017 |
ble | +0.015 |
iring | +0.014 |
av | +0.014 |
rad | +0.014 |
Neg logit contributions | |
ar | -0.022 |
t | -0.021 |
rd | -0.021 |
ake | -0.020 |
z | -0.020 |
Token | to |
Token ID | 284 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
ar | +0.028 |
rd | +0.028 |
zed | +0.027 |
basis | +0.027 |
ake | +0.026 |
Neg logit contributions | |
nam | -0.036 |
ishes | -0.035 |
iring | -0.035 |
bles | -0.034 |
ble | -0.034 |
Token | down |
Token ID | 866 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
nam | +0.006 |
efully | +0.005 |
iring | +0.005 |
ishes | +0.005 |
ble | +0.005 |
Neg logit contributions | |
ar | -0.014 |
zed | -0.014 |
rd | -0.014 |
ake | -0.014 |
t | -0.014 |
Token | on |
Token ID | 319 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
iring | +0.009 |
nam | +0.009 |
ble | +0.008 |
efully | +0.008 |
vendors | +0.008 |
Neg logit contributions | |
rd | -0.013 |
ake | -0.013 |
zed | -0.013 |
ar | -0.012 |
gh | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
t | +0.006 |
rd | +0.006 |
ar | +0.006 |
zed | +0.006 |
ake | +0.006 |
Neg logit contributions | |
nam | -0.002 |
rad | -0.002 |
efully | -0.002 |
vendors | -0.002 |
iring | -0.002 |
Token | roller |
Token ID | 24471 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
ar | +0.004 |
t | +0.004 |
ake | +0.004 |
rd | +0.004 |
zed | +0.004 |
Neg logit contributions | |
nam | -0.003 |
ble | -0.003 |
iring | -0.003 |
efully | -0.003 |
uted | -0.003 |
Token | co |
Token ID | 1073 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
ake | +0.067 |
t | +0.067 |
payoff | +0.067 |
ever | +0.067 |
dreaming | +0.066 |
Neg logit contributions | |
ble | -0.096 |
uted | -0.094 |
bles | -0.090 |
efully | -0.090 |
iring | -0.089 |
Token | aster |
Token ID | 1603 |
Feature activation | -4.96e+00 |
Pos logit contributions | |
ar | +0.071 |
dreaming | +0.067 |
zed | +0.066 |
t | +0.065 |
minutes | +0.065 |
Neg logit contributions | |
nam | -0.075 |
iring | -0.072 |
ble | -0.071 |
uted | -0.071 |
efully | -0.070 |
Token | , |
Token ID | 11 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
ar | +0.148 |
ake | +0.147 |
zed | +0.147 |
da | +0.142 |
injuries | +0.142 |
Neg logit contributions | |
nam | -0.106 |
uted | -0.102 |
ble | -0.100 |
bles | -0.100 |
iring | -0.100 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
nam | +0.016 |
iring | +0.014 |
ble | +0.014 |
ot | +0.013 |
rad | +0.013 |
Neg logit contributions | |
ar | -0.014 |
ake | -0.013 |
rd | -0.013 |
zed | -0.013 |
t | -0.013 |
Token | shouted |
Token ID | 17293 |
Feature activation | -5.78e-01 |
Pos logit contributions | |
nam | +0.006 |
iring | +0.005 |
ble | +0.005 |
efully | +0.005 |
uted | +0.005 |
Neg logit contributions | |
ar | -0.006 |
zed | -0.006 |
t | -0.005 |
rd | -0.005 |
ake | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | -5.45e-01 |
Pos logit contributions | |
ar | +0.018 |
zed | +0.018 |
rd | +0.018 |
t | +0.018 |
minutes | +0.017 |
Neg logit contributions | |
nam | -0.014 |
ble | -0.013 |
iring | -0.013 |
uted | -0.013 |
efully | -0.012 |
Token | " |
Token ID | 366 |
Feature activation | -4.60e-01 |
Pos logit contributions | |
ar | +0.019 |
rd | +0.018 |
zed | +0.018 |
ake | +0.018 |
t | +0.018 |
Neg logit contributions | |
nam | -0.012 |
ble | -0.011 |
iring | -0.011 |
efully | -0.011 |
uted | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +7.74e-02 |
Pos logit contributions | |
rd | +0.002 |
zed | +0.002 |
ar | +0.002 |
basis | +0.002 |
seek | +0.002 |
Neg logit contributions | |
ble | -0.002 |
iring | -0.002 |
uted | -0.001 |
ishes | -0.001 |
ot | -0.001 |
Token | She |
Token ID | 1375 |
Feature activation | +5.02e-01 |
Pos logit contributions | |
nam | +0.002 |
ble | +0.002 |
iring | +0.002 |
ishes | +0.002 |
efully | +0.002 |
Neg logit contributions | |
ar | -0.002 |
t | -0.002 |
zed | -0.002 |
minutes | -0.002 |
dreaming | -0.002 |
Token | grabbed |
Token ID | 13176 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
nam | +0.016 |
iring | +0.016 |
ble | +0.015 |
efully | +0.015 |
ishes | +0.015 |
Neg logit contributions | |
ar | -0.012 |
zed | -0.012 |
t | -0.012 |
minutes | -0.012 |
ever | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | -9.57e-01 |
Pos logit contributions | |
nam | +0.005 |
ble | +0.004 |
iring | +0.004 |
efully | +0.004 |
ishes | +0.004 |
Neg logit contributions | |
ar | -0.005 |
rd | -0.005 |
zed | -0.005 |
t | -0.005 |
ake | -0.005 |
Token | to |
Token ID | 284 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
ar | +0.034 |
zed | +0.033 |
rd | +0.033 |
t | +0.032 |
ake | +0.032 |
Neg logit contributions | |
nam | -0.021 |
ble | -0.019 |
iring | -0.019 |
ishes | -0.018 |
uted | -0.017 |
Token | aster |
Token ID | 1603 |
Feature activation | -4.89e+00 |
Pos logit contributions | |
ar | +0.006 |
rd | +0.006 |
t | +0.005 |
ake | +0.005 |
zed | +0.005 |
Neg logit contributions | |
nam | -0.005 |
ble | -0.004 |
iring | -0.004 |
efully | -0.004 |
rad | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
ar | +0.180 |
t | +0.173 |
da | +0.169 |
basis | +0.168 |
rd | +0.167 |
Neg logit contributions | |
ble | -0.088 |
ins | -0.082 |
uted | -0.080 |
bles | -0.076 |
ishes | -0.075 |
Token | threw |
Token ID | 9617 |
Feature activation | +5.14e-01 |
Pos logit contributions | |
nam | +0.009 |
iring | +0.008 |
ble | +0.008 |
efully | +0.008 |
uted | +0.008 |
Neg logit contributions | |
ar | -0.007 |
zed | -0.007 |
t | -0.007 |
minutes | -0.007 |
rd | -0.007 |
Token | it |
Token ID | 340 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
nam | +0.014 |
efully | +0.013 |
ble | +0.013 |
iring | +0.013 |
ishes | +0.013 |
Neg logit contributions | |
ar | -0.015 |
rd | -0.015 |
zed | -0.015 |
t | -0.014 |
ake | -0.014 |
Token | in |
Token ID | 287 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
ar | +0.038 |
rd | +0.037 |
zed | +0.037 |
ake | +0.036 |
t | +0.035 |
Neg logit contributions | |
nam | -0.027 |
ble | -0.025 |
iring | -0.025 |
efully | -0.024 |
uted | -0.023 |
Token | the |
Token ID | 262 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
nam | +0.032 |
efully | +0.029 |
rad | +0.028 |
ble | +0.028 |
iring | +0.028 |
Neg logit contributions | |
ar | -0.058 |
zed | -0.056 |
t | -0.054 |
rd | -0.054 |
ake | -0.053 |
Token | toast |
Token ID | 27805 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
ar | +0.020 |
zed | +0.019 |
rd | +0.019 |
t | +0.019 |
ake | +0.019 |
Neg logit contributions | |
nam | -0.016 |
ble | -0.015 |
iring | -0.015 |
efully | -0.014 |
ishes | -0.014 |
Token | out |
Token ID | 503 |
Feature activation | -4.64e-01 |
Pos logit contributions | |
ar | +0.036 |
zed | +0.035 |
t | +0.034 |
rd | +0.034 |
minutes | +0.033 |
Neg logit contributions | |
nam | -0.036 |
ble | -0.034 |
iring | -0.034 |
efully | -0.033 |
uted | -0.032 |
Token | of |
Token ID | 286 |
Feature activation | -3.30e-02 |
Pos logit contributions | |
ar | +0.016 |
zed | +0.015 |
seek | +0.015 |
rd | +0.015 |
t | +0.014 |
Neg logit contributions | |
iring | -0.011 |
ble | -0.010 |
nam | -0.010 |
efully | -0.010 |
rad | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
ar | +0.001 |
t | +0.001 |
zed | +0.001 |
rd | +0.001 |
ake | +0.001 |
Neg logit contributions | |
nam | -0.001 |
iring | -0.001 |
ble | -0.001 |
efully | -0.001 |
uted | -0.001 |
Token | to |
Token ID | 284 |
Feature activation | -5.60e-01 |
Pos logit contributions | |
ar | +0.004 |
zed | +0.004 |
minutes | +0.004 |
ake | +0.004 |
t | +0.004 |
Neg logit contributions | |
nam | -0.004 |
iring | -0.004 |
ble | -0.004 |
efully | -0.004 |
uted | -0.004 |
Token | aster |
Token ID | 1603 |
Feature activation | -4.87e+00 |
Pos logit contributions | |
t | +0.010 |
ar | +0.009 |
rd | +0.009 |
ake | +0.008 |
zed | +0.008 |
Neg logit contributions | |
nam | -0.022 |
ble | -0.021 |
rad | -0.021 |
efully | -0.021 |
av | -0.021 |
Token | and |
Token ID | 290 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
ar | +0.155 |
t | +0.144 |
zed | +0.143 |
rd | +0.137 |
ake | +0.137 |
Neg logit contributions | |
ble | -0.108 |
nam | -0.106 |
uted | -0.105 |
iring | -0.103 |
efully | -0.103 |
Token | put |
Token ID | 1234 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
nam | +0.004 |
iring | +0.004 |
ble | +0.004 |
efully | +0.003 |
uted | +0.003 |
Neg logit contributions | |
ar | -0.003 |
zed | -0.003 |
t | -0.003 |
ake | -0.003 |
rd | -0.003 |
Token | it |
Token ID | 340 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
rd | +0.013 |
seek | +0.012 |
t | +0.012 |
ar | +0.012 |
zed | +0.012 |
Neg logit contributions | |
nam | -0.012 |
ishes | -0.011 |
efully | -0.011 |
ble | -0.011 |
rad | -0.011 |
Token | on |
Token ID | 319 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
ar | +0.004 |
zed | +0.004 |
rd | +0.004 |
t | +0.004 |
ake | +0.004 |
Neg logit contributions | |
nam | -0.004 |
ble | -0.004 |
iring | -0.003 |
efully | -0.003 |
ishes | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | -4.23e-01 |
Pos logit contributions | |
nam | +0.008 |
efully | +0.008 |
ble | +0.008 |
iring | +0.008 |
rad | +0.007 |
Neg logit contributions | |
ar | -0.010 |
t | -0.010 |
zed | -0.010 |
rd | -0.010 |
ake | -0.009 |
Token | some |
Token ID | 617 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
rd | +0.052 |
seek | +0.051 |
t | +0.051 |
ar | +0.051 |
zed | +0.050 |
Neg logit contributions | |
nam | -0.043 |
ishes | -0.039 |
ble | -0.037 |
efully | -0.037 |
av | -0.036 |
Token | bread |
Token ID | 8509 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
nam | +0.007 |
iring | +0.007 |
ble | +0.006 |
efully | +0.006 |
uted | +0.006 |
Neg logit contributions | |
ar | -0.008 |
minutes | -0.008 |
t | -0.008 |
zed | -0.008 |
ake | -0.008 |
Token | in |
Token ID | 287 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
nam | +0.040 |
iring | +0.038 |
ble | +0.038 |
efully | +0.037 |
ishes | +0.036 |
Neg logit contributions | |
ar | -0.040 |
zed | -0.040 |
rd | -0.038 |
t | -0.038 |
ake | -0.037 |
Token | the |
Token ID | 262 |
Feature activation | -3.55e-02 |
Pos logit contributions | |
nam | +0.030 |
rad | +0.026 |
ble | +0.026 |
iring | +0.024 |
av | +0.024 |
Neg logit contributions | |
ar | -0.053 |
zed | -0.052 |
rd | -0.051 |
t | -0.051 |
seek | -0.050 |
Token | to |
Token ID | 284 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
ar | +0.001 |
zed | +0.001 |
t | +0.001 |
rd | +0.001 |
ake | +0.001 |
Neg logit contributions | |
nam | -0.001 |
iring | -0.001 |
ble | -0.001 |
efully | -0.001 |
ishes | -0.001 |
Token | aster |
Token ID | 1603 |
Feature activation | -4.87e+00 |
Pos logit contributions | |
ar | +0.006 |
t | +0.005 |
rd | +0.005 |
ake | +0.005 |
zed | +0.005 |
Neg logit contributions | |
nam | -0.013 |
ble | -0.012 |
iring | -0.012 |
efully | -0.012 |
rad | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | +5.26e-01 |
Pos logit contributions | |
ar | +0.162 |
t | +0.155 |
zed | +0.151 |
da | +0.151 |
rd | +0.147 |
Neg logit contributions | |
ins | -0.093 |
ble | -0.092 |
nam | -0.091 |
ishes | -0.091 |
uted | -0.088 |
Token | He |
Token ID | 679 |
Feature activation | +5.00e-01 |
Pos logit contributions | |
nam | +0.017 |
iring | +0.016 |
ble | +0.016 |
efully | +0.016 |
ishes | +0.015 |
Neg logit contributions | |
ar | -0.013 |
t | -0.013 |
zed | -0.013 |
minutes | -0.012 |
rd | -0.012 |
Token | goes |
Token ID | 2925 |
Feature activation | -8.00e-01 |
Pos logit contributions | |
nam | +0.016 |
iring | +0.015 |
ble | +0.015 |
efully | +0.015 |
uted | +0.014 |
Neg logit contributions | |
ar | -0.012 |
zed | -0.012 |
t | -0.012 |
minutes | -0.011 |
rd | -0.011 |
Token | to |
Token ID | 284 |
Feature activation | -2.06e-02 |
Pos logit contributions | |
rd | +0.020 |
zed | +0.020 |
ar | +0.020 |
gh | +0.018 |
ake | +0.018 |
Neg logit contributions | |
nam | -0.025 |
ble | -0.024 |
iring | -0.024 |
bles | -0.023 |
efully | -0.023 |
Token | his |
Token ID | 465 |
Feature activation | -8.19e-01 |
Pos logit contributions | |
ar | +0.001 |
zed | +0.001 |
t | +0.001 |
rd | +0.001 |
ake | +0.001 |
Neg logit contributions | |
nam | -0.001 |
iring | -0.001 |
ble | -0.001 |
efully | -0.001 |
uted | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
rd | +0.012 |
ar | +0.011 |
seek | +0.011 |
t | +0.011 |
ake | +0.011 |
Neg logit contributions | |
nam | -0.010 |
ble | -0.009 |
ishes | -0.009 |
efully | -0.009 |
iring | -0.009 |
Token | bread |
Token ID | 8509 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
nam | +0.006 |
iring | +0.006 |
ble | +0.005 |
efully | +0.005 |
ishes | +0.005 |
Neg logit contributions | |
ar | -0.010 |
zed | -0.009 |
t | -0.009 |
rd | -0.009 |
ake | -0.009 |
Token | in |
Token ID | 287 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
nam | +0.047 |
iring | +0.045 |
efully | +0.044 |
uted | +0.043 |
ble | +0.042 |
Neg logit contributions | |
ar | -0.042 |
t | -0.041 |
zed | -0.040 |
ake | -0.040 |
ever | -0.039 |
Token | the |
Token ID | 262 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
nam | +0.044 |
ble | +0.040 |
iring | +0.039 |
rad | +0.038 |
efully | +0.038 |
Neg logit contributions | |
ar | -0.061 |
t | -0.059 |
zed | -0.058 |
rd | -0.057 |
ake | -0.056 |
Token | to |
Token ID | 284 |
Feature activation | -2.81e-02 |
Pos logit contributions | |
nam | +0.007 |
iring | +0.006 |
ble | +0.006 |
uted | +0.006 |
efully | +0.006 |
Neg logit contributions | |
ar | -0.007 |
zed | -0.007 |
t | -0.007 |
minutes | -0.007 |
ake | -0.007 |
Token | aster |
Token ID | 1603 |
Feature activation | -4.83e+00 |
Pos logit contributions | |
ar | +0.000 |
t | +0.000 |
zed | +0.000 |
rd | +0.000 |
ake | +0.000 |
Neg logit contributions | |
nam | -0.001 |
ble | -0.001 |
iring | -0.001 |
efully | -0.001 |
uted | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | +7.05e-01 |
Pos logit contributions | |
ar | +0.161 |
t | +0.152 |
zed | +0.149 |
da | +0.148 |
basis | +0.146 |
Neg logit contributions | |
ble | -0.095 |
ins | -0.092 |
nam | -0.091 |
uted | -0.089 |
ishes | -0.087 |
Token | pushed |
Token ID | 7121 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
nam | +0.022 |
iring | +0.022 |
ble | +0.021 |
efully | +0.021 |
uted | +0.020 |
Neg logit contributions | |
ar | -0.018 |
zed | -0.017 |
t | -0.017 |
minutes | -0.016 |
dreaming | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | +5.81e-01 |
Pos logit contributions | |
ar | +0.000 |
zed | +0.000 |
t | +0.000 |
rd | +0.000 |
ake | +0.000 |
Neg logit contributions | |
nam | -0.000 |
ble | -0.000 |
iring | -0.000 |
efully | -0.000 |
uted | -0.000 |
Token | button |
Token ID | 4936 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
nam | +0.015 |
iring | +0.014 |
efully | +0.014 |
ble | +0.014 |
uted | +0.014 |
Neg logit contributions | |
ar | -0.017 |
zed | -0.017 |
t | -0.017 |
ake | -0.017 |
minutes | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | +8.96e-01 |
Pos logit contributions | |
ar | +0.038 |
zed | +0.038 |
rd | +0.038 |
ake | +0.037 |
basis | +0.036 |
Neg logit contributions | |
nam | -0.031 |
ble | -0.030 |
iring | -0.029 |
efully | -0.028 |
bles | -0.028 |
Token | just |
Token ID | 655 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
ar | +0.012 |
t | +0.012 |
zed | +0.012 |
rd | +0.011 |
ake | +0.011 |
Neg logit contributions | |
nam | -0.014 |
efully | -0.013 |
ble | -0.013 |
iring | -0.013 |
uted | -0.012 |
Token | stuck |
Token ID | 7819 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
ar | +0.037 |
t | +0.035 |
zed | +0.035 |
ake | +0.034 |
rd | +0.034 |
Neg logit contributions | |
nam | -0.044 |
efully | -0.040 |
ble | -0.039 |
iring | -0.038 |
rad | -0.037 |
Token | with |
Token ID | 351 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
nam | +0.005 |
ble | +0.004 |
iring | +0.004 |
efully | +0.004 |
ishes | +0.004 |
Neg logit contributions | |
ar | -0.005 |
zed | -0.005 |
rd | -0.005 |
t | -0.005 |
ake | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | -6.17e-01 |
Pos logit contributions | |
nam | +0.005 |
ishes | +0.004 |
efully | +0.004 |
rad | +0.004 |
iring | +0.004 |
Neg logit contributions | |
ar | -0.007 |
t | -0.007 |
ake | -0.006 |
rd | -0.006 |
zed | -0.006 |
Token | to |
Token ID | 284 |
Feature activation | -4.15e-01 |
Pos logit contributions | |
ar | +0.019 |
zed | +0.019 |
t | +0.019 |
rd | +0.019 |
ake | +0.018 |
Neg logit contributions | |
nam | -0.016 |
iring | -0.014 |
ble | -0.014 |
efully | -0.014 |
ishes | -0.013 |
Token | aster |
Token ID | 1603 |
Feature activation | -4.80e+00 |
Pos logit contributions | |
ar | +0.014 |
rd | +0.013 |
t | +0.013 |
ake | +0.013 |
zed | +0.013 |
Neg logit contributions | |
nam | -0.010 |
ble | -0.009 |
iring | -0.009 |
ot | -0.009 |
rad | -0.008 |
Token | in |
Token ID | 287 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
ar | +0.143 |
da | +0.138 |
zed | +0.136 |
ake | +0.133 |
t | +0.129 |
Neg logit contributions | |
nam | -0.110 |
uted | -0.104 |
ishes | -0.103 |
ins | -0.102 |
iring | -0.101 |
Token | their |
Token ID | 511 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
nam | +0.022 |
rad | +0.019 |
efully | +0.019 |
ble | +0.019 |
iring | +0.018 |
Neg logit contributions | |
seek | -0.060 |
ar | -0.060 |
zed | -0.058 |
t | -0.057 |
rd | -0.056 |
Token | modern |
Token ID | 3660 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
t | +0.037 |
ar | +0.036 |
zed | +0.035 |
ake | +0.034 |
rd | +0.034 |
Neg logit contributions | |
nam | -0.025 |
ishes | -0.022 |
efully | -0.022 |
iring | -0.022 |
rad | -0.021 |
Token | home |
Token ID | 1363 |
Feature activation | -6.48e-01 |
Pos logit contributions | |
t | +0.017 |
ar | +0.017 |
zed | +0.016 |
ever | +0.015 |
da | +0.015 |
Neg logit contributions | |
nam | -0.010 |
ishes | -0.010 |
rad | -0.010 |
efully | -0.009 |
av | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
ar | +0.020 |
zed | +0.019 |
ake | +0.019 |
t | +0.018 |
da | +0.018 |
Neg logit contributions | |
nam | -0.017 |
iring | -0.016 |
ble | -0.016 |
bles | -0.014 |
efully | -0.014 |
Token | more |
Token ID | 517 |
Feature activation | -5.54e-01 |
Pos logit contributions | |
rd | +0.019 |
ar | +0.019 |
t | +0.019 |
zed | +0.019 |
ake | +0.018 |
Neg logit contributions | |
nam | -0.022 |
efully | -0.020 |
ble | -0.020 |
ishes | -0.020 |
iring | -0.020 |
Token | bread |
Token ID | 8509 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
ar | +0.017 |
zed | +0.016 |
t | +0.016 |
ake | +0.016 |
rd | +0.016 |
Neg logit contributions | |
nam | -0.015 |
iring | -0.014 |
ble | -0.014 |
efully | -0.013 |
ishes | -0.013 |
Token | in |
Token ID | 287 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
nam | +0.050 |
iring | +0.047 |
ble | +0.046 |
efully | +0.045 |
ishes | +0.045 |
Neg logit contributions | |
ar | -0.052 |
zed | -0.051 |
t | -0.050 |
rd | -0.050 |
ake | -0.049 |
Token | the |
Token ID | 262 |
Feature activation | -3.32e-02 |
Pos logit contributions | |
nam | +0.027 |
ble | +0.023 |
rad | +0.023 |
efully | +0.022 |
av | +0.022 |
Neg logit contributions | |
ar | -0.040 |
zed | -0.039 |
t | -0.039 |
rd | -0.039 |
seek | -0.038 |
Token | to |
Token ID | 284 |
Feature activation | -5.84e-01 |
Pos logit contributions | |
ar | +0.001 |
zed | +0.001 |
t | +0.001 |
rd | +0.001 |
ake | +0.001 |
Neg logit contributions | |
nam | -0.001 |
iring | -0.001 |
ble | -0.001 |
efully | -0.001 |
ishes | -0.001 |
Token | aster |
Token ID | 1603 |
Feature activation | -4.79e+00 |
Pos logit contributions | |
t | +0.010 |
ar | +0.010 |
rd | +0.009 |
ake | +0.009 |
zed | +0.009 |
Neg logit contributions | |
nam | -0.023 |
ble | -0.022 |
rad | -0.022 |
efully | -0.021 |
av | -0.021 |
Token | and |
Token ID | 290 |
Feature activation | -5.06e-02 |
Pos logit contributions | |
ar | +0.155 |
t | +0.153 |
da | +0.148 |
basis | +0.148 |
rd | +0.147 |
Neg logit contributions | |
ins | -0.099 |
ishes | -0.098 |
ble | -0.095 |
nam | -0.093 |
av | -0.091 |
Token | turned |
Token ID | 2900 |
Feature activation | -2.42e-02 |
Pos logit contributions | |
ar | +0.001 |
t | +0.001 |
rd | +0.001 |
ake | +0.001 |
zed | +0.001 |
Neg logit contributions | |
nam | -0.002 |
ble | -0.001 |
efully | -0.001 |
iring | -0.001 |
ishes | -0.001 |
Token | it |
Token ID | 340 |
Feature activation | -8.80e-01 |
Pos logit contributions | |
ar | +0.001 |
zed | +0.001 |
t | +0.001 |
rd | +0.001 |
ake | +0.001 |
Neg logit contributions | |
nam | -0.001 |
iring | -0.001 |
ble | -0.001 |
efully | -0.001 |
ishes | -0.001 |
Token | on |
Token ID | 319 |
Feature activation | +6.19e-01 |
Pos logit contributions | |
ar | +0.024 |
zed | +0.023 |
rd | +0.023 |
t | +0.023 |
ake | +0.022 |
Neg logit contributions | |
nam | -0.026 |
iring | -0.024 |
ble | -0.024 |
efully | -0.024 |
ishes | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
nam | +0.016 |
iring | +0.015 |
efully | +0.014 |
ble | +0.014 |
rad | +0.014 |
Neg logit contributions | |
ar | -0.020 |
zed | -0.019 |
t | -0.019 |
rd | -0.019 |
seek | -0.018 |
Token | saw |
Token ID | 2497 |
Feature activation | -6.63e-01 |
Pos logit contributions | |
ar | +0.004 |
zed | +0.004 |
t | +0.004 |
rd | +0.004 |
ake | +0.004 |
Neg logit contributions | |
nam | -0.005 |
efully | -0.004 |
ble | -0.004 |
iring | -0.004 |
ishes | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
ar | +0.018 |
ake | +0.018 |
t | +0.018 |
zed | +0.017 |
rd | +0.017 |
Neg logit contributions | |
nam | -0.020 |
ble | -0.018 |
iring | -0.018 |
efully | -0.018 |
uted | -0.017 |
Token | different |
Token ID | 1180 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
nam | +0.011 |
efully | +0.011 |
iring | +0.011 |
uted | +0.010 |
ishes | +0.010 |
Neg logit contributions | |
ar | -0.011 |
t | -0.010 |
minutes | -0.010 |
dreaming | -0.010 |
ake | -0.010 |
Token | roller |
Token ID | 24471 |
Feature activation | -3.30e+00 |
Pos logit contributions | |
ar | +0.003 |
rd | +0.003 |
moment | +0.003 |
ake | +0.003 |
minutes | +0.003 |
Neg logit contributions | |
nam | -0.004 |
iring | -0.003 |
efully | -0.003 |
ishes | -0.003 |
uted | -0.003 |
Token | co |
Token ID | 1073 |
Feature activation | -2.93e+00 |
Pos logit contributions | |
minutes | +0.072 |
t | +0.072 |
rd | +0.072 |
payoff | +0.071 |
ake | +0.070 |
Neg logit contributions | |
ble | -0.106 |
nam | -0.093 |
uted | -0.092 |
bles | -0.092 |
iring | -0.091 |
Token | aster |
Token ID | 1603 |
Feature activation | -4.76e+00 |
Pos logit contributions | |
ar | +0.081 |
zed | +0.076 |
minutes | +0.075 |
dreaming | +0.074 |
t | +0.073 |
Neg logit contributions | |
nam | -0.082 |
ble | -0.077 |
iring | -0.076 |
uted | -0.075 |
ins | -0.071 |
Token | - |
Token ID | 12 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
ar | +0.170 |
da | +0.165 |
zed | +0.160 |
basis | +0.157 |
payoff | +0.153 |
Neg logit contributions | |
nam | -0.094 |
ble | -0.088 |
uted | -0.085 |
iring | -0.079 |
av | -0.078 |
Token | like |
Token ID | 2339 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
dreaming | +0.037 |
zed | +0.037 |
ar | +0.037 |
minutes | +0.037 |
injuries | +0.036 |
Neg logit contributions | |
nam | -0.037 |
iring | -0.035 |
ble | -0.035 |
efully | -0.034 |
uted | -0.034 |
Token | ride |
Token ID | 6594 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
t | +0.006 |
ar | +0.006 |
zed | +0.006 |
rd | +0.006 |
seek | +0.006 |
Neg logit contributions | |
nam | -0.006 |
ble | -0.006 |
iring | -0.005 |
rad | -0.005 |
ot | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -5.58e-02 |
Pos logit contributions | |
ar | +0.044 |
zed | +0.044 |
rd | +0.042 |
minutes | +0.042 |
ake | +0.042 |
Neg logit contributions | |
nam | -0.040 |
iring | -0.037 |
ble | -0.036 |
efully | -0.035 |
uted | -0.035 |
Token |
|
Token ID | 198 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
ar | +0.002 |
zed | +0.002 |
t | +0.002 |
ake | +0.002 |
rd | +0.002 |
Neg logit contributions | |
nam | -0.001 |
iring | -0.001 |
efully | -0.001 |
ble | -0.001 |
uted | -0.001 |
Token | looking |
Token ID | 2045 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
ar | +0.016 |
t | +0.016 |
rd | +0.015 |
zed | +0.015 |
ake | +0.015 |
Neg logit contributions | |
nam | -0.015 |
iring | -0.014 |
ble | -0.013 |
uted | -0.013 |
efully | -0.013 |
Token | at |
Token ID | 379 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
nam | +0.009 |
ble | +0.008 |
efully | +0.008 |
iring | +0.008 |
uted | +0.008 |
Neg logit contributions | |
minutes | -0.005 |
ar | -0.005 |
dreaming | -0.005 |
zed | -0.005 |
t | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
ar | +0.010 |
t | +0.009 |
zed | +0.009 |
rd | +0.009 |
ake | +0.009 |
Neg logit contributions | |
nam | -0.007 |
iring | -0.006 |
efully | -0.006 |
ble | -0.006 |
ishes | -0.006 |
Token | burnt |
Token ID | 22999 |
Feature activation | +2.91e-01 |
Pos logit contributions | |
nam | +0.007 |
iring | +0.007 |
ble | +0.007 |
efully | +0.007 |
uted | +0.006 |
Neg logit contributions | |
ar | -0.008 |
zed | -0.008 |
t | -0.008 |
rd | -0.008 |
ake | -0.008 |
Token | to |
Token ID | 284 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
nam | +0.008 |
iring | +0.007 |
ble | +0.007 |
efully | +0.007 |
uted | +0.007 |
Neg logit contributions | |
ar | -0.009 |
zed | -0.008 |
t | -0.008 |
rd | -0.008 |
ake | -0.008 |
Token | aster |
Token ID | 1603 |
Feature activation | -4.70e+00 |
Pos logit contributions | |
ar | +0.005 |
t | +0.004 |
zed | +0.004 |
ake | +0.004 |
rd | +0.004 |
Neg logit contributions | |
nam | -0.004 |
ble | -0.004 |
iring | -0.003 |
rad | -0.003 |
efully | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
ar | +0.169 |
da | +0.166 |
t | +0.163 |
zed | +0.161 |
basis | +0.161 |
Neg logit contributions | |
ble | -0.081 |
uted | -0.079 |
ins | -0.077 |
iring | -0.074 |
ducks | -0.070 |
Token | They |
Token ID | 1119 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
ar | +0.004 |
t | +0.004 |
zed | +0.004 |
minutes | +0.004 |
rd | +0.004 |
Neg logit contributions | |
nam | -0.004 |
ble | -0.004 |
iring | -0.004 |
efully | -0.004 |
ishes | -0.004 |
Token | smelled |
Token ID | 37609 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
ever | +0.007 |
ar | +0.007 |
dreaming | +0.007 |
minutes | +0.007 |
t | +0.007 |
Neg logit contributions | |
iring | -0.012 |
nam | -0.011 |
ble | -0.011 |
efully | -0.011 |
ishes | -0.011 |
Token | something |
Token ID | 1223 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
nam | +0.013 |
iring | +0.012 |
efully | +0.012 |
ble | +0.012 |
uted | +0.012 |
Neg logit contributions | |
ar | -0.008 |
zed | -0.008 |
minutes | -0.008 |
dreaming | -0.008 |
ake | -0.008 |
Token | bad |
Token ID | 2089 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
ar | +0.016 |
zed | +0.015 |
rd | +0.015 |
seek | +0.015 |
t | +0.015 |
Neg logit contributions | |
nam | -0.013 |
iring | -0.013 |
ble | -0.013 |
rad | -0.012 |
uted | -0.012 |
Token | white |
Token ID | 2330 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
nam | +0.013 |
iring | +0.012 |
ishes | +0.012 |
efully | +0.011 |
av | +0.011 |
Neg logit contributions | |
ar | -0.017 |
t | -0.017 |
zed | -0.017 |
ake | -0.017 |
rd | -0.016 |
Token | bread |
Token ID | 8509 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
zed | +0.012 |
t | +0.011 |
ar | +0.011 |
rd | +0.011 |
ake | +0.011 |
Neg logit contributions | |
nam | -0.007 |
ishes | -0.007 |
efully | -0.007 |
iring | -0.006 |
rad | -0.006 |
Token | into |
Token ID | 656 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
nam | +0.041 |
iring | +0.039 |
ble | +0.038 |
efully | +0.038 |
ishes | +0.037 |
Neg logit contributions | |
ar | -0.036 |
zed | -0.035 |
t | -0.034 |
rd | -0.034 |
ake | -0.034 |
Token | the |
Token ID | 262 |
Feature activation | +4.91e-02 |
Pos logit contributions | |
nam | +0.044 |
efully | +0.039 |
iring | +0.039 |
ble | +0.039 |
rad | +0.038 |
Neg logit contributions | |
ar | -0.046 |
t | -0.045 |
zed | -0.044 |
rd | -0.043 |
ake | -0.043 |
Token | to |
Token ID | 284 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
nam | +0.001 |
iring | +0.001 |
efully | +0.001 |
ble | +0.001 |
ishes | +0.001 |
Neg logit contributions | |
ar | -0.002 |
zed | -0.002 |
t | -0.002 |
rd | -0.002 |
ake | -0.002 |
Token | aster |
Token ID | 1603 |
Feature activation | -4.69e+00 |
Pos logit contributions | |
t | +0.013 |
ar | +0.012 |
rd | +0.012 |
zed | +0.012 |
ake | +0.012 |
Neg logit contributions | |
nam | -0.016 |
ble | -0.015 |
efully | -0.015 |
rad | -0.015 |
iring | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
ar | +0.136 |
zed | +0.130 |
t | +0.128 |
ake | +0.123 |
rd | +0.123 |
Neg logit contributions | |
nam | -0.121 |
ble | -0.115 |
iring | -0.113 |
efully | -0.113 |
ishes | -0.111 |
Token | She |
Token ID | 1375 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
nam | +0.009 |
ble | +0.009 |
iring | +0.009 |
uted | +0.008 |
ishes | +0.008 |
Neg logit contributions | |
ar | -0.008 |
zed | -0.008 |
t | -0.008 |
ake | -0.008 |
rd | -0.008 |
Token | saw |
Token ID | 2497 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
nam | +0.008 |
iring | +0.007 |
ble | +0.007 |
efully | +0.007 |
uted | +0.007 |
Neg logit contributions | |
ar | -0.008 |
zed | -0.008 |
t | -0.008 |
ake | -0.007 |
rd | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
ar | +0.030 |
t | +0.029 |
zed | +0.029 |
rd | +0.028 |
ake | +0.028 |
Neg logit contributions | |
nam | -0.033 |
iring | -0.031 |
ble | -0.030 |
efully | -0.030 |
uted | -0.029 |
Token | glowing |
Token ID | 21377 |
Feature activation | -6.22e-01 |
Pos logit contributions | |
ar | +0.012 |
zed | +0.012 |
t | +0.012 |
rd | +0.011 |
ake | +0.011 |
Neg logit contributions | |
nam | -0.010 |
iring | -0.009 |
ble | -0.009 |
efully | -0.008 |
ishes | -0.008 |
Token | of |
Token ID | 286 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
ble | +0.042 |
nam | +0.042 |
iring | +0.040 |
efully | +0.039 |
bles | +0.039 |
Neg logit contributions | |
zed | -0.060 |
ar | -0.059 |
rd | -0.059 |
basis | -0.057 |
seek | -0.056 |
Token | bread |
Token ID | 8509 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
nam | +0.009 |
iring | +0.009 |
ble | +0.009 |
efully | +0.008 |
ishes | +0.008 |
Neg logit contributions | |
ar | -0.011 |
zed | -0.011 |
t | -0.011 |
rd | -0.011 |
ake | -0.011 |
Token | in |
Token ID | 287 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
nam | +0.044 |
ble | +0.042 |
iring | +0.041 |
ishes | +0.041 |
efully | +0.040 |
Neg logit contributions | |
zed | -0.046 |
ar | -0.046 |
rd | -0.045 |
t | -0.045 |
ake | -0.044 |
Token | the |
Token ID | 262 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
nam | +0.035 |
efully | +0.030 |
ble | +0.029 |
rad | +0.029 |
iring | +0.028 |
Neg logit contributions | |
ar | -0.052 |
zed | -0.050 |
rd | -0.050 |
seek | -0.049 |
t | -0.049 |
Token | to |
Token ID | 284 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
nam | +0.007 |
efully | +0.006 |
iring | +0.006 |
ble | +0.006 |
ishes | +0.006 |
Neg logit contributions | |
ar | -0.007 |
t | -0.007 |
zed | -0.007 |
ake | -0.007 |
rd | -0.007 |
Token | aster |
Token ID | 1603 |
Feature activation | -4.66e+00 |
Pos logit contributions | |
t | +0.005 |
ar | +0.005 |
rd | +0.005 |
ake | +0.004 |
zed | +0.004 |
Neg logit contributions | |
nam | -0.013 |
ble | -0.013 |
efully | -0.012 |
rad | -0.012 |
iring | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
ar | +0.159 |
t | +0.154 |
da | +0.152 |
zed | +0.147 |
rd | +0.147 |
Neg logit contributions | |
ins | -0.086 |
nam | -0.084 |
ble | -0.083 |
ishes | -0.080 |
uted | -0.080 |
Token | pushed |
Token ID | 7121 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
nam | +0.011 |
ble | +0.010 |
iring | +0.010 |
efully | +0.010 |
ishes | +0.009 |
Neg logit contributions | |
ar | -0.010 |
t | -0.010 |
zed | -0.009 |
rd | -0.009 |
ake | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | +7.48e-01 |
Pos logit contributions | |
ar | +0.004 |
zed | +0.004 |
rd | +0.004 |
t | +0.004 |
dreaming | +0.004 |
Neg logit contributions | |
nam | -0.004 |
efully | -0.004 |
ble | -0.004 |
iring | -0.004 |
ishes | -0.004 |
Token | lever |
Token ID | 17124 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
nam | +0.020 |
ble | +0.018 |
iring | +0.018 |
av | +0.017 |
efully | +0.017 |
Neg logit contributions | |
ar | -0.024 |
zed | -0.022 |
rd | -0.022 |
ake | -0.022 |
t | -0.021 |
Token | down |
Token ID | 866 |
Feature activation | +5.85e-01 |
Pos logit contributions | |
rd | +0.042 |
zed | +0.041 |
ar | +0.041 |
ake | +0.038 |
basis | +0.038 |
Neg logit contributions | |
ble | -0.035 |
nam | -0.034 |
iring | -0.033 |
ishes | -0.032 |
efully | -0.032 |
Token | She |
Token ID | 1375 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
t | +0.003 |
ar | +0.003 |
zed | +0.003 |
seek | +0.003 |
rd | +0.003 |
Neg logit contributions | |
nam | -0.004 |
ble | -0.004 |
ishes | -0.003 |
bles | -0.003 |
iring | -0.003 |
Token | turned |
Token ID | 2900 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
nam | +0.015 |
iring | +0.014 |
ble | +0.013 |
ying | +0.013 |
ishes | +0.013 |
Neg logit contributions | |
ever | -0.010 |
minutes | -0.010 |
ar | -0.010 |
zed | -0.010 |
t | -0.010 |
Token | off |
Token ID | 572 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
ar | +0.009 |
rd | +0.009 |
zed | +0.009 |
seek | +0.009 |
ake | +0.008 |
Neg logit contributions | |
nam | -0.008 |
iring | -0.008 |
ble | -0.008 |
efully | -0.008 |
ishes | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
nam | +0.024 |
rad | +0.023 |
av | +0.023 |
iring | +0.022 |
efully | +0.021 |
Neg logit contributions | |
rd | -0.049 |
ar | -0.048 |
ake | -0.048 |
seek | -0.047 |
zed | -0.046 |
Token | to |
Token ID | 284 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
ar | +0.010 |
zed | +0.009 |
rd | +0.009 |
seek | +0.009 |
ake | +0.009 |
Neg logit contributions | |
nam | -0.007 |
ble | -0.006 |
iring | -0.006 |
rad | -0.006 |
uted | -0.006 |
Token | aster |
Token ID | 1603 |
Feature activation | -4.64e+00 |
Pos logit contributions | |
nam | +0.009 |
iring | +0.008 |
ble | +0.008 |
efully | +0.008 |
uted | +0.008 |
Neg logit contributions | |
ar | -0.009 |
t | -0.008 |
zed | -0.008 |
rd | -0.008 |
ake | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | +7.23e-01 |
Pos logit contributions | |
ar | +0.181 |
da | +0.178 |
rd | +0.174 |
t | +0.171 |
zed | +0.170 |
Neg logit contributions | |
uted | -0.058 |
av | -0.054 |
ble | -0.054 |
ins | -0.052 |
ot | -0.050 |
Token | opened |
Token ID | 4721 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
iring | +0.019 |
nam | +0.018 |
ble | +0.018 |
efully | +0.017 |
bles | +0.017 |
Neg logit contributions | |
ar | -0.022 |
zed | -0.022 |
minutes | -0.021 |
ever | -0.021 |
dreaming | -0.021 |
Token | the |
Token ID | 262 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
nam | +0.027 |
ble | +0.026 |
iring | +0.026 |
efully | +0.025 |
rad | +0.024 |
Neg logit contributions | |
ar | -0.031 |
t | -0.030 |
rd | -0.030 |
zed | -0.029 |
ake | -0.029 |
Token | window |
Token ID | 4324 |
Feature activation | -8.02e-01 |
Pos logit contributions | |
nam | +0.006 |
iring | +0.005 |
ble | +0.005 |
efully | +0.005 |
uted | +0.005 |
Neg logit contributions | |
ar | -0.008 |
zed | -0.007 |
t | -0.007 |
rd | -0.007 |
ake | -0.007 |
Token | to |
Token ID | 284 |
Feature activation | +7.10e-01 |
Pos logit contributions | |
zed | +0.029 |
ar | +0.028 |
gh | +0.027 |
ake | +0.026 |
basis | +0.026 |
Neg logit contributions | |
iring | -0.018 |
ble | -0.015 |
efully | -0.015 |
nam | -0.015 |
uted | -0.014 |
Token | put |
Token ID | 1234 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
nam | +0.016 |
ble | +0.014 |
efully | +0.014 |
ishes | +0.014 |
rad | +0.014 |
Neg logit contributions | |
ar | -0.017 |
t | -0.016 |
rd | -0.016 |
ake | -0.016 |
zed | -0.015 |
Token | it |
Token ID | 340 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
rd | +0.009 |
t | +0.009 |
seek | +0.009 |
ar | +0.009 |
zed | +0.009 |
Neg logit contributions | |
nam | -0.008 |
efully | -0.008 |
ishes | -0.008 |
ble | -0.008 |
av | -0.008 |
Token | in |
Token ID | 287 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
ar | +0.006 |
rd | +0.006 |
t | +0.006 |
zed | +0.006 |
ake | +0.006 |
Neg logit contributions | |
nam | -0.004 |
ble | -0.003 |
iring | -0.003 |
ishes | -0.003 |
efully | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
nam | +0.046 |
rad | +0.041 |
efully | +0.040 |
ble | +0.040 |
av | +0.039 |
Neg logit contributions | |
ar | -0.069 |
t | -0.066 |
zed | -0.064 |
rd | -0.064 |
seek | -0.063 |
Token | to |
Token ID | 284 |
Feature activation | -8.82e-02 |
Pos logit contributions | |
nam | +0.006 |
iring | +0.006 |
ble | +0.006 |
efully | +0.005 |
uted | +0.005 |
Neg logit contributions | |
ar | -0.007 |
zed | -0.007 |
t | -0.007 |
ake | -0.007 |
rd | -0.007 |
Token | aster |
Token ID | 1603 |
Feature activation | -4.64e+00 |
Pos logit contributions | |
ar | +0.001 |
t | +0.001 |
rd | +0.001 |
ake | +0.001 |
zed | +0.001 |
Neg logit contributions | |
nam | -0.004 |
ble | -0.003 |
iring | -0.003 |
efully | -0.003 |
rad | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +4.94e-01 |
Pos logit contributions | |
ar | +0.141 |
t | +0.135 |
zed | +0.132 |
da | +0.128 |
ake | +0.128 |
Neg logit contributions | |
nam | -0.106 |
ishes | -0.104 |
ins | -0.103 |
ble | -0.102 |
av | -0.101 |
Token | Then |
Token ID | 3244 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
nam | +0.014 |
ble | +0.013 |
iring | +0.013 |
ishes | +0.013 |
efully | +0.013 |
Neg logit contributions | |
ar | -0.014 |
zed | -0.014 |
t | -0.014 |
rd | -0.013 |
ake | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
nam | +0.029 |
efully | +0.027 |
rad | +0.026 |
ble | +0.026 |
ishes | +0.026 |
Neg logit contributions | |
ake | -0.032 |
t | -0.032 |
rd | -0.031 |
ar | -0.031 |
seek | -0.030 |
Token | she |
Token ID | 673 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
nam | +0.009 |
iring | +0.008 |
ble | +0.008 |
efully | +0.008 |
uted | +0.008 |
Neg logit contributions | |
ar | -0.007 |
zed | -0.007 |
t | -0.007 |
ake | -0.007 |
rd | -0.007 |
Token | went |
Token ID | 1816 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
ar | +0.006 |
zed | +0.006 |
t | +0.005 |
minutes | +0.005 |
ake | +0.005 |
Neg logit contributions | |
nam | -0.007 |
iring | -0.006 |
ble | -0.006 |
efully | -0.006 |
uted | -0.006 |
Token | flames |
Token ID | 16209 |
Feature activation | +6.79e-01 |
Pos logit contributions | |
ar | +0.013 |
ake | +0.012 |
t | +0.012 |
rd | +0.012 |
zed | +0.012 |
Neg logit contributions | |
nam | -0.009 |
ble | -0.008 |
iring | -0.007 |
efully | -0.007 |
ot | -0.007 |
Token | coming |
Token ID | 2406 |
Feature activation | +5.77e-01 |
Pos logit contributions | |
ble | +0.017 |
iring | +0.016 |
uted | +0.016 |
ot | +0.015 |
rad | +0.015 |
Neg logit contributions | |
rd | -0.021 |
ar | -0.021 |
zed | -0.020 |
seek | -0.019 |
t | -0.019 |
Token | from |
Token ID | 422 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
nam | +0.016 |
efully | +0.014 |
iring | +0.014 |
uted | +0.014 |
ishes | +0.014 |
Neg logit contributions | |
t | -0.017 |
ever | -0.017 |
ar | -0.016 |
ake | -0.016 |
minutes | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
nam | +0.060 |
iring | +0.056 |
ble | +0.055 |
efully | +0.054 |
uted | +0.053 |
Neg logit contributions | |
ar | -0.062 |
zed | -0.060 |
t | -0.060 |
rd | -0.058 |
ake | -0.058 |
Token | to |
Token ID | 284 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
ar | +0.015 |
zed | +0.015 |
t | +0.014 |
rd | +0.014 |
ake | +0.014 |
Neg logit contributions | |
nam | -0.009 |
iring | -0.008 |
ble | -0.008 |
rad | -0.008 |
ot | -0.008 |
Token | aster |
Token ID | 1603 |
Feature activation | -4.62e+00 |
Pos logit contributions | |
nam | +0.002 |
ble | +0.002 |
iring | +0.002 |
efully | +0.002 |
rad | +0.002 |
Neg logit contributions | |
ar | -0.004 |
t | -0.004 |
rd | -0.004 |
ake | -0.003 |
zed | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
ar | +0.170 |
da | +0.159 |
zed | +0.156 |
t | +0.152 |
basis | +0.150 |
Neg logit contributions | |
uted | -0.076 |
ble | -0.073 |
ins | -0.068 |
iring | -0.067 |
vendors | -0.064 |
Token | Their |
Token ID | 5334 |
Feature activation | -8.71e-01 |
Pos logit contributions | |
nam | +0.005 |
ble | +0.005 |
iring | +0.005 |
efully | +0.004 |
ishes | +0.004 |
Neg logit contributions | |
ar | -0.005 |
t | -0.005 |
zed | -0.005 |
minutes | -0.005 |
ake | -0.005 |
Token | mom |
Token ID | 1995 |
Feature activation | -4.95e-01 |
Pos logit contributions | |
ar | +0.031 |
t | +0.030 |
zed | +0.030 |
rd | +0.029 |
ake | +0.029 |
Neg logit contributions | |
nam | -0.018 |
iring | -0.018 |
ble | -0.017 |
efully | -0.016 |
ishes | -0.016 |
Token | is |
Token ID | 318 |
Feature activation | -8.21e-01 |
Pos logit contributions | |
zed | +0.015 |
ar | +0.015 |
t | +0.015 |
rd | +0.014 |
ake | +0.014 |
Neg logit contributions | |
iring | -0.012 |
efully | -0.012 |
uted | -0.012 |
nam | -0.012 |
ishes | -0.012 |
Token | trying |
Token ID | 2111 |
Feature activation | +4.16e-01 |
Pos logit contributions | |
ar | +0.026 |
zed | +0.025 |
t | +0.025 |
rd | +0.025 |
ake | +0.024 |
Neg logit contributions | |
nam | -0.021 |
iring | -0.020 |
ble | -0.019 |
efully | -0.019 |
uted | -0.018 |
Token | put |
Token ID | 1234 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
nam | +0.016 |
iring | +0.015 |
ble | +0.015 |
efully | +0.015 |
uted | +0.014 |
Neg logit contributions | |
ar | -0.012 |
zed | -0.012 |
t | -0.011 |
minutes | -0.011 |
ake | -0.011 |
Token | it |
Token ID | 340 |
Feature activation | -5.82e-01 |
Pos logit contributions | |
ar | +0.009 |
zed | +0.008 |
t | +0.008 |
rd | +0.008 |
ake | +0.008 |
Neg logit contributions | |
nam | -0.011 |
iring | -0.010 |
ble | -0.010 |
efully | -0.010 |
ishes | -0.010 |
Token | in |
Token ID | 287 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
ar | +0.017 |
zed | +0.017 |
rd | +0.016 |
t | +0.016 |
ake | +0.016 |
Neg logit contributions | |
nam | -0.016 |
iring | -0.015 |
ble | -0.015 |
efully | -0.014 |
ishes | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | +2.89e-02 |
Pos logit contributions | |
nam | +0.047 |
ble | +0.041 |
iring | +0.041 |
efully | +0.041 |
rad | +0.039 |
Neg logit contributions | |
ar | -0.051 |
zed | -0.049 |
t | -0.048 |
rd | -0.048 |
ake | -0.047 |
Token | to |
Token ID | 284 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
nam | +0.001 |
iring | +0.001 |
uted | +0.001 |
ble | +0.001 |
efully | +0.001 |
Neg logit contributions | |
ar | -0.001 |
minutes | -0.001 |
zed | -0.001 |
ake | -0.001 |
t | -0.001 |
Token | aster |
Token ID | 1603 |
Feature activation | -4.62e+00 |
Pos logit contributions | |
ar | +0.008 |
t | +0.007 |
zed | +0.007 |
rd | +0.007 |
ake | +0.007 |
Neg logit contributions | |
nam | -0.012 |
iring | -0.011 |
ble | -0.011 |
efully | -0.011 |
uted | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | +6.84e-01 |
Pos logit contributions | |
ar | +0.161 |
t | +0.152 |
da | +0.148 |
zed | +0.148 |
rd | +0.147 |
Neg logit contributions | |
ble | -0.082 |
ins | -0.081 |
nam | -0.081 |
bles | -0.077 |
ishes | -0.076 |
Token | waited |
Token ID | 13488 |
Feature activation | -5.37e-02 |
Pos logit contributions | |
nam | +0.022 |
iring | +0.021 |
ble | +0.020 |
efully | +0.020 |
uted | +0.020 |
Neg logit contributions | |
ar | -0.017 |
zed | -0.017 |
t | -0.016 |
minutes | -0.016 |
dreaming | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
ar | +0.002 |
rd | +0.002 |
t | +0.002 |
ake | +0.002 |
seek | +0.002 |
Neg logit contributions | |
nam | -0.001 |
ble | -0.001 |
iring | -0.001 |
bles | -0.001 |
uted | -0.001 |
Token | When |
Token ID | 1649 |
Feature activation | +9.51e-01 |
Pos logit contributions | |
nam | +0.003 |
iring | +0.003 |
ble | +0.003 |
efully | +0.003 |
uted | +0.003 |
Neg logit contributions | |
ar | -0.003 |
zed | -0.003 |
t | -0.003 |
rd | -0.003 |
ake | -0.003 |
Token | it |
Token ID | 340 |
Feature activation | +6.01e-01 |
Pos logit contributions | |
nam | +0.025 |
ble | +0.021 |
iring | +0.020 |
rad | +0.020 |
av | +0.020 |
Neg logit contributions | |
ar | -0.031 |
rd | -0.030 |
ake | -0.029 |
t | -0.028 |
basis | -0.028 |
Token | saw |
Token ID | 2497 |
Feature activation | -6.21e-01 |
Pos logit contributions | |
nam | +0.009 |
iring | +0.009 |
efully | +0.008 |
ble | +0.008 |
uted | +0.008 |
Neg logit contributions | |
ar | -0.009 |
zed | -0.009 |
t | -0.009 |
rd | -0.009 |
ake | -0.009 |
Token | a |
Token ID | 257 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
ar | +0.015 |
zed | +0.015 |
t | +0.014 |
rd | +0.014 |
ake | +0.014 |
Neg logit contributions | |
nam | -0.020 |
iring | -0.019 |
ble | -0.019 |
efully | -0.019 |
ishes | -0.018 |
Token | big |
Token ID | 1263 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
nam | +0.008 |
iring | +0.008 |
efully | +0.008 |
ble | +0.007 |
uted | +0.007 |
Neg logit contributions | |
ar | -0.008 |
t | -0.008 |
zed | -0.008 |
ake | -0.008 |
minutes | -0.007 |
Token | roller |
Token ID | 24471 |
Feature activation | -3.10e+00 |
Pos logit contributions | |
nam | +0.007 |
ot | +0.006 |
rad | +0.006 |
ble | +0.006 |
iring | +0.006 |
Neg logit contributions | |
zed | -0.009 |
t | -0.009 |
ar | -0.009 |
rd | -0.009 |
seek | -0.009 |
Token | co |
Token ID | 1073 |
Feature activation | -3.06e+00 |
Pos logit contributions | |
t | +0.070 |
payoff | +0.070 |
minutes | +0.068 |
ever | +0.068 |
rd | +0.067 |
Neg logit contributions | |
ble | -0.092 |
uted | -0.085 |
iring | -0.083 |
nam | -0.082 |
bles | -0.080 |
Token | aster |
Token ID | 1603 |
Feature activation | -4.62e+00 |
Pos logit contributions | |
ar | +0.084 |
zed | +0.078 |
minutes | +0.077 |
dreaming | +0.077 |
payoff | +0.076 |
Neg logit contributions | |
nam | -0.083 |
uted | -0.080 |
iring | -0.080 |
ble | -0.079 |
efully | -0.075 |
Token | and |
Token ID | 290 |
Feature activation | +4.53e-01 |
Pos logit contributions | |
ar | +0.152 |
zed | +0.144 |
da | +0.142 |
basis | +0.140 |
payoff | +0.139 |
Neg logit contributions | |
uted | -0.095 |
ble | -0.094 |
iring | -0.092 |
nam | -0.092 |
pole | -0.086 |
Token | asked |
Token ID | 1965 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
iring | +0.014 |
ble | +0.014 |
ishes | +0.013 |
nam | +0.013 |
efully | +0.013 |
Neg logit contributions | |
zed | -0.011 |
dreaming | -0.011 |
minutes | -0.011 |
t | -0.011 |
ar | -0.011 |
Token | her |
Token ID | 607 |
Feature activation | +8.63e-01 |
Pos logit contributions | |
ar | +0.004 |
zed | +0.004 |
t | +0.004 |
rd | +0.004 |
ake | +0.004 |
Neg logit contributions | |
nam | -0.004 |
iring | -0.004 |
ble | -0.004 |
efully | -0.003 |
uted | -0.003 |
Token | mom |
Token ID | 1995 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
nam | +0.025 |
iring | +0.023 |
efully | +0.023 |
ble | +0.023 |
uted | +0.023 |
Neg logit contributions | |
ar | -0.024 |
zed | -0.023 |
t | -0.023 |
minutes | -0.023 |
dreaming | -0.023 |
Token | if |
Token ID | 611 |
Feature activation | +4.08e-01 |
Pos logit contributions | |
ar | +0.005 |
t | +0.005 |
zed | +0.005 |
ake | +0.005 |
rd | +0.005 |
Neg logit contributions | |
nam | -0.006 |
iring | -0.006 |
ble | -0.006 |
efully | -0.006 |
uted | -0.005 |
Token | on |
Token ID | 319 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
rd | +0.001 |
zed | +0.001 |
t | +0.001 |
ar | +0.001 |
ake | +0.001 |
Neg logit contributions | |
nam | -0.001 |
ble | -0.001 |
iring | -0.001 |
efully | -0.001 |
bles | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | -3.74e-02 |
Pos logit contributions | |
t | +0.010 |
ar | +0.010 |
da | +0.009 |
rd | +0.009 |
storm | +0.009 |
Neg logit contributions | |
nam | -0.006 |
vendors | -0.005 |
efully | -0.005 |
rad | -0.004 |
av | -0.004 |
Token | scary |
Token ID | 14343 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
ar | +0.001 |
ake | +0.001 |
t | +0.001 |
zed | +0.001 |
seek | +0.001 |
Neg logit contributions | |
nam | -0.001 |
rad | -0.001 |
raft | -0.001 |
vendors | -0.001 |
squash | -0.001 |
Token | roller |
Token ID | 24471 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
raft | +0.006 |
rad | +0.006 |
ot | +0.006 |
squash | +0.005 |
tire | +0.005 |
Neg logit contributions | |
t | -0.007 |
side | -0.006 |
ar | -0.006 |
z | -0.006 |
less | -0.006 |
Token | co |
Token ID | 1073 |
Feature activation | -2.74e+00 |
Pos logit contributions | |
t | +0.062 |
ake | +0.061 |
payoff | +0.061 |
minutes | +0.060 |
ever | +0.060 |
Neg logit contributions | |
ble | -0.085 |
uted | -0.078 |
ot | -0.076 |
bles | -0.075 |
ter | -0.075 |
Token | aster |
Token ID | 1603 |
Feature activation | -4.61e+00 |
Pos logit contributions | |
ar | +0.068 |
minutes | +0.064 |
dreaming | +0.064 |
payoff | +0.063 |
zed | +0.062 |
Neg logit contributions | |
nam | -0.077 |
uted | -0.076 |
iring | -0.075 |
ble | -0.075 |
ins | -0.074 |
Token | ride |
Token ID | 6594 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
da | +0.145 |
ar | +0.144 |
zed | +0.139 |
joy | +0.135 |
ake | +0.134 |
Neg logit contributions | |
uted | -0.089 |
nam | -0.086 |
pole | -0.086 |
ters | -0.082 |
bles | -0.080 |
Token | . |
Token ID | 13 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
zed | +0.036 |
rd | +0.035 |
ar | +0.035 |
t | +0.035 |
minutes | +0.035 |
Neg logit contributions | |
nam | -0.029 |
ble | -0.027 |
iring | -0.027 |
efully | -0.026 |
uted | -0.026 |
Token | Tim |
Token ID | 5045 |
Feature activation | +6.71e-01 |
Pos logit contributions | |
nam | +0.006 |
ble | +0.006 |
iring | +0.006 |
ishes | +0.005 |
efully | +0.005 |
Neg logit contributions | |
t | -0.005 |
ar | -0.005 |
zed | -0.005 |
rd | -0.005 |
ake | -0.005 |
Token | my |
Token ID | 1820 |
Feature activation | -9.48e-03 |
Pos logit contributions | |
nam | +0.017 |
iring | +0.016 |
efully | +0.016 |
ble | +0.016 |
ishes | +0.015 |
Neg logit contributions | |
ar | -0.021 |
zed | -0.020 |
t | -0.020 |
rd | -0.020 |
minutes | -0.019 |
Token | was |
Token ID | 373 |
Feature activation | -7.91e-02 |
Pos logit contributions | |
ar | +0.000 |
t | +0.000 |
rd | +0.000 |
ake | +0.000 |
zed | +0.000 |
Neg logit contributions | |
nam | -0.000 |
efully | -0.000 |
ble | -0.000 |
iring | -0.000 |
uted | -0.000 |
Token | the |
Token ID | 262 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
ar | +0.013 |
rd | +0.013 |
zed | +0.013 |
t | +0.013 |
ake | +0.013 |
Neg logit contributions | |
nam | -0.014 |
ble | -0.013 |
iring | -0.013 |
efully | -0.013 |
ishes | -0.013 |
Token | bread |
Token ID | 8509 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
nam | +0.010 |
iring | +0.009 |
ble | +0.009 |
av | +0.009 |
efully | +0.009 |
Neg logit contributions | |
ar | -0.013 |
zed | -0.012 |
rd | -0.012 |
ake | -0.012 |
t | -0.012 |
Token | in |
Token ID | 287 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
nam | +0.045 |
iring | +0.042 |
ble | +0.042 |
efully | +0.041 |
uted | +0.040 |
Neg logit contributions | |
ar | -0.050 |
zed | -0.049 |
t | -0.048 |
rd | -0.048 |
ake | -0.047 |
Token | the |
Token ID | 262 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
nam | +0.041 |
ble | +0.037 |
iring | +0.037 |
efully | +0.036 |
rad | +0.036 |
Neg logit contributions | |
ar | -0.056 |
zed | -0.054 |
t | -0.053 |
rd | -0.052 |
ake | -0.052 |
Token | to |
Token ID | 284 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
nam | +0.007 |
iring | +0.007 |
ble | +0.007 |
efully | +0.007 |
uted | +0.006 |
Neg logit contributions | |
ar | -0.008 |
zed | -0.008 |
t | -0.008 |
ake | -0.008 |
rd | -0.008 |
Token | aster |
Token ID | 1603 |
Feature activation | -4.61e+00 |
Pos logit contributions | |
ar | +0.005 |
t | +0.004 |
zed | +0.004 |
rd | +0.004 |
ake | +0.004 |
Neg logit contributions | |
nam | -0.010 |
ble | -0.009 |
iring | -0.009 |
efully | -0.009 |
ishes | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | +6.04e-01 |
Pos logit contributions | |
ar | +0.155 |
rd | +0.144 |
da | +0.143 |
payoff | +0.143 |
t | +0.143 |
Neg logit contributions | |
ble | -0.086 |
ins | -0.086 |
nam | -0.085 |
ishes | -0.084 |
uted | -0.081 |
Token | pushed |
Token ID | 7121 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
nam | +0.019 |
iring | +0.018 |
ble | +0.018 |
efully | +0.018 |
uted | +0.017 |
Neg logit contributions | |
ar | -0.015 |
zed | -0.015 |
t | -0.014 |
minutes | -0.014 |
dreaming | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | +7.80e-01 |
Pos logit contributions | |
ar | +0.003 |
zed | +0.003 |
t | +0.003 |
rd | +0.003 |
ake | +0.003 |
Neg logit contributions | |
nam | -0.004 |
iring | -0.004 |
ble | -0.004 |
efully | -0.004 |
uted | -0.004 |
Token | button |
Token ID | 4936 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
nam | +0.023 |
iring | +0.021 |
ble | +0.021 |
efully | +0.021 |
uted | +0.020 |
Neg logit contributions | |
ar | -0.022 |
zed | -0.021 |
t | -0.021 |
rd | -0.020 |
ake | -0.020 |
Token | down |
Token ID | 866 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
rd | +0.040 |
ar | +0.039 |
zed | +0.039 |
ake | +0.038 |
basis | +0.037 |
Neg logit contributions | |
ble | -0.027 |
nam | -0.027 |
iring | -0.026 |
bles | -0.024 |
ishes | -0.024 |
Token | never |
Token ID | 1239 |
Feature activation | -6.41e-01 |
Pos logit contributions | |
ar | +0.006 |
t | +0.006 |
rd | +0.006 |
zed | +0.005 |
minutes | +0.005 |
Neg logit contributions | |
nam | -0.009 |
efully | -0.008 |
ble | -0.008 |
iring | -0.008 |
ishes | -0.008 |
Token | played |
Token ID | 2826 |
Feature activation | -7.47e-01 |
Pos logit contributions | |
ar | +0.017 |
zed | +0.017 |
t | +0.017 |
rd | +0.017 |
ake | +0.016 |
Neg logit contributions | |
nam | -0.019 |
iring | -0.017 |
efully | -0.017 |
ble | -0.017 |
ishes | -0.017 |
Token | with |
Token ID | 351 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
t | +0.023 |
ar | +0.022 |
zed | +0.022 |
ake | +0.021 |
rd | +0.021 |
Neg logit contributions | |
nam | -0.019 |
ble | -0.018 |
iring | -0.018 |
av | -0.018 |
uted | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | -4.53e-01 |
Pos logit contributions | |
ar | +0.007 |
t | +0.007 |
zed | +0.007 |
rd | +0.007 |
ake | +0.007 |
Neg logit contributions | |
nam | -0.006 |
iring | -0.005 |
ishes | -0.005 |
ble | -0.005 |
rad | -0.005 |
Token | or |
Token ID | 393 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
ar | +0.014 |
zed | +0.014 |
t | +0.014 |
rd | +0.014 |
ake | +0.013 |
Neg logit contributions | |
nam | -0.012 |
iring | -0.011 |
ble | -0.010 |
ishes | -0.010 |
efully | -0.010 |
Token | nam |
Token ID | 7402 |
Feature activation | +3.40e+00 |
Pos logit contributions | |
ar | +0.031 |
zed | +0.029 |
rd | +0.029 |
ake | +0.029 |
t | +0.029 |
Neg logit contributions | |
nam | -0.031 |
iring | -0.026 |
ble | -0.026 |
ishes | -0.026 |
av | -0.026 |
Token | ents |
Token ID | 658 |
Feature activation | -4.92e-01 |
Pos logit contributions | |
nam | +0.064 |
ble | +0.061 |
ot | +0.059 |
efully | +0.059 |
rad | +0.058 |
Neg logit contributions | |
t | -0.125 |
ake | -0.123 |
z | -0.118 |
ar | -0.118 |
ever | -0.117 |
Token | again |
Token ID | 757 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
ar | +0.012 |
rd | +0.011 |
zed | +0.011 |
minutes | +0.011 |
ake | +0.011 |
Neg logit contributions | |
nam | -0.016 |
ble | -0.015 |
iring | -0.015 |
av | -0.014 |
uted | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | +2.54e-02 |
Pos logit contributions | |
ar | +0.040 |
zed | +0.040 |
t | +0.039 |
rd | +0.038 |
da | +0.038 |
Neg logit contributions | |
nam | -0.025 |
ble | -0.025 |
iring | -0.025 |
av | -0.023 |
rad | -0.023 |
Token | They |
Token ID | 1119 |
Feature activation | -5.41e-01 |
Pos logit contributions | |
nam | +0.001 |
iring | +0.001 |
ble | +0.001 |
efully | +0.001 |
uted | +0.001 |
Neg logit contributions | |
ar | -0.001 |
zed | -0.001 |
t | -0.001 |
ake | -0.001 |
rd | -0.001 |
Token | still |
Token ID | 991 |
Feature activation | -6.06e-01 |
Pos logit contributions | |
ar | +0.014 |
ever | +0.013 |
zed | +0.013 |
t | +0.013 |
dreaming | +0.013 |
Neg logit contributions | |
iring | -0.017 |
nam | -0.017 |
ble | -0.016 |
uted | -0.016 |
efully | -0.016 |
Token | They |
Token ID | 1119 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
nam | +0.006 |
ble | +0.005 |
iring | +0.005 |
efully | +0.005 |
ishes | +0.005 |
Neg logit contributions | |
ar | -0.007 |
zed | -0.006 |
t | -0.006 |
minutes | -0.006 |
rd | -0.006 |
Token | played |
Token ID | 2826 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
iring | +0.005 |
ble | +0.005 |
nam | +0.005 |
uted | +0.004 |
ins | +0.004 |
Neg logit contributions | |
ever | -0.003 |
ar | -0.003 |
dreaming | -0.003 |
t | -0.003 |
zed | -0.003 |
Token | with |
Token ID | 351 |
Feature activation | +5.15e-01 |
Pos logit contributions | |
ar | +0.003 |
zed | +0.003 |
t | +0.002 |
ake | +0.002 |
rd | +0.002 |
Neg logit contributions | |
nam | -0.004 |
iring | -0.004 |
efully | -0.004 |
ble | -0.004 |
ishes | -0.004 |
Token | their |
Token ID | 511 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
nam | +0.012 |
ishes | +0.011 |
iring | +0.011 |
ble | +0.010 |
ot | +0.010 |
Neg logit contributions | |
ar | -0.018 |
t | -0.018 |
zed | -0.018 |
rd | -0.018 |
ake | -0.017 |
Token | other |
Token ID | 584 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
injuries | +0.043 |
dreaming | +0.042 |
minutes | +0.041 |
ever | +0.041 |
ar | +0.040 |
Neg logit contributions | |
efully | -0.042 |
uted | -0.040 |
iring | -0.040 |
ble | -0.039 |
nam | -0.038 |
Token | magnets |
Token ID | 37446 |
Feature activation | +3.38e+00 |
Pos logit contributions | |
nam | +0.007 |
efully | +0.007 |
iring | +0.007 |
ble | +0.007 |
uted | +0.007 |
Neg logit contributions | |
minutes | -0.008 |
dreaming | -0.008 |
ar | -0.008 |
ever | -0.008 |
injuries | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | +6.84e-02 |
Pos logit contributions | |
nam | +0.089 |
ble | +0.084 |
iring | +0.083 |
bles | +0.080 |
efully | +0.080 |
Neg logit contributions | |
zed | -0.102 |
ar | -0.101 |
rd | -0.099 |
ake | -0.096 |
t | -0.094 |
Token | They |
Token ID | 1119 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
nam | +0.001 |
iring | +0.001 |
efully | +0.001 |
ble | +0.001 |
uted | +0.001 |
Neg logit contributions | |
ar | -0.003 |
zed | -0.003 |
ake | -0.003 |
t | -0.003 |
rd | -0.003 |
Token | played |
Token ID | 2826 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
ar | +0.003 |
ever | +0.003 |
zed | +0.003 |
t | +0.003 |
dreaming | +0.003 |
Neg logit contributions | |
iring | -0.004 |
nam | -0.004 |
ble | -0.004 |
efully | -0.004 |
uted | -0.004 |
Token | with |
Token ID | 351 |
Feature activation | +3.78e-01 |
Pos logit contributions | |
ar | +0.004 |
zed | +0.004 |
t | +0.004 |
rd | +0.004 |
ake | +0.004 |
Neg logit contributions | |
nam | -0.005 |
iring | -0.005 |
ble | -0.005 |
efully | -0.005 |
uted | -0.005 |
Token | them |
Token ID | 606 |
Feature activation | -7.82e-01 |
Pos logit contributions | |
nam | +0.010 |
iring | +0.009 |
ishes | +0.009 |
ble | +0.009 |
efully | +0.008 |
Neg logit contributions | |
ar | -0.012 |
zed | -0.012 |
rd | -0.012 |
t | -0.012 |
ake | -0.012 |
Token | |
Token ID | 220 |
Feature activation | +5.70e-01 |
Pos logit contributions | |
nam | +0.004 |
iring | +0.004 |
ble | +0.004 |
uted | +0.003 |
efully | +0.003 |
Neg logit contributions | |
ar | -0.005 |
zed | -0.005 |
t | -0.005 |
rd | -0.005 |
minutes | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | -6.00e-02 |
Pos logit contributions | |
nam | +0.021 |
ishes | +0.019 |
efully | +0.019 |
ot | +0.019 |
rad | +0.018 |
Neg logit contributions | |
t | -0.013 |
zed | -0.012 |
ar | -0.011 |
ake | -0.011 |
stand | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
ar | +0.002 |
t | +0.002 |
zed | +0.002 |
rd | +0.002 |
ake | +0.002 |
Neg logit contributions | |
nam | -0.002 |
ishes | -0.002 |
iring | -0.002 |
efully | -0.002 |
ble | -0.002 |
Token | The |
Token ID | 464 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
ar | +0.011 |
zed | +0.011 |
t | +0.011 |
ake | +0.010 |
rd | +0.010 |
Neg logit contributions | |
nam | -0.009 |
iring | -0.009 |
ble | -0.008 |
efully | -0.008 |
uted | -0.008 |
Token | all |
Token ID | 477 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
moment | +0.013 |
minutes | +0.012 |
ever | +0.012 |
ar | +0.012 |
minute | +0.012 |
Neg logit contributions | |
nam | -0.011 |
uted | -0.010 |
iring | -0.010 |
asure | -0.010 |
ishes | -0.010 |
Token | igator |
Token ID | 23823 |
Feature activation | +3.77e+00 |
Pos logit contributions | |
nam | +0.030 |
iring | +0.027 |
ble | +0.026 |
uted | +0.025 |
efully | +0.024 |
Neg logit contributions | |
zed | -0.057 |
ar | -0.057 |
ever | -0.056 |
t | -0.056 |
minutes | -0.055 |
Token | ended |
Token ID | 4444 |
Feature activation | -7.17e-01 |
Pos logit contributions | |
nam | +0.103 |
iring | +0.096 |
ble | +0.094 |
efully | +0.093 |
uted | +0.090 |
Neg logit contributions | |
ar | -0.111 |
zed | -0.108 |
t | -0.107 |
rd | -0.104 |
ake | -0.104 |
Token | his |
Token ID | 465 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
zed | +0.026 |
ar | +0.026 |
dreaming | +0.025 |
ake | +0.025 |
ever | +0.025 |
Neg logit contributions | |
nam | -0.014 |
iring | -0.012 |
efully | -0.012 |
ble | -0.012 |
ishes | -0.012 |
Token | journey |
Token ID | 7002 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
t | +0.029 |
ar | +0.029 |
zed | +0.028 |
da | +0.027 |
ake | +0.027 |
Neg logit contributions | |
nam | -0.034 |
ble | -0.031 |
iring | -0.031 |
rad | -0.031 |
efully | -0.031 |
Token | at |
Token ID | 379 |
Feature activation | -9.57e-01 |
Pos logit contributions | |
ar | +0.008 |
rd | +0.008 |
zed | +0.008 |
ake | +0.008 |
minutes | +0.008 |
Neg logit contributions | |
nam | -0.007 |
iring | -0.007 |
ble | -0.007 |
uted | -0.006 |
efully | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | -3.41e-02 |
Pos logit contributions | |
ar | +0.029 |
t | +0.028 |
zed | +0.027 |
rd | +0.027 |
ake | +0.027 |
Neg logit contributions | |
nam | -0.026 |
ble | -0.024 |
iring | -0.024 |
efully | -0.023 |
uted | -0.022 |
Token | and |
Token ID | 290 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
ar | +0.007 |
zed | +0.007 |
gh | +0.006 |
ake | +0.006 |
da | +0.006 |
Neg logit contributions | |
nam | -0.004 |
iring | -0.004 |
ble | -0.004 |
rad | -0.004 |
ins | -0.004 |
Token | ate |
Token ID | 15063 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
nam | +0.007 |
iring | +0.006 |
ble | +0.006 |
efully | +0.006 |
uted | +0.006 |
Neg logit contributions | |
ar | -0.006 |
zed | -0.006 |
t | -0.006 |
ake | -0.006 |
rd | -0.006 |
Token | their |
Token ID | 511 |
Feature activation | -8.85e-01 |
Pos logit contributions | |
nam | +0.007 |
iring | +0.007 |
efully | +0.006 |
ble | +0.006 |
uted | +0.006 |
Neg logit contributions | |
ar | -0.005 |
zed | -0.005 |
minutes | -0.005 |
t | -0.005 |
ake | -0.005 |
Token | sandwiches |
Token ID | 29777 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
ar | +0.023 |
zed | +0.023 |
t | +0.022 |
ake | +0.022 |
rd | +0.022 |
Neg logit contributions | |
nam | -0.027 |
iring | -0.025 |
ble | -0.025 |
efully | -0.025 |
ishes | -0.024 |
Token | and |
Token ID | 290 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
nam | +0.062 |
iring | +0.059 |
ble | +0.058 |
efully | +0.057 |
uted | +0.056 |
Neg logit contributions | |
ar | -0.049 |
zed | -0.047 |
t | -0.047 |
rd | -0.045 |
ake | -0.045 |
Token | carrots |
Token ID | 34397 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
ar | +0.006 |
zed | +0.006 |
t | +0.006 |
rd | +0.006 |
ake | +0.006 |
Neg logit contributions | |
nam | -0.007 |
iring | -0.006 |
ble | -0.006 |
efully | -0.006 |
uted | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
nam | +0.118 |
iring | +0.112 |
efully | +0.109 |
ble | +0.107 |
uted | +0.106 |
Neg logit contributions | |
ar | -0.076 |
t | -0.074 |
zed | -0.072 |
ever | -0.071 |
ake | -0.071 |
Token | They |
Token ID | 1119 |
Feature activation | +2.77e-03 |
Pos logit contributions | |
nam | +0.006 |
iring | +0.006 |
efully | +0.006 |
uted | +0.006 |
ble | +0.005 |
Neg logit contributions | |
ar | -0.012 |
ake | -0.012 |
zed | -0.012 |
rd | -0.012 |
t | -0.012 |
Token | were |
Token ID | 547 |
Feature activation | -8.52e-01 |
Pos logit contributions | |
iring | +0.000 |
nam | +0.000 |
ble | +0.000 |
efully | +0.000 |
uted | +0.000 |
Neg logit contributions | |
ar | -0.000 |
ever | -0.000 |
zed | -0.000 |
t | -0.000 |
minutes | -0.000 |
Token | very |
Token ID | 845 |
Feature activation | -6.35e-01 |
Pos logit contributions | |
ever | +0.022 |
dreaming | +0.022 |
minutes | +0.021 |
zed | +0.020 |
no | +0.020 |
Neg logit contributions | |
nam | -0.025 |
ishes | -0.024 |
ble | -0.024 |
iring | -0.023 |
ada | -0.023 |
Token | hungry |
Token ID | 14720 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
ever | +0.017 |
minutes | +0.017 |
zed | +0.017 |
t | +0.017 |
rd | +0.016 |
Neg logit contributions | |
nam | -0.018 |
efully | -0.017 |
ishes | -0.017 |
uted | -0.017 |
ble | -0.016 |
Token | try |
Token ID | 1949 |
Feature activation | -2.91e-02 |
Pos logit contributions | |
ar | +0.007 |
zed | +0.007 |
t | +0.007 |
ake | +0.007 |
rd | +0.007 |
Neg logit contributions | |
nam | -0.009 |
iring | -0.008 |
efully | -0.008 |
ble | -0.008 |
uted | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
ar | +0.001 |
rd | +0.001 |
t | +0.001 |
zed | +0.001 |
minutes | +0.001 |
Neg logit contributions | |
nam | -0.001 |
ble | -0.001 |
rad | -0.001 |
av | -0.001 |
iring | -0.001 |
Token | broccoli |
Token ID | 44653 |
Feature activation | +2.42e+00 |
Pos logit contributions | |
nam | +0.032 |
iring | +0.030 |
ble | +0.029 |
efully | +0.028 |
uted | +0.027 |
Neg logit contributions | |
ar | -0.049 |
zed | -0.047 |
t | -0.046 |
rd | -0.046 |
ake | -0.046 |
Token | c |
Token ID | 269 |
Feature activation | +6.72e-01 |
Pos logit contributions | |
nam | +0.068 |
ble | +0.066 |
iring | +0.065 |
efully | +0.063 |
rad | +0.062 |
Neg logit contributions | |
ar | -0.066 |
zed | -0.065 |
rd | -0.063 |
ake | -0.062 |
t | -0.062 |
Token | asser |
Token ID | 24929 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
nam | +0.013 |
iring | +0.013 |
ble | +0.012 |
efully | +0.012 |
uted | +0.011 |
Neg logit contributions | |
ar | -0.024 |
zed | -0.024 |
t | -0.024 |
rd | -0.023 |
ake | -0.023 |
Token | ole |
Token ID | 2305 |
Feature activation | +3.57e+00 |
Pos logit contributions | |
t | +0.014 |
ar | +0.013 |
ake | +0.013 |
ever | +0.013 |
rd | +0.013 |
Neg logit contributions | |
nam | -0.011 |
efully | -0.009 |
uted | -0.009 |
iring | -0.009 |
ishes | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -1.85e-03 |
Pos logit contributions | |
nam | +0.103 |
iring | +0.096 |
ble | +0.093 |
av | +0.093 |
rad | +0.093 |
Neg logit contributions | |
zed | -0.097 |
ar | -0.097 |
ake | -0.094 |
rd | -0.092 |
dreaming | -0.092 |
Token | He |
Token ID | 679 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
ar | +0.000 |
t | +0.000 |
zed | +0.000 |
rd | +0.000 |
dreaming | +0.000 |
Neg logit contributions | |
nam | -0.000 |
ble | -0.000 |
iring | -0.000 |
efully | -0.000 |
uted | -0.000 |
Token | said |
Token ID | 531 |
Feature activation | -2.62e-02 |
Pos logit contributions | |
nam | +0.008 |
iring | +0.008 |
ble | +0.008 |
uted | +0.007 |
efully | +0.007 |
Neg logit contributions | |
ar | -0.007 |
zed | -0.007 |
t | -0.007 |
ever | -0.007 |
minutes | -0.007 |
Token | , |
Token ID | 11 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
ar | +0.001 |
rd | +0.001 |
zed | +0.001 |
minutes | +0.001 |
ake | +0.001 |
Neg logit contributions | |
nam | -0.001 |
ble | -0.001 |
rad | -0.001 |
iring | -0.001 |
av | -0.001 |
Token | " |
Token ID | 366 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
ar | +0.012 |
zed | +0.012 |
rd | +0.012 |
t | +0.012 |
ake | +0.012 |
Neg logit contributions | |
nam | -0.009 |
iring | -0.008 |
ble | -0.008 |
efully | -0.008 |
uted | -0.008 |
Token | ." |
Token ID | 526 |
Feature activation | +8.32e-01 |
Pos logit contributions | |
nam | +0.024 |
ble | +0.023 |
iring | +0.023 |
ishes | +0.023 |
efully | +0.022 |
Neg logit contributions | |
zed | -0.015 |
ar | -0.015 |
rd | -0.015 |
ake | -0.014 |
minutes | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | +6.74e-01 |
Pos logit contributions | |
nam | +0.024 |
iring | +0.023 |
ble | +0.023 |
efully | +0.022 |
ishes | +0.022 |
Neg logit contributions | |
ar | -0.023 |
t | -0.022 |
zed | -0.022 |
rd | -0.021 |
ake | -0.021 |
Token |
|
Token ID | 198 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
nam | +0.020 |
iring | +0.018 |
ishes | +0.018 |
efully | +0.018 |
ble | +0.018 |
Neg logit contributions | |
ar | -0.019 |
t | -0.019 |
zed | -0.019 |
ake | -0.018 |
rd | -0.018 |
Token | Tom |
Token ID | 13787 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
nam | +0.012 |
iring | +0.011 |
ble | +0.011 |
efully | +0.011 |
uted | +0.011 |
Neg logit contributions | |
ar | -0.009 |
zed | -0.008 |
t | -0.008 |
ake | -0.008 |
rd | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | -6.61e-01 |
Pos logit contributions | |
ar | +0.047 |
zed | +0.046 |
t | +0.046 |
ake | +0.045 |
rd | +0.045 |
Neg logit contributions | |
nam | -0.046 |
efully | -0.044 |
iring | -0.044 |
ble | -0.044 |
uted | -0.043 |
Token | Lily |
Token ID | 20037 |
Feature activation | +7.11e-01 |
Pos logit contributions | |
ar | +0.016 |
ake | +0.016 |
t | +0.015 |
zed | +0.015 |
rd | +0.015 |
Neg logit contributions | |
nam | -0.022 |
efully | -0.020 |
iring | -0.020 |
ishes | -0.020 |
ble | -0.020 |
Token | were |
Token ID | 547 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
nam | +0.023 |
iring | +0.023 |
ble | +0.021 |
ins | +0.020 |
ishes | +0.020 |
Neg logit contributions | |
ar | -0.019 |
zed | -0.017 |
t | -0.017 |
ever | -0.017 |
dreaming | -0.016 |
Token | shocked |
Token ID | 11472 |
Feature activation | -1.86e-02 |
Pos logit contributions | |
dreaming | +0.005 |
minutes | +0.005 |
zed | +0.005 |
ever | +0.005 |
rd | +0.005 |
Neg logit contributions | |
nam | -0.004 |
ishes | -0.004 |
av | -0.004 |
iring | -0.004 |
ot | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | -9.07e-01 |
Pos logit contributions | |
zed | +0.001 |
ar | +0.001 |
rd | +0.001 |
gh | +0.001 |
t | +0.001 |
Neg logit contributions | |
iring | -0.000 |
ble | -0.000 |
nam | -0.000 |
uted | -0.000 |
efully | -0.000 |
Token | scared |
Token ID | 12008 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
ar | +0.031 |
zed | +0.031 |
dreaming | +0.031 |
minutes | +0.030 |
t | +0.030 |
Neg logit contributions | |
nam | -0.019 |
iring | -0.019 |
ble | -0.018 |
efully | -0.018 |
ishes | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
iring | +0.010 |
nam | +0.009 |
efully | +0.009 |
uted | +0.009 |
ble | +0.009 |
Neg logit contributions | |
zed | -0.013 |
ar | -0.013 |
rd | -0.012 |
z | -0.012 |
seek | -0.012 |
Token | drum |
Token ID | 13026 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
t | +0.033 |
ar | +0.032 |
da | +0.030 |
rd | +0.030 |
z | +0.029 |
Neg logit contributions | |
nam | -0.024 |
ble | -0.019 |
av | -0.019 |
uted | -0.018 |
iring | -0.017 |
Token | ming |
Token ID | 2229 |
Feature activation | -9.54e-01 |
Pos logit contributions | |
zed | +0.038 |
ar | +0.038 |
minutes | +0.038 |
da | +0.037 |
ake | +0.036 |
Neg logit contributions | |
nam | -0.032 |
bles | -0.030 |
ble | -0.030 |
iring | -0.029 |
ishes | -0.029 |
Token | with |
Token ID | 351 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
ar | +0.027 |
zed | +0.026 |
t | +0.026 |
ake | +0.025 |
rd | +0.025 |
Neg logit contributions | |
nam | -0.027 |
ble | -0.025 |
iring | -0.025 |
efully | -0.025 |
uted | -0.024 |
Token | his |
Token ID | 465 |
Feature activation | +8.87e-03 |
Pos logit contributions | |
nam | +0.005 |
iring | +0.005 |
ble | +0.005 |
efully | +0.005 |
ot | +0.004 |
Neg logit contributions | |
ar | -0.008 |
rd | -0.007 |
t | -0.007 |
zed | -0.007 |
ake | -0.007 |
Token | friends |
Token ID | 2460 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
nam | +0.000 |
ble | +0.000 |
iring | +0.000 |
efully | +0.000 |
ishes | +0.000 |
Neg logit contributions | |
ar | -0.000 |
zed | -0.000 |
t | -0.000 |
rd | -0.000 |
ake | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | +4.39e-01 |
Pos logit contributions | |
nam | +0.040 |
ble | +0.035 |
iring | +0.035 |
efully | +0.035 |
uted | +0.034 |
Neg logit contributions | |
zed | -0.042 |
ar | -0.042 |
t | -0.040 |
rd | -0.039 |
minutes | -0.039 |
Token | And |
Token ID | 843 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
nam | +0.013 |
iring | +0.012 |
ble | +0.012 |
efully | +0.011 |
ishes | +0.011 |
Neg logit contributions | |
ar | -0.013 |
zed | -0.013 |
t | -0.012 |
ake | -0.012 |
rd | -0.012 |
Token | they |
Token ID | 484 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
ar | +0.003 |
zed | +0.003 |
rd | +0.003 |
t | +0.003 |
ake | +0.003 |
Neg logit contributions | |
nam | -0.004 |
iring | -0.003 |
efully | -0.003 |
ble | -0.003 |
uted | -0.003 |
Token | all |
Token ID | 477 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
ar | +0.012 |
zed | +0.012 |
ever | +0.012 |
dreaming | +0.011 |
ake | +0.011 |
Neg logit contributions | |
iring | -0.010 |
nam | -0.010 |
uted | -0.009 |
ble | -0.009 |
ins | -0.009 |
Token | lived |
Token ID | 5615 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
nam | +0.054 |
iring | +0.053 |
ble | +0.050 |
uted | +0.048 |
efully | +0.048 |
Neg logit contributions | |
ar | -0.062 |
zed | -0.061 |
ever | -0.059 |
t | -0.059 |
ake | -0.058 |
Token | happily |
Token ID | 18177 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
nam | +0.006 |
iring | +0.006 |
ble | +0.005 |
uted | +0.005 |
ishes | +0.005 |
Neg logit contributions | |
ar | -0.011 |
zed | -0.011 |
ever | -0.011 |
ake | -0.010 |
rd | -0.010 |
Token | playing |
Token ID | 2712 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
ar | +0.030 |
rd | +0.029 |
t | +0.028 |
zed | +0.027 |
ake | +0.027 |
Neg logit contributions | |
nam | -0.025 |
uted | -0.022 |
iring | -0.022 |
ble | -0.022 |
rad | -0.022 |
Token | with |
Token ID | 351 |
Feature activation | +6.37e-01 |
Pos logit contributions | |
nam | +0.007 |
ble | +0.006 |
uted | +0.006 |
iring | +0.006 |
av | +0.006 |
Neg logit contributions | |
t | -0.007 |
ar | -0.007 |
ake | -0.007 |
rd | -0.007 |
zed | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
nam | +0.016 |
iring | +0.014 |
ble | +0.014 |
rad | +0.014 |
ot | +0.013 |
Neg logit contributions | |
ar | -0.021 |
t | -0.020 |
rd | -0.020 |
ake | -0.020 |
zed | -0.020 |
Token | ball |
Token ID | 2613 |
Feature activation | +9.33e-01 |
Pos logit contributions | |
ar | +0.013 |
zed | +0.012 |
t | +0.012 |
rd | +0.012 |
ake | +0.012 |
Neg logit contributions | |
nam | -0.012 |
iring | -0.011 |
ble | -0.011 |
efully | -0.011 |
uted | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
nam | +0.023 |
iring | +0.022 |
ble | +0.022 |
ot | +0.021 |
uted | +0.021 |
Neg logit contributions | |
zed | -0.030 |
rd | -0.028 |
ar | -0.028 |
da | -0.027 |
ake | -0.026 |
Token | Tim |
Token ID | 5045 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
nam | +0.005 |
ble | +0.005 |
efully | +0.005 |
ishes | +0.005 |
iring | +0.005 |
Neg logit contributions | |
t | -0.004 |
ar | -0.004 |
zed | -0.004 |
rd | -0.004 |
ake | -0.004 |
Token | laughed |
Token ID | 13818 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
nam | +0.037 |
iring | +0.035 |
ble | +0.034 |
efully | +0.034 |
uted | +0.033 |
Neg logit contributions | |
ar | -0.034 |
zed | -0.033 |
t | -0.032 |
ake | -0.031 |
rd | -0.031 |
Token | and |
Token ID | 290 |
Feature activation | -5.02e-01 |
Pos logit contributions | |
nam | +0.024 |
iring | +0.024 |
ble | +0.024 |
uted | +0.023 |
efully | +0.023 |
Neg logit contributions | |
ar | -0.032 |
rd | -0.032 |
zed | -0.032 |
t | -0.031 |
ake | -0.031 |
Token | said |
Token ID | 531 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
ar | +0.014 |
zed | +0.014 |
t | +0.014 |
rd | +0.014 |
ake | +0.014 |
Neg logit contributions | |
nam | -0.014 |
iring | -0.013 |
ble | -0.013 |
efully | -0.013 |
uted | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
nam | +0.008 |
ble | +0.008 |
iring | +0.008 |
efully | +0.007 |
uted | +0.007 |
Neg logit contributions | |
ar | -0.006 |
zed | -0.006 |
ake | -0.006 |
t | -0.006 |
rd | -0.006 |
Token | " |
Token ID | 366 |
Feature activation | -3.86e-02 |
Pos logit contributions | |
ar | +0.012 |
rd | +0.011 |
zed | +0.011 |
ake | +0.011 |
t | +0.011 |
Neg logit contributions | |
nam | -0.008 |
ble | -0.007 |
iring | -0.007 |
uted | -0.007 |
efully | -0.007 |
Token | in |
Token ID | 287 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
ar | +0.034 |
zed | +0.033 |
t | +0.033 |
rd | +0.032 |
ake | +0.032 |
Neg logit contributions | |
nam | -0.036 |
iring | -0.034 |
ble | -0.033 |
efully | -0.033 |
uted | -0.031 |
Token | front |
Token ID | 2166 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
nam | +0.023 |
efully | +0.021 |
rad | +0.020 |
iring | +0.019 |
av | +0.018 |
Neg logit contributions | |
ar | -0.042 |
t | -0.041 |
zed | -0.040 |
ake | -0.039 |
seek | -0.039 |
Token | of |
Token ID | 286 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
ar | +0.043 |
zed | +0.043 |
gh | +0.040 |
t | +0.040 |
ake | +0.040 |
Neg logit contributions | |
iring | -0.023 |
nam | -0.021 |
efully | -0.021 |
uted | -0.019 |
ble | -0.019 |
Token | him |
Token ID | 683 |
Feature activation | -5.53e-01 |
Pos logit contributions | |
nam | +0.006 |
av | +0.006 |
efully | +0.005 |
rad | +0.005 |
iring | +0.005 |
Neg logit contributions | |
ar | -0.014 |
t | -0.014 |
z | -0.013 |
rd | -0.013 |
seek | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
zed | +0.017 |
ar | +0.017 |
t | +0.016 |
rd | +0.016 |
minutes | +0.016 |
Neg logit contributions | |
nam | -0.014 |
iring | -0.014 |
ble | -0.014 |
efully | -0.013 |
uted | -0.012 |
Token | She |
Token ID | 1375 |
Feature activation | +5.18e-01 |
Pos logit contributions | |
nam | +0.013 |
ble | +0.012 |
ishes | +0.012 |
iring | +0.012 |
bles | +0.011 |
Neg logit contributions | |
t | -0.011 |
ar | -0.011 |
zed | -0.010 |
rd | -0.010 |
dreaming | -0.010 |
Token | smiled |
Token ID | 13541 |
Feature activation | +7.32e-01 |
Pos logit contributions | |
nam | +0.014 |
iring | +0.013 |
efully | +0.013 |
ble | +0.013 |
uted | +0.012 |
Neg logit contributions | |
ar | -0.015 |
t | -0.015 |
zed | -0.015 |
rd | -0.015 |
ake | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | +8.21e-02 |
Pos logit contributions | |
iring | +0.019 |
nam | +0.018 |
ble | +0.018 |
efully | +0.018 |
uted | +0.017 |
Neg logit contributions | |
ar | -0.023 |
zed | -0.023 |
t | -0.022 |
rd | -0.022 |
ake | -0.022 |
Token | said |
Token ID | 531 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
nam | +0.002 |
iring | +0.002 |
efully | +0.002 |
ble | +0.002 |
uted | +0.001 |
Neg logit contributions | |
ar | -0.003 |
t | -0.003 |
ake | -0.003 |
rd | -0.003 |
zed | -0.003 |
Token | " |
Token ID | 366 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
nam | +0.009 |
iring | +0.009 |
ble | +0.009 |
efully | +0.008 |
uted | +0.008 |
Neg logit contributions | |
ar | -0.007 |
t | -0.007 |
zed | -0.007 |
ake | -0.007 |
rd | -0.007 |
Token | Welcome |
Token ID | 14618 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
zed | +0.010 |
ar | +0.010 |
minutes | +0.009 |
rd | +0.009 |
injuries | +0.009 |
Neg logit contributions | |
nam | -0.007 |
efully | -0.007 |
iring | -0.007 |
ble | -0.007 |
uted | -0.007 |
Token | ball |
Token ID | 2613 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
nam | +0.021 |
iring | +0.020 |
efully | +0.020 |
ble | +0.019 |
uted | +0.019 |
Neg logit contributions | |
ar | -0.021 |
t | -0.020 |
zed | -0.020 |
ake | -0.020 |
rd | -0.020 |
Token | very |
Token ID | 845 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
nam | +0.041 |
iring | +0.039 |
ble | +0.038 |
efully | +0.038 |
uted | +0.037 |
Neg logit contributions | |
zed | -0.037 |
ar | -0.037 |
rd | -0.036 |
ake | -0.035 |
t | -0.034 |
Token | high |
Token ID | 1029 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
nam | +0.043 |
iring | +0.041 |
ble | +0.040 |
efully | +0.039 |
uted | +0.038 |
Neg logit contributions | |
ar | -0.034 |
zed | -0.033 |
ake | -0.032 |
rd | -0.032 |
t | -0.032 |
Token | and |
Token ID | 290 |
Feature activation | +6.23e-01 |
Pos logit contributions | |
nam | +0.003 |
iring | +0.003 |
ble | +0.003 |
efully | +0.003 |
uted | +0.003 |
Neg logit contributions | |
zed | -0.003 |
ar | -0.003 |
t | -0.003 |
rd | -0.003 |
ake | -0.003 |
Token | far |
Token ID | 1290 |
Feature activation | +6.26e-01 |
Pos logit contributions | |
nam | +0.019 |
ble | +0.017 |
efully | +0.017 |
iring | +0.017 |
uted | +0.016 |
Neg logit contributions | |
ar | -0.017 |
ake | -0.017 |
rd | -0.016 |
zed | -0.016 |
t | -0.016 |
Token | with |
Token ID | 351 |
Feature activation | +7.38e-01 |
Pos logit contributions | |
nam | +0.016 |
iring | +0.015 |
ble | +0.015 |
efully | +0.014 |
uted | +0.014 |
Neg logit contributions | |
zed | -0.019 |
rd | -0.019 |
ar | -0.019 |
ake | -0.019 |
t | -0.018 |
Token | her |
Token ID | 607 |
Feature activation | +4.10e-01 |
Pos logit contributions | |
nam | +0.017 |
efully | +0.015 |
iring | +0.015 |
uted | +0.014 |
rad | +0.014 |
Neg logit contributions | |
ar | -0.026 |
ake | -0.025 |
zed | -0.025 |
t | -0.025 |
rd | -0.025 |
Token | foot |
Token ID | 2366 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
nam | +0.010 |
iring | +0.009 |
efully | +0.009 |
ble | +0.009 |
uted | +0.009 |
Neg logit contributions | |
ar | -0.013 |
zed | -0.013 |
t | -0.013 |
rd | -0.012 |
ever | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
ar | +0.034 |
zed | +0.033 |
rd | +0.033 |
ake | +0.032 |
basis | +0.032 |
Neg logit contributions | |
ble | -0.029 |
nam | -0.029 |
bles | -0.027 |
iring | -0.027 |
efully | -0.026 |
Token | Her |
Token ID | 2332 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
nam | +0.011 |
iring | +0.010 |
ble | +0.010 |
ishes | +0.010 |
uted | +0.010 |
Neg logit contributions | |
ar | -0.008 |
zed | -0.008 |
t | -0.008 |
rd | -0.008 |
minutes | -0.008 |
Token | friends |
Token ID | 2460 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
nam | +0.008 |
iring | +0.008 |
ble | +0.008 |
efully | +0.008 |
uted | +0.007 |
Neg logit contributions | |
ar | -0.011 |
zed | -0.011 |
t | -0.011 |
rd | -0.011 |
ake | -0.011 |
Token | eating |
Token ID | 6600 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
iring | +0.026 |
nam | +0.026 |
ble | +0.025 |
efully | +0.025 |
ins | +0.024 |
Neg logit contributions | |
ar | -0.032 |
zed | -0.032 |
t | -0.031 |
da | -0.030 |
gh | -0.030 |
Token | it |
Token ID | 340 |
Feature activation | -7.06e-01 |
Pos logit contributions | |
nam | +0.013 |
iring | +0.013 |
ble | +0.012 |
efully | +0.012 |
uted | +0.012 |
Neg logit contributions | |
ar | -0.011 |
zed | -0.010 |
minutes | -0.010 |
ever | -0.010 |
t | -0.010 |
Token | together |
Token ID | 1978 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
ar | +0.019 |
zed | +0.018 |
t | +0.018 |
ake | +0.018 |
rd | +0.018 |
Neg logit contributions | |
nam | -0.021 |
ble | -0.019 |
iring | -0.019 |
efully | -0.019 |
ishes | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
ar | +0.009 |
zed | +0.008 |
t | +0.008 |
ake | +0.008 |
rd | +0.008 |
Neg logit contributions | |
nam | -0.008 |
iring | -0.008 |
ble | -0.008 |
efully | -0.007 |
rad | -0.007 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
nam | +0.010 |
ble | +0.010 |
iring | +0.010 |
ishes | +0.009 |
bles | +0.009 |
Neg logit contributions | |
ar | -0.008 |
t | -0.008 |
zed | -0.008 |
rd | -0.008 |
ake | -0.008 |
Token | Once |
Token ID | 7454 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
nam | +0.011 |
iring | +0.010 |
ble | +0.009 |
efully | +0.009 |
ishes | +0.009 |
Neg logit contributions | |
ar | -0.011 |
t | -0.011 |
zed | -0.011 |
ake | -0.011 |
rd | -0.011 |
Token | upon |
Token ID | 2402 |
Feature activation | +8.13e-01 |
Pos logit contributions | |
nam | +0.003 |
efully | +0.003 |
uted | +0.003 |
iring | +0.003 |
ishes | +0.003 |
Neg logit contributions | |
t | -0.004 |
ar | -0.004 |
zed | -0.004 |
ever | -0.004 |
ake | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
nam | +0.025 |
iring | +0.024 |
ble | +0.023 |
efully | +0.023 |
uted | +0.023 |
Neg logit contributions | |
ar | -0.021 |
zed | -0.020 |
t | -0.020 |
ake | -0.020 |
rd | -0.019 |
Token | time |
Token ID | 640 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
ar | +0.011 |
seek | +0.010 |
t | +0.010 |
zed | +0.010 |
payoff | +0.010 |
Neg logit contributions | |
efully | -0.013 |
rad | -0.012 |
iring | -0.012 |
nam | -0.012 |
uted | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | -7.74e-01 |
Pos logit contributions | |
nam | +0.006 |
iring | +0.006 |
ble | +0.006 |
uted | +0.005 |
efully | +0.005 |
Neg logit contributions | |
zed | -0.005 |
ar | -0.005 |
minutes | -0.005 |
rd | -0.005 |
ake | -0.005 |
Token | there |
Token ID | 612 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
ar | +0.019 |
zed | +0.018 |
t | +0.018 |
ake | +0.017 |
rd | +0.017 |
Neg logit contributions | |
nam | -0.025 |
iring | -0.024 |
ble | -0.023 |
efully | -0.023 |
uted | -0.023 |
Token | time |
Token ID | 640 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
ar | +0.003 |
seek | +0.003 |
payoff | +0.003 |
zed | +0.003 |
t | +0.003 |
Neg logit contributions | |
efully | -0.003 |
iring | -0.003 |
uted | -0.003 |
rad | -0.003 |
idea | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
nam | +0.011 |
iring | +0.010 |
ble | +0.010 |
uted | +0.009 |
rad | +0.009 |
Neg logit contributions | |
zed | -0.010 |
ar | -0.010 |
minutes | -0.009 |
ake | -0.009 |
dreaming | -0.009 |
Token | there |
Token ID | 612 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
ar | +0.012 |
zed | +0.012 |
t | +0.012 |
ake | +0.012 |
rd | +0.011 |
Neg logit contributions | |
nam | -0.019 |
iring | -0.018 |
efully | -0.017 |
ble | -0.017 |
uted | -0.017 |
Token | was |
Token ID | 373 |
Feature activation | +4.16e-01 |
Pos logit contributions | |
ar | +0.003 |
zed | +0.003 |
t | +0.003 |
ake | +0.003 |
rd | +0.003 |
Neg logit contributions | |
nam | -0.003 |
iring | -0.003 |
ble | -0.003 |
efully | -0.003 |
uted | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
nam | +0.015 |
iring | +0.014 |
ble | +0.014 |
ishes | +0.014 |
efully | +0.014 |
Neg logit contributions | |
zed | -0.008 |
ar | -0.008 |
t | -0.008 |
ake | -0.008 |
rd | -0.008 |
Token | pengu |
Token ID | 38373 |
Feature activation | -9.30e-01 |
Pos logit contributions | |
ar | +0.010 |
minutes | +0.009 |
dreaming | +0.009 |
zed | +0.009 |
t | +0.009 |
Neg logit contributions | |
nam | -0.009 |
efully | -0.009 |
iring | -0.009 |
uted | -0.009 |
ishes | -0.008 |
Token | in |
Token ID | 259 |
Feature activation | -8.11e-02 |
Pos logit contributions | |
ar | +0.031 |
t | +0.030 |
ake | +0.030 |
zed | +0.029 |
rd | +0.029 |
Neg logit contributions | |
nam | -0.022 |
efully | -0.020 |
iring | -0.019 |
ishes | -0.019 |
uted | -0.018 |
Token | who |
Token ID | 508 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
ar | +0.002 |
zed | +0.002 |
t | +0.002 |
rd | +0.002 |
ake | +0.002 |
Neg logit contributions | |
nam | -0.002 |
iring | -0.002 |
ble | -0.002 |
efully | -0.002 |
uted | -0.002 |
Token | lived |
Token ID | 5615 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
minutes | +0.061 |
ar | +0.061 |
injuries | +0.060 |
payoff | +0.060 |
t | +0.059 |
Neg logit contributions | |
nam | -0.021 |
ot | -0.019 |
efully | -0.018 |
ble | -0.017 |
rad | -0.017 |
Token | in |
Token ID | 287 |
Feature activation | -8.88e-02 |
Pos logit contributions | |
ever | +0.006 |
dreaming | +0.006 |
t | +0.005 |
ar | +0.005 |
ake | +0.005 |
Neg logit contributions | |
nam | -0.007 |
ishes | -0.007 |
efully | -0.007 |
uted | -0.007 |
iring | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
ar | +0.003 |
t | +0.003 |
rd | +0.003 |
ake | +0.003 |
gh | +0.003 |
Neg logit contributions | |
nam | -0.002 |
rad | -0.002 |
ot | -0.002 |
ble | -0.002 |
efully | -0.002 |
Token | gray |
Token ID | 12768 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
ar | +0.017 |
zed | +0.016 |
t | +0.016 |
ake | +0.016 |
rd | +0.016 |
Neg logit contributions | |
nam | -0.018 |
iring | -0.016 |
ble | -0.016 |
efully | -0.016 |
ishes | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | +5.37e-01 |
Pos logit contributions | |
ar | +0.011 |
zed | +0.011 |
t | +0.011 |
rd | +0.011 |
ake | +0.011 |
Neg logit contributions | |
nam | -0.012 |
iring | -0.012 |
ble | -0.012 |
efully | -0.012 |
uted | -0.011 |
Token | They |
Token ID | 1119 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
nam | +0.017 |
iring | +0.015 |
ble | +0.015 |
efully | +0.015 |
uted | +0.015 |
Neg logit contributions | |
ar | -0.014 |
t | -0.014 |
zed | -0.013 |
minutes | -0.013 |
ake | -0.013 |
Token | want |
Token ID | 765 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
iring | +0.004 |
nam | +0.004 |
ins | +0.004 |
uted | +0.004 |
ble | +0.004 |
Neg logit contributions | |
ever | -0.003 |
t | -0.002 |
ar | -0.002 |
minutes | -0.002 |
dreaming | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
nam | +0.012 |
iring | +0.012 |
ble | +0.011 |
rad | +0.011 |
efully | +0.011 |
Neg logit contributions | |
ar | -0.007 |
zed | -0.007 |
rd | -0.007 |
t | -0.007 |
ake | -0.007 |
Token | see |
Token ID | 766 |
Feature activation | +3.77e-02 |
Pos logit contributions | |
nam | +0.008 |
iring | +0.008 |
ins | +0.008 |
ishes | +0.007 |
uted | +0.007 |
Neg logit contributions | |
ever | -0.004 |
ar | -0.004 |
zed | -0.004 |
t | -0.004 |
blast | -0.004 |
Token | what |
Token ID | 644 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
nam | +0.001 |
efully | +0.001 |
iring | +0.001 |
ble | +0.001 |
bles | +0.001 |
Neg logit contributions | |
ever | -0.001 |
minutes | -0.001 |
dreaming | -0.001 |
ar | -0.001 |
moment | -0.001 |
Token | is |
Token ID | 318 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
nam | +0.013 |
iring | +0.012 |
ble | +0.012 |
efully | +0.012 |
ishes | +0.012 |
Neg logit contributions | |
ar | -0.011 |
zed | -0.011 |
t | -0.010 |
ake | -0.010 |
rd | -0.010 |
Token | in |
Token ID | 287 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
nam | +0.052 |
iring | +0.048 |
ble | +0.048 |
efully | +0.047 |
uted | +0.046 |
Neg logit contributions | |
ar | -0.053 |
zed | -0.052 |
t | -0.051 |
rd | -0.050 |
ake | -0.050 |
Token | the |
Token ID | 262 |
Feature activation | +4.91e-01 |
Pos logit contributions | |
nam | +0.037 |
ble | +0.034 |
iring | +0.033 |
rad | +0.030 |
efully | +0.029 |
Neg logit contributions | |
ar | -0.057 |
zed | -0.056 |
rd | -0.056 |
seek | -0.055 |
t | -0.054 |
Token | pond |
Token ID | 16723 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
nam | +0.013 |
uted | +0.012 |
iring | +0.011 |
efully | +0.011 |
ishes | +0.011 |
Neg logit contributions | |
ar | -0.016 |
minutes | -0.015 |
t | -0.015 |
ever | -0.015 |
moment | -0.015 |
Token | One |
Token ID | 1881 |
Feature activation | -6.06e-01 |
Pos logit contributions | |
nam | +0.010 |
iring | +0.009 |
ble | +0.009 |
efully | +0.009 |
uted | +0.009 |
Neg logit contributions | |
ar | -0.009 |
t | -0.009 |
zed | -0.009 |
rd | -0.009 |
ake | -0.009 |
Token | day |
Token ID | 1110 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
ar | +0.018 |
seek | +0.016 |
zed | +0.016 |
injuries | +0.015 |
z | +0.015 |
Neg logit contributions | |
nam | -0.016 |
ble | -0.016 |
rad | -0.016 |
iring | -0.015 |
ot | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | -2.26e-02 |
Pos logit contributions | |
ar | +0.013 |
zed | +0.012 |
t | +0.012 |
rd | +0.012 |
ake | +0.012 |
Neg logit contributions | |
nam | -0.018 |
iring | -0.017 |
ble | -0.017 |
efully | -0.017 |
uted | -0.017 |
Token | Tim |
Token ID | 5045 |
Feature activation | +6.43e-01 |
Pos logit contributions | |
ar | +0.001 |
zed | +0.001 |
rd | +0.001 |
ake | +0.001 |
t | +0.001 |
Neg logit contributions | |
nam | -0.001 |
iring | -0.001 |
ble | -0.001 |
efully | -0.001 |
ishes | -0.001 |
Token | 's |
Token ID | 338 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
nam | +0.022 |
iring | +0.021 |
ble | +0.020 |
efully | +0.020 |
uted | +0.019 |
Neg logit contributions | |
ar | -0.015 |
t | -0.015 |
zed | -0.015 |
ake | -0.014 |
ever | -0.014 |
Token | mom |
Token ID | 1995 |
Feature activation | -4.74e-01 |
Pos logit contributions | |
zed | +0.007 |
ar | +0.007 |
rd | +0.006 |
t | +0.006 |
ake | +0.006 |
Neg logit contributions | |
nam | -0.004 |
iring | -0.004 |
ble | -0.004 |
ishes | -0.004 |
ot | -0.004 |
Token | made |
Token ID | 925 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
ar | +0.014 |
zed | +0.014 |
t | +0.014 |
ake | +0.013 |
rd | +0.013 |
Neg logit contributions | |
nam | -0.013 |
iring | -0.012 |
ble | -0.012 |
efully | -0.012 |
uted | -0.011 |
Token | some |
Token ID | 617 |
Feature activation | +5.57e-02 |
Pos logit contributions | |
ar | +0.029 |
zed | +0.028 |
t | +0.028 |
rd | +0.027 |
ake | +0.027 |
Neg logit contributions | |
nam | -0.037 |
iring | -0.035 |
ble | -0.035 |
efully | -0.034 |
uted | -0.033 |
Token | pasta |
Token ID | 26296 |
Feature activation | +4.04e-02 |
Pos logit contributions | |
nam | +0.002 |
efully | +0.002 |
uted | +0.002 |
iring | +0.002 |
ble | +0.002 |
Neg logit contributions | |
minutes | -0.001 |
rd | -0.001 |
t | -0.001 |
dreaming | -0.001 |
ever | -0.001 |
Token | for |
Token ID | 329 |
Feature activation | -8.58e-01 |
Pos logit contributions | |
nam | +0.001 |
ble | +0.001 |
iring | +0.001 |
bles | +0.001 |
ishes | +0.001 |
Neg logit contributions | |
ar | -0.001 |
zed | -0.001 |
rd | -0.001 |
t | -0.001 |
ake | -0.001 |
Token | dinner |
Token ID | 8073 |
Feature activation | -8.03e-01 |
Pos logit contributions | |
ar | +0.023 |
t | +0.023 |
rd | +0.022 |
ake | +0.022 |
zed | +0.021 |
Neg logit contributions | |
nam | -0.026 |
ble | -0.024 |
iring | -0.024 |
efully | -0.024 |
rad | -0.023 |
Token | out |
Token ID | 503 |
Feature activation | +7.86e-01 |
Pos logit contributions | |
nam | +0.023 |
iring | +0.021 |
ble | +0.021 |
efully | +0.021 |
uted | +0.020 |
Neg logit contributions | |
ar | -0.026 |
zed | -0.025 |
t | -0.025 |
rd | -0.024 |
ake | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | +5.10e-02 |
Pos logit contributions | |
nam | +0.021 |
iring | +0.019 |
ble | +0.018 |
efully | +0.018 |
ishes | +0.017 |
Neg logit contributions | |
ar | -0.025 |
t | -0.024 |
ake | -0.023 |
zed | -0.023 |
rd | -0.023 |
Token | She |
Token ID | 1375 |
Feature activation | +7.02e-01 |
Pos logit contributions | |
nam | +0.002 |
ble | +0.002 |
iring | +0.001 |
ishes | +0.001 |
efully | +0.001 |
Neg logit contributions | |
t | -0.001 |
ar | -0.001 |
minutes | -0.001 |
dreaming | -0.001 |
rd | -0.001 |
Token | said |
Token ID | 531 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
nam | +0.019 |
iring | +0.018 |
ble | +0.017 |
efully | +0.016 |
uted | +0.016 |
Neg logit contributions | |
ar | -0.021 |
ever | -0.021 |
zed | -0.021 |
t | -0.021 |
minutes | -0.021 |
Token | they |
Token ID | 484 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
ar | +0.008 |
ake | +0.008 |
rd | +0.008 |
zed | +0.008 |
t | +0.008 |
Neg logit contributions | |
nam | -0.009 |
av | -0.008 |
rad | -0.008 |
ot | -0.008 |
iring | -0.008 |
Token | were |
Token ID | 547 |
Feature activation | -4.15e-01 |
Pos logit contributions | |
ar | +0.041 |
t | +0.040 |
zed | +0.040 |
ever | +0.038 |
ake | +0.038 |
Neg logit contributions | |
nam | -0.038 |
iring | -0.036 |
ble | -0.035 |
efully | -0.035 |
uted | -0.034 |
Token | impressive |
Token ID | 8036 |
Feature activation | -4.91e-01 |
Pos logit contributions | |
dreaming | +0.011 |
ever | +0.011 |
minutes | +0.010 |
zed | +0.010 |
ar | +0.009 |
Neg logit contributions | |
iring | -0.012 |
ishes | -0.012 |
uted | -0.012 |
ble | -0.012 |
nam | -0.012 |
Token | twins |
Token ID | 20345 |
Feature activation | +4.95e-01 |
Pos logit contributions | |
zed | +0.017 |
t | +0.016 |
ar | +0.016 |
gh | +0.016 |
ake | +0.015 |
Neg logit contributions | |
iring | -0.012 |
nam | -0.011 |
efully | -0.011 |
ishes | -0.011 |
ins | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
nam | +0.009 |
iring | +0.008 |
ter | +0.008 |
friends | +0.008 |
efully | +0.007 |
Neg logit contributions | |
zed | -0.018 |
ar | -0.018 |
gh | -0.017 |
z | -0.017 |
ake | -0.017 |
Token | She |
Token ID | 1375 |
Feature activation | +8.28e-01 |
Pos logit contributions | |
nam | +0.004 |
ble | +0.003 |
iring | +0.003 |
ishes | +0.003 |
efully | +0.003 |
Neg logit contributions | |
t | -0.003 |
ar | -0.003 |
minutes | -0.003 |
dreaming | -0.003 |
rd | -0.003 |
Token | cl |
Token ID | 537 |
Feature activation | +7.51e-01 |
Pos logit contributions | |
nam | +0.022 |
iring | +0.020 |
ble | +0.019 |
efully | +0.018 |
ishes | +0.018 |
Neg logit contributions | |
ar | -0.026 |
ever | -0.026 |
t | -0.025 |
zed | -0.025 |
minutes | -0.024 |
Token | the |
Token ID | 262 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
nam | +0.029 |
iring | +0.027 |
ble | +0.026 |
rad | +0.024 |
uted | +0.024 |
Neg logit contributions | |
ar | -0.039 |
t | -0.038 |
ake | -0.036 |
rd | -0.036 |
seek | -0.035 |
Token | ugly |
Token ID | 13400 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
nam | +0.005 |
iring | +0.004 |
ble | +0.004 |
av | +0.004 |
rad | +0.004 |
Neg logit contributions | |
ar | -0.009 |
zed | -0.009 |
ake | -0.009 |
seek | -0.008 |
rd | -0.008 |
Token | things |
Token ID | 1243 |
Feature activation | +8.71e-01 |
Pos logit contributions | |
nam | +0.025 |
ble | +0.023 |
iring | +0.023 |
av | +0.021 |
rad | +0.021 |
Neg logit contributions | |
ar | -0.049 |
zed | -0.048 |
ake | -0.047 |
t | -0.046 |
rd | -0.046 |
Token | she |
Token ID | 673 |
Feature activation | -9.58e-01 |
Pos logit contributions | |
nam | +0.024 |
iring | +0.023 |
ble | +0.023 |
efully | +0.021 |
uted | +0.021 |
Neg logit contributions | |
ar | -0.025 |
rd | -0.024 |
zed | -0.024 |
ake | -0.024 |
minutes | -0.023 |
Token | had |
Token ID | 550 |
Feature activation | -7.01e-01 |
Pos logit contributions | |
ar | +0.027 |
ake | +0.027 |
rd | +0.027 |
zed | +0.026 |
stand | +0.026 |
Neg logit contributions | |
nam | -0.025 |
efully | -0.023 |
iring | -0.023 |
ble | -0.022 |
ishes | -0.022 |
Token | glimps |
Token ID | 41226 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
ar | +0.018 |
ake | +0.017 |
rd | +0.016 |
zed | +0.016 |
storm | +0.016 |
Neg logit contributions | |
nam | -0.021 |
iring | -0.019 |
uted | -0.019 |
ble | -0.019 |
efully | -0.019 |
Token | ed |
Token ID | 276 |
Feature activation | +4.16e-01 |
Pos logit contributions | |
ar | +0.071 |
minutes | +0.067 |
zed | +0.067 |
payoff | +0.066 |
rd | +0.066 |
Neg logit contributions | |
ble | -0.069 |
iring | -0.067 |
nam | -0.067 |
uted | -0.064 |
bles | -0.064 |
Token | . |
Token ID | 13 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
iring | +0.010 |
nam | +0.010 |
ble | +0.009 |
ishes | +0.008 |
rad | +0.008 |
Neg logit contributions | |
zed | -0.014 |
ar | -0.014 |
rd | -0.013 |
t | -0.013 |
seek | -0.013 |
Token | With |
Token ID | 2080 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
nam | +0.007 |
ble | +0.007 |
iring | +0.007 |
ishes | +0.006 |
bles | +0.006 |
Neg logit contributions | |
ar | -0.006 |
t | -0.006 |
zed | -0.006 |
rd | -0.006 |
ake | -0.006 |
Token | that |
Token ID | 326 |
Feature activation | +4.83e-01 |
Pos logit contributions | |
nam | +0.004 |
efully | +0.004 |
rad | +0.003 |
iring | +0.003 |
av | +0.003 |
Neg logit contributions | |
ar | -0.006 |
t | -0.005 |
rd | -0.005 |
ake | -0.005 |
seek | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | +8.34e-01 |
Pos logit contributions | |
nam | +0.013 |
rad | +0.011 |
ble | +0.011 |
iring | +0.011 |
efully | +0.010 |
Neg logit contributions | |
ake | -0.015 |
seek | -0.015 |
ar | -0.015 |
storm | -0.014 |
zed | -0.014 |
Token | things |
Token ID | 1243 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
ar | +0.045 |
zed | +0.043 |
t | +0.043 |
rd | +0.042 |
ake | +0.042 |
Neg logit contributions | |
nam | -0.042 |
iring | -0.040 |
ble | -0.039 |
efully | -0.039 |
uted | -0.038 |
Token | look |
Token ID | 804 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
nam | +0.045 |
iring | +0.043 |
ble | +0.043 |
efully | +0.041 |
uted | +0.040 |
Neg logit contributions | |
ar | -0.043 |
zed | -0.041 |
rd | -0.040 |
t | -0.040 |
ake | -0.040 |
Token | different |
Token ID | 1180 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
ar | +0.016 |
zed | +0.016 |
rd | +0.015 |
ake | +0.015 |
t | +0.015 |
Neg logit contributions | |
nam | -0.013 |
iring | -0.012 |
ble | -0.011 |
ishes | -0.011 |
uted | -0.011 |
Token | for |
Token ID | 329 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
nam | +0.048 |
iring | +0.045 |
ble | +0.044 |
efully | +0.044 |
uted | +0.042 |
Neg logit contributions | |
ar | -0.045 |
zed | -0.044 |
t | -0.044 |
ake | -0.042 |
rd | -0.042 |
Token | a |
Token ID | 257 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
ar | +0.010 |
zed | +0.010 |
t | +0.010 |
rd | +0.010 |
ake | +0.010 |
Neg logit contributions | |
nam | -0.011 |
iring | -0.010 |
ble | -0.010 |
efully | -0.009 |
uted | -0.009 |
Token | while |
Token ID | 981 |
Feature activation | -2.97e+00 |
Pos logit contributions | |
ar | +0.004 |
zed | +0.004 |
t | +0.004 |
rd | +0.004 |
ake | +0.004 |
Neg logit contributions | |
nam | -0.004 |
ble | -0.003 |
iring | -0.003 |
rad | -0.003 |
efully | -0.003 |
Token | ." |
Token ID | 526 |
Feature activation | -3.31e-02 |
Pos logit contributions | |
zed | +0.097 |
ar | +0.096 |
seek | +0.092 |
z | +0.090 |
rd | +0.090 |
Neg logit contributions | |
nam | -0.065 |
iring | -0.065 |
ble | -0.065 |
ot | -0.060 |
rad | -0.060 |
Token |
|
Token ID | 198 |
Feature activation | -8.80e-03 |
Pos logit contributions | |
t | +0.001 |
dreaming | +0.001 |
minutes | +0.001 |
ar | +0.001 |
stand | +0.001 |
Neg logit contributions | |
nam | -0.001 |
iring | -0.001 |
ishes | -0.001 |
ble | -0.001 |
efully | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
ake | +0.000 |
t | +0.000 |
zed | +0.000 |
stand | +0.000 |
ar | +0.000 |
Neg logit contributions | |
nam | -0.000 |
ishes | -0.000 |
efully | -0.000 |
iring | -0.000 |
ish | -0.000 |
Token | Ben |
Token ID | 11696 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
ar | +0.006 |
zed | +0.006 |
t | +0.006 |
ake | +0.006 |
rd | +0.006 |
Neg logit contributions | |
nam | -0.011 |
iring | -0.010 |
ble | -0.010 |
efully | -0.010 |
uted | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | -7.52e-01 |
Pos logit contributions | |
ar | +0.036 |
zed | +0.035 |
t | +0.035 |
ake | +0.034 |
rd | +0.034 |
Neg logit contributions | |
nam | -0.033 |
iring | -0.031 |
efully | -0.030 |
ble | -0.030 |
uted | -0.029 |
Token | Sometimes |
Token ID | 8975 |
Feature activation | -5.56e-01 |
Pos logit contributions | |
nam | +0.017 |
ble | +0.016 |
iring | +0.016 |
uted | +0.015 |
efully | +0.015 |
Neg logit contributions | |
ar | -0.011 |
t | -0.011 |
rd | -0.011 |
zed | -0.011 |
ake | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
ake | +0.018 |
ar | +0.017 |
zed | +0.017 |
t | +0.017 |
seek | +0.017 |
Neg logit contributions | |
nam | -0.013 |
iring | -0.013 |
ot | -0.012 |
rad | -0.012 |
ishes | -0.012 |
Token | Sam |
Token ID | 3409 |
Feature activation | -5.01e-01 |
Pos logit contributions | |
nam | +0.009 |
iring | +0.008 |
ble | +0.008 |
ot | +0.008 |
ishes | +0.008 |
Neg logit contributions | |
ar | -0.012 |
zed | -0.012 |
ake | -0.012 |
rd | -0.011 |
t | -0.011 |
Token | goes |
Token ID | 2925 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
ar | +0.014 |
rd | +0.014 |
ake | +0.013 |
t | +0.013 |
zed | +0.013 |
Neg logit contributions | |
nam | -0.013 |
ishes | -0.013 |
iring | -0.013 |
uted | -0.012 |
ble | -0.012 |
Token | with |
Token ID | 351 |
Feature activation | +2.36e-02 |
Pos logit contributions | |
rd | +0.034 |
zed | +0.033 |
ake | +0.031 |
gh | +0.030 |
basis | +0.029 |
Neg logit contributions | |
nam | -0.027 |
iring | -0.026 |
bles | -0.025 |
ishes | -0.024 |
ble | -0.024 |
Token | Jen |
Token ID | 13364 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
nam | +0.001 |
ot | +0.000 |
av | +0.000 |
rad | +0.000 |
ishes | +0.000 |
Neg logit contributions | |
ar | -0.001 |
ake | -0.001 |
t | -0.001 |
zed | -0.001 |
rd | -0.001 |
Token | to |
Token ID | 284 |
Feature activation | -6.11e-01 |
Pos logit contributions | |
ar | +0.073 |
zed | +0.071 |
rd | +0.070 |
t | +0.069 |
minutes | +0.069 |
Neg logit contributions | |
nam | -0.063 |
ishes | -0.061 |
iring | -0.057 |
ish | -0.055 |
uted | -0.055 |
Token | the |
Token ID | 262 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
ar | +0.019 |
t | +0.019 |
ake | +0.019 |
rd | +0.018 |
zed | +0.018 |
Neg logit contributions | |
nam | -0.017 |
ble | -0.014 |
iring | -0.014 |
efully | -0.014 |
rad | -0.014 |
Token | lab |
Token ID | 2248 |
Feature activation | -2.48e-02 |
Pos logit contributions | |
zed | +0.013 |
ar | +0.012 |
ake | +0.012 |
rd | +0.012 |
t | +0.012 |
Neg logit contributions | |
nam | -0.009 |
iring | -0.009 |
ble | -0.008 |
ot | -0.008 |
efully | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
zed | +0.001 |
ake | +0.001 |
rd | +0.001 |
da | +0.001 |
gh | +0.001 |
Neg logit contributions | |
nam | -0.001 |
iring | -0.001 |
vendors | -0.001 |
ishes | -0.000 |
ot | -0.000 |
Token | and |
Token ID | 290 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
ar | +0.011 |
rd | +0.011 |
ake | +0.011 |
t | +0.010 |
gh | +0.010 |
Neg logit contributions | |
nam | -0.009 |
iring | -0.007 |
ot | -0.007 |
ishes | -0.007 |
rad | -0.007 |
Token | , |
Token ID | 11 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
ar | +0.010 |
zed | +0.010 |
rd | +0.009 |
ake | +0.009 |
t | +0.009 |
Neg logit contributions | |
nam | -0.012 |
ble | -0.011 |
iring | -0.011 |
efully | -0.011 |
rad | -0.011 |
Token | a |
Token ID | 257 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
ar | +0.003 |
zed | +0.003 |
t | +0.003 |
rd | +0.003 |
ake | +0.003 |
Neg logit contributions | |
nam | -0.004 |
iring | -0.004 |
ble | -0.004 |
efully | -0.004 |
uted | -0.004 |
Token | little |
Token ID | 1310 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
nam | +0.007 |
iring | +0.006 |
ble | +0.006 |
efully | +0.006 |
uted | +0.006 |
Neg logit contributions | |
ar | -0.009 |
zed | -0.009 |
t | -0.009 |
rd | -0.009 |
ake | -0.009 |
Token | vehicle |
Token ID | 4038 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
nam | +0.025 |
iring | +0.023 |
ble | +0.022 |
efully | +0.022 |
uted | +0.021 |
Neg logit contributions | |
ar | -0.044 |
zed | -0.044 |
t | -0.043 |
rd | -0.042 |
ake | -0.042 |
Token | named |
Token ID | 3706 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
ar | +0.010 |
minutes | +0.010 |
rd | +0.010 |
zed | +0.009 |
ake | +0.009 |
Neg logit contributions | |
nam | -0.008 |
ble | -0.008 |
iring | -0.008 |
ot | -0.008 |
uted | -0.007 |
Token | V |
Token ID | 569 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
ar | +0.057 |
zed | +0.057 |
rd | +0.055 |
dreaming | +0.055 |
minutes | +0.055 |
Neg logit contributions | |
nam | -0.042 |
iring | -0.039 |
efully | -0.038 |
ble | -0.038 |
uted | -0.036 |
Token | icky |
Token ID | 17479 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
dreaming | +0.076 |
payoff | +0.074 |
minutes | +0.073 |
ar | +0.072 |
zed | +0.072 |
Neg logit contributions | |
ble | -0.062 |
iring | -0.061 |
uted | -0.060 |
efully | -0.058 |
ins | -0.058 |
Token | was |
Token ID | 373 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
ot | +0.003 |
ble | +0.003 |
rad | +0.003 |
uted | +0.003 |
iring | +0.003 |
Neg logit contributions | |
payoff | -0.005 |
injuries | -0.005 |
ar | -0.005 |
dreaming | -0.005 |
stand | -0.005 |
Token | driving |
Token ID | 5059 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
nam | +0.006 |
iring | +0.006 |
ble | +0.006 |
efully | +0.005 |
uted | +0.005 |
Neg logit contributions | |
ar | -0.006 |
zed | -0.005 |
t | -0.005 |
rd | -0.005 |
ake | -0.005 |
Token | down |
Token ID | 866 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
ar | +0.038 |
zed | +0.037 |
t | +0.036 |
rd | +0.035 |
ake | +0.035 |
Neg logit contributions | |
nam | -0.045 |
iring | -0.042 |
ble | -0.042 |
efully | -0.041 |
uted | -0.040 |
Token | a |
Token ID | 257 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
ar | +0.005 |
zed | +0.005 |
t | +0.005 |
rd | +0.005 |
ake | +0.005 |
Neg logit contributions | |
nam | -0.005 |
iring | -0.005 |
ble | -0.005 |
efully | -0.005 |
uted | -0.005 |
Token | dream |
Token ID | 4320 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
nam | +0.005 |
ble | +0.004 |
iring | +0.004 |
friends | +0.004 |
bles | +0.004 |
Neg logit contributions | |
ar | -0.008 |
ake | -0.007 |
t | -0.007 |
zed | -0.007 |
rd | -0.007 |
Token | was |
Token ID | 373 |
Feature activation | +4.97e-01 |
Pos logit contributions | |
rd | +0.074 |
ake | +0.072 |
ar | +0.072 |
basis | +0.070 |
minutes | +0.069 |
Neg logit contributions | |
ble | -0.045 |
iring | -0.044 |
bles | -0.040 |
nam | -0.040 |
ying | -0.039 |
Token | not |
Token ID | 407 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
nam | +0.011 |
iring | +0.010 |
ble | +0.010 |
rad | +0.009 |
av | +0.009 |
Neg logit contributions | |
ar | -0.018 |
rd | -0.017 |
ake | -0.017 |
z | -0.016 |
basis | -0.016 |
Token | just |
Token ID | 655 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
ar | +0.036 |
zed | +0.034 |
t | +0.034 |
rd | +0.034 |
ake | +0.033 |
Neg logit contributions | |
nam | -0.036 |
iring | -0.033 |
ble | -0.032 |
efully | -0.032 |
ishes | -0.031 |
Token | a |
Token ID | 257 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
ar | +0.081 |
t | +0.078 |
ake | +0.076 |
z | +0.075 |
rd | +0.074 |
Neg logit contributions | |
nam | -0.060 |
iring | -0.051 |
ot | -0.048 |
rad | -0.048 |
av | -0.047 |
Token | dream |
Token ID | 4320 |
Feature activation | -2.74e+00 |
Pos logit contributions | |
zed | +0.010 |
ar | +0.010 |
ake | +0.010 |
rd | +0.009 |
seek | +0.009 |
Neg logit contributions | |
nam | -0.006 |
rad | -0.006 |
ot | -0.006 |
friends | -0.005 |
idea | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -7.03e-02 |
Pos logit contributions | |
rd | +0.091 |
ar | +0.091 |
zed | +0.090 |
joy | +0.090 |
z | +0.089 |
Neg logit contributions | |
iring | -0.053 |
ble | -0.051 |
ying | -0.050 |
uted | -0.045 |
ters | -0.045 |
Token | It |
Token ID | 632 |
Feature activation | -5.47e-01 |
Pos logit contributions | |
t | +0.002 |
ar | +0.002 |
zed | +0.002 |
dreaming | +0.002 |
ake | +0.002 |
Neg logit contributions | |
nam | -0.002 |
ble | -0.002 |
iring | -0.002 |
ishes | -0.002 |
efully | -0.002 |
Token | was |
Token ID | 373 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
ar | +0.018 |
ake | +0.017 |
rd | +0.017 |
zed | +0.017 |
minutes | +0.017 |
Neg logit contributions | |
nam | -0.012 |
iring | -0.012 |
efully | -0.012 |
ble | -0.012 |
uted | -0.011 |
Token | a |
Token ID | 257 |
Feature activation | -6.94e-01 |
Pos logit contributions | |
ar | +0.009 |
rd | +0.008 |
t | +0.008 |
ake | +0.008 |
zed | +0.008 |
Neg logit contributions | |
nam | -0.007 |
iring | -0.007 |
ble | -0.006 |
efully | -0.006 |
rad | -0.006 |
Token | goal |
Token ID | 3061 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
zed | +0.024 |
ar | +0.023 |
rd | +0.023 |
seek | +0.023 |
t | +0.023 |
Neg logit contributions | |
nam | -0.016 |
rad | -0.015 |
ot | -0.014 |
ble | -0.014 |
rob | -0.013 |