Token | too |
Token ID | 1165 |
Feature activation | -3.05e-04 |
Pos logit contributions | |
bean | +0.004 |
narrative | +0.004 |
thank | +0.003 |
Prince | +0.003 |
relief | +0.003 |
Neg logit contributions | |
z | -0.005 |
ats | -0.005 |
ew | -0.005 |
zag | -0.004 |
om | -0.004 |
Token | dangerous |
Token ID | 4923 |
Feature activation | -1.36e-03 |
Pos logit contributions | |
z | +0.001 |
ats | +0.001 |
ew | +0.001 |
zag | +0.001 |
ahs | +0.000 |
Neg logit contributions | |
bean | -0.000 |
narrative | -0.000 |
Prince | -0.000 |
reef | -0.000 |
thank | -0.000 |
Token | to |
Token ID | 284 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
z | +0.003 |
ew | +0.003 |
ats | +0.003 |
zag | +0.003 |
eps | +0.003 |
Neg logit contributions | |
bean | -0.002 |
Prince | -0.002 |
thank | -0.002 |
Penny | -0.002 |
Claire | -0.002 |
Token | use |
Token ID | 779 |
Feature activation | -2.50e-03 |
Pos logit contributions | |
bean | +0.017 |
narrative | +0.016 |
Prince | +0.016 |
reef | +0.015 |
thank | +0.015 |
Neg logit contributions | |
z | -0.023 |
ats | -0.022 |
ew | -0.022 |
om | -0.021 |
zag | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | +1.53e-02 |
Pos logit contributions | |
z | +0.005 |
ew | +0.005 |
ats | +0.005 |
zag | +0.005 |
uddy | +0.005 |
Neg logit contributions | |
bean | -0.004 |
thank | -0.003 |
Prince | -0.003 |
Penny | -0.003 |
narrative | -0.003 |
Token | Fre |
Token ID | 4848 |
Feature activation | +5.99e-02 |
Pos logit contributions | |
bean | +0.024 |
narrative | +0.022 |
Prince | +0.022 |
reef | +0.021 |
cuc | +0.020 |
Neg logit contributions | |
z | -0.029 |
ats | -0.028 |
ew | -0.028 |
zag | -0.027 |
om | -0.026 |
Token | ya |
Token ID | 3972 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
bean | +0.113 |
Prince | +0.099 |
beans | +0.097 |
narrative | +0.094 |
salad | +0.094 |
Neg logit contributions | |
ats | -0.103 |
z | -0.098 |
out | -0.091 |
ind | -0.088 |
- | -0.088 |
Token | was |
Token ID | 373 |
Feature activation | +5.36e-03 |
Pos logit contributions | |
bean | +0.032 |
narrative | +0.029 |
Prince | +0.029 |
thank | +0.027 |
reef | +0.027 |
Neg logit contributions | |
z | -0.036 |
ats | -0.035 |
ew | -0.034 |
zag | -0.033 |
om | -0.032 |
Token | very |
Token ID | 845 |
Feature activation | -3.85e-03 |
Pos logit contributions | |
bean | +0.008 |
Prince | +0.008 |
thank | +0.007 |
narrative | +0.007 |
relief | +0.007 |
Neg logit contributions | |
z | -0.011 |
ats | -0.011 |
ew | -0.010 |
zag | -0.010 |
om | -0.009 |
Token | disappointed |
Token ID | 11679 |
Feature activation | +1.86e-02 |
Pos logit contributions | |
z | +0.008 |
ats | +0.008 |
ew | +0.007 |
zag | +0.007 |
om | +0.007 |
Neg logit contributions | |
bean | -0.006 |
narrative | -0.005 |
Prince | -0.005 |
thank | -0.005 |
reef | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | -3.15e-03 |
Pos logit contributions | |
bean | +0.027 |
thank | +0.026 |
Prince | +0.025 |
narrative | +0.025 |
Av | +0.023 |
Neg logit contributions | |
z | -0.040 |
ats | -0.039 |
ew | -0.037 |
zag | -0.035 |
om | -0.034 |
Token | lots |
Token ID | 6041 |
Feature activation | -6.80e-03 |
Pos logit contributions | |
bean | +0.016 |
Prince | +0.015 |
rice | +0.015 |
seaw | +0.015 |
diamonds | +0.015 |
Neg logit contributions | |
z | -0.025 |
ats | -0.025 |
ew | -0.025 |
zag | -0.024 |
om | -0.022 |
Token | of |
Token ID | 286 |
Feature activation | -2.66e-02 |
Pos logit contributions | |
z | +0.015 |
zag | +0.014 |
ats | +0.014 |
gy | +0.013 |
ew | +0.013 |
Neg logit contributions | |
thank | -0.010 |
bean | -0.009 |
Prince | -0.009 |
satisfaction | -0.009 |
refreshed | -0.009 |
Token | interesting |
Token ID | 3499 |
Feature activation | -4.06e-03 |
Pos logit contributions | |
z | +0.066 |
zag | +0.065 |
ats | +0.061 |
ew | +0.060 |
gy | +0.059 |
Neg logit contributions | |
thank | -0.031 |
Prince | -0.030 |
bean | -0.029 |
satisfaction | -0.029 |
seaw | -0.027 |
Token | things |
Token ID | 1243 |
Feature activation | +2.20e-03 |
Pos logit contributions | |
z | +0.009 |
zag | +0.009 |
o | +0.009 |
ew | +0.009 |
uddy | +0.009 |
Neg logit contributions | |
diamonds | -0.005 |
bean | -0.005 |
beans | -0.005 |
Prince | -0.005 |
rice | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +2.20e-02 |
Pos logit contributions | |
bean | +0.004 |
Prince | +0.003 |
thank | +0.003 |
rice | +0.003 |
reef | +0.003 |
Neg logit contributions | |
ew | -0.004 |
z | -0.004 |
ats | -0.004 |
om | -0.004 |
zag | -0.003 |
Token | J |
Token ID | 449 |
Feature activation | +5.94e-02 |
Pos logit contributions | |
bean | +0.032 |
narrative | +0.029 |
Prince | +0.029 |
reef | +0.028 |
pearl | +0.027 |
Neg logit contributions | |
z | -0.044 |
ats | -0.043 |
ew | -0.043 |
om | -0.041 |
zag | -0.040 |
Token | illy |
Token ID | 6548 |
Feature activation | -9.48e-06 |
Pos logit contributions | |
narrative | +0.081 |
bean | +0.080 |
reef | +0.080 |
Prince | +0.074 |
relief | +0.072 |
Neg logit contributions | |
ats | -0.125 |
z | -0.120 |
ew | -0.117 |
om | -0.110 |
- | -0.109 |
Token | had |
Token ID | 550 |
Feature activation | +7.79e-03 |
Token | a |
Token ID | 257 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
bean | +0.012 |
Prince | +0.012 |
Av | +0.011 |
refreshed | +0.011 |
Claire | +0.011 |
Neg logit contributions | |
z | -0.015 |
ew | -0.015 |
ats | -0.015 |
zag | -0.014 |
om | -0.014 |
Token | great |
Token ID | 1049 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
z | +0.029 |
ats | +0.028 |
ew | +0.027 |
zag | +0.026 |
oses | +0.025 |
Neg logit contributions | |
bean | -0.024 |
Prince | -0.022 |
reef | -0.021 |
narrative | -0.021 |
thank | -0.021 |
Token | time |
Token ID | 640 |
Feature activation | -9.24e-03 |
Pos logit contributions | |
z | +0.031 |
ew | +0.030 |
ats | +0.029 |
zag | +0.027 |
oses | +0.027 |
Neg logit contributions | |
bean | -0.023 |
Prince | -0.021 |
narrative | -0.021 |
reef | -0.020 |
thank | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | -5.12e-03 |
Pos logit contributions | |
z | +0.025 |
ats | +0.024 |
ew | +0.023 |
zag | +0.023 |
attered | +0.022 |
Neg logit contributions | |
bean | -0.011 |
Prince | -0.011 |
narrative | -0.010 |
Av | -0.009 |
Claire | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | +8.35e-03 |
Pos logit contributions | |
z | +0.010 |
ats | +0.010 |
ew | +0.009 |
zag | +0.009 |
om | +0.009 |
Neg logit contributions | |
bean | -0.008 |
Prince | -0.007 |
narrative | -0.007 |
reef | -0.007 |
Av | -0.007 |
Token | One |
Token ID | 3198 |
Feature activation | +1.51e-02 |
Pos logit contributions | |
bean | +0.016 |
Prince | +0.015 |
narrative | +0.015 |
reef | +0.015 |
thank | +0.014 |
Neg logit contributions | |
z | -0.013 |
ats | -0.012 |
ew | -0.012 |
zag | -0.011 |
om | -0.011 |
Token | morning |
Token ID | 3329 |
Feature activation | +1.00e-02 |
Pos logit contributions | |
narrative | +0.025 |
bean | +0.024 |
Prince | +0.024 |
cuc | +0.022 |
diamonds | +0.022 |
Neg logit contributions | |
z | -0.027 |
ats | -0.027 |
zag | -0.025 |
o | -0.025 |
- | -0.025 |
Token | , |
Token ID | 11 |
Feature activation | +1.71e-02 |
Pos logit contributions | |
bean | +0.019 |
Prince | +0.018 |
narrative | +0.017 |
reef | +0.017 |
cuc | +0.016 |
Neg logit contributions | |
z | -0.016 |
ats | -0.016 |
ew | -0.015 |
zag | -0.015 |
om | -0.014 |
Token | Fre |
Token ID | 4848 |
Feature activation | +5.88e-02 |
Pos logit contributions | |
bean | +0.027 |
narrative | +0.027 |
Prince | +0.025 |
reef | +0.023 |
relief | +0.023 |
Neg logit contributions | |
z | -0.033 |
ats | -0.031 |
ew | -0.030 |
zag | -0.030 |
om | -0.029 |
Token | ya |
Token ID | 3972 |
Feature activation | +8.94e-03 |
Pos logit contributions | |
bean | +0.099 |
Prince | +0.095 |
narrative | +0.091 |
beans | +0.083 |
Cr | +0.082 |
Neg logit contributions | |
ats | -0.109 |
z | -0.107 |
out | -0.099 |
zag | -0.094 |
- | -0.093 |
Token | was |
Token ID | 373 |
Feature activation | -3.62e-03 |
Pos logit contributions | |
bean | +0.016 |
Prince | +0.015 |
narrative | +0.014 |
reef | +0.014 |
thank | +0.013 |
Neg logit contributions | |
z | -0.016 |
ats | -0.015 |
ew | -0.015 |
zag | -0.014 |
om | -0.014 |
Token | feeling |
Token ID | 4203 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
z | +0.007 |
ats | +0.007 |
ew | +0.007 |
uddy | +0.007 |
ahs | +0.007 |
Neg logit contributions | |
bean | -0.005 |
refreshed | -0.005 |
Prince | -0.005 |
energ | -0.005 |
reef | -0.004 |
Token | very |
Token ID | 845 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
bean | +0.023 |
Prince | +0.021 |
narrative | +0.021 |
reef | +0.020 |
cuc | +0.019 |
Neg logit contributions | |
z | -0.023 |
ats | -0.022 |
ew | -0.022 |
zag | -0.021 |
om | -0.020 |
Token | anxious |
Token ID | 18116 |
Feature activation | +1.38e-03 |
Pos logit contributions | |
z | +0.029 |
ats | +0.029 |
ew | +0.028 |
zag | +0.027 |
om | +0.026 |
Neg logit contributions | |
bean | -0.021 |
narrative | -0.021 |
Prince | -0.020 |
reef | -0.018 |
cuc | -0.018 |
Token | |
Token ID | 220 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
bean | +0.016 |
Prince | +0.015 |
narrative | +0.015 |
reef | +0.014 |
Av | +0.013 |
Neg logit contributions | |
z | -0.022 |
ats | -0.021 |
ew | -0.021 |
zag | -0.020 |
om | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | -7.31e-03 |
Pos logit contributions | |
z | +0.026 |
ats | +0.026 |
ew | +0.025 |
attered | +0.024 |
zag | +0.024 |
Neg logit contributions | |
Prince | -0.011 |
bean | -0.011 |
narrative | -0.010 |
Av | -0.010 |
Claire | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | +9.50e-03 |
Pos logit contributions | |
z | +0.015 |
ats | +0.014 |
ew | +0.014 |
zag | +0.013 |
attered | +0.013 |
Neg logit contributions | |
bean | -0.010 |
Prince | -0.010 |
narrative | -0.010 |
reef | -0.009 |
Av | -0.009 |
Token | So |
Token ID | 2396 |
Feature activation | +8.06e-03 |
Pos logit contributions | |
bean | +0.017 |
narrative | +0.017 |
Prince | +0.017 |
reef | +0.016 |
Av | +0.015 |
Neg logit contributions | |
z | -0.015 |
ats | -0.015 |
ew | -0.014 |
zag | -0.014 |
om | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | +1.69e-02 |
Pos logit contributions | |
bean | +0.017 |
Prince | +0.015 |
narrative | +0.015 |
cuc | +0.015 |
reef | +0.015 |
Neg logit contributions | |
z | -0.011 |
ats | -0.010 |
ew | -0.010 |
zag | -0.010 |
- | -0.009 |
Token | Fre |
Token ID | 4848 |
Feature activation | +5.88e-02 |
Pos logit contributions | |
bean | +0.029 |
narrative | +0.027 |
Prince | +0.026 |
reef | +0.025 |
rice | +0.024 |
Neg logit contributions | |
z | -0.030 |
ats | -0.028 |
ew | -0.027 |
zag | -0.027 |
om | -0.026 |
Token | ya |
Token ID | 3972 |
Feature activation | +5.52e-03 |
Pos logit contributions | |
bean | +0.106 |
Prince | +0.100 |
narrative | +0.095 |
Cr | +0.092 |
beans | +0.091 |
Neg logit contributions | |
ats | -0.102 |
z | -0.098 |
out | -0.093 |
- | -0.089 |
ches | -0.087 |
Token | took |
Token ID | 1718 |
Feature activation | -1.67e-02 |
Pos logit contributions | |
bean | +0.008 |
Prince | +0.008 |
narrative | +0.007 |
reef | +0.007 |
sailor | +0.007 |
Neg logit contributions | |
z | -0.011 |
ew | -0.011 |
ats | -0.010 |
zag | -0.010 |
om | -0.010 |
Token | a |
Token ID | 257 |
Feature activation | -1.83e-02 |
Pos logit contributions | |
z | +0.030 |
ats | +0.029 |
ew | +0.028 |
zag | +0.027 |
om | +0.027 |
Neg logit contributions | |
bean | -0.028 |
Prince | -0.027 |
narrative | -0.027 |
reef | -0.025 |
cuc | -0.024 |
Token | deep |
Token ID | 2769 |
Feature activation | -2.08e-02 |
Pos logit contributions | |
z | +0.035 |
ats | +0.034 |
ew | +0.033 |
oses | +0.032 |
zag | +0.031 |
Neg logit contributions | |
bean | -0.030 |
Prince | -0.026 |
reef | -0.025 |
thank | -0.025 |
pearl | -0.024 |
Token | breath |
Token ID | 8033 |
Feature activation | -7.91e-03 |
Pos logit contributions | |
z | +0.040 |
ats | +0.039 |
ew | +0.037 |
zag | +0.036 |
om | +0.035 |
Neg logit contributions | |
bean | -0.033 |
Prince | -0.031 |
narrative | -0.031 |
reef | -0.029 |
cuc | -0.028 |
Token | their |
Token ID | 511 |
Feature activation | +2.45e-02 |
Pos logit contributions | |
bean | +0.002 |
narrative | +0.002 |
Prince | +0.002 |
reef | +0.002 |
cuc | +0.002 |
Neg logit contributions | |
z | -0.003 |
ats | -0.002 |
ew | -0.002 |
zag | -0.002 |
om | -0.002 |
Token | memories |
Token ID | 9846 |
Feature activation | +2.46e-02 |
Pos logit contributions | |
bean | +0.038 |
Prince | +0.036 |
narrative | +0.035 |
reef | +0.032 |
cuc | +0.032 |
Neg logit contributions | |
z | -0.048 |
ats | -0.046 |
ew | -0.045 |
zag | -0.043 |
om | -0.043 |
Token | forever |
Token ID | 8097 |
Feature activation | +2.63e-02 |
Pos logit contributions | |
bean | +0.045 |
Prince | +0.041 |
reef | +0.040 |
narrative | +0.040 |
thank | +0.039 |
Neg logit contributions | |
z | -0.042 |
ats | -0.042 |
ew | -0.042 |
zag | -0.038 |
om | -0.037 |
Token | . |
Token ID | 13 |
Feature activation | +3.47e-02 |
Pos logit contributions | |
bean | +0.048 |
Prince | +0.044 |
narrative | +0.042 |
reef | +0.041 |
thank | +0.041 |
Neg logit contributions | |
z | -0.046 |
ats | -0.045 |
ew | -0.044 |
zag | -0.041 |
om | -0.041 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +2.09e-02 |
Pos logit contributions | |
bean | +0.074 |
pearl | +0.070 |
seaw | +0.068 |
reef | +0.068 |
poppy | +0.068 |
Neg logit contributions | |
z | -0.041 |
om | -0.038 |
ats | -0.038 |
ables | -0.038 |
ew | -0.037 |
Token | Once |
Token ID | 7454 |
Feature activation | +5.86e-02 |
Pos logit contributions | |
bean | +0.040 |
narrative | +0.039 |
Prince | +0.037 |
thank | +0.036 |
pearl | +0.036 |
Neg logit contributions | |
z | -0.032 |
ats | -0.030 |
ew | -0.029 |
zag | -0.028 |
om | -0.028 |
Token | there |
Token ID | 612 |
Feature activation | -8.77e-03 |
Pos logit contributions | |
bean | +0.133 |
Prince | +0.127 |
narrative | +0.127 |
cuc | +0.120 |
reef | +0.120 |
Neg logit contributions | |
z | -0.070 |
ats | -0.069 |
ew | -0.064 |
zag | -0.062 |
om | -0.061 |
Token | was |
Token ID | 373 |
Feature activation | +9.05e-03 |
Pos logit contributions | |
ats | +0.013 |
z | +0.013 |
ew | +0.012 |
zag | +0.011 |
om | +0.011 |
Neg logit contributions | |
bean | -0.018 |
Prince | -0.017 |
reef | -0.016 |
narrative | -0.016 |
Av | -0.016 |
Token | a |
Token ID | 257 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
bean | +0.016 |
narrative | +0.015 |
Prince | +0.015 |
reef | +0.014 |
thank | +0.014 |
Neg logit contributions | |
z | -0.015 |
ats | -0.015 |
ew | -0.014 |
om | -0.014 |
zag | -0.014 |
Token | tree |
Token ID | 5509 |
Feature activation | -4.73e-04 |
Pos logit contributions | |
narrative | +0.020 |
bean | +0.018 |
Prince | +0.018 |
hospitality | +0.017 |
generosity | +0.017 |
Neg logit contributions | |
z | -0.016 |
ew | -0.015 |
om | -0.015 |
zag | -0.015 |
ats | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | +2.21e-02 |
Pos logit contributions | |
ats | +0.001 |
z | +0.001 |
ew | +0.001 |
drivers | +0.001 |
aned | +0.001 |
Neg logit contributions | |
bean | -0.001 |
reef | -0.001 |
poppy | -0.001 |
Prince | -0.001 |
narrative | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | +5.00e-03 |
Pos logit contributions | |
bean | +0.006 |
diamonds | +0.005 |
reef | +0.005 |
beans | +0.005 |
rice | +0.005 |
Neg logit contributions | |
ats | -0.008 |
z | -0.007 |
ew | -0.007 |
uddy | -0.007 |
erved | -0.007 |
Token | decorations |
Token ID | 39011 |
Feature activation | -5.69e-03 |
Pos logit contributions | |
bean | +0.008 |
Prince | +0.007 |
narrative | +0.007 |
thank | +0.007 |
reef | +0.007 |
Neg logit contributions | |
z | -0.010 |
ats | -0.010 |
ew | -0.009 |
zag | -0.009 |
om | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | +2.13e-02 |
Pos logit contributions | |
z | +0.010 |
ats | +0.010 |
ew | +0.010 |
zag | +0.010 |
om | +0.009 |
Neg logit contributions | |
bean | -0.009 |
thank | -0.008 |
Prince | -0.008 |
reef | -0.008 |
rice | -0.008 |
Token | M |
Token ID | 337 |
Feature activation | +2.00e-02 |
Pos logit contributions | |
bean | +0.036 |
narrative | +0.034 |
Prince | +0.033 |
reef | +0.031 |
pearl | +0.030 |
Neg logit contributions | |
z | -0.039 |
ats | -0.037 |
ew | -0.036 |
zag | -0.035 |
om | -0.034 |
Token | ummy |
Token ID | 13513 |
Feature activation | -8.84e-03 |
Pos logit contributions | |
bean | +0.033 |
narrative | +0.031 |
Prince | +0.031 |
reef | +0.029 |
thank | +0.028 |
Neg logit contributions | |
z | -0.037 |
ats | -0.036 |
ew | -0.035 |
zag | -0.033 |
om | -0.033 |
Token | and |
Token ID | 290 |
Feature activation | +5.74e-02 |
Pos logit contributions | |
z | +0.016 |
ats | +0.015 |
ew | +0.015 |
zag | +0.014 |
om | +0.013 |
Neg logit contributions | |
bean | -0.016 |
Prince | -0.015 |
reef | -0.014 |
cuc | -0.013 |
sailor | -0.013 |
Token | Daddy |
Token ID | 26926 |
Feature activation | -5.98e-03 |
Pos logit contributions | |
narrative | +0.083 |
bean | +0.068 |
tournament | +0.062 |
Prince | +0.061 |
reef | +0.061 |
Neg logit contributions | |
z | -0.110 |
om | -0.106 |
ew | -0.105 |
ats | -0.102 |
d | -0.101 |
Token | say |
Token ID | 910 |
Feature activation | +9.31e-03 |
Pos logit contributions | |
z | +0.012 |
ats | +0.011 |
ew | +0.011 |
zag | +0.011 |
om | +0.010 |
Neg logit contributions | |
bean | -0.009 |
Prince | -0.008 |
reef | -0.008 |
thank | -0.008 |
narrative | -0.008 |
Token | ed |
Token ID | 276 |
Feature activation | +8.50e-04 |
Pos logit contributions | |
bean | +0.015 |
narrative | +0.015 |
Prince | +0.014 |
reef | +0.013 |
cuc | +0.013 |
Neg logit contributions | |
z | -0.017 |
ew | -0.016 |
ats | -0.016 |
om | -0.015 |
zag | -0.015 |
Token | it |
Token ID | 340 |
Feature activation | +5.28e-03 |
Pos logit contributions | |
bean | +0.001 |
Prince | +0.001 |
thank | +0.001 |
Claire | +0.001 |
Av | +0.001 |
Neg logit contributions | |
ats | -0.002 |
zag | -0.002 |
z | -0.002 |
ew | -0.001 |
icycle | -0.001 |
Token | was |
Token ID | 373 |
Feature activation | +6.32e-03 |
Pos logit contributions | |
bean | +0.008 |
Av | +0.007 |
Claire | +0.007 |
thank | +0.007 |
reef | +0.007 |
Neg logit contributions | |
ats | -0.010 |
ew | -0.010 |
ud | -0.009 |
ippy | -0.009 |
z | -0.009 |
Token | with |
Token ID | 351 |
Feature activation | +2.38e-02 |
Pos logit contributions | |
bean | +0.062 |
Prince | +0.057 |
reef | +0.055 |
narrative | +0.055 |
thank | +0.053 |
Neg logit contributions | |
ats | -0.053 |
z | -0.052 |
ew | -0.051 |
zag | -0.047 |
om | -0.046 |
Token | sunshine |
Token ID | 34488 |
Feature activation | +5.72e-03 |
Pos logit contributions | |
bean | +0.023 |
Prince | +0.021 |
narrative | +0.020 |
reef | +0.018 |
thank | +0.017 |
Neg logit contributions | |
z | -0.060 |
ats | -0.059 |
ew | -0.058 |
zag | -0.057 |
om | -0.055 |
Token | . |
Token ID | 13 |
Feature activation | +1.74e-02 |
Pos logit contributions | |
bean | +0.010 |
Prince | +0.009 |
reef | +0.009 |
rice | +0.009 |
narrative | +0.009 |
Neg logit contributions | |
ats | -0.010 |
z | -0.010 |
ew | -0.010 |
zag | -0.009 |
om | -0.009 |
Token | M |
Token ID | 337 |
Feature activation | +2.70e-02 |
Pos logit contributions | |
bean | +0.031 |
narrative | +0.030 |
Prince | +0.028 |
pearl | +0.027 |
reef | +0.027 |
Neg logit contributions | |
z | -0.029 |
ew | -0.028 |
ats | -0.027 |
om | -0.027 |
zag | -0.025 |
Token | ummy |
Token ID | 13513 |
Feature activation | -5.47e-03 |
Pos logit contributions | |
bean | +0.049 |
narrative | +0.048 |
Prince | +0.048 |
reef | +0.046 |
cuc | +0.045 |
Neg logit contributions | |
z | -0.042 |
ats | -0.041 |
ew | -0.041 |
om | -0.038 |
zag | -0.036 |
Token | and |
Token ID | 290 |
Feature activation | +5.74e-02 |
Pos logit contributions | |
z | +0.008 |
ats | +0.008 |
ew | +0.008 |
zag | +0.007 |
om | +0.007 |
Neg logit contributions | |
bean | -0.011 |
Prince | -0.010 |
narrative | -0.010 |
reef | -0.010 |
thank | -0.009 |
Token | Daddy |
Token ID | 26926 |
Feature activation | -4.15e-03 |
Pos logit contributions | |
narrative | +0.097 |
tournament | +0.077 |
bean | +0.074 |
reef | +0.071 |
bead | +0.071 |
Neg logit contributions | |
z | -0.098 |
om | -0.095 |
ew | -0.092 |
d | -0.090 |
- | -0.090 |
Token | showed |
Token ID | 3751 |
Feature activation | +7.21e-03 |
Pos logit contributions | |
z | +0.007 |
ats | +0.007 |
ew | +0.007 |
zag | +0.007 |
om | +0.006 |
Neg logit contributions | |
bean | -0.007 |
Prince | -0.007 |
narrative | -0.007 |
reef | -0.006 |
thank | -0.006 |
Token | each |
Token ID | 1123 |
Feature activation | +8.73e-04 |
Pos logit contributions | |
bean | +0.008 |
Prince | +0.008 |
Av | +0.007 |
Claire | +0.007 |
beans | +0.006 |
Neg logit contributions | |
zag | -0.018 |
z | -0.018 |
ats | -0.017 |
ew | -0.017 |
icycle | -0.016 |
Token | other |
Token ID | 584 |
Feature activation | +1.95e-02 |
Pos logit contributions | |
bean | +0.001 |
Prince | +0.001 |
narrative | +0.001 |
reef | +0.001 |
thank | +0.001 |
Neg logit contributions | |
z | -0.002 |
ats | -0.002 |
ew | -0.002 |
zag | -0.002 |
om | -0.002 |
Token | how |
Token ID | 703 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
bean | +0.030 |
Prince | +0.027 |
reef | +0.026 |
rice | +0.025 |
thank | +0.025 |
Neg logit contributions | |
z | -0.039 |
ew | -0.039 |
ats | -0.038 |
zag | -0.037 |
om | -0.035 |
Token | sang |
Token ID | 25889 |
Feature activation | -1.90e-03 |
Pos logit contributions | |
z | +0.003 |
ats | +0.003 |
ew | +0.003 |
zag | +0.003 |
om | +0.003 |
Neg logit contributions | |
bean | -0.003 |
Prince | -0.003 |
reef | -0.003 |
narrative | -0.003 |
thank | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | -6.67e-03 |
Pos logit contributions | |
ats | +0.004 |
z | +0.004 |
ew | +0.004 |
zag | +0.003 |
om | +0.003 |
Neg logit contributions | |
bean | -0.003 |
Prince | -0.003 |
thank | -0.003 |
Av | -0.003 |
reef | -0.003 |
Token | happy |
Token ID | 3772 |
Feature activation | -3.62e-03 |
Pos logit contributions | |
z | +0.012 |
ew | +0.012 |
ats | +0.011 |
zag | +0.011 |
om | +0.011 |
Neg logit contributions | |
bean | -0.010 |
narrative | -0.010 |
Prince | -0.010 |
reef | -0.009 |
riage | -0.009 |
Token | song |
Token ID | 3496 |
Feature activation | -9.27e-03 |
Pos logit contributions | |
z | +0.007 |
ats | +0.006 |
ew | +0.006 |
zag | +0.006 |
om | +0.006 |
Neg logit contributions | |
bean | -0.005 |
narrative | -0.005 |
Prince | -0.005 |
reef | -0.005 |
cuc | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
ats | +0.018 |
z | +0.017 |
ew | +0.017 |
om | +0.015 |
attered | +0.015 |
Neg logit contributions | |
bean | -0.015 |
thank | -0.014 |
Prince | -0.014 |
Av | -0.012 |
reef | -0.012 |
Token | J |
Token ID | 449 |
Feature activation | +5.71e-02 |
Pos logit contributions | |
bean | +0.023 |
hospitality | +0.022 |
pearl | +0.022 |
sailor | +0.021 |
reef | +0.021 |
Neg logit contributions | |
om | -0.018 |
ew | -0.017 |
ats | -0.016 |
z | -0.016 |
d | -0.016 |
Token | illy |
Token ID | 6548 |
Feature activation | -9.03e-03 |
Pos logit contributions | |
narrative | +0.085 |
reef | +0.079 |
relief | +0.078 |
bean | +0.078 |
thank | +0.076 |
Neg logit contributions | |
ats | -0.116 |
z | -0.107 |
ew | -0.105 |
- | -0.102 |
om | -0.100 |
Token | started |
Token ID | 2067 |
Feature activation | -6.73e-03 |
Pos logit contributions | |
z | +0.016 |
ats | +0.015 |
ew | +0.015 |
zag | +0.014 |
om | +0.014 |
Neg logit contributions | |
bean | -0.016 |
Prince | -0.015 |
reef | -0.014 |
narrative | -0.014 |
thank | -0.014 |
Token | to |
Token ID | 284 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
ats | +0.009 |
z | +0.009 |
ew | +0.009 |
zag | +0.008 |
uddy | +0.007 |
Neg logit contributions | |
bean | -0.015 |
Prince | -0.014 |
reef | -0.013 |
poppy | -0.013 |
cuc | -0.013 |
Token | smile |
Token ID | 8212 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
bean | +0.015 |
narrative | +0.014 |
Prince | +0.014 |
reef | +0.013 |
pearl | +0.012 |
Neg logit contributions | |
z | -0.027 |
ats | -0.026 |
ew | -0.025 |
zag | -0.025 |
om | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | +5.44e-03 |
Pos logit contributions | |
bean | +0.021 |
Prince | +0.020 |
narrative | +0.019 |
reef | +0.018 |
thank | +0.018 |
Neg logit contributions | |
ats | -0.018 |
z | -0.018 |
ew | -0.017 |
zag | -0.016 |
om | -0.015 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +2.21e-04 |
Pos logit contributions | |
ew | +0.003 |
om | +0.003 |
o | +0.003 |
z | +0.003 |
ats | +0.002 |
Neg logit contributions | |
pearl | -0.006 |
reef | -0.006 |
bean | -0.006 |
narrative | -0.006 |
seaw | -0.006 |
Token | Tom |
Token ID | 13787 |
Feature activation | +1.76e-02 |
Pos logit contributions | |
bean | +0.000 |
narrative | +0.000 |
Prince | +0.000 |
thank | +0.000 |
generosity | +0.000 |
Neg logit contributions | |
z | -0.000 |
ew | -0.000 |
ats | -0.000 |
om | -0.000 |
zag | -0.000 |
Token | my |
Token ID | 1820 |
Feature activation | -2.77e-03 |
Pos logit contributions | |
bean | +0.038 |
Prince | +0.037 |
narrative | +0.034 |
reef | +0.034 |
Av | +0.033 |
Neg logit contributions | |
z | -0.025 |
ew | -0.023 |
ats | -0.022 |
zag | -0.022 |
om | -0.019 |
Token | loved |
Token ID | 6151 |
Feature activation | +2.10e-02 |
Pos logit contributions | |
z | +0.005 |
ats | +0.004 |
ew | +0.004 |
zag | +0.004 |
om | +0.004 |
Neg logit contributions | |
bean | -0.005 |
Prince | -0.005 |
narrative | -0.005 |
reef | -0.004 |
thank | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | +1.98e-02 |
Pos logit contributions | |
bean | +0.051 |
narrative | +0.049 |
Prince | +0.049 |
reef | +0.047 |
thank | +0.045 |
Neg logit contributions | |
z | -0.022 |
ats | -0.021 |
ew | -0.020 |
zag | -0.018 |
om | -0.018 |
Token | look |
Token ID | 804 |
Feature activation | +5.69e-02 |
Pos logit contributions | |
narrative | +0.032 |
bean | +0.032 |
Prince | +0.030 |
reef | +0.028 |
pearl | +0.027 |
Neg logit contributions | |
z | -0.035 |
ats | -0.035 |
ew | -0.033 |
zag | -0.033 |
om | -0.032 |
Token | at |
Token ID | 379 |
Feature activation | +5.39e-04 |
Pos logit contributions | |
bean | +0.116 |
Prince | +0.111 |
reef | +0.105 |
narrative | +0.104 |
thank | +0.102 |
Neg logit contributions | |
z | -0.087 |
ats | -0.081 |
ew | -0.080 |
zag | -0.080 |
om | -0.072 |
Token | small |
Token ID | 1402 |
Feature activation | +1.59e-02 |
Pos logit contributions | |
bean | +0.001 |
Prince | +0.001 |
reef | +0.001 |
narrative | +0.001 |
pearl | +0.000 |
Neg logit contributions | |
z | -0.001 |
ats | -0.001 |
ew | -0.001 |
zag | -0.001 |
om | -0.001 |
Token | things |
Token ID | 1243 |
Feature activation | +1.96e-02 |
Pos logit contributions | |
bean | +0.027 |
Prince | +0.025 |
reef | +0.024 |
beans | +0.023 |
narrative | +0.023 |
Neg logit contributions | |
z | -0.032 |
zag | -0.031 |
ats | -0.030 |
ew | -0.029 |
om | -0.027 |
Token | with |
Token ID | 351 |
Feature activation | +2.12e-02 |
Pos logit contributions | |
bean | +0.037 |
Prince | +0.035 |
narrative | +0.033 |
reef | +0.033 |
thank | +0.032 |
Neg logit contributions | |
z | -0.032 |
ats | -0.032 |
ew | -0.031 |
zag | -0.029 |
om | -0.028 |
Token | his |
Token ID | 465 |
Feature activation | +1.53e-02 |
Pos logit contributions | |
bean | +0.031 |
Prince | +0.029 |
reef | +0.026 |
narrative | +0.026 |
rice | +0.026 |
Neg logit contributions | |
z | -0.046 |
ats | -0.044 |
ew | -0.043 |
zag | -0.043 |
om | -0.039 |
Token | relax |
Token ID | 8960 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
z | +0.027 |
ats | +0.027 |
ew | +0.026 |
om | +0.025 |
zag | +0.025 |
Neg logit contributions | |
bean | -0.017 |
Prince | -0.016 |
thank | -0.015 |
narrative | -0.015 |
reef | -0.015 |
Token | for |
Token ID | 329 |
Feature activation | -2.06e-02 |
Pos logit contributions | |
bean | +0.026 |
Prince | +0.024 |
narrative | +0.024 |
reef | +0.023 |
thank | +0.022 |
Neg logit contributions | |
z | -0.033 |
ats | -0.033 |
ew | -0.032 |
zag | -0.031 |
om | -0.030 |
Token | a |
Token ID | 257 |
Feature activation | -9.97e-03 |
Pos logit contributions | |
z | +0.039 |
ats | +0.038 |
ew | +0.037 |
zag | +0.036 |
om | +0.035 |
Neg logit contributions | |
bean | -0.033 |
Prince | -0.031 |
narrative | -0.030 |
reef | -0.028 |
thank | -0.027 |
Token | bit |
Token ID | 1643 |
Feature activation | +3.45e-02 |
Pos logit contributions | |
z | +0.018 |
ats | +0.018 |
ew | +0.017 |
zag | +0.016 |
om | +0.016 |
Neg logit contributions | |
bean | -0.017 |
Prince | -0.016 |
narrative | -0.015 |
reef | -0.015 |
thank | -0.014 |
Token | ?". |
Token ID | 43634 |
Feature activation | +3.31e-02 |
Pos logit contributions | |
bean | +0.048 |
Prince | +0.044 |
narrative | +0.043 |
reef | +0.042 |
thank | +0.041 |
Neg logit contributions | |
z | -0.075 |
ats | -0.070 |
ew | -0.069 |
zag | -0.068 |
om | -0.065 |
Token | C |
Token ID | 327 |
Feature activation | +5.62e-02 |
Pos logit contributions | |
bean | +0.047 |
narrative | +0.044 |
reef | +0.043 |
Prince | +0.042 |
pearl | +0.039 |
Neg logit contributions | |
z | -0.068 |
ew | -0.066 |
ats | -0.065 |
om | -0.063 |
zag | -0.061 |
Token | eline |
Token ID | 4470 |
Feature activation | +2.18e-02 |
Pos logit contributions | |
bean | +0.100 |
Prince | +0.094 |
narrative | +0.093 |
reef | +0.088 |
Av | +0.086 |
Neg logit contributions | |
z | -0.096 |
ats | -0.092 |
ew | -0.089 |
zag | -0.088 |
om | -0.083 |
Token | nodded |
Token ID | 14464 |
Feature activation | +2.37e-02 |
Pos logit contributions | |
bean | +0.022 |
Prince | +0.020 |
Av | +0.018 |
reef | +0.017 |
thank | +0.017 |
Neg logit contributions | |
z | -0.054 |
ats | -0.054 |
ew | -0.052 |
zag | -0.051 |
om | -0.049 |
Token | . |
Token ID | 13 |
Feature activation | +2.90e-02 |
Pos logit contributions | |
bean | +0.048 |
narrative | +0.046 |
Prince | +0.045 |
reef | +0.043 |
cuc | +0.042 |
Neg logit contributions | |
z | -0.035 |
ats | -0.033 |
ew | -0.032 |
zag | -0.030 |
om | -0.030 |
Token | |
Token ID | 220 |
Feature activation | +4.18e-03 |
Pos logit contributions | |
bean | +0.047 |
narrative | +0.044 |
Prince | +0.044 |
reef | +0.042 |
pearl | +0.039 |
Neg logit contributions | |
z | -0.054 |
ats | -0.052 |
ew | -0.051 |
zag | -0.049 |
om | -0.049 |
Token |
|
Token ID | 198 |
Feature activation | +7.47e-03 |
Pos logit contributions | |
Prince | +0.004 |
bean | +0.004 |
Av | +0.004 |
narrative | +0.004 |
Nancy | +0.004 |
Neg logit contributions | |
z | -0.009 |
ats | -0.009 |
zag | -0.009 |
ew | -0.009 |
erved | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
z | +0.002 |
ats | +0.002 |
ew | +0.002 |
zag | +0.002 |
om | +0.002 |
Neg logit contributions | |
bean | -0.003 |
Prince | -0.002 |
narrative | -0.002 |
reef | -0.002 |
thank | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +8.29e-03 |
Pos logit contributions | |
bean | +0.025 |
Prince | +0.023 |
narrative | +0.023 |
reef | +0.021 |
thank | +0.021 |
Neg logit contributions | |
z | -0.027 |
ats | -0.027 |
ew | -0.026 |
zag | -0.025 |
om | -0.024 |
Token |
|
Token ID | 198 |
Feature activation | +1.85e-02 |
Pos logit contributions | |
bean | +0.013 |
Prince | +0.012 |
narrative | +0.012 |
reef | +0.011 |
thank | +0.011 |
Neg logit contributions | |
z | -0.016 |
ats | -0.015 |
ew | -0.015 |
zag | -0.015 |
om | -0.014 |
Token | Grand |
Token ID | 23581 |
Feature activation | +2.48e-02 |
Pos logit contributions | |
bean | +0.036 |
Prince | +0.034 |
narrative | +0.033 |
reef | +0.032 |
cuc | +0.031 |
Neg logit contributions | |
z | -0.029 |
ats | -0.028 |
ew | -0.027 |
zag | -0.026 |
om | -0.026 |
Token | ma |
Token ID | 2611 |
Feature activation | +3.68e-03 |
Pos logit contributions | |
bean | +0.047 |
Prince | +0.044 |
narrative | +0.043 |
reef | +0.042 |
cuc | +0.041 |
Neg logit contributions | |
z | -0.040 |
ats | -0.039 |
ew | -0.038 |
zag | -0.036 |
om | -0.035 |
Token | and |
Token ID | 290 |
Feature activation | +5.61e-02 |
Pos logit contributions | |
bean | +0.006 |
Prince | +0.006 |
thank | +0.005 |
sailor | +0.005 |
reef | +0.005 |
Neg logit contributions | |
ats | -0.007 |
z | -0.007 |
ew | -0.006 |
zag | -0.006 |
attered | -0.006 |
Token | grand |
Token ID | 4490 |
Feature activation | +1.72e-02 |
Pos logit contributions | |
bean | +0.083 |
narrative | +0.081 |
reef | +0.076 |
Prince | +0.072 |
pearl | +0.071 |
Neg logit contributions | |
z | -0.108 |
ats | -0.106 |
ew | -0.102 |
om | -0.102 |
zag | -0.096 |
Token | pa |
Token ID | 8957 |
Feature activation | -8.75e-03 |
Pos logit contributions | |
bean | +0.026 |
Prince | +0.025 |
narrative | +0.025 |
reef | +0.023 |
thank | +0.023 |
Neg logit contributions | |
z | -0.034 |
ats | -0.032 |
ew | -0.032 |
zag | -0.031 |
om | -0.030 |
Token | took |
Token ID | 1718 |
Feature activation | -1.30e-03 |
Pos logit contributions | |
z | +0.017 |
ats | +0.016 |
ew | +0.016 |
om | +0.015 |
zag | +0.015 |
Neg logit contributions | |
bean | -0.014 |
narrative | -0.013 |
Prince | -0.013 |
reef | -0.012 |
cuc | -0.012 |
Token | them |
Token ID | 606 |
Feature activation | -5.15e-03 |
Pos logit contributions | |
zag | +0.002 |
z | +0.002 |
ew | +0.002 |
ats | +0.002 |
ahs | +0.002 |
Neg logit contributions | |
Prince | -0.002 |
bean | -0.002 |
Claire | -0.002 |
Av | -0.002 |
thank | -0.002 |
Token | inside |
Token ID | 2641 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
ew | +0.009 |
z | +0.008 |
ats | +0.008 |
attered | +0.007 |
zag | +0.007 |
Neg logit contributions | |
bean | -0.009 |
Prince | -0.009 |
hospitality | -0.008 |
thank | -0.008 |
Av | -0.008 |
Token | when |
Token ID | 618 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
bean | +0.017 |
narrative | +0.016 |
Prince | +0.014 |
reef | +0.014 |
cuc | +0.014 |
Neg logit contributions | |
z | -0.021 |
ats | -0.020 |
zag | -0.020 |
ew | -0.019 |
om | -0.019 |
Token | she |
Token ID | 673 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
bean | +0.025 |
narrative | +0.023 |
cuc | +0.022 |
Prince | +0.022 |
rice | +0.021 |
Neg logit contributions | |
z | -0.028 |
zag | -0.027 |
ats | -0.026 |
ew | -0.026 |
om | -0.025 |
Token | was |
Token ID | 373 |
Feature activation | -2.96e-03 |
Pos logit contributions | |
z | +0.020 |
ats | +0.020 |
ew | +0.019 |
zag | +0.018 |
om | +0.017 |
Neg logit contributions | |
bean | -0.027 |
Prince | -0.025 |
narrative | -0.025 |
reef | -0.024 |
thank | -0.023 |
Token | done |
Token ID | 1760 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
z | +0.005 |
ats | +0.005 |
ew | +0.005 |
zag | +0.005 |
om | +0.004 |
Neg logit contributions | |
bean | -0.005 |
Prince | -0.005 |
narrative | -0.005 |
reef | -0.005 |
thank | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | +9.69e-03 |
Pos logit contributions | |
ats | +0.019 |
z | +0.019 |
ew | +0.018 |
zag | +0.018 |
ches | +0.017 |
Neg logit contributions | |
bean | -0.016 |
Prince | -0.015 |
narrative | -0.014 |
thank | -0.014 |
Av | -0.014 |
Token | Fre |
Token ID | 4848 |
Feature activation | +5.61e-02 |
Pos logit contributions | |
bean | +0.015 |
narrative | +0.014 |
Prince | +0.012 |
reef | +0.012 |
cuc | +0.012 |
Neg logit contributions | |
z | -0.018 |
ats | -0.017 |
ew | -0.017 |
zag | -0.017 |
om | -0.016 |
Token | ya |
Token ID | 3972 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
bean | +0.104 |
Prince | +0.092 |
beans | +0.089 |
narrative | +0.089 |
Cr | +0.087 |
Neg logit contributions | |
ats | -0.095 |
z | -0.091 |
out | -0.086 |
ind | -0.083 |
- | -0.082 |
Token | realized |
Token ID | 6939 |
Feature activation | -6.56e-03 |
Pos logit contributions | |
bean | +0.028 |
Prince | +0.025 |
narrative | +0.025 |
reef | +0.024 |
thank | +0.023 |
Neg logit contributions | |
z | -0.031 |
ats | -0.030 |
ew | -0.029 |
zag | -0.028 |
om | -0.027 |
Token | that |
Token ID | 326 |
Feature activation | +5.29e-03 |
Pos logit contributions | |
z | +0.013 |
ats | +0.013 |
ew | +0.013 |
zag | +0.012 |
om | +0.012 |
Neg logit contributions | |
bean | -0.010 |
Prince | -0.009 |
narrative | -0.009 |
reef | -0.009 |
thank | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | -7.43e-03 |
Pos logit contributions | |
bean | +0.007 |
Prince | +0.007 |
narrative | +0.007 |
reef | +0.007 |
cuc | +0.006 |
Neg logit contributions | |
z | -0.011 |
ats | -0.011 |
ew | -0.010 |
zag | -0.010 |
om | -0.010 |
Token | stair |
Token ID | 18761 |
Feature activation | -4.61e-04 |
Pos logit contributions | |
z | +0.014 |
ats | +0.014 |
ew | +0.014 |
zag | +0.013 |
om | +0.013 |
Neg logit contributions | |
bean | -0.012 |
narrative | -0.011 |
Prince | -0.011 |
reef | -0.010 |
thank | -0.010 |
Token | in |
Token ID | 287 |
Feature activation | -3.79e-03 |
Pos logit contributions | |
bean | +0.016 |
Prince | +0.015 |
narrative | +0.015 |
thank | +0.014 |
reef | +0.014 |
Neg logit contributions | |
z | -0.020 |
ats | -0.020 |
ew | -0.020 |
zag | -0.019 |
om | -0.018 |
Token | order |
Token ID | 1502 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
z | +0.007 |
ats | +0.007 |
ew | +0.007 |
zag | +0.007 |
om | +0.007 |
Neg logit contributions | |
bean | -0.006 |
Prince | -0.005 |
narrative | -0.005 |
reef | -0.005 |
cuc | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +1.93e-02 |
Pos logit contributions | |
bean | +0.015 |
thank | +0.015 |
Prince | +0.014 |
rice | +0.014 |
generosity | +0.014 |
Neg logit contributions | |
z | -0.020 |
ew | -0.020 |
zag | -0.019 |
ats | -0.019 |
om | -0.018 |
Token | M |
Token ID | 337 |
Feature activation | +1.88e-02 |
Pos logit contributions | |
bean | +0.032 |
narrative | +0.030 |
Prince | +0.029 |
reef | +0.028 |
pearl | +0.026 |
Neg logit contributions | |
z | -0.036 |
ats | -0.035 |
ew | -0.034 |
zag | -0.033 |
om | -0.032 |
Token | ummy |
Token ID | 13513 |
Feature activation | -7.89e-03 |
Pos logit contributions | |
bean | +0.031 |
narrative | +0.029 |
Prince | +0.029 |
reef | +0.028 |
cuc | +0.027 |
Neg logit contributions | |
z | -0.034 |
ats | -0.034 |
ew | -0.033 |
zag | -0.031 |
om | -0.031 |
Token | and |
Token ID | 290 |
Feature activation | +5.60e-02 |
Pos logit contributions | |
z | +0.014 |
ats | +0.014 |
ew | +0.014 |
zag | +0.013 |
om | +0.012 |
Neg logit contributions | |
bean | -0.014 |
Prince | -0.013 |
narrative | -0.012 |
reef | -0.012 |
thank | -0.012 |
Token | Daddy |
Token ID | 26926 |
Feature activation | -8.10e-03 |
Pos logit contributions | |
narrative | +0.087 |
bean | +0.069 |
tournament | +0.068 |
reef | +0.067 |
riage | +0.064 |
Neg logit contributions | |
z | -0.098 |
om | -0.095 |
ew | -0.091 |
ats | -0.089 |
o | -0.088 |
Token | breathed |
Token ID | 39545 |
Feature activation | +2.18e-02 |
Pos logit contributions | |
z | +0.017 |
ats | +0.016 |
ew | +0.016 |
zag | +0.016 |
om | +0.015 |
Neg logit contributions | |
bean | -0.011 |
Prince | -0.010 |
narrative | -0.010 |
thank | -0.010 |
reef | -0.010 |
Token | a |
Token ID | 257 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
bean | +0.039 |
Prince | +0.037 |
narrative | +0.036 |
reef | +0.034 |
thank | +0.033 |
Neg logit contributions | |
z | -0.038 |
ats | -0.037 |
ew | -0.035 |
zag | -0.035 |
om | -0.033 |
Token | huge |
Token ID | 3236 |
Feature activation | -7.95e-03 |
Pos logit contributions | |
z | +0.033 |
ats | +0.032 |
ew | +0.032 |
zag | +0.031 |
om | +0.030 |
Neg logit contributions | |
bean | -0.021 |
Prince | -0.020 |
narrative | -0.019 |
reef | -0.018 |
cuc | -0.017 |
Token | sigh |
Token ID | 19680 |
Feature activation | +2.00e-02 |
Pos logit contributions | |
z | +0.018 |
ats | +0.017 |
ew | +0.017 |
zag | +0.016 |
om | +0.016 |
Neg logit contributions | |
bean | -0.010 |
Prince | -0.009 |
narrative | -0.009 |
reef | -0.008 |
thank | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | +6.42e-03 |
Pos logit contributions | |
z | +0.013 |
ats | +0.013 |
ew | +0.012 |
zag | +0.012 |
om | +0.012 |
Neg logit contributions | |
bean | -0.005 |
Prince | -0.004 |
reef | -0.004 |
narrative | -0.004 |
seaw | -0.004 |
Token | lake |
Token ID | 13546 |
Feature activation | -3.57e-03 |
Pos logit contributions | |
bean | +0.009 |
Prince | +0.009 |
narrative | +0.009 |
Av | +0.008 |
thank | +0.008 |
Neg logit contributions | |
z | -0.013 |
ats | -0.013 |
ew | -0.012 |
zag | -0.012 |
om | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | +2.15e-02 |
Pos logit contributions | |
ats | +0.007 |
ew | +0.007 |
z | +0.007 |
icycle | +0.006 |
uddy | +0.006 |
Neg logit contributions | |
bean | -0.005 |
reef | -0.005 |
refreshed | -0.004 |
Prince | -0.004 |
rice | -0.004 |
Token | M |
Token ID | 337 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
bean | +0.037 |
Prince | +0.035 |
narrative | +0.034 |
reef | +0.033 |
cuc | +0.032 |
Neg logit contributions | |
z | -0.038 |
ats | -0.037 |
ew | -0.036 |
zag | -0.035 |
om | -0.033 |
Token | ummy |
Token ID | 13513 |
Feature activation | -4.67e-03 |
Pos logit contributions | |
bean | +0.035 |
narrative | +0.033 |
Prince | +0.033 |
reef | +0.032 |
cuc | +0.031 |
Neg logit contributions | |
z | -0.036 |
ats | -0.035 |
ew | -0.034 |
zag | -0.032 |
om | -0.032 |
Token | and |
Token ID | 290 |
Feature activation | +5.57e-02 |
Pos logit contributions | |
z | +0.008 |
ats | +0.008 |
ew | +0.008 |
zag | +0.007 |
attered | +0.007 |
Neg logit contributions | |
bean | -0.008 |
Prince | -0.008 |
reef | -0.007 |
sailor | -0.007 |
cuc | -0.007 |
Token | daddy |
Token ID | 35822 |
Feature activation | -7.78e-03 |
Pos logit contributions | |
narrative | +0.088 |
bean | +0.067 |
tournament | +0.065 |
hospitality | +0.064 |
coc | +0.063 |
Neg logit contributions | |
z | -0.101 |
om | -0.098 |
ew | -0.093 |
- | -0.092 |
ats | -0.090 |
Token | waved |
Token ID | 26834 |
Feature activation | +7.08e-03 |
Pos logit contributions | |
z | +0.015 |
ew | +0.015 |
ats | +0.015 |
zag | +0.014 |
om | +0.014 |
Neg logit contributions | |
bean | -0.011 |
Prince | -0.010 |
reef | -0.010 |
sailor | -0.010 |
thank | -0.010 |
Token | to |
Token ID | 284 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
bean | +0.011 |
Prince | +0.011 |
thank | +0.010 |
narrative | +0.010 |
reef | +0.010 |
Neg logit contributions | |
ats | -0.014 |
z | -0.014 |
ew | -0.013 |
zag | -0.013 |
om | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
narrative | +0.035 |
bean | +0.034 |
Prince | +0.031 |
reef | +0.030 |
pearl | +0.029 |
Neg logit contributions | |
z | -0.035 |
ats | -0.034 |
ew | -0.032 |
om | -0.030 |
zag | -0.029 |
Token | elderly |
Token ID | 13830 |
Feature activation | +2.83e-02 |
Pos logit contributions | |
bean | +0.022 |
narrative | +0.021 |
Prince | +0.020 |
reef | +0.018 |
cuc | +0.018 |
Neg logit contributions | |
z | -0.034 |
ats | -0.033 |
ew | -0.032 |
zag | -0.031 |
om | -0.031 |
Token | was |
Token ID | 373 |
Feature activation | +1.46e-02 |
Pos logit contributions | |
z | +0.024 |
ats | +0.024 |
ew | +0.023 |
zag | +0.022 |
om | +0.021 |
Neg logit contributions | |
bean | -0.018 |
Prince | -0.017 |
narrative | -0.016 |
reef | -0.016 |
thank | -0.015 |
Token | very |
Token ID | 845 |
Feature activation | +5.69e-03 |
Pos logit contributions | |
Prince | +0.017 |
refreshed | +0.017 |
thank | +0.017 |
bean | +0.017 |
relief | +0.016 |
Neg logit contributions | |
ats | -0.033 |
z | -0.032 |
ew | -0.031 |
zag | -0.030 |
uddy | -0.029 |
Token | kind |
Token ID | 1611 |
Feature activation | +2.74e-02 |
Pos logit contributions | |
bean | +0.006 |
Prince | +0.005 |
narrative | +0.005 |
thank | +0.005 |
reef | +0.005 |
Neg logit contributions | |
z | -0.014 |
ats | -0.014 |
ew | -0.014 |
zag | -0.013 |
om | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | +2.45e-02 |
Pos logit contributions | |
bean | +0.043 |
Prince | +0.042 |
thank | +0.040 |
generosity | +0.037 |
hospitality | +0.037 |
Neg logit contributions | |
ats | -0.055 |
z | -0.054 |
ew | -0.051 |
zag | -0.049 |
eps | -0.048 |
Token | offered |
Token ID | 4438 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
bean | +0.035 |
narrative | +0.033 |
Prince | +0.032 |
reef | +0.030 |
cuc | +0.028 |
Neg logit contributions | |
z | -0.050 |
ats | -0.049 |
ew | -0.048 |
zag | -0.046 |
om | -0.045 |
Token | Hel |
Token ID | 5053 |
Feature activation | +5.55e-02 |
Pos logit contributions | |
Prince | +0.025 |
bean | +0.024 |
Av | +0.022 |
thank | +0.022 |
Penny | +0.022 |
Neg logit contributions | |
z | -0.025 |
zag | -0.024 |
ew | -0.024 |
ats | -0.023 |
icycle | -0.021 |
Token | io |
Token ID | 952 |
Feature activation | -1.33e-02 |
Pos logit contributions | |
bean | +0.095 |
Prince | +0.094 |
Av | +0.088 |
narrative | +0.086 |
cuc | +0.084 |
Neg logit contributions | |
z | -0.093 |
ats | -0.091 |
ew | -0.088 |
zag | -0.086 |
om | -0.078 |
Token | some |
Token ID | 617 |
Feature activation | +1.83e-02 |
Pos logit contributions | |
ew | +0.023 |
attered | +0.022 |
z | +0.021 |
aned | +0.021 |
oving | +0.020 |
Neg logit contributions | |
bean | -0.022 |
Prince | -0.021 |
thank | -0.020 |
generosity | -0.020 |
Av | -0.019 |
Token | of |
Token ID | 286 |
Feature activation | +1.56e-02 |
Pos logit contributions | |
bean | +0.027 |
Prince | +0.025 |
thank | +0.024 |
narrative | +0.024 |
reef | +0.023 |
Neg logit contributions | |
z | -0.039 |
ats | -0.037 |
zag | -0.036 |
ew | -0.036 |
om | -0.034 |
Token | the |
Token ID | 262 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
bean | +0.023 |
Prince | +0.023 |
narrative | +0.020 |
Av | +0.020 |
thank | +0.019 |
Neg logit contributions | |
z | -0.032 |
ats | -0.031 |
ew | -0.031 |
zag | -0.030 |
om | -0.028 |
Token | oxygen |
Token ID | 11863 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
bean | +0.027 |
Prince | +0.025 |
narrative | +0.024 |
reef | +0.023 |
thank | +0.022 |
Neg logit contributions | |
z | -0.037 |
ats | -0.036 |
ew | -0.035 |
zag | -0.034 |
om | -0.033 |
Token | ?" |
Token ID | 1701 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
bean | +0.058 |
narrative | +0.056 |
Prince | +0.054 |
reef | +0.051 |
cuc | +0.051 |
Neg logit contributions | |
z | -0.068 |
ats | -0.066 |
ew | -0.063 |
zag | -0.062 |
om | -0.060 |
Token |
|
Token ID | 198 |
Feature activation | +1.35e-02 |
Pos logit contributions | |
bean | +0.042 |
narrative | +0.040 |
reef | +0.038 |
pearl | +0.037 |
seaw | +0.037 |
Neg logit contributions | |
z | -0.030 |
om | -0.029 |
ew | -0.029 |
ats | -0.028 |
zag | -0.026 |
Token |
|
Token ID | 198 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
bean | +0.025 |
narrative | +0.023 |
Prince | +0.023 |
reef | +0.022 |
cuc | +0.021 |
Neg logit contributions | |
z | -0.023 |
ats | -0.022 |
ew | -0.021 |
om | -0.020 |
zag | -0.020 |
Token | Grand |
Token ID | 23581 |
Feature activation | +3.26e-02 |
Pos logit contributions | |
bean | +0.037 |
Prince | +0.034 |
narrative | +0.034 |
reef | +0.032 |
cuc | +0.031 |
Neg logit contributions | |
z | -0.035 |
ats | -0.033 |
ew | -0.033 |
zag | -0.031 |
om | -0.031 |
Token | ma |
Token ID | 2611 |
Feature activation | +1.71e-03 |
Pos logit contributions | |
bean | +0.069 |
Prince | +0.063 |
reef | +0.062 |
cuc | +0.062 |
seaw | +0.060 |
Neg logit contributions | |
z | -0.047 |
ats | -0.046 |
ew | -0.044 |
om | -0.042 |
zag | -0.042 |
Token | and |
Token ID | 290 |
Feature activation | +5.54e-02 |
Pos logit contributions | |
bean | +0.003 |
Prince | +0.003 |
narrative | +0.002 |
thank | +0.002 |
reef | +0.002 |
Neg logit contributions | |
z | -0.003 |
ats | -0.003 |
ew | -0.003 |
zag | -0.003 |
attered | -0.003 |
Token | grand |
Token ID | 4490 |
Feature activation | +1.68e-02 |
Pos logit contributions | |
narrative | +0.088 |
bean | +0.083 |
reef | +0.079 |
pearl | +0.074 |
refreshed | +0.073 |
Neg logit contributions | |
z | -0.099 |
om | -0.097 |
ats | -0.095 |
ew | -0.093 |
oses | -0.089 |
Token | pa |
Token ID | 8957 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
bean | +0.027 |
Prince | +0.026 |
narrative | +0.025 |
reef | +0.024 |
cuc | +0.023 |
Neg logit contributions | |
z | -0.031 |
ats | -0.030 |
ew | -0.029 |
zag | -0.028 |
om | -0.028 |
Token | say |
Token ID | 910 |
Feature activation | +2.46e-04 |
Pos logit contributions | |
ats | +0.024 |
z | +0.024 |
ew | +0.022 |
zag | +0.022 |
om | +0.022 |
Neg logit contributions | |
bean | -0.014 |
Prince | -0.013 |
narrative | -0.013 |
reef | -0.012 |
cuc | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | +4.46e-03 |
Pos logit contributions | |
bean | +0.000 |
narrative | +0.000 |
Prince | +0.000 |
reef | +0.000 |
cuc | +0.000 |
Neg logit contributions | |
z | -0.000 |
ats | -0.000 |
ew | -0.000 |
zag | -0.000 |
om | -0.000 |
Token | " |
Token ID | 366 |
Feature activation | +1.03e-03 |
Pos logit contributions | |
bean | +0.009 |
narrative | +0.008 |
Prince | +0.008 |
reef | +0.008 |
pearl | +0.008 |
Neg logit contributions | |
z | -0.007 |
ew | -0.006 |
ats | -0.006 |
zag | -0.006 |
om | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
z | +0.007 |
ats | +0.007 |
ew | +0.007 |
zag | +0.007 |
om | +0.006 |
Neg logit contributions | |
bean | -0.007 |
Prince | -0.006 |
thank | -0.006 |
rice | -0.006 |
narrative | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -2.15e-03 |
Pos logit contributions | |
narrative | +0.026 |
bean | +0.024 |
pearl | +0.023 |
Prince | +0.022 |
tournament | +0.022 |
Neg logit contributions | |
om | -0.019 |
ew | -0.019 |
z | -0.019 |
o | -0.018 |
ats | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | +8.50e-03 |
Pos logit contributions | |
z | +0.004 |
ats | +0.004 |
ew | +0.004 |
om | +0.003 |
zag | +0.003 |
Neg logit contributions | |
bean | -0.004 |
narrative | -0.004 |
Prince | -0.004 |
cuc | -0.003 |
pearl | -0.003 |
Token | M |
Token ID | 44 |
Feature activation | +1.59e-02 |
Pos logit contributions | |
Prince | +0.016 |
bean | +0.016 |
narrative | +0.016 |
pearl | +0.015 |
thank | +0.015 |
Neg logit contributions | |
z | -0.013 |
ew | -0.012 |
ats | -0.012 |
om | -0.011 |
zag | -0.011 |
Token | ummy |
Token ID | 13513 |
Feature activation | -5.01e-03 |
Pos logit contributions | |
Prince | +0.033 |
bean | +0.033 |
reef | +0.031 |
seaw | +0.030 |
narrative | +0.030 |
Neg logit contributions | |
ew | -0.021 |
ats | -0.021 |
z | -0.020 |
om | -0.020 |
- | -0.019 |
Token | and |
Token ID | 290 |
Feature activation | +5.50e-02 |
Pos logit contributions | |
z | +0.007 |
ats | +0.006 |
ew | +0.006 |
zag | +0.006 |
om | +0.006 |
Neg logit contributions | |
bean | -0.011 |
narrative | -0.010 |
Prince | -0.010 |
reef | -0.010 |
cuc | -0.009 |
Token | Daddy |
Token ID | 26926 |
Feature activation | -9.77e-03 |
Pos logit contributions | |
narrative | +0.114 |
tournament | +0.096 |
hospitality | +0.086 |
riage | +0.086 |
ruby | +0.085 |
Neg logit contributions | |
om | -0.074 |
- | -0.067 |
z | -0.066 |
d | -0.063 |
s | -0.063 |
Token | were |
Token ID | 547 |
Feature activation | +2.38e-03 |
Pos logit contributions | |
z | +0.017 |
ats | +0.017 |
ew | +0.016 |
zag | +0.016 |
om | +0.015 |
Neg logit contributions | |
bean | -0.017 |
narrative | -0.016 |
Prince | -0.016 |
reef | -0.015 |
cuc | -0.014 |
Token | very |
Token ID | 845 |
Feature activation | -2.79e-03 |
Pos logit contributions | |
bean | +0.004 |
Prince | +0.004 |
narrative | +0.004 |
reef | +0.004 |
cuc | +0.004 |
Neg logit contributions | |
z | -0.004 |
ats | -0.004 |
ew | -0.004 |
zag | -0.004 |
om | -0.003 |
Token | happy |
Token ID | 3772 |
Feature activation | +8.64e-03 |
Pos logit contributions | |
z | +0.006 |
ew | +0.005 |
ats | +0.005 |
om | +0.005 |
zag | +0.005 |
Neg logit contributions | |
bean | -0.004 |
narrative | -0.004 |
Prince | -0.004 |
reef | -0.003 |
seaw | -0.003 |
Token | that |
Token ID | 326 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
bean | +0.018 |
Prince | +0.017 |
narrative | +0.017 |
reef | +0.016 |
thank | +0.016 |
Neg logit contributions | |
z | -0.013 |
ats | -0.012 |
ew | -0.012 |
zag | -0.011 |
om | -0.011 |
Token | it |
Token ID | 340 |
Feature activation | +2.34e-03 |
Pos logit contributions | |
z | +0.005 |
ats | +0.005 |
ew | +0.005 |
zag | +0.005 |
om | +0.004 |
Neg logit contributions | |
bean | -0.003 |
Prince | -0.003 |
narrative | -0.002 |
thank | -0.002 |
Av | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +2.04e-02 |
Pos logit contributions | |
bean | +0.004 |
Prince | +0.004 |
narrative | +0.004 |
thank | +0.004 |
Av | +0.004 |
Neg logit contributions | |
ew | -0.004 |
ats | -0.004 |
z | -0.004 |
om | -0.004 |
attered | -0.003 |
Token | And |
Token ID | 843 |
Feature activation | +2.62e-03 |
Pos logit contributions | |
bean | +0.037 |
narrative | +0.034 |
Prince | +0.034 |
reef | +0.034 |
pearl | +0.032 |
Neg logit contributions | |
z | -0.034 |
ats | -0.033 |
ew | -0.032 |
om | -0.031 |
zag | -0.030 |
Token | that |
Token ID | 326 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
bean | +0.005 |
narrative | +0.004 |
Prince | +0.004 |
reef | +0.004 |
cuc | +0.004 |
Neg logit contributions | |
z | -0.005 |
ats | -0.004 |
ew | -0.004 |
om | -0.004 |
zag | -0.004 |
Token | made |
Token ID | 925 |
Feature activation | +2.05e-02 |
Pos logit contributions | |
bean | +0.022 |
Prince | +0.021 |
narrative | +0.021 |
reef | +0.020 |
cuc | +0.019 |
Neg logit contributions | |
z | -0.014 |
ats | -0.014 |
ew | -0.013 |
zag | -0.012 |
om | -0.012 |
Token | J |
Token ID | 449 |
Feature activation | +5.50e-02 |
Pos logit contributions | |
bean | +0.028 |
Prince | +0.026 |
narrative | +0.026 |
Av | +0.025 |
reef | +0.023 |
Neg logit contributions | |
z | -0.043 |
ats | -0.041 |
zag | -0.041 |
ew | -0.041 |
om | -0.038 |
Token | illy |
Token ID | 6548 |
Feature activation | -2.69e-03 |
Pos logit contributions | |
bean | +0.068 |
narrative | +0.065 |
Prince | +0.064 |
reef | +0.064 |
thank | +0.059 |
Neg logit contributions | |
ats | -0.123 |
z | -0.120 |
ew | -0.117 |
om | -0.110 |
zag | -0.108 |
Token | very |
Token ID | 845 |
Feature activation | -8.37e-03 |
Pos logit contributions | |
ats | +0.006 |
ew | +0.005 |
z | +0.005 |
zag | +0.005 |
om | +0.005 |
Neg logit contributions | |
bean | -0.004 |
thank | -0.003 |
refreshed | -0.003 |
Prince | -0.003 |
generosity | -0.003 |
Token | proud |
Token ID | 6613 |
Feature activation | +8.57e-03 |
Pos logit contributions | |
z | +0.021 |
ats | +0.020 |
ew | +0.020 |
zag | +0.019 |
om | +0.019 |
Neg logit contributions | |
bean | -0.009 |
narrative | -0.008 |
Prince | -0.008 |
thank | -0.007 |
reef | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +8.19e-03 |
Pos logit contributions | |
bean | +0.016 |
Prince | +0.015 |
narrative | +0.015 |
thank | +0.014 |
reef | +0.014 |
Neg logit contributions | |
z | -0.014 |
ats | -0.014 |
ew | -0.013 |
zag | -0.013 |
om | -0.012 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +4.73e-03 |
Pos logit contributions | |
bean | +0.016 |
narrative | +0.015 |
reef | +0.015 |
Prince | +0.015 |
pearl | +0.014 |
Neg logit contributions | |
z | -0.012 |
ew | -0.012 |
ats | -0.012 |
om | -0.011 |
zag | -0.011 |
Token | treats |
Token ID | 18432 |
Feature activation | -8.89e-03 |
Pos logit contributions | |
bean | +0.006 |
rice | +0.006 |
beans | +0.006 |
seaw | +0.005 |
cuc | +0.005 |
Neg logit contributions | |
zag | -0.012 |
z | -0.012 |
ew | -0.011 |
aned | -0.011 |
uddy | -0.011 |
Token | on |
Token ID | 319 |
Feature activation | +7.18e-03 |
Pos logit contributions | |
ew | +0.016 |
z | +0.016 |
ats | +0.015 |
zag | +0.015 |
om | +0.014 |
Neg logit contributions | |
bean | -0.015 |
rice | -0.013 |
beans | -0.013 |
reef | -0.013 |
Prince | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | -1.18e-03 |
Pos logit contributions | |
bean | +0.009 |
Prince | +0.008 |
narrative | +0.007 |
reef | +0.007 |
Av | +0.007 |
Neg logit contributions | |
z | -0.017 |
ats | -0.016 |
ew | -0.016 |
zag | -0.016 |
om | -0.015 |
Token | table |
Token ID | 3084 |
Feature activation | +5.14e-03 |
Pos logit contributions | |
z | +0.003 |
ew | +0.002 |
ats | +0.002 |
om | +0.002 |
o | +0.002 |
Neg logit contributions | |
bean | -0.002 |
Prince | -0.002 |
narrative | -0.002 |
thank | -0.001 |
reef | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +2.23e-02 |
Pos logit contributions | |
bean | +0.008 |
reef | +0.007 |
Prince | +0.007 |
beans | +0.007 |
Claire | +0.007 |
Neg logit contributions | |
z | -0.010 |
ew | -0.010 |
ats | -0.010 |
zag | -0.009 |
uddy | -0.009 |
Token | J |
Token ID | 449 |
Feature activation | +5.47e-02 |
Pos logit contributions | |
bean | +0.033 |
narrative | +0.030 |
Prince | +0.030 |
reef | +0.029 |
pearl | +0.027 |
Neg logit contributions | |
z | -0.045 |
ats | -0.044 |
ew | -0.043 |
zag | -0.041 |
om | -0.041 |
Token | illy |
Token ID | 6548 |
Feature activation | -7.50e-03 |
Pos logit contributions | |
bean | +0.068 |
narrative | +0.067 |
reef | +0.064 |
Prince | +0.063 |
thank | +0.059 |
Neg logit contributions | |
ats | -0.122 |
z | -0.119 |
ew | -0.116 |
om | -0.109 |
zag | -0.107 |
Token | was |
Token ID | 373 |
Feature activation | +1.44e-03 |
Pos logit contributions | |
z | +0.014 |
ew | +0.014 |
ats | +0.014 |
zag | +0.013 |
om | +0.012 |
Neg logit contributions | |
bean | -0.012 |
Prince | -0.011 |
Av | -0.010 |
Claire | -0.010 |
reef | -0.010 |
Token | so |
Token ID | 523 |
Feature activation | -2.07e-03 |
Pos logit contributions | |
Prince | +0.002 |
refreshed | +0.002 |
Claire | +0.002 |
Av | +0.002 |
bean | +0.002 |
Neg logit contributions | |
ats | -0.003 |
z | -0.003 |
ew | -0.003 |
zag | -0.003 |
uddy | -0.003 |
Token | happy |
Token ID | 3772 |
Feature activation | +1.53e-03 |
Pos logit contributions | |
z | +0.005 |
ats | +0.005 |
ew | +0.004 |
zag | +0.004 |
om | +0.004 |
Neg logit contributions | |
bean | -0.003 |
Prince | -0.002 |
narrative | -0.002 |
reef | -0.002 |
thank | -0.002 |
Token | ! |
Token ID | 0 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
bean | +0.003 |
Prince | +0.002 |
Av | +0.002 |
thank | +0.002 |
reef | +0.002 |
Neg logit contributions | |
ats | -0.003 |
z | -0.003 |
ew | -0.003 |
zag | -0.003 |
om | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
bean | +0.049 |
Prince | +0.047 |
narrative | +0.046 |
reef | +0.044 |
cuc | +0.044 |
Neg logit contributions | |
z | -0.031 |
ats | -0.030 |
ew | -0.028 |
zag | -0.027 |
om | -0.026 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -7.01e-03 |
Pos logit contributions | |
om | +0.013 |
ew | +0.013 |
z | +0.013 |
o | +0.012 |
ats | +0.011 |
Neg logit contributions | |
bean | -0.028 |
cuc | -0.026 |
pearl | -0.026 |
seaw | -0.026 |
reef | -0.026 |
Token | Lisa |
Token ID | 44203 |
Feature activation | +6.68e-03 |
Pos logit contributions | |
z | +0.011 |
ats | +0.010 |
ew | +0.010 |
om | +0.009 |
zag | +0.009 |
Neg logit contributions | |
bean | -0.014 |
narrative | -0.013 |
Prince | -0.013 |
generosity | -0.012 |
thank | -0.012 |
Token | loved |
Token ID | 6151 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
bean | +0.014 |
Prince | +0.013 |
narrative | +0.013 |
reef | +0.012 |
thank | +0.012 |
Neg logit contributions | |
z | -0.010 |
ats | -0.009 |
ew | -0.009 |
zag | -0.009 |
om | -0.008 |
Token | to |
Token ID | 284 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
bean | +0.046 |
narrative | +0.046 |
Prince | +0.045 |
reef | +0.043 |
thank | +0.042 |
Neg logit contributions | |
z | -0.020 |
ats | -0.019 |
ew | -0.018 |
om | -0.016 |
zag | -0.016 |
Token | look |
Token ID | 804 |
Feature activation | +5.45e-02 |
Pos logit contributions | |
narrative | +0.025 |
bean | +0.025 |
Prince | +0.024 |
reef | +0.022 |
pearl | +0.022 |
Neg logit contributions | |
z | -0.029 |
ats | -0.028 |
ew | -0.027 |
zag | -0.027 |
om | -0.026 |
Token | at |
Token ID | 379 |
Feature activation | +1.40e-04 |
Pos logit contributions | |
bean | +0.121 |
Prince | +0.116 |
narrative | +0.116 |
reef | +0.111 |
cuc | +0.107 |
Neg logit contributions | |
z | -0.068 |
ats | -0.066 |
ew | -0.062 |
zag | -0.059 |
om | -0.057 |
Token | photos |
Token ID | 5205 |
Feature activation | +3.22e-02 |
Pos logit contributions | |
bean | +0.000 |
Prince | +0.000 |
reef | +0.000 |
narrative | +0.000 |
poppy | +0.000 |
Neg logit contributions | |
z | -0.000 |
ats | -0.000 |
ew | -0.000 |
zag | -0.000 |
om | -0.000 |
Token | of |
Token ID | 286 |
Feature activation | -3.11e-03 |
Pos logit contributions | |
bean | +0.064 |
Prince | +0.060 |
narrative | +0.058 |
reef | +0.056 |
rice | +0.054 |
Neg logit contributions | |
z | -0.051 |
ats | -0.049 |
ew | -0.047 |
zag | -0.045 |
om | -0.043 |
Token | her |
Token ID | 607 |
Feature activation | +3.33e-02 |
Pos logit contributions | |
z | +0.005 |
ats | +0.005 |
ew | +0.005 |
om | +0.005 |
zag | +0.005 |
Neg logit contributions | |
narrative | -0.005 |
bean | -0.005 |
Prince | -0.004 |
reef | -0.004 |
energ | -0.004 |
Token | family |
Token ID | 1641 |
Feature activation | +2.18e-02 |
Pos logit contributions | |
bean | +0.046 |
narrative | +0.043 |
Prince | +0.043 |
reef | +0.040 |
cuc | +0.038 |
Neg logit contributions | |
z | -0.068 |
ats | -0.067 |
ew | -0.065 |
zag | -0.063 |
om | -0.063 |
Token | ball |
Token ID | 2613 |
Feature activation | -1.58e-02 |
Pos logit contributions | |
z | +0.018 |
ats | +0.018 |
ew | +0.016 |
zag | +0.016 |
oses | +0.016 |
Neg logit contributions | |
bean | -0.016 |
Prince | -0.014 |
reef | -0.013 |
narrative | -0.013 |
seaw | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | -5.38e-03 |
Pos logit contributions | |
ats | +0.027 |
z | +0.026 |
ew | +0.025 |
zag | +0.024 |
om | +0.022 |
Neg logit contributions | |
bean | -0.029 |
Prince | -0.026 |
narrative | -0.025 |
reef | -0.025 |
thank | -0.025 |
Token | the |
Token ID | 262 |
Feature activation | -4.10e-03 |
Pos logit contributions | |
z | +0.008 |
ats | +0.008 |
zag | +0.007 |
ew | +0.007 |
om | +0.007 |
Neg logit contributions | |
bean | -0.010 |
narrative | -0.010 |
Prince | -0.010 |
reef | -0.009 |
pearl | -0.009 |
Token | dog |
Token ID | 3290 |
Feature activation | +8.49e-03 |
Pos logit contributions | |
z | +0.008 |
ats | +0.008 |
ew | +0.008 |
zag | +0.008 |
oses | +0.007 |
Neg logit contributions | |
bean | -0.006 |
narrative | -0.006 |
Prince | -0.006 |
rice | -0.005 |
reef | -0.005 |
Token | fet |
Token ID | 11351 |
Feature activation | -2.59e-02 |
Pos logit contributions | |
bean | +0.014 |
thank | +0.013 |
Prince | +0.012 |
reef | +0.012 |
Av | +0.011 |
Neg logit contributions | |
ats | -0.016 |
z | -0.016 |
ew | -0.015 |
zag | -0.015 |
icycle | -0.014 |
Token | ches |
Token ID | 2052 |
Feature activation | -7.86e-02 |
Pos logit contributions | |
z | +0.023 |
ew | +0.021 |
zag | +0.020 |
ats | +0.019 |
attered | +0.018 |
Neg logit contributions | |
bean | -0.066 |
thank | -0.062 |
Prince | -0.061 |
narrative | -0.059 |
Av | -0.058 |
Token | it |
Token ID | 340 |
Feature activation | -1.84e-02 |
Pos logit contributions | |
ats | +0.188 |
z | +0.186 |
ew | +0.182 |
icycle | +0.181 |
attered | +0.181 |
Neg logit contributions | |
bean | -0.080 |
Prince | -0.065 |
Av | -0.064 |
thank | -0.062 |
reef | -0.056 |
Token | . |
Token ID | 13 |
Feature activation | -5.00e-03 |
Pos logit contributions | |
ats | +0.038 |
ew | +0.035 |
z | +0.035 |
icycle | +0.032 |
zag | +0.032 |
Neg logit contributions | |
bean | -0.028 |
Prince | -0.024 |
thank | -0.024 |
Av | -0.023 |
reef | -0.023 |
Token | They |
Token ID | 1119 |
Feature activation | +2.14e-04 |
Pos logit contributions | |
z | +0.008 |
ew | +0.007 |
ats | +0.007 |
om | +0.007 |
zag | +0.007 |
Neg logit contributions | |
bean | -0.010 |
narrative | -0.009 |
Prince | -0.009 |
reef | -0.009 |
pearl | -0.009 |
Token | hug |
Token ID | 16225 |
Feature activation | -5.16e-03 |
Pos logit contributions | |
bean | +0.000 |
Prince | +0.000 |
narrative | +0.000 |
reef | +0.000 |
pearl | +0.000 |
Neg logit contributions | |
z | -0.000 |
ats | -0.000 |
ew | -0.000 |
zag | -0.000 |
om | -0.000 |
Token | the |
Token ID | 262 |
Feature activation | -8.18e-03 |
Pos logit contributions | |
z | +0.010 |
ats | +0.010 |
ew | +0.009 |
zag | +0.009 |
om | +0.009 |
Neg logit contributions | |
bean | -0.008 |
Prince | -0.008 |
narrative | -0.008 |
reef | -0.007 |
thank | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
seaw | +0.001 |
bean | +0.001 |
Prince | +0.001 |
jelly | +0.001 |
thank | +0.001 |
Neg logit contributions | |
zag | -0.002 |
ats | -0.002 |
oses | -0.002 |
z | -0.002 |
ew | -0.002 |
Token | ball |
Token ID | 2613 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
z | +0.020 |
ats | +0.020 |
zag | +0.019 |
oses | +0.019 |
ew | +0.018 |
Neg logit contributions | |
bean | -0.017 |
reef | -0.014 |
seaw | -0.014 |
Prince | -0.014 |
pearl | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | -1.71e-04 |
Pos logit contributions | |
ats | +0.028 |
z | +0.027 |
ew | +0.026 |
zag | +0.024 |
aned | +0.023 |
Neg logit contributions | |
bean | -0.028 |
reef | -0.024 |
Prince | -0.024 |
thank | -0.023 |
Av | -0.023 |
Token | he |
Token ID | 339 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
z | +0.000 |
ats | +0.000 |
ew | +0.000 |
zag | +0.000 |
om | +0.000 |
Neg logit contributions | |
bean | -0.000 |
narrative | -0.000 |
Prince | -0.000 |
reef | -0.000 |
pearl | -0.000 |
Token | fet |
Token ID | 11351 |
Feature activation | -2.79e-02 |
Pos logit contributions | |
z | +0.020 |
ew | +0.020 |
ats | +0.019 |
attered | +0.018 |
zag | +0.018 |
Neg logit contributions | |
bean | -0.016 |
Prince | -0.014 |
thank | -0.014 |
reef | -0.014 |
Av | -0.013 |
Token | ches |
Token ID | 2052 |
Feature activation | -7.83e-02 |
Pos logit contributions | |
z | +0.027 |
ew | +0.025 |
zag | +0.024 |
attered | +0.023 |
ats | +0.023 |
Neg logit contributions | |
bean | -0.067 |
thank | -0.065 |
Prince | -0.062 |
narrative | -0.060 |
Av | -0.060 |
Token | it |
Token ID | 340 |
Feature activation | -1.53e-02 |
Pos logit contributions | |
attered | +0.201 |
ats | +0.194 |
icycle | +0.192 |
ew | +0.192 |
tr | +0.190 |
Neg logit contributions | |
bean | -0.057 |
thank | -0.051 |
Av | -0.050 |
Prince | -0.048 |
reef | -0.039 |
Token | . |
Token ID | 13 |
Feature activation | -9.96e-04 |
Pos logit contributions | |
ats | +0.033 |
ew | +0.031 |
z | +0.029 |
attered | +0.028 |
icycle | +0.028 |
Neg logit contributions | |
bean | -0.021 |
thank | -0.019 |
Prince | -0.019 |
Av | -0.018 |
reef | -0.017 |
Token | They |
Token ID | 1119 |
Feature activation | +1.17e-03 |
Pos logit contributions | |
ats | +0.002 |
z | +0.002 |
ew | +0.002 |
zag | +0.002 |
ches | +0.002 |
Neg logit contributions | |
Prince | -0.001 |
bean | -0.001 |
thank | -0.001 |
Honey | -0.001 |
Av | -0.001 |
Token | run |
Token ID | 1057 |
Feature activation | -2.36e-03 |
Pos logit contributions | |
bean | +0.002 |
Prince | +0.002 |
narrative | +0.002 |
reef | +0.001 |
thank | +0.001 |
Neg logit contributions | |
z | -0.002 |
ats | -0.002 |
ew | -0.002 |
zag | -0.002 |
om | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | -5.91e-03 |
Pos logit contributions | |
ew | +0.005 |
ats | +0.005 |
oses | +0.005 |
z | +0.004 |
zag | +0.004 |
Neg logit contributions | |
bean | -0.003 |
Prince | -0.003 |
thank | -0.003 |
Av | -0.003 |
Princess | -0.003 |
Token | ball |
Token ID | 2613 |
Feature activation | -4.69e-03 |
Pos logit contributions | |
z | +0.025 |
ats | +0.024 |
ew | +0.023 |
zag | +0.023 |
oses | +0.021 |
Neg logit contributions | |
bean | -0.025 |
Prince | -0.022 |
narrative | -0.022 |
thank | -0.021 |
poppy | -0.021 |
Token | and |
Token ID | 290 |
Feature activation | -8.33e-03 |
Pos logit contributions | |
ats | +0.008 |
ew | +0.008 |
z | +0.008 |
zag | +0.007 |
oses | +0.007 |
Neg logit contributions | |
bean | -0.009 |
reef | -0.007 |
Prince | -0.007 |
thank | -0.007 |
narrative | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | -4.98e-03 |
Pos logit contributions | |
z | +0.013 |
ats | +0.013 |
ew | +0.012 |
zag | +0.012 |
om | +0.012 |
Neg logit contributions | |
narrative | -0.015 |
bean | -0.015 |
Prince | -0.014 |
reef | -0.013 |
pearl | -0.013 |
Token | dog |
Token ID | 3290 |
Feature activation | +8.16e-03 |
Pos logit contributions | |
z | +0.009 |
ats | +0.009 |
ew | +0.009 |
zag | +0.009 |
om | +0.008 |
Neg logit contributions | |
bean | -0.008 |
narrative | -0.007 |
Prince | -0.007 |
reef | -0.007 |
thank | -0.007 |
Token | fet |
Token ID | 11351 |
Feature activation | -2.98e-02 |
Pos logit contributions | |
bean | +0.013 |
thank | +0.012 |
Prince | +0.011 |
reef | +0.011 |
Av | +0.011 |
Neg logit contributions | |
ew | -0.015 |
ats | -0.015 |
z | -0.015 |
icycle | -0.014 |
zag | -0.014 |
Token | ches |
Token ID | 2052 |
Feature activation | -7.79e-02 |
Pos logit contributions | |
z | +0.030 |
ew | +0.027 |
zag | +0.027 |
ats | +0.025 |
attered | +0.025 |
Neg logit contributions | |
bean | -0.072 |
thank | -0.068 |
Prince | -0.066 |
narrative | -0.063 |
Av | -0.063 |
Token | it |
Token ID | 340 |
Feature activation | -1.71e-02 |
Pos logit contributions | |
z | +0.181 |
ats | +0.179 |
attered | +0.178 |
ew | +0.176 |
icycle | +0.176 |
Neg logit contributions | |
bean | -0.082 |
Prince | -0.069 |
Av | -0.066 |
thank | -0.065 |
reef | -0.061 |
Token | . |
Token ID | 13 |
Feature activation | -6.95e-03 |
Pos logit contributions | |
ats | +0.035 |
ew | +0.033 |
z | +0.032 |
icycle | +0.030 |
attered | +0.029 |
Neg logit contributions | |
bean | -0.025 |
Prince | -0.022 |
thank | -0.022 |
Av | -0.021 |
reef | -0.021 |
Token | They |
Token ID | 1119 |
Feature activation | -2.13e-03 |
Pos logit contributions | |
z | +0.012 |
ats | +0.012 |
ew | +0.012 |
zag | +0.011 |
om | +0.011 |
Neg logit contributions | |
bean | -0.012 |
narrative | -0.011 |
Prince | -0.011 |
reef | -0.011 |
pearl | -0.010 |
Token | push |
Token ID | 4574 |
Feature activation | -1.60e-03 |
Pos logit contributions | |
z | +0.004 |
ats | +0.004 |
ew | +0.004 |
zag | +0.004 |
om | +0.004 |
Neg logit contributions | |
bean | -0.003 |
Prince | -0.003 |
narrative | -0.003 |
reef | -0.003 |
cuc | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | -2.04e-02 |
Pos logit contributions | |
zag | +0.004 |
ats | +0.004 |
z | +0.004 |
ew | +0.003 |
icycle | +0.003 |
Neg logit contributions | |
bean | -0.002 |
Prince | -0.002 |
Av | -0.001 |
thank | -0.001 |
Honey | -0.001 |
Token | ball |
Token ID | 2613 |
Feature activation | -2.51e-03 |
Pos logit contributions | |
z | +0.015 |
ats | +0.015 |
zag | +0.014 |
oses | +0.014 |
ew | +0.014 |
Neg logit contributions | |
bean | -0.010 |
Prince | -0.009 |
rice | -0.009 |
seaw | -0.009 |
poppy | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | -5.39e-03 |
Pos logit contributions | |
ats | +0.005 |
ew | +0.004 |
z | +0.004 |
zag | +0.004 |
icycle | +0.004 |
Neg logit contributions | |
bean | -0.004 |
reef | -0.004 |
thank | -0.004 |
narrative | -0.004 |
Prince | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | -2.44e-03 |
Pos logit contributions | |
z | +0.009 |
ats | +0.009 |
zag | +0.008 |
ew | +0.008 |
om | +0.008 |
Neg logit contributions | |
bean | -0.009 |
narrative | -0.009 |
Prince | -0.009 |
reef | -0.008 |
pearl | -0.008 |
Token | dog |
Token ID | 3290 |
Feature activation | +8.93e-03 |
Pos logit contributions | |
z | +0.005 |
ats | +0.005 |
ew | +0.005 |
zag | +0.005 |
oses | +0.004 |
Neg logit contributions | |
bean | -0.004 |
narrative | -0.003 |
Prince | -0.003 |
rice | -0.003 |
reef | -0.003 |
Token | fet |
Token ID | 11351 |
Feature activation | -2.55e-02 |
Pos logit contributions | |
bean | +0.014 |
thank | +0.013 |
Prince | +0.012 |
reef | +0.012 |
Av | +0.012 |
Neg logit contributions | |
ew | -0.016 |
ats | -0.016 |
z | -0.016 |
zag | -0.015 |
icycle | -0.015 |
Token | ches |
Token ID | 2052 |
Feature activation | -7.62e-02 |
Pos logit contributions | |
z | +0.024 |
ew | +0.022 |
zag | +0.021 |
attered | +0.020 |
ats | +0.020 |
Neg logit contributions | |
bean | -0.062 |
thank | -0.060 |
Prince | -0.058 |
narrative | -0.056 |
Av | -0.055 |
Token | it |
Token ID | 340 |
Feature activation | -1.82e-02 |
Pos logit contributions | |
z | +0.181 |
ats | +0.179 |
ew | +0.177 |
attered | +0.177 |
icycle | +0.175 |
Neg logit contributions | |
bean | -0.077 |
Prince | -0.063 |
thank | -0.061 |
Av | -0.060 |
reef | -0.057 |
Token | . |
Token ID | 13 |
Feature activation | -4.99e-03 |
Pos logit contributions | |
ats | +0.038 |
ew | +0.036 |
z | +0.035 |
icycle | +0.032 |
attered | +0.032 |
Neg logit contributions | |
bean | -0.027 |
thank | -0.023 |
Prince | -0.023 |
Av | -0.022 |
reef | -0.022 |
Token | They |
Token ID | 1119 |
Feature activation | +7.58e-04 |
Pos logit contributions | |
z | +0.008 |
ew | +0.008 |
ats | +0.008 |
om | +0.007 |
zag | +0.007 |
Neg logit contributions | |
bean | -0.009 |
narrative | -0.009 |
Prince | -0.009 |
reef | -0.008 |
pearl | -0.008 |
Token | have |
Token ID | 423 |
Feature activation | -6.43e-04 |
Pos logit contributions | |
bean | +0.001 |
Prince | +0.001 |
narrative | +0.001 |
reef | +0.001 |
cuc | +0.001 |
Neg logit contributions | |
z | -0.002 |
ats | -0.002 |
ew | -0.001 |
zag | -0.001 |
om | -0.001 |
Token | fun |
Token ID | 1257 |
Feature activation | -7.87e-03 |
Pos logit contributions | |
z | +0.001 |
ats | +0.001 |
ew | +0.001 |
zag | +0.001 |
om | +0.001 |
Neg logit contributions | |
bean | -0.001 |
Prince | -0.001 |
thank | -0.001 |
reef | -0.001 |
narrative | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
bean | +0.001 |
Prince | +0.001 |
seaw | +0.001 |
Av | +0.001 |
reef | +0.001 |
Neg logit contributions | |
zag | -0.003 |
z | -0.003 |
ats | -0.003 |
ew | -0.002 |
oses | -0.002 |
Token | ball |
Token ID | 2613 |
Feature activation | -9.21e-04 |
Pos logit contributions | |
z | +0.028 |
ats | +0.027 |
ew | +0.026 |
zag | +0.025 |
om | +0.024 |
Neg logit contributions | |
bean | -0.025 |
narrative | -0.022 |
Prince | -0.022 |
reef | -0.022 |
rice | -0.020 |
Token | and |
Token ID | 290 |
Feature activation | -8.35e-03 |
Pos logit contributions | |
ats | +0.002 |
z | +0.002 |
ew | +0.001 |
zag | +0.001 |
oses | +0.001 |
Neg logit contributions | |
bean | -0.002 |
reef | -0.001 |
Prince | -0.001 |
narrative | -0.001 |
thank | -0.001 |
Token | he |
Token ID | 339 |
Feature activation | -8.49e-03 |
Pos logit contributions | |
z | +0.014 |
ats | +0.014 |
ew | +0.013 |
zag | +0.013 |
om | +0.013 |
Neg logit contributions | |
bean | -0.014 |
narrative | -0.014 |
Prince | -0.014 |
reef | -0.013 |
pearl | -0.013 |
Token | fet |
Token ID | 11351 |
Feature activation | -2.40e-02 |
Pos logit contributions | |
z | +0.017 |
ew | +0.016 |
ats | +0.015 |
zag | +0.015 |
attered | +0.015 |
Neg logit contributions | |
bean | -0.013 |
thank | -0.012 |
Prince | -0.012 |
reef | -0.012 |
seaw | -0.011 |
Token | ches |
Token ID | 2052 |
Feature activation | -7.44e-02 |
Pos logit contributions | |
z | +0.026 |
ew | +0.024 |
zag | +0.023 |
ats | +0.022 |
attered | +0.021 |
Neg logit contributions | |
bean | -0.057 |
thank | -0.053 |
Prince | -0.052 |
narrative | -0.051 |
Av | -0.049 |
Token | it |
Token ID | 340 |
Feature activation | -1.54e-02 |
Pos logit contributions | |
ats | +0.190 |
z | +0.189 |
attered | +0.187 |
ew | +0.186 |
icycle | +0.182 |
Neg logit contributions | |
bean | -0.061 |
Prince | -0.049 |
Av | -0.047 |
thank | -0.045 |
reef | -0.040 |
Token | . |
Token ID | 13 |
Feature activation | -2.11e-03 |
Pos logit contributions | |
ats | +0.030 |
ew | +0.028 |
z | +0.028 |
zag | +0.025 |
attered | +0.024 |
Neg logit contributions | |
bean | -0.025 |
Prince | -0.022 |
thank | -0.022 |
reef | -0.021 |
Av | -0.021 |
Token | They |
Token ID | 1119 |
Feature activation | +2.45e-03 |
Pos logit contributions | |
z | +0.004 |
ats | +0.004 |
ew | +0.003 |
zag | +0.003 |
om | +0.003 |
Neg logit contributions | |
bean | -0.004 |
Prince | -0.004 |
narrative | -0.003 |
reef | -0.003 |
thank | -0.003 |
Token | take |
Token ID | 1011 |
Feature activation | -3.14e-03 |
Pos logit contributions | |
bean | +0.004 |
Prince | +0.004 |
narrative | +0.004 |
reef | +0.003 |
pearl | +0.003 |
Neg logit contributions | |
z | -0.005 |
ats | -0.005 |
ew | -0.004 |
zag | -0.004 |
om | -0.004 |
Token | turns |
Token ID | 4962 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
zag | +0.006 |
ats | +0.006 |
z | +0.006 |
ew | +0.006 |
icycle | +0.006 |
Neg logit contributions | |
bean | -0.005 |
Prince | -0.004 |
thank | -0.004 |
Av | -0.004 |
seaw | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +4.60e-03 |
Pos logit contributions | |
bean | +0.002 |
thank | +0.002 |
Prince | +0.001 |
generosity | +0.001 |
energ | +0.001 |
Neg logit contributions | |
ats | -0.003 |
z | -0.003 |
ew | -0.003 |
zag | -0.002 |
ches | -0.002 |
Token | He |
Token ID | 679 |
Feature activation | -4.56e-03 |
Pos logit contributions | |
Prince | +0.007 |
bean | +0.006 |
Av | +0.006 |
Claire | +0.006 |
Princess | +0.006 |
Neg logit contributions | |
ats | -0.010 |
z | -0.010 |
ew | -0.009 |
zag | -0.009 |
out | -0.009 |
Token | just |
Token ID | 655 |
Feature activation | -2.55e-02 |
Pos logit contributions | |
z | +0.010 |
ats | +0.010 |
ew | +0.010 |
ings | +0.009 |
zag | +0.009 |
Neg logit contributions | |
bean | -0.005 |
Prince | -0.005 |
thank | -0.005 |
prince | -0.005 |
sailor | -0.005 |
Token | couldn |
Token ID | 3521 |
Feature activation | -2.84e-02 |
Pos logit contributions | |
z | +0.056 |
ats | +0.053 |
zag | +0.052 |
ew | +0.051 |
ings | +0.048 |
Neg logit contributions | |
bean | -0.033 |
thank | -0.031 |
Prince | -0.031 |
seaw | -0.030 |
Av | -0.028 |
Token | 't |
Token ID | 470 |
Feature activation | -1.83e-02 |
Pos logit contributions | |
ats | +0.047 |
z | +0.043 |
attered | +0.042 |
as | +0.042 |
out | +0.040 |
Neg logit contributions | |
bean | -0.051 |
thank | -0.048 |
narrative | -0.047 |
Prince | -0.047 |
Av | -0.046 |
Token | quite |
Token ID | 2407 |
Feature activation | -7.14e-02 |
Pos logit contributions | |
z | +0.041 |
ats | +0.039 |
ew | +0.039 |
om | +0.038 |
zag | +0.037 |
Neg logit contributions | |
bean | -0.024 |
Prince | -0.022 |
narrative | -0.021 |
thank | -0.021 |
reef | -0.020 |
Token | get |
Token ID | 651 |
Feature activation | -2.12e-02 |
Pos logit contributions | |
z | +0.168 |
ew | +0.159 |
ats | +0.154 |
om | +0.151 |
zag | +0.149 |
Neg logit contributions | |
thank | -0.089 |
bean | -0.088 |
Prince | -0.077 |
sailor | -0.072 |
seaw | -0.071 |
Token | them |
Token ID | 606 |
Feature activation | -1.62e-02 |
Pos logit contributions | |
z | +0.046 |
zag | +0.044 |
ew | +0.043 |
tr | +0.043 |
ats | +0.042 |
Neg logit contributions | |
bean | -0.031 |
Prince | -0.029 |
thank | -0.027 |
shrimp | -0.027 |
Nancy | -0.027 |
Token | to |
Token ID | 284 |
Feature activation | +2.87e-03 |
Pos logit contributions | |
z | +0.031 |
ew | +0.031 |
ats | +0.029 |
om | +0.028 |
zag | +0.026 |
Neg logit contributions | |
bean | -0.026 |
Prince | -0.022 |
rice | -0.021 |
beans | -0.021 |
reef | -0.021 |
Token | fit |
Token ID | 4197 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
bean | +0.004 |
Prince | +0.004 |
narrative | +0.004 |
thank | +0.004 |
reef | +0.004 |
Neg logit contributions | |
z | -0.006 |
ats | -0.006 |
ew | -0.006 |
zag | -0.005 |
om | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -8.55e-04 |
Pos logit contributions | |
ew | +0.022 |
z | +0.022 |
ats | +0.021 |
zag | +0.021 |
om | +0.020 |
Neg logit contributions | |
bean | -0.018 |
Prince | -0.017 |
reef | -0.016 |
Claire | -0.016 |
Nancy | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | +9.85e-03 |
Pos logit contributions | |
ats | +0.014 |
z | +0.013 |
ew | +0.013 |
uddy | +0.012 |
icycle | +0.012 |
Neg logit contributions | |
bean | -0.008 |
reef | -0.007 |
poppy | -0.007 |
refreshed | -0.007 |
thank | -0.007 |
Token | They |
Token ID | 1119 |
Feature activation | +8.05e-03 |
Pos logit contributions | |
bean | +0.015 |
Prince | +0.015 |
narrative | +0.014 |
reef | +0.013 |
Av | +0.013 |
Neg logit contributions | |
z | -0.019 |
ats | -0.019 |
ew | -0.018 |
zag | -0.018 |
om | -0.017 |
Token | were |
Token ID | 547 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
bean | +0.013 |
Prince | +0.012 |
reef | +0.012 |
narrative | +0.012 |
thank | +0.011 |
Neg logit contributions | |
z | -0.016 |
ats | -0.015 |
ew | -0.015 |
zag | -0.014 |
om | -0.014 |
Token | called |
Token ID | 1444 |
Feature activation | -2.24e-02 |
Pos logit contributions | |
z | +0.024 |
ats | +0.023 |
ew | +0.022 |
zag | +0.021 |
attered | +0.021 |
Neg logit contributions | |
Prince | -0.014 |
reef | -0.013 |
thank | -0.013 |
bean | -0.013 |
refreshed | -0.012 |
Token | ost |
Token ID | 23619 |
Feature activation | -1.71e-02 |
Pos logit contributions | |
z | +0.048 |
ats | +0.047 |
ew | +0.045 |
zag | +0.044 |
om | +0.043 |
Neg logit contributions | |
bean | -0.031 |
Prince | -0.029 |
narrative | -0.027 |
reef | -0.026 |
thank | -0.026 |
Token | ric |
Token ID | 1173 |
Feature activation | -6.78e-02 |
Pos logit contributions | |
z | +0.026 |
attered | +0.023 |
coat | +0.023 |
ggies | +0.022 |
erved | +0.022 |
Neg logit contributions | |
reef | -0.025 |
Whale | -0.024 |
bean | -0.024 |
riage | -0.024 |
coral | -0.024 |
Token | hes |
Token ID | 956 |
Feature activation | -9.73e-03 |
Pos logit contributions | |
z | +0.129 |
attered | +0.121 |
ats | +0.120 |
eth | +0.120 |
ew | +0.119 |
Neg logit contributions | |
narrative | -0.091 |
bean | -0.090 |
Prince | -0.090 |
reef | -0.090 |
refreshed | -0.084 |
Token | . |
Token ID | 13 |
Feature activation | +1.31e-03 |
Pos logit contributions | |
z | +0.019 |
icycle | +0.018 |
ew | +0.017 |
ats | +0.017 |
zag | +0.017 |
Neg logit contributions | |
bean | -0.015 |
Prince | -0.013 |
thank | -0.013 |
rice | -0.013 |
reef | -0.013 |
Token | Lily |
Token ID | 20037 |
Feature activation | +9.07e-03 |
Pos logit contributions | |
bean | +0.002 |
Prince | +0.002 |
narrative | +0.002 |
reef | +0.002 |
Av | +0.002 |
Neg logit contributions | |
z | -0.003 |
ats | -0.003 |
zag | -0.002 |
ew | -0.002 |
om | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
bean | +0.013 |
Prince | +0.013 |
reef | +0.012 |
prince | +0.011 |
Av | +0.011 |
Neg logit contributions | |
z | -0.017 |
ew | -0.017 |
ats | -0.017 |
zag | -0.016 |
attered | -0.016 |
Token | Ben |
Token ID | 3932 |
Feature activation | -1.29e-02 |
Pos logit contributions | |
bean | +0.020 |
Prince | +0.018 |
narrative | +0.018 |
reef | +0.017 |
cuc | +0.016 |
Neg logit contributions | |
z | -0.027 |
ats | -0.026 |
ew | -0.025 |
zag | -0.025 |
om | -0.024 |
Token |
|
Token ID | 198 |
Feature activation | -8.82e-05 |
Pos logit contributions | |
z | +0.014 |
ats | +0.014 |
zag | +0.013 |
ew | +0.013 |
attered | +0.013 |
Neg logit contributions | |
bean | -0.009 |
Prince | -0.009 |
narrative | -0.008 |
reef | -0.008 |
thank | -0.008 |
Token | L |
Token ID | 43 |
Feature activation | +1.52e-03 |
Pos logit contributions | |
ats | +0.000 |
z | +0.000 |
ew | +0.000 |
zag | +0.000 |
om | +0.000 |
Neg logit contributions | |
bean | -0.000 |
narrative | -0.000 |
Prince | -0.000 |
reef | -0.000 |
Av | -0.000 |
Token | ily |
Token ID | 813 |
Feature activation | -4.08e-03 |
Pos logit contributions | |
bean | +0.001 |
narrative | +0.001 |
Prince | +0.001 |
Av | +0.001 |
reef | +0.001 |
Neg logit contributions | |
z | -0.004 |
ats | -0.004 |
ew | -0.004 |
zag | -0.004 |
om | -0.004 |
Token | didn |
Token ID | 1422 |
Feature activation | -2.26e-02 |
Pos logit contributions | |
z | +0.008 |
ew | +0.007 |
ats | +0.007 |
zag | +0.007 |
oses | +0.007 |
Neg logit contributions | |
bean | -0.006 |
Prince | -0.006 |
narrative | -0.006 |
thank | -0.006 |
reef | -0.006 |
Token | 't |
Token ID | 470 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
ats | +0.027 |
z | +0.027 |
ew | +0.024 |
om | +0.022 |
zag | +0.022 |
Neg logit contributions | |
bean | -0.051 |
narrative | -0.049 |
Prince | -0.048 |
thank | -0.047 |
Av | -0.046 |
Token | quite |
Token ID | 2407 |
Feature activation | -6.78e-02 |
Pos logit contributions | |
ats | +0.023 |
z | +0.023 |
zag | +0.022 |
ew | +0.022 |
om | +0.021 |
Neg logit contributions | |
bean | -0.019 |
narrative | -0.018 |
Prince | -0.018 |
reef | -0.017 |
cuc | -0.017 |
Token | understand |
Token ID | 1833 |
Feature activation | -1.86e-02 |
Pos logit contributions | |
z | +0.130 |
ats | +0.130 |
ew | +0.124 |
zag | +0.121 |
om | +0.118 |
Neg logit contributions | |
bean | -0.102 |
narrative | -0.095 |
Prince | -0.093 |
reef | -0.089 |
cuc | -0.085 |
Token | , |
Token ID | 11 |
Feature activation | -8.45e-03 |
Pos logit contributions | |
z | +0.041 |
ats | +0.038 |
zag | +0.038 |
ew | +0.037 |
om | +0.036 |
Neg logit contributions | |
bean | -0.026 |
Prince | -0.026 |
narrative | -0.024 |
thank | -0.024 |
Av | -0.022 |
Token | but |
Token ID | 475 |
Feature activation | -2.05e-02 |
Pos logit contributions | |
z | +0.018 |
ats | +0.018 |
ew | +0.016 |
zag | +0.016 |
om | +0.015 |
Neg logit contributions | |
bean | -0.012 |
Prince | -0.012 |
thank | -0.012 |
narrative | -0.011 |
poppy | -0.011 |
Token | then |
Token ID | 788 |
Feature activation | -1.76e-03 |
Pos logit contributions | |
z | +0.040 |
ats | +0.039 |
ew | +0.038 |
zag | +0.037 |
om | +0.036 |
Neg logit contributions | |
bean | -0.030 |
narrative | -0.027 |
Prince | -0.027 |
reef | -0.027 |
cuc | -0.026 |
Token | her |
Token ID | 607 |
Feature activation | -7.72e-03 |
Pos logit contributions | |
z | +0.004 |
ats | +0.004 |
ew | +0.004 |
zag | +0.004 |
om | +0.004 |
Neg logit contributions | |
bean | -0.002 |
Prince | -0.002 |
narrative | -0.002 |
reef | -0.002 |
thank | -0.002 |
Token | far |
Token ID | 1290 |
Feature activation | +3.00e-03 |
Pos logit contributions | |
z | +0.013 |
ats | +0.012 |
ew | +0.012 |
zag | +0.012 |
om | +0.011 |
Neg logit contributions | |
bean | -0.014 |
Prince | -0.013 |
narrative | -0.013 |
reef | -0.012 |
cuc | -0.012 |
Token | away |
Token ID | 1497 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
bean | +0.006 |
Prince | +0.006 |
narrative | +0.005 |
thank | +0.005 |
reef | +0.005 |
Neg logit contributions | |
z | -0.005 |
ats | -0.005 |
ew | -0.004 |
zag | -0.004 |
om | -0.004 |
Token | he |
Token ID | 339 |
Feature activation | -7.01e-03 |
Pos logit contributions | |
ats | +0.022 |
z | +0.022 |
ew | +0.021 |
co | +0.020 |
ches | +0.019 |
Neg logit contributions | |
reef | -0.016 |
bean | -0.015 |
Prince | -0.014 |
coral | -0.014 |
pearl | -0.013 |
Token | couldn |
Token ID | 3521 |
Feature activation | -2.72e-02 |
Pos logit contributions | |
ats | +0.015 |
z | +0.015 |
ew | +0.015 |
zag | +0.014 |
om | +0.014 |
Neg logit contributions | |
bean | -0.010 |
reef | -0.008 |
Prince | -0.008 |
seaw | -0.008 |
sailor | -0.008 |
Token | 't |
Token ID | 470 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
ats | +0.040 |
z | +0.035 |
as | +0.033 |
ew | +0.032 |
om | +0.031 |
Neg logit contributions | |
bean | -0.056 |
narrative | -0.049 |
thank | -0.049 |
Av | -0.049 |
Prince | -0.048 |
Token | quite |
Token ID | 2407 |
Feature activation | -6.69e-02 |
Pos logit contributions | |
z | +0.024 |
zag | +0.022 |
ats | +0.022 |
ew | +0.022 |
om | +0.020 |
Neg logit contributions | |
narrative | -0.024 |
bean | -0.024 |
Prince | -0.023 |
reef | -0.022 |
rice | -0.021 |
Token | see |
Token ID | 766 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
z | +0.134 |
ats | +0.130 |
ew | +0.127 |
zag | +0.122 |
om | +0.120 |
Neg logit contributions | |
bean | -0.101 |
Prince | -0.093 |
narrative | -0.091 |
reef | -0.088 |
thank | -0.085 |
Token | what |
Token ID | 644 |
Feature activation | -7.98e-03 |
Pos logit contributions | |
z | +0.033 |
ats | +0.033 |
ew | +0.031 |
zag | +0.031 |
om | +0.030 |
Neg logit contributions | |
bean | -0.021 |
Prince | -0.020 |
reef | -0.019 |
pearl | -0.018 |
narrative | -0.018 |
Token | it |
Token ID | 340 |
Feature activation | -1.70e-03 |
Pos logit contributions | |
z | +0.014 |
ats | +0.013 |
ew | +0.013 |
zag | +0.012 |
om | +0.012 |
Neg logit contributions | |
bean | -0.015 |
Prince | -0.013 |
narrative | -0.013 |
reef | -0.013 |
thank | -0.012 |
Token | was |
Token ID | 373 |
Feature activation | +8.59e-03 |
Pos logit contributions | |
z | +0.002 |
ats | +0.002 |
ew | +0.002 |
zag | +0.002 |
om | +0.002 |
Neg logit contributions | |
bean | -0.004 |
Prince | -0.003 |
narrative | -0.003 |
reef | -0.003 |
thank | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +5.29e-03 |
Pos logit contributions | |
bean | +0.016 |
Prince | +0.015 |
reef | +0.015 |
narrative | +0.014 |
thank | +0.014 |
Neg logit contributions | |
z | -0.014 |
ats | -0.014 |
ew | -0.013 |
om | -0.012 |
zag | -0.012 |
Token | The |
Token ID | 383 |
Feature activation | +9.09e-03 |
Pos logit contributions | |
bean | +0.009 |
narrative | +0.009 |
Prince | +0.009 |
reef | +0.009 |
pearl | +0.008 |
Neg logit contributions | |
z | -0.009 |
ats | -0.009 |
ew | -0.009 |
zag | -0.008 |
om | -0.008 |
Token | little |
Token ID | 1310 |
Feature activation | +2.60e-02 |
Pos logit contributions | |
narrative | +0.015 |
bean | +0.015 |
Prince | +0.014 |
reef | +0.014 |
cuc | +0.014 |
Neg logit contributions | |
z | -0.014 |
ats | -0.014 |
ew | -0.014 |
zag | -0.014 |
om | -0.013 |
Token | girl |
Token ID | 2576 |
Feature activation | +4.46e-03 |
Pos logit contributions | |
narrative | +0.038 |
Prince | +0.035 |
reef | +0.033 |
Cr | +0.033 |
thank | +0.033 |
Neg logit contributions | |
z | -0.047 |
- | -0.046 |
ew | -0.043 |
om | -0.043 |
ats | -0.043 |
Token | couldn |
Token ID | 3521 |
Feature activation | -1.99e-02 |
Pos logit contributions | |
bean | +0.006 |
Prince | +0.005 |
narrative | +0.005 |
thank | +0.005 |
Av | +0.005 |
Neg logit contributions | |
z | -0.010 |
ats | -0.010 |
ew | -0.009 |
zag | -0.009 |
om | -0.009 |
Token | 't |
Token ID | 470 |
Feature activation | -6.98e-03 |
Pos logit contributions | |
ats | +0.024 |
z | +0.023 |
ew | +0.021 |
om | +0.020 |
zag | +0.019 |
Neg logit contributions | |
bean | -0.046 |
Prince | -0.043 |
narrative | -0.043 |
thank | -0.041 |
Av | -0.041 |
Token | quite |
Token ID | 2407 |
Feature activation | -6.45e-02 |
Pos logit contributions | |
zag | +0.011 |
z | +0.011 |
ats | +0.010 |
ches | +0.010 |
- | +0.010 |
Neg logit contributions | |
narrative | -0.012 |
bean | -0.011 |
pearl | -0.011 |
cuc | -0.011 |
Prince | -0.011 |
Token | explain |
Token ID | 4727 |
Feature activation | -2.38e-02 |
Pos logit contributions | |
z | +0.133 |
ats | +0.131 |
ew | +0.126 |
zag | +0.124 |
om | +0.120 |
Neg logit contributions | |
bean | -0.089 |
narrative | -0.084 |
Prince | -0.083 |
reef | -0.078 |
cuc | -0.074 |
Token | , |
Token ID | 11 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
z | +0.052 |
ats | +0.049 |
ew | +0.048 |
zag | +0.048 |
om | +0.045 |
Neg logit contributions | |
bean | -0.034 |
Prince | -0.033 |
thank | -0.031 |
poppy | -0.029 |
narrative | -0.029 |
Token | so |
Token ID | 523 |
Feature activation | -1.43e-02 |
Pos logit contributions | |
z | +0.025 |
ats | +0.025 |
ew | +0.023 |
zag | +0.023 |
om | +0.022 |
Neg logit contributions | |
bean | -0.025 |
Prince | -0.024 |
narrative | -0.023 |
thank | -0.022 |
reef | -0.022 |
Token | her |
Token ID | 607 |
Feature activation | -7.47e-03 |
Pos logit contributions | |
z | +0.026 |
ats | +0.024 |
ew | +0.024 |
om | +0.024 |
zag | +0.023 |
Neg logit contributions | |
bean | -0.023 |
narrative | -0.023 |
reef | -0.022 |
Prince | -0.021 |
seaw | -0.020 |
Token | mom |
Token ID | 1995 |
Feature activation | +3.81e-03 |
Pos logit contributions | |
z | +0.013 |
ats | +0.013 |
ew | +0.012 |
zag | +0.012 |
om | +0.012 |
Neg logit contributions | |
bean | -0.012 |
Prince | -0.012 |
narrative | -0.012 |
reef | -0.011 |
cuc | -0.011 |
Token | scared |
Token ID | 12008 |
Feature activation | +6.00e-03 |
Pos logit contributions | |
z | +0.042 |
ats | +0.042 |
zag | +0.039 |
ew | +0.038 |
co | +0.037 |
Neg logit contributions | |
bean | -0.027 |
Prince | -0.026 |
thank | -0.026 |
relief | -0.025 |
narrative | -0.024 |
Token | , |
Token ID | 11 |
Feature activation | -1.62e-02 |
Pos logit contributions | |
Prince | +0.006 |
bean | +0.006 |
thank | +0.005 |
Pete | +0.005 |
Nem | +0.005 |
Neg logit contributions | |
z | -0.016 |
ats | -0.015 |
zag | -0.015 |
tr | -0.014 |
icycle | -0.014 |
Token | he |
Token ID | 339 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
ats | +0.039 |
z | +0.038 |
ew | +0.035 |
zag | +0.035 |
om | +0.033 |
Neg logit contributions | |
bean | -0.020 |
Prince | -0.020 |
thank | -0.018 |
narrative | -0.017 |
reef | -0.016 |
Token | couldn |
Token ID | 3521 |
Feature activation | -3.12e-02 |
Pos logit contributions | |
z | +0.042 |
ats | +0.041 |
ew | +0.038 |
om | +0.037 |
zag | +0.037 |
Neg logit contributions | |
bean | -0.025 |
Prince | -0.023 |
thank | -0.023 |
prince | -0.022 |
sailor | -0.021 |
Token | 't |
Token ID | 470 |
Feature activation | -2.00e-02 |
Pos logit contributions | |
ats | +0.042 |
z | +0.039 |
ew | +0.036 |
om | +0.035 |
as | +0.035 |
Neg logit contributions | |
bean | -0.066 |
Prince | -0.062 |
narrative | -0.062 |
thank | -0.060 |
Av | -0.058 |
Token | even |
Token ID | 772 |
Feature activation | -6.43e-02 |
Pos logit contributions | |
z | +0.040 |
ats | +0.039 |
ew | +0.038 |
zag | +0.037 |
om | +0.037 |
Neg logit contributions | |
bean | -0.030 |
Prince | -0.028 |
narrative | -0.027 |
reef | -0.026 |
thank | -0.025 |
Token | scream |
Token ID | 8196 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
z | +0.136 |
ats | +0.131 |
ew | +0.128 |
om | +0.122 |
zag | +0.121 |
Neg logit contributions | |
bean | -0.095 |
Prince | -0.089 |
narrative | -0.083 |
thank | -0.082 |
reef | -0.082 |
Token | . |
Token ID | 13 |
Feature activation | -9.93e-03 |
Pos logit contributions | |
ats | +0.028 |
z | +0.026 |
ew | +0.025 |
icycle | +0.024 |
zag | +0.024 |
Neg logit contributions | |
Prince | -0.016 |
bean | -0.015 |
thank | -0.014 |
Av | -0.013 |
mer | -0.013 |
Token | The |
Token ID | 383 |
Feature activation | -3.58e-03 |
Pos logit contributions | |
ats | +0.024 |
z | +0.023 |
zag | +0.021 |
ew | +0.021 |
as | +0.021 |
Neg logit contributions | |
Prince | -0.012 |
bean | -0.012 |
Av | -0.011 |
thank | -0.011 |
Cr | -0.010 |
Token | monster |
Token ID | 9234 |
Feature activation | -7.68e-03 |
Pos logit contributions | |
z | +0.005 |
zag | +0.005 |
ew | +0.004 |
ats | +0.004 |
om | +0.004 |
Neg logit contributions | |
bean | -0.007 |
narrative | -0.007 |
cuc | -0.007 |
Prince | -0.006 |
thy | -0.006 |
Token | then |
Token ID | 788 |
Feature activation | -9.40e-03 |
Pos logit contributions | |
ats | +0.016 |
z | +0.016 |
ew | +0.016 |
om | +0.015 |
ings | +0.015 |
Neg logit contributions | |
bean | -0.010 |
Prince | -0.009 |
thank | -0.009 |
prince | -0.009 |
sailor | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
bean | +0.003 |
narrative | +0.003 |
Prince | +0.003 |
reef | +0.003 |
pearl | +0.003 |
Neg logit contributions | |
z | -0.003 |
ats | -0.003 |
ew | -0.003 |
zag | -0.003 |
om | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +1.99e-03 |
Pos logit contributions | |
z | +0.022 |
ats | +0.022 |
ew | +0.021 |
zag | +0.021 |
attered | +0.020 |
Neg logit contributions | |
bean | -0.014 |
Prince | -0.013 |
reef | -0.012 |
narrative | -0.012 |
Av | -0.011 |
Token | Jack |
Token ID | 14295 |
Feature activation | -7.79e-03 |
Pos logit contributions | |
bean | +0.003 |
Prince | +0.003 |
narrative | +0.003 |
reef | +0.003 |
cuc | +0.003 |
Neg logit contributions | |
z | -0.004 |
ats | -0.004 |
ew | -0.004 |
zag | -0.004 |
om | -0.004 |
Token | didn |
Token ID | 1422 |
Feature activation | -2.27e-02 |
Pos logit contributions | |
z | +0.015 |
ew | +0.015 |
zag | +0.014 |
ats | +0.014 |
rol | +0.013 |
Neg logit contributions | |
bean | -0.012 |
cuc | -0.010 |
reef | -0.010 |
Prince | -0.010 |
seaw | -0.010 |
Token | 't |
Token ID | 470 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
ats | +0.025 |
z | +0.025 |
ew | +0.022 |
zag | +0.020 |
om | +0.020 |
Neg logit contributions | |
bean | -0.054 |
Prince | -0.050 |
narrative | -0.050 |
thank | -0.048 |
Av | -0.048 |
Token | quite |
Token ID | 2407 |
Feature activation | -6.42e-02 |
Pos logit contributions | |
z | +0.018 |
ats | +0.018 |
zag | +0.017 |
ew | +0.017 |
om | +0.016 |
Neg logit contributions | |
bean | -0.020 |
narrative | -0.020 |
Prince | -0.019 |
reef | -0.019 |
pearl | -0.018 |
Token | know |
Token ID | 760 |
Feature activation | -1.37e-02 |
Pos logit contributions | |
ats | +0.102 |
z | +0.102 |
ew | +0.097 |
om | +0.096 |
zag | +0.094 |
Neg logit contributions | |
narrative | -0.107 |
bean | -0.107 |
Prince | -0.102 |
reef | -0.100 |
Dolphin | -0.093 |
Token | what |
Token ID | 644 |
Feature activation | -1.37e-02 |
Pos logit contributions | |
z | +0.025 |
ats | +0.025 |
ew | +0.024 |
zag | +0.023 |
om | +0.022 |
Neg logit contributions | |
bean | -0.023 |
Prince | -0.022 |
narrative | -0.021 |
reef | -0.020 |
thank | -0.020 |
Token | he |
Token ID | 339 |
Feature activation | -2.70e-02 |
Pos logit contributions | |
z | +0.017 |
ats | +0.016 |
ew | +0.015 |
zag | +0.014 |
om | +0.013 |
Neg logit contributions | |
bean | -0.033 |
Prince | -0.031 |
narrative | -0.030 |
reef | -0.030 |
cuc | -0.029 |
Token | wanted |
Token ID | 2227 |
Feature activation | +7.42e-03 |
Pos logit contributions | |
z | +0.053 |
ats | +0.051 |
ew | +0.050 |
zag | +0.049 |
om | +0.047 |
Neg logit contributions | |
bean | -0.041 |
Prince | -0.037 |
narrative | -0.037 |
thank | -0.034 |
reef | -0.034 |
Token | to |
Token ID | 284 |
Feature activation | +2.83e-03 |
Pos logit contributions | |
bean | +0.012 |
Prince | +0.010 |
narrative | +0.010 |
thank | +0.010 |
Av | +0.010 |
Neg logit contributions | |
z | -0.015 |
ats | -0.014 |
ew | -0.014 |
zag | -0.014 |
attered | -0.013 |
Token | different |
Token ID | 1180 |
Feature activation | -3.21e-03 |
Pos logit contributions | |
z | +0.019 |
ats | +0.018 |
ew | +0.018 |
zag | +0.017 |
om | +0.017 |
Neg logit contributions | |
bean | -0.017 |
Prince | -0.016 |
narrative | -0.016 |
reef | -0.015 |
cuc | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | +9.33e-03 |
Pos logit contributions | |
ats | +0.007 |
z | +0.007 |
ew | +0.007 |
zag | +0.006 |
om | +0.006 |
Neg logit contributions | |
bean | -0.005 |
Prince | -0.004 |
beans | -0.004 |
caul | -0.004 |
rice | -0.004 |
Token | she |
Token ID | 673 |
Feature activation | -2.89e-03 |
Pos logit contributions | |
bean | +0.013 |
Prince | +0.012 |
narrative | +0.011 |
reef | +0.011 |
thank | +0.011 |
Neg logit contributions | |
z | -0.020 |
ats | -0.020 |
ew | -0.019 |
zag | -0.019 |
om | -0.018 |
Token | couldn |
Token ID | 3521 |
Feature activation | -2.61e-02 |
Pos logit contributions | |
z | +0.006 |
ew | +0.006 |
ats | +0.006 |
zag | +0.006 |
oses | +0.005 |
Neg logit contributions | |
bean | -0.004 |
Prince | -0.003 |
Honey | -0.003 |
refreshed | -0.003 |
reef | -0.003 |
Token | 't |
Token ID | 470 |
Feature activation | -1.00e-02 |
Pos logit contributions | |
ats | +0.035 |
z | +0.033 |
ew | +0.030 |
om | +0.028 |
as | +0.028 |
Neg logit contributions | |
bean | -0.057 |
narrative | -0.052 |
Prince | -0.052 |
Av | -0.051 |
thank | -0.050 |
Token | quite |
Token ID | 2407 |
Feature activation | -6.37e-02 |
Pos logit contributions | |
z | +0.019 |
ats | +0.018 |
zag | +0.018 |
ew | +0.018 |
om | +0.017 |
Neg logit contributions | |
bean | -0.016 |
narrative | -0.015 |
Prince | -0.015 |
reef | -0.014 |
cuc | -0.013 |
Token | get |
Token ID | 651 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
z | +0.136 |
ats | +0.132 |
ew | +0.129 |
zag | +0.125 |
om | +0.122 |
Neg logit contributions | |
bean | -0.089 |
Prince | -0.082 |
narrative | -0.079 |
reef | -0.076 |
thank | -0.074 |
Token | comfortable |
Token ID | 6792 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
z | +0.027 |
ats | +0.026 |
zag | +0.026 |
ew | +0.026 |
uddy | +0.024 |
Neg logit contributions | |
bean | -0.025 |
Prince | -0.022 |
refreshed | -0.021 |
poppy | -0.021 |
Honey | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | +2.11e-03 |
Pos logit contributions | |
z | +0.025 |
ats | +0.025 |
ew | +0.025 |
zag | +0.023 |
om | +0.023 |
Neg logit contributions | |
bean | -0.024 |
Prince | -0.022 |
narrative | -0.021 |
reef | -0.021 |
rice | -0.021 |
Token | It |
Token ID | 632 |
Feature activation | +3.62e-03 |
Pos logit contributions | |
bean | +0.003 |
Prince | +0.003 |
Av | +0.003 |
Claire | +0.003 |
narrative | +0.003 |
Neg logit contributions | |
ats | -0.004 |
z | -0.004 |
zag | -0.004 |
ew | -0.004 |
ep | -0.004 |
Token | was |
Token ID | 373 |
Feature activation | -8.49e-04 |
Pos logit contributions | |
bean | +0.006 |
narrative | +0.005 |
Honey | +0.005 |
refreshed | +0.005 |
energ | +0.005 |
Neg logit contributions | |
ats | -0.007 |
ew | -0.007 |
oses | -0.006 |
z | -0.006 |
om | -0.006 |
Token | cried |
Token ID | 16896 |
Feature activation | -1.95e-02 |
Pos logit contributions | |
z | +0.048 |
ats | +0.045 |
zag | +0.044 |
icycle | +0.042 |
ew | +0.042 |
Neg logit contributions | |
bean | -0.025 |
thank | -0.023 |
Prince | -0.023 |
narrative | -0.021 |
perk | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | -1.43e-02 |
Pos logit contributions | |
z | +0.032 |
ats | +0.031 |
ew | +0.029 |
zag | +0.029 |
om | +0.027 |
Neg logit contributions | |
bean | -0.037 |
Prince | -0.035 |
narrative | -0.034 |
thank | -0.032 |
reef | -0.032 |
Token | " |
Token ID | 366 |
Feature activation | -2.00e-02 |
Pos logit contributions | |
ats | +0.034 |
z | +0.033 |
zag | +0.030 |
ew | +0.030 |
ches | +0.029 |
Neg logit contributions | |
bean | -0.017 |
Prince | -0.017 |
narrative | -0.016 |
thank | -0.016 |
Av | -0.014 |
Token | The |
Token ID | 464 |
Feature activation | -7.37e-03 |
Pos logit contributions | |
z | +0.037 |
ats | +0.034 |
ew | +0.034 |
zag | +0.032 |
om | +0.032 |
Neg logit contributions | |
bean | -0.033 |
Prince | -0.032 |
narrative | -0.031 |
reef | -0.030 |
thank | -0.029 |
Token | ost |
Token ID | 23619 |
Feature activation | -2.08e-02 |
Pos logit contributions | |
z | +0.015 |
ats | +0.015 |
ew | +0.014 |
zag | +0.014 |
om | +0.013 |
Neg logit contributions | |
bean | -0.011 |
narrative | -0.011 |
Prince | -0.010 |
reef | -0.010 |
thank | -0.009 |
Token | ric |
Token ID | 1173 |
Feature activation | -6.35e-02 |
Pos logit contributions | |
z | +0.033 |
eth | +0.031 |
ables | +0.029 |
icycle | +0.029 |
attered | +0.028 |
Neg logit contributions | |
narrative | -0.030 |
bean | -0.028 |
riage | -0.028 |
reef | -0.027 |
crabs | -0.027 |
Token | hes |
Token ID | 956 |
Feature activation | -1.92e-02 |
Pos logit contributions | |
z | +0.129 |
ats | +0.120 |
eth | +0.119 |
zag | +0.119 |
uddy | +0.117 |
Neg logit contributions | |
narrative | -0.082 |
bean | -0.077 |
Prince | -0.072 |
reef | -0.071 |
refreshed | -0.069 |
Token | are |
Token ID | 389 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
z | +0.039 |
ats | +0.036 |
ew | +0.036 |
icycle | +0.035 |
zag | +0.035 |
Neg logit contributions | |
bean | -0.028 |
thank | -0.025 |
narrative | -0.024 |
reef | -0.023 |
kin | -0.022 |
Token | mean |
Token ID | 1612 |
Feature activation | +9.52e-03 |
Pos logit contributions | |
z | +0.024 |
ats | +0.022 |
icycle | +0.022 |
zag | +0.022 |
eth | +0.020 |
Neg logit contributions | |
bean | -0.017 |
thank | -0.016 |
rice | -0.014 |
lav | -0.014 |
Prince | -0.014 |
Token | ! |
Token ID | 0 |
Feature activation | -1.98e-02 |
Pos logit contributions | |
bean | +0.012 |
thank | +0.012 |
Prince | +0.011 |
rice | +0.011 |
seaw | +0.010 |
Neg logit contributions | |
z | -0.021 |
zag | -0.021 |
icycle | -0.019 |
ats | -0.019 |
tr | -0.018 |
Token | They |
Token ID | 1119 |
Feature activation | -4.04e-03 |
Pos logit contributions | |
z | +0.040 |
ats | +0.040 |
zag | +0.037 |
ew | +0.036 |
om | +0.034 |
Neg logit contributions | |
bean | -0.030 |
Prince | -0.028 |
narrative | -0.027 |
Av | -0.025 |
thank | -0.025 |
Token | , |
Token ID | 11 |
Feature activation | +1.98e-04 |
Pos logit contributions | |
ats | +0.014 |
z | +0.014 |
ew | +0.013 |
zag | +0.013 |
om | +0.012 |
Neg logit contributions | |
bean | -0.014 |
Prince | -0.013 |
narrative | -0.013 |
thank | -0.013 |
reef | -0.012 |
Token | but |
Token ID | 475 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
Prince | +0.000 |
refreshed | +0.000 |
bean | +0.000 |
energ | +0.000 |
Av | +0.000 |
Neg logit contributions | |
ats | -0.000 |
z | -0.000 |
ew | -0.000 |
zag | -0.000 |
uddy | -0.000 |
Token | she |
Token ID | 673 |
Feature activation | -1.96e-02 |
Pos logit contributions | |
z | +0.027 |
ats | +0.026 |
ew | +0.025 |
zag | +0.025 |
om | +0.024 |
Neg logit contributions | |
bean | -0.020 |
Prince | -0.018 |
narrative | -0.018 |
reef | -0.017 |
cuc | -0.016 |
Token | couldn |
Token ID | 3521 |
Feature activation | -2.46e-02 |
Pos logit contributions | |
z | +0.045 |
ats | +0.043 |
zag | +0.041 |
ew | +0.040 |
oses | +0.039 |
Neg logit contributions | |
bean | -0.024 |
Prince | -0.023 |
Av | -0.019 |
prince | -0.019 |
reef | -0.019 |
Token | 't |
Token ID | 470 |
Feature activation | -9.93e-03 |
Pos logit contributions | |
ats | +0.032 |
z | +0.031 |
ew | +0.028 |
om | +0.027 |
attered | +0.026 |
Neg logit contributions | |
bean | -0.053 |
Prince | -0.050 |
narrative | -0.050 |
thank | -0.048 |
Av | -0.048 |
Token | quite |
Token ID | 2407 |
Feature activation | -6.29e-02 |
Pos logit contributions | |
z | +0.016 |
ats | +0.016 |
zag | +0.015 |
ew | +0.015 |
co | +0.014 |
Neg logit contributions | |
bean | -0.017 |
narrative | -0.017 |
cuc | -0.016 |
Prince | -0.016 |
reef | -0.016 |
Token | figure |
Token ID | 3785 |
Feature activation | -2.30e-02 |
Pos logit contributions | |
z | +0.135 |
ats | +0.130 |
ew | +0.128 |
zag | +0.123 |
om | +0.121 |
Neg logit contributions | |
bean | -0.087 |
Prince | -0.082 |
narrative | -0.079 |
reef | -0.075 |
thank | -0.074 |
Token | out |
Token ID | 503 |
Feature activation | -3.36e-02 |
Pos logit contributions | |
z | +0.044 |
attered | +0.041 |
ew | +0.040 |
om | +0.039 |
zag | +0.039 |
Neg logit contributions | |
Prince | -0.038 |
thank | -0.036 |
bean | -0.033 |
Princess | -0.033 |
God | -0.033 |
Token | what |
Token ID | 644 |
Feature activation | -7.56e-03 |
Pos logit contributions | |
z | +0.079 |
ats | +0.075 |
ew | +0.074 |
zag | +0.074 |
om | +0.071 |
Neg logit contributions | |
Prince | -0.040 |
bean | -0.040 |
thank | -0.037 |
reef | -0.035 |
relief | -0.035 |
Token | it |
Token ID | 340 |
Feature activation | -4.59e-03 |
Pos logit contributions | |
z | +0.015 |
ats | +0.014 |
ew | +0.014 |
zag | +0.013 |
om | +0.013 |
Neg logit contributions | |
bean | -0.012 |
Prince | -0.011 |
narrative | -0.011 |
thank | -0.011 |
reef | -0.011 |
Token | was |
Token ID | 373 |
Feature activation | +2.94e-03 |
Pos logit contributions | |
z | +0.007 |
ats | +0.007 |
ew | +0.007 |
om | +0.006 |
zag | +0.006 |
Neg logit contributions | |
bean | -0.009 |
Prince | -0.008 |
narrative | -0.008 |
reef | -0.008 |
thank | -0.008 |
Token | it |
Token ID | 340 |
Feature activation | +5.39e-03 |
Pos logit contributions | |
z | +0.047 |
ats | +0.046 |
ew | +0.045 |
zag | +0.044 |
om | +0.042 |
Neg logit contributions | |
bean | -0.035 |
Prince | -0.032 |
narrative | -0.031 |
reef | -0.030 |
thank | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | +5.13e-03 |
Pos logit contributions | |
bean | +0.008 |
reef | +0.007 |
Prince | +0.007 |
beans | +0.007 |
Claire | +0.006 |
Neg logit contributions | |
ew | -0.011 |
z | -0.011 |
ats | -0.011 |
om | -0.010 |
zag | -0.009 |
Token | She |
Token ID | 1375 |
Feature activation | +3.61e-03 |
Pos logit contributions | |
bean | +0.007 |
Prince | +0.007 |
Av | +0.007 |
Claire | +0.006 |
narrative | +0.006 |
Neg logit contributions | |
ats | -0.011 |
z | -0.011 |
zag | -0.010 |
ew | -0.010 |
om | -0.009 |
Token | couldn |
Token ID | 3521 |
Feature activation | -2.26e-02 |
Pos logit contributions | |
bean | +0.005 |
Prince | +0.004 |
thank | +0.004 |
reef | +0.004 |
cuc | +0.004 |
Neg logit contributions | |
z | -0.007 |
ats | -0.007 |
ew | -0.007 |
zag | -0.007 |
attered | -0.007 |
Token | 't |
Token ID | 470 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
ats | +0.034 |
z | +0.032 |
attered | +0.029 |
ew | +0.029 |
as | +0.029 |
Neg logit contributions | |
bean | -0.045 |
Prince | -0.041 |
thank | -0.041 |
Av | -0.041 |
narrative | -0.040 |
Token | quite |
Token ID | 2407 |
Feature activation | -6.26e-02 |
Pos logit contributions | |
z | +0.022 |
ats | +0.022 |
zag | +0.021 |
ew | +0.021 |
co | +0.020 |
Neg logit contributions | |
bean | -0.013 |
narrative | -0.013 |
Prince | -0.013 |
reef | -0.012 |
cuc | -0.011 |
Token | reach |
Token ID | 3151 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
z | +0.144 |
ats | +0.137 |
ew | +0.136 |
zag | +0.131 |
om | +0.129 |
Neg logit contributions | |
bean | -0.080 |
Prince | -0.073 |
thank | -0.072 |
narrative | -0.068 |
reef | -0.067 |
Token | it |
Token ID | 340 |
Feature activation | -6.36e-03 |
Pos logit contributions | |
z | +0.029 |
ew | +0.028 |
ats | +0.028 |
zag | +0.027 |
attered | +0.027 |
Neg logit contributions | |
bean | -0.013 |
Prince | -0.012 |
pearl | -0.011 |
Av | -0.010 |
poppy | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | -7.90e-03 |
Pos logit contributions | |
ats | +0.014 |
ew | +0.013 |
z | +0.013 |
om | +0.013 |
attered | +0.012 |
Neg logit contributions | |
bean | -0.009 |
Prince | -0.007 |
reef | -0.007 |
Honey | -0.007 |
thank | -0.007 |
Token | so |
Token ID | 523 |
Feature activation | -9.32e-03 |
Pos logit contributions | |
ats | +0.018 |
z | +0.018 |
ew | +0.017 |
zag | +0.017 |
om | +0.016 |
Neg logit contributions | |
bean | -0.010 |
Prince | -0.010 |
thank | -0.010 |
Claire | -0.009 |
refreshed | -0.009 |
Token | she |
Token ID | 673 |
Feature activation | -6.63e-03 |
Pos logit contributions | |
ats | +0.024 |
z | +0.024 |
ew | +0.023 |
zag | +0.023 |
om | +0.022 |
Neg logit contributions | |
bean | -0.009 |
Prince | -0.008 |
thank | -0.007 |
narrative | -0.007 |
Av | -0.007 |
Token | Lily |
Token ID | 20037 |
Feature activation | +3.01e-03 |
Pos logit contributions | |
z | +0.000 |
ats | +0.000 |
ew | +0.000 |
zag | +0.000 |
om | +0.000 |
Neg logit contributions | |
bean | -0.000 |
Prince | -0.000 |
narrative | -0.000 |
reef | -0.000 |
cuc | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | -5.56e-03 |
Pos logit contributions | |
bean | +0.006 |
Prince | +0.006 |
narrative | +0.006 |
reef | +0.006 |
cuc | +0.005 |
Neg logit contributions | |
z | -0.004 |
ats | -0.004 |
ew | -0.004 |
zag | -0.004 |
om | -0.004 |
Token | She |
Token ID | 1375 |
Feature activation | -1.35e-03 |
Pos logit contributions | |
z | +0.007 |
om | +0.007 |
ew | +0.007 |
zag | +0.006 |
o | +0.006 |
Neg logit contributions | |
pearl | -0.012 |
bean | -0.011 |
sailor | -0.011 |
narrative | -0.011 |
seaw | -0.011 |
Token | had |
Token ID | 550 |
Feature activation | -4.57e-03 |
Pos logit contributions | |
z | +0.002 |
ats | +0.002 |
ew | +0.002 |
zag | +0.002 |
om | +0.002 |
Neg logit contributions | |
bean | -0.003 |
Prince | -0.003 |
narrative | -0.003 |
reef | -0.003 |
cuc | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | -1.82e-02 |
Pos logit contributions | |
ats | +0.010 |
z | +0.010 |
ew | +0.010 |
zag | +0.009 |
oses | +0.009 |
Neg logit contributions | |
bean | -0.006 |
Prince | -0.006 |
narrative | -0.005 |
poppy | -0.005 |
rice | -0.005 |
Token | best |
Token ID | 1266 |
Feature activation | -6.24e-02 |
Pos logit contributions | |
z | +0.034 |
ats | +0.033 |
ew | +0.032 |
zag | +0.030 |
om | +0.029 |
Neg logit contributions | |
bean | -0.032 |
Prince | -0.029 |
narrative | -0.028 |
reef | -0.027 |
poppy | -0.027 |
Token | friend |
Token ID | 1545 |
Feature activation | -2.18e-02 |
Pos logit contributions | |
z | +0.100 |
ats | +0.098 |
ew | +0.096 |
zag | +0.087 |
ches | +0.084 |
Neg logit contributions | |
bean | -0.121 |
Prince | -0.111 |
narrative | -0.108 |
reef | -0.105 |
poppy | -0.103 |
Token | named |
Token ID | 3706 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
z | +0.049 |
ats | +0.047 |
ew | +0.046 |
zag | +0.046 |
aned | +0.046 |
Neg logit contributions | |
bean | -0.028 |
Prince | -0.025 |
thank | -0.023 |
poppy | -0.023 |
Pink | -0.022 |
Token | Tim |
Token ID | 5045 |
Feature activation | -7.66e-03 |
Pos logit contributions | |
z | +0.030 |
ats | +0.029 |
ew | +0.028 |
zag | +0.027 |
om | +0.027 |
Neg logit contributions | |
bean | -0.019 |
Prince | -0.018 |
Av | -0.016 |
narrative | -0.016 |
reef | -0.015 |
Token | my |
Token ID | 1820 |
Feature activation | -1.55e-02 |
Pos logit contributions | |
z | +0.013 |
ew | +0.013 |
ats | +0.013 |
zag | +0.012 |
om | +0.011 |
Neg logit contributions | |
bean | -0.014 |
Prince | -0.013 |
reef | -0.012 |
narrative | -0.012 |
Av | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -9.97e-03 |
Pos logit contributions | |
z | +0.027 |
ats | +0.026 |
ew | +0.026 |
zag | +0.025 |
om | +0.023 |
Neg logit contributions | |
bean | -0.027 |
Prince | -0.026 |
reef | -0.024 |
narrative | -0.024 |
thank | -0.023 |
Token | ostr |
Token ID | 42387 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
z | +0.031 |
ats | +0.030 |
ew | +0.030 |
run | +0.027 |
zag | +0.027 |
Neg logit contributions | |
bean | -0.019 |
Prince | -0.019 |
reef | -0.019 |
narrative | -0.016 |
prince | -0.016 |
Token | ich |
Token ID | 488 |
Feature activation | -3.93e-03 |
Pos logit contributions | |
ches | +0.020 |
ats | +0.020 |
run | +0.019 |
z | +0.019 |
attered | +0.019 |
Neg logit contributions | |
reef | -0.015 |
narrative | -0.015 |
crab | -0.015 |
sailor | -0.015 |
bean | -0.015 |
Token | pen |
Token ID | 3112 |
Feature activation | -5.84e-03 |
Pos logit contributions | |
z | +0.006 |
ew | +0.006 |
ats | +0.006 |
zag | +0.005 |
om | +0.005 |
Neg logit contributions | |
bean | -0.008 |
Prince | -0.007 |
reef | -0.007 |
Av | -0.006 |
narrative | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -6.72e-04 |
Pos logit contributions | |
z | +0.009 |
ats | +0.009 |
ew | +0.009 |
zag | +0.008 |
om | +0.008 |
Neg logit contributions | |
bean | -0.011 |
Prince | -0.011 |
narrative | -0.010 |
reef | -0.010 |
rice | -0.010 |
Token | Ost |
Token ID | 38919 |
Feature activation | -2.00e-02 |
Pos logit contributions | |
z | +0.001 |
ew | +0.001 |
ats | +0.001 |
om | +0.001 |
zag | +0.001 |
Neg logit contributions | |
bean | -0.001 |
narrative | -0.001 |
Prince | -0.001 |
reef | -0.001 |
pearl | -0.001 |
Token | ric |
Token ID | 1173 |
Feature activation | -6.20e-02 |
Pos logit contributions | |
z | +0.020 |
ats | +0.018 |
ew | +0.017 |
zag | +0.016 |
om | +0.015 |
Neg logit contributions | |
bean | -0.050 |
Prince | -0.048 |
narrative | -0.048 |
reef | -0.047 |
Av | -0.045 |
Token | hes |
Token ID | 956 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
z | +0.123 |
attered | +0.116 |
ats | +0.115 |
eth | +0.114 |
coat | +0.111 |
Neg logit contributions | |
narrative | -0.079 |
Prince | -0.075 |
bean | -0.074 |
reef | -0.074 |
refreshed | -0.072 |
Token | are |
Token ID | 389 |
Feature activation | +1.05e-03 |
Pos logit contributions | |
z | +0.021 |
ew | +0.019 |
ats | +0.018 |
zag | +0.018 |
icycle | +0.018 |
Neg logit contributions | |
bean | -0.017 |
reef | -0.015 |
thank | -0.015 |
narrative | -0.015 |
Prince | -0.014 |
Token | big |
Token ID | 1263 |
Feature activation | +6.68e-04 |
Pos logit contributions | |
bean | +0.001 |
Prince | +0.001 |
reef | +0.001 |
caul | +0.001 |
rice | +0.001 |
Neg logit contributions | |
z | -0.002 |
ats | -0.002 |
ew | -0.002 |
zag | -0.002 |
attered | -0.002 |
Token | birds |
Token ID | 10087 |
Feature activation | -2.23e-03 |
Pos logit contributions | |
bean | +0.001 |
Prince | +0.001 |
narrative | +0.001 |
reef | +0.001 |
seaw | +0.001 |
Neg logit contributions | |
z | -0.001 |
ats | -0.001 |
zag | -0.001 |
ew | -0.001 |
attered | -0.001 |
Token | with |
Token ID | 351 |
Feature activation | -1.46e-03 |
Pos logit contributions | |
z | +0.004 |
ats | +0.004 |
ew | +0.004 |
zag | +0.004 |
attered | +0.004 |
Neg logit contributions | |
bean | -0.004 |
reef | -0.003 |
Prince | -0.003 |
poppy | -0.003 |
thank | -0.003 |
Token | Ann |
Token ID | 5506 |
Feature activation | -2.31e-02 |
Pos logit contributions | |
z | +0.020 |
ats | +0.019 |
ew | +0.019 |
zag | +0.018 |
om | +0.018 |
Neg logit contributions | |
bean | -0.017 |
narrative | -0.016 |
Prince | -0.016 |
reef | -0.015 |
cuc | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -8.64e-03 |
Pos logit contributions | |
z | +0.048 |
ew | +0.046 |
zag | +0.045 |
icycle | +0.045 |
ats | +0.044 |
Neg logit contributions | |
thank | -0.029 |
bean | -0.028 |
Prince | -0.028 |
agreement | -0.027 |
hospitality | -0.026 |
Token | They |
Token ID | 1119 |
Feature activation | +4.32e-03 |
Pos logit contributions | |
z | +0.019 |
ats | +0.018 |
ew | +0.018 |
zag | +0.017 |
om | +0.016 |
Neg logit contributions | |
bean | -0.010 |
reef | -0.010 |
Prince | -0.010 |
narrative | -0.010 |
thank | -0.009 |
Token | had |
Token ID | 550 |
Feature activation | -4.59e-03 |
Pos logit contributions | |
bean | +0.008 |
Prince | +0.008 |
narrative | +0.008 |
reef | +0.008 |
pearl | +0.007 |
Neg logit contributions | |
z | -0.007 |
ats | -0.006 |
ew | -0.006 |
zag | -0.006 |
om | -0.006 |
Token | been |
Token ID | 587 |
Feature activation | -9.72e-03 |
Pos logit contributions | |
z | +0.011 |
ats | +0.011 |
ew | +0.011 |
zag | +0.010 |
ches | +0.010 |
Neg logit contributions | |
bean | -0.005 |
Prince | -0.005 |
rice | -0.005 |
narrative | -0.005 |
reef | -0.004 |
Token | best |
Token ID | 1266 |
Feature activation | -6.19e-02 |
Pos logit contributions | |
z | +0.017 |
ats | +0.017 |
ew | +0.017 |
zag | +0.016 |
om | +0.015 |
Neg logit contributions | |
bean | -0.016 |
Prince | -0.015 |
Av | -0.014 |
narrative | -0.014 |
reef | -0.014 |
Token | friends |
Token ID | 2460 |
Feature activation | -2.56e-02 |
Pos logit contributions | |
z | +0.153 |
ew | +0.142 |
zag | +0.137 |
attered | +0.137 |
ats | +0.136 |
Neg logit contributions | |
thank | -0.068 |
bean | -0.057 |
generosity | -0.055 |
hospitality | -0.054 |
Prince | -0.053 |
Token | for |
Token ID | 329 |
Feature activation | -2.45e-02 |
Pos logit contributions | |
z | +0.044 |
ew | +0.042 |
ats | +0.042 |
zag | +0.039 |
om | +0.038 |
Neg logit contributions | |
bean | -0.046 |
Prince | -0.043 |
narrative | -0.042 |
reef | -0.041 |
thank | -0.039 |
Token | a |
Token ID | 257 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
z | +0.045 |
ats | +0.044 |
ew | +0.043 |
zag | +0.041 |
om | +0.040 |
Neg logit contributions | |
bean | -0.040 |
Prince | -0.038 |
narrative | -0.037 |
reef | -0.036 |
thank | -0.034 |
Token | long |
Token ID | 890 |
Feature activation | -2.51e-02 |
Pos logit contributions | |
z | +0.035 |
ats | +0.034 |
ew | +0.033 |
zag | +0.031 |
om | +0.031 |
Neg logit contributions | |
bean | -0.031 |
Prince | -0.029 |
narrative | -0.028 |
reef | -0.027 |
thank | -0.026 |
Token | time |
Token ID | 640 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
ew | +0.051 |
z | +0.049 |
ats | +0.047 |
attered | +0.046 |
oses | +0.045 |
Neg logit contributions | |
bean | -0.038 |
reef | -0.033 |
narrative | -0.032 |
Prince | -0.032 |
thank | -0.031 |
Token | Bear |
Token ID | 14732 |
Feature activation | -1.71e-02 |
Pos logit contributions | |
z | +0.000 |
ats | +0.000 |
ew | +0.000 |
zag | +0.000 |
om | +0.000 |
Neg logit contributions | |
bean | -0.000 |
Prince | -0.000 |
reef | -0.000 |
Av | -0.000 |
Honey | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | +4.08e-03 |
Pos logit contributions | |
z | +0.028 |
ew | +0.026 |
ats | +0.026 |
zag | +0.024 |
om | +0.023 |
Neg logit contributions | |
bean | -0.033 |
Prince | -0.031 |
reef | -0.030 |
narrative | -0.029 |
sailor | -0.028 |
Token | He |
Token ID | 679 |
Feature activation | -3.19e-03 |
Pos logit contributions | |
narrative | +0.006 |
bean | +0.006 |
Prince | +0.006 |
pearl | +0.005 |
relief | +0.005 |
Neg logit contributions | |
z | -0.008 |
ew | -0.007 |
ats | -0.007 |
om | -0.007 |
zag | -0.007 |
Token | had |
Token ID | 550 |
Feature activation | -2.59e-03 |
Pos logit contributions | |
z | +0.005 |
ats | +0.005 |
ew | +0.005 |
zag | +0.005 |
om | +0.005 |
Neg logit contributions | |
bean | -0.006 |
Prince | -0.005 |
narrative | -0.005 |
reef | -0.005 |
thank | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | -2.00e-02 |
Pos logit contributions | |
ats | +0.006 |
z | +0.006 |
ew | +0.006 |
zag | +0.006 |
oses | +0.006 |
Neg logit contributions | |
bean | -0.003 |
Prince | -0.003 |
rice | -0.003 |
prince | -0.003 |
refreshed | -0.003 |
Token | best |
Token ID | 1266 |
Feature activation | -6.19e-02 |
Pos logit contributions | |
z | +0.039 |
ats | +0.038 |
ew | +0.037 |
zag | +0.034 |
aned | +0.033 |
Neg logit contributions | |
bean | -0.035 |
Prince | -0.032 |
reef | -0.031 |
narrative | -0.029 |
poppy | -0.029 |
Token | friend |
Token ID | 1545 |
Feature activation | -2.06e-02 |
Pos logit contributions | |
z | +0.108 |
ew | +0.108 |
ats | +0.104 |
aned | +0.098 |
ches | +0.094 |
Neg logit contributions | |
bean | -0.112 |
Prince | -0.099 |
reef | -0.096 |
sailor | -0.095 |
narrative | -0.094 |
Token | named |
Token ID | 3706 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
z | +0.047 |
ew | +0.045 |
ats | +0.044 |
aned | +0.044 |
zag | +0.044 |
Neg logit contributions | |
bean | -0.026 |
Prince | -0.024 |
Pink | -0.022 |
thank | -0.022 |
Honey | -0.021 |
Token | Fox |
Token ID | 5426 |
Feature activation | -2.72e-03 |
Pos logit contributions | |
z | +0.028 |
ats | +0.027 |
ew | +0.027 |
zag | +0.026 |
om | +0.025 |
Neg logit contributions | |
bean | -0.015 |
Prince | -0.014 |
reef | -0.012 |
Honey | -0.012 |
Av | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | +1.04e-03 |
Pos logit contributions | |
z | +0.005 |
ew | +0.004 |
ats | +0.004 |
zag | +0.004 |
attered | +0.004 |
Neg logit contributions | |
bean | -0.005 |
Prince | -0.005 |
reef | -0.005 |
sailor | -0.005 |
cuc | -0.005 |
Token | Every |
Token ID | 3887 |
Feature activation | -9.67e-03 |
Pos logit contributions | |
narrative | +0.002 |
bean | +0.002 |
Prince | +0.002 |
pearl | +0.002 |
relief | +0.002 |
Neg logit contributions | |
z | -0.002 |
ew | -0.002 |
ats | -0.002 |
om | -0.001 |
zag | -0.001 |
Token | watch |
Token ID | 2342 |
Feature activation | +7.23e-03 |
Pos logit contributions | |
bean | +0.008 |
Prince | +0.007 |
thank | +0.007 |
reef | +0.006 |
Av | +0.006 |
Neg logit contributions | |
z | -0.013 |
ats | -0.013 |
ew | -0.013 |
zag | -0.012 |
om | -0.012 |
Token | this |
Token ID | 428 |
Feature activation | +5.91e-03 |
Pos logit contributions | |
bean | +0.011 |
Prince | +0.011 |
thank | +0.010 |
Honey | +0.009 |
Av | +0.009 |
Neg logit contributions | |
z | -0.015 |
ats | -0.014 |
attered | -0.014 |
ew | -0.014 |
zag | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -1.48e-03 |
Pos logit contributions | |
bean | +0.010 |
Prince | +0.009 |
reef | +0.009 |
thank | +0.009 |
narrative | +0.008 |
Neg logit contributions | |
ats | -0.011 |
z | -0.011 |
ew | -0.011 |
attered | -0.010 |
om | -0.010 |
Token | That |
Token ID | 1320 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
z | +0.003 |
ats | +0.003 |
ew | +0.003 |
zag | +0.003 |
om | +0.003 |
Neg logit contributions | |
bean | -0.002 |
Prince | -0.002 |
narrative | -0.002 |
reef | -0.002 |
thank | -0.002 |
Token | squirrel |
Token ID | 33039 |
Feature activation | +1.38e-02 |
Pos logit contributions | |
z | +0.020 |
ats | +0.019 |
ew | +0.019 |
om | +0.017 |
zag | +0.017 |
Neg logit contributions | |
bean | -0.023 |
Prince | -0.021 |
reef | -0.020 |
narrative | -0.020 |
thank | -0.019 |
Token | looks |
Token ID | 3073 |
Feature activation | +2.96e-02 |
Pos logit contributions | |
bean | +0.023 |
reef | +0.021 |
thank | +0.019 |
Prince | +0.019 |
Honey | +0.018 |
Neg logit contributions | |
z | -0.024 |
ew | -0.022 |
eth | -0.022 |
attered | -0.022 |
tr | -0.022 |
Token | very |
Token ID | 845 |
Feature activation | +4.76e-03 |
Pos logit contributions | |
bean | +0.045 |
Prince | +0.044 |
thank | +0.041 |
reef | +0.039 |
relief | +0.038 |
Neg logit contributions | |
z | -0.064 |
ats | -0.061 |
zag | -0.061 |
ew | -0.058 |
uddy | -0.055 |
Token | en |
Token ID | 551 |
Feature activation | +2.91e-02 |
Pos logit contributions | |
bean | +0.007 |
Prince | +0.007 |
narrative | +0.006 |
reef | +0.006 |
thank | +0.006 |
Neg logit contributions | |
z | -0.010 |
ats | -0.010 |
ew | -0.009 |
zag | -0.009 |
om | -0.009 |
Token | vious |
Token ID | 1442 |
Feature activation | +2.32e-02 |
Pos logit contributions | |
bean | +0.042 |
Prince | +0.039 |
narrative | +0.039 |
reef | +0.037 |
pearl | +0.035 |
Neg logit contributions | |
z | -0.059 |
ats | -0.058 |
ew | -0.057 |
zag | -0.054 |
om | -0.054 |
Token | . |
Token ID | 13 |
Feature activation | +3.65e-03 |
Pos logit contributions | |
bean | +0.038 |
Prince | +0.035 |
narrative | +0.033 |
thank | +0.033 |
reef | +0.032 |
Neg logit contributions | |
z | -0.046 |
ats | -0.043 |
zag | -0.041 |
ew | -0.041 |
om | -0.039 |
Token | I |
Token ID | 314 |
Feature activation | +1.14e-03 |
Pos logit contributions | |
bean | +0.005 |
Prince | +0.005 |
narrative | +0.005 |
reef | +0.005 |
thank | +0.004 |
Neg logit contributions | |
z | -0.007 |
ats | -0.007 |
ew | -0.007 |
zag | -0.007 |
om | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -2.72e-03 |
Pos logit contributions | |
ats | +0.008 |
z | +0.007 |
ew | +0.007 |
zag | +0.007 |
om | +0.007 |
Neg logit contributions | |
bean | -0.008 |
narrative | -0.007 |
Prince | -0.007 |
reef | -0.007 |
thank | -0.007 |
Token | The |
Token ID | 383 |
Feature activation | +7.11e-03 |
Pos logit contributions | |
z | +0.005 |
ats | +0.005 |
ew | +0.005 |
zag | +0.004 |
om | +0.004 |
Neg logit contributions | |
bean | -0.005 |
narrative | -0.004 |
Prince | -0.004 |
reef | -0.004 |
pearl | -0.004 |
Token | end |
Token ID | 886 |
Feature activation | +2.41e-03 |
Pos logit contributions | |
bean | +0.008 |
Prince | +0.008 |
narrative | +0.007 |
reef | +0.007 |
pearl | +0.007 |
Neg logit contributions | |
z | -0.016 |
ats | -0.016 |
ew | -0.015 |
zag | -0.015 |
om | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | -7.73e-03 |
Pos logit contributions | |
bean | +0.004 |
narrative | +0.003 |
Prince | +0.003 |
thank | +0.003 |
reef | +0.003 |
Neg logit contributions | |
z | -0.004 |
ats | -0.004 |
ew | -0.004 |
zag | -0.004 |
om | -0.004 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
ew | +0.009 |
z | +0.009 |
o | +0.009 |
ats | +0.009 |
om | +0.009 |
Neg logit contributions | |
bean | -0.017 |
narrative | -0.017 |
reef | -0.016 |
pearl | -0.016 |
Prince | -0.016 |
Token | Once |
Token ID | 7454 |
Feature activation | +3.10e-02 |
Pos logit contributions | |
z | +0.022 |
ats | +0.022 |
ew | +0.021 |
zag | +0.020 |
om | +0.020 |
Neg logit contributions | |
bean | -0.024 |
narrative | -0.023 |
Prince | -0.023 |
reef | -0.022 |
cuc | -0.021 |
Token | upon |
Token ID | 2402 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
bean | +0.066 |
Prince | +0.063 |
narrative | +0.062 |
reef | +0.060 |
cuc | +0.058 |
Neg logit contributions | |
z | -0.042 |
ats | -0.041 |
ew | -0.039 |
zag | -0.037 |
om | -0.036 |
Token | a |
Token ID | 257 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
z | +0.020 |
ats | +0.018 |
ew | +0.018 |
zag | +0.017 |
om | +0.017 |
Neg logit contributions | |
bean | -0.025 |
narrative | -0.025 |
Prince | -0.024 |
reef | -0.023 |
pearl | -0.022 |
Token | time |
Token ID | 640 |
Feature activation | -1.20e-03 |
Pos logit contributions | |
bean | +0.020 |
narrative | +0.019 |
Prince | +0.018 |
reef | +0.018 |
thank | +0.017 |
Neg logit contributions | |
z | -0.019 |
ats | -0.018 |
ew | -0.017 |
zag | -0.017 |
om | -0.016 |
Token | , |
Token ID | 11 |
Feature activation | +5.60e-04 |
Pos logit contributions | |
z | +0.002 |
ats | +0.002 |
ew | +0.002 |
zag | +0.002 |
om | +0.002 |
Neg logit contributions | |
bean | -0.002 |
Prince | -0.002 |
narrative | -0.002 |
reef | -0.002 |
thank | -0.002 |
Token | there |
Token ID | 612 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
bean | +0.001 |
Prince | +0.001 |
narrative | +0.001 |
reef | +0.001 |
cuc | +0.001 |
Neg logit contributions | |
z | -0.001 |
ats | -0.001 |
ew | -0.001 |
zag | -0.001 |
om | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +2.76e-03 |
Pos logit contributions | |
bean | +0.003 |
thank | +0.003 |
Prince | +0.003 |
refreshed | +0.003 |
rice | +0.003 |
Neg logit contributions | |
ew | -0.004 |
ats | -0.004 |
z | -0.004 |
ggies | -0.004 |
zag | -0.003 |
Token | The |
Token ID | 383 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
bean | +0.006 |
narrative | +0.006 |
pearl | +0.006 |
reef | +0.006 |
seaw | +0.005 |
Neg logit contributions | |
z | -0.004 |
om | -0.003 |
o | -0.003 |
ew | -0.003 |
ats | -0.003 |
Token | end |
Token ID | 886 |
Feature activation | +4.35e-03 |
Pos logit contributions | |
bean | +0.016 |
Prince | +0.015 |
Av | +0.014 |
reef | +0.014 |
Amber | +0.014 |
Neg logit contributions | |
z | -0.023 |
ats | -0.021 |
zag | -0.020 |
co | -0.020 |
ew | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | -2.94e-03 |
Pos logit contributions | |
bean | +0.008 |
Prince | +0.007 |
narrative | +0.007 |
thank | +0.007 |
reef | +0.007 |
Neg logit contributions | |
z | -0.007 |
ats | -0.007 |
ew | -0.007 |
zag | -0.006 |
om | -0.006 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -2.49e-03 |
Pos logit contributions | |
z | +0.003 |
o | +0.003 |
om | +0.003 |
ew | +0.003 |
tr | +0.002 |
Neg logit contributions | |
bean | -0.007 |
reef | -0.007 |
seaw | -0.007 |
pearl | -0.007 |
narrative | -0.007 |
Token | Once |
Token ID | 7454 |
Feature activation | +3.70e-02 |
Pos logit contributions | |
z | +0.004 |
ats | +0.004 |
ew | +0.004 |
zag | +0.004 |
om | +0.004 |
Neg logit contributions | |
bean | -0.005 |
narrative | -0.004 |
Prince | -0.004 |
reef | -0.004 |
cuc | -0.004 |
Token | upon |
Token ID | 2402 |
Feature activation | -4.68e-03 |
Pos logit contributions | |
bean | +0.081 |
Prince | +0.078 |
narrative | +0.077 |
reef | +0.074 |
cuc | +0.072 |
Neg logit contributions | |
z | -0.048 |
ats | -0.046 |
ew | -0.044 |
zag | -0.042 |
om | -0.041 |
Token | a |
Token ID | 257 |
Feature activation | +1.77e-02 |
Pos logit contributions | |
z | +0.007 |
ats | +0.006 |
ew | +0.006 |
zag | +0.006 |
om | +0.006 |
Neg logit contributions | |
bean | -0.009 |
narrative | -0.009 |
Prince | -0.009 |
reef | -0.008 |
pearl | -0.008 |
Token | time |
Token ID | 640 |
Feature activation | +5.84e-03 |
Pos logit contributions | |
bean | +0.033 |
narrative | +0.031 |
Prince | +0.031 |
reef | +0.030 |
thank | +0.029 |
Neg logit contributions | |
z | -0.028 |
ats | -0.027 |
ew | -0.026 |
zag | -0.025 |
om | -0.024 |
Token | , |
Token ID | 11 |
Feature activation | +8.67e-03 |
Pos logit contributions | |
bean | +0.011 |
Prince | +0.011 |
narrative | +0.011 |
reef | +0.010 |
cuc | +0.010 |
Neg logit contributions | |
z | -0.009 |
ats | -0.009 |
ew | -0.008 |
zag | -0.008 |
om | -0.008 |
Token | there |
Token ID | 612 |
Feature activation | -1.77e-03 |
Pos logit contributions | |
bean | +0.015 |
Prince | +0.015 |
narrative | +0.015 |
hospitality | +0.014 |
generosity | +0.014 |
Neg logit contributions | |
z | -0.015 |
ew | -0.014 |
ats | -0.014 |
zag | -0.013 |
om | -0.013 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -2.38e-03 |
Pos logit contributions | |
z | +0.002 |
ats | +0.002 |
ew | +0.002 |
zag | +0.002 |
om | +0.002 |
Neg logit contributions | |
bean | -0.002 |
narrative | -0.002 |
Prince | -0.002 |
reef | -0.002 |
pearl | -0.002 |
Token | Bob |
Token ID | 18861 |
Feature activation | -7.72e-03 |
Pos logit contributions | |
z | +0.004 |
ats | +0.004 |
ew | +0.004 |
zag | +0.004 |
om | +0.004 |
Neg logit contributions | |
bean | -0.004 |
Prince | -0.004 |
narrative | -0.004 |
reef | -0.004 |
thank | -0.003 |
Token | was |
Token ID | 373 |
Feature activation | -1.47e-03 |
Pos logit contributions | |
z | +0.014 |
ew | +0.014 |
ats | +0.013 |
zag | +0.013 |
ggies | +0.012 |
Neg logit contributions | |
bean | -0.013 |
Prince | -0.012 |
reef | -0.012 |
sailor | -0.011 |
Av | -0.011 |
Token | a |
Token ID | 257 |
Feature activation | +1.61e-03 |
Pos logit contributions | |
ats | +0.003 |
z | +0.003 |
ew | +0.003 |
zag | +0.003 |
uddy | +0.003 |
Neg logit contributions | |
Prince | -0.002 |
refreshed | -0.002 |
bean | -0.002 |
energ | -0.002 |
reef | -0.002 |
Token | three |
Token ID | 1115 |
Feature activation | +5.19e-03 |
Pos logit contributions | |
narrative | +0.003 |
bean | +0.003 |
Prince | +0.002 |
reef | +0.002 |
hospitality | +0.002 |
Neg logit contributions | |
z | -0.003 |
ats | -0.003 |
ew | -0.003 |
om | -0.003 |
zag | -0.003 |
Token | year |
Token ID | 614 |
Feature activation | +3.13e-02 |
Pos logit contributions | |
bean | +0.010 |
Prince | +0.009 |
narrative | +0.009 |
reef | +0.009 |
sailor | +0.009 |
Neg logit contributions | |
z | -0.008 |
ats | -0.008 |
zag | -0.008 |
ew | -0.008 |
om | -0.007 |
Token | old |
Token ID | 1468 |
Feature activation | +8.55e-03 |
Pos logit contributions | |
bean | +0.039 |
Prince | +0.036 |
reef | +0.034 |
narrative | +0.033 |
cuc | +0.031 |
Neg logit contributions | |
z | -0.071 |
ats | -0.070 |
ew | -0.066 |
zag | -0.066 |
om | -0.062 |
Token | child |
Token ID | 1200 |
Feature activation | +7.40e-03 |
Pos logit contributions | |
bean | +0.013 |
Prince | +0.012 |
narrative | +0.011 |
reef | +0.011 |
sailor | +0.010 |
Neg logit contributions | |
z | -0.018 |
ats | -0.017 |
ew | -0.017 |
zag | -0.016 |
om | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -2.76e-03 |
Pos logit contributions | |
bean | +0.011 |
Prince | +0.010 |
reef | +0.010 |
Av | +0.009 |
Claire | +0.009 |
Neg logit contributions | |
z | -0.015 |
ats | -0.014 |
zag | -0.014 |
ew | -0.013 |
erved | -0.013 |
Token | He |
Token ID | 679 |
Feature activation | +3.07e-03 |
Pos logit contributions | |
z | +0.005 |
ats | +0.005 |
ew | +0.005 |
zag | +0.005 |
om | +0.004 |
Neg logit contributions | |
bean | -0.005 |
Prince | -0.004 |
narrative | -0.004 |
reef | -0.004 |
thank | -0.004 |
Token | liked |
Token ID | 8288 |
Feature activation | +1.85e-02 |
Pos logit contributions | |
bean | +0.005 |
Prince | +0.005 |
reef | +0.004 |
narrative | +0.004 |
thank | +0.004 |
Neg logit contributions | |
z | -0.006 |
ew | -0.006 |
ats | -0.006 |
zag | -0.006 |
om | -0.005 |
Token | proud |
Token ID | 6613 |
Feature activation | +1.00e-02 |
Pos logit contributions | |
bean | +0.004 |
narrative | +0.003 |
Prince | +0.003 |
reef | +0.003 |
cuc | +0.003 |
Neg logit contributions | |
z | -0.006 |
ats | -0.006 |
ew | -0.006 |
om | -0.006 |
zag | -0.006 |
Token | that |
Token ID | 326 |
Feature activation | -1.76e-03 |
Pos logit contributions | |
bean | +0.018 |
Prince | +0.016 |
thank | +0.016 |
reef | +0.015 |
narrative | +0.015 |
Neg logit contributions | |
z | -0.018 |
ats | -0.018 |
zag | -0.017 |
ew | -0.017 |
om | -0.016 |
Token | she |
Token ID | 673 |
Feature activation | +7.97e-03 |
Pos logit contributions | |
z | +0.004 |
ats | +0.004 |
ew | +0.004 |
zag | +0.004 |
om | +0.004 |
Neg logit contributions | |
bean | -0.002 |
narrative | -0.002 |
Prince | -0.002 |
reef | -0.002 |
cuc | -0.002 |
Token | improved |
Token ID | 6596 |
Feature activation | -8.69e-03 |
Pos logit contributions | |
bean | +0.014 |
narrative | +0.014 |
Prince | +0.013 |
reef | +0.013 |
cuc | +0.012 |
Neg logit contributions | |
z | -0.014 |
ats | -0.013 |
ew | -0.013 |
zag | -0.012 |
om | -0.012 |
Token | her |
Token ID | 607 |
Feature activation | +1.95e-03 |
Pos logit contributions | |
z | +0.019 |
ats | +0.018 |
ew | +0.018 |
zag | +0.017 |
om | +0.017 |
Neg logit contributions | |
bean | -0.012 |
Prince | -0.012 |
narrative | -0.011 |
thank | -0.010 |
Av | -0.010 |
Token | look |
Token ID | 804 |
Feature activation | +3.87e-02 |
Pos logit contributions | |
bean | +0.003 |
Prince | +0.003 |
narrative | +0.003 |
thank | +0.002 |
reef | +0.002 |
Neg logit contributions | |
z | -0.004 |
ats | -0.004 |
ew | -0.004 |
zag | -0.004 |
om | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +3.60e-03 |
Pos logit contributions | |
bean | +0.062 |
thank | +0.057 |
Prince | +0.055 |
refreshed | +0.053 |
Av | +0.053 |
Neg logit contributions | |
ats | -0.073 |
ew | -0.073 |
z | -0.071 |
uddy | -0.071 |
zag | -0.069 |
Token | She |
Token ID | 1375 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
bean | +0.006 |
Prince | +0.006 |
narrative | +0.006 |
reef | +0.005 |
thank | +0.005 |
Neg logit contributions | |
z | -0.007 |
ats | -0.006 |
ew | -0.006 |
zag | -0.006 |
om | -0.006 |
Token | smiled |
Token ID | 13541 |
Feature activation | +1.77e-02 |
Pos logit contributions | |
bean | +0.020 |
Prince | +0.019 |
narrative | +0.019 |
reef | +0.018 |
thank | +0.017 |
Neg logit contributions | |
z | -0.026 |
ats | -0.025 |
ew | -0.025 |
zag | -0.024 |
om | -0.023 |
Token | and |
Token ID | 290 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
bean | +0.037 |
Prince | +0.035 |
narrative | +0.035 |
reef | +0.034 |
thank | +0.032 |
Neg logit contributions | |
z | -0.025 |
ats | -0.024 |
ew | -0.023 |
zag | -0.022 |
om | -0.021 |
Token | looked |
Token ID | 3114 |
Feature activation | +2.43e-02 |
Pos logit contributions | |
narrative | +0.021 |
bean | +0.020 |
reef | +0.020 |
Prince | +0.019 |
cuc | +0.018 |
Neg logit contributions | |
z | -0.020 |
ats | -0.019 |
ew | -0.018 |
om | -0.017 |
zag | -0.017 |
Token | She |
Token ID | 1375 |
Feature activation | -7.64e-03 |
Pos logit contributions | |
z | +0.037 |
zag | +0.033 |
ew | +0.033 |
ats | +0.032 |
icycle | +0.031 |
Neg logit contributions | |
bean | -0.017 |
Prince | -0.016 |
thank | -0.016 |
narrative | -0.014 |
rice | -0.014 |
Token | did |
Token ID | 750 |
Feature activation | +2.58e-03 |
Pos logit contributions | |
z | +0.016 |
ew | +0.015 |
ats | +0.015 |
zag | +0.015 |
om | +0.014 |
Neg logit contributions | |
bean | -0.011 |
Prince | -0.010 |
thank | -0.010 |
narrative | -0.010 |
reef | -0.010 |
Token | not |
Token ID | 407 |
Feature activation | -5.23e-03 |
Pos logit contributions | |
thank | +0.004 |
bean | +0.004 |
Av | +0.004 |
Prince | +0.004 |
refreshed | +0.003 |
Neg logit contributions | |
z | -0.005 |
attered | -0.005 |
ats | -0.005 |
ew | -0.005 |
uddy | -0.005 |
Token | know |
Token ID | 760 |
Feature activation | -6.74e-03 |
Pos logit contributions | |
z | +0.012 |
ats | +0.011 |
ew | +0.011 |
zag | +0.011 |
om | +0.011 |
Neg logit contributions | |
bean | -0.007 |
Prince | -0.006 |
thank | -0.006 |
narrative | -0.006 |
reef | -0.006 |
Token | them |
Token ID | 606 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
z | +0.016 |
ats | +0.015 |
zag | +0.014 |
ew | +0.014 |
attered | +0.014 |
Neg logit contributions | |
bean | -0.009 |
Prince | -0.009 |
thank | -0.008 |
narrative | -0.008 |
God | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -6.81e-03 |
Pos logit contributions | |
z | +0.025 |
ew | +0.023 |
ats | +0.021 |
om | +0.021 |
zag | +0.021 |
Neg logit contributions | |
bean | -0.018 |
Prince | -0.016 |
thank | -0.016 |
narrative | -0.016 |
reef | -0.015 |
Token | She |
Token ID | 1375 |
Feature activation | -3.27e-03 |
Pos logit contributions | |
z | +0.011 |
ew | +0.010 |
ats | +0.010 |
zag | +0.010 |
om | +0.010 |
Neg logit contributions | |
bean | -0.013 |
narrative | -0.012 |
Prince | -0.012 |
reef | -0.011 |
pearl | -0.011 |
Token | did |
Token ID | 750 |
Feature activation | -2.89e-03 |
Pos logit contributions | |
z | +0.007 |
ats | +0.007 |
ew | +0.007 |
zag | +0.007 |
om | +0.006 |
Neg logit contributions | |
bean | -0.004 |
narrative | -0.004 |
Prince | -0.004 |
thank | -0.004 |
Av | -0.004 |
Token | not |
Token ID | 407 |
Feature activation | -5.36e-03 |
Pos logit contributions | |
z | +0.006 |
ew | +0.006 |
attered | +0.006 |
ats | +0.006 |
rol | +0.005 |
Neg logit contributions | |
thank | -0.004 |
bean | -0.004 |
Av | -0.004 |
Prince | -0.004 |
narrative | -0.004 |
Token | know |
Token ID | 760 |
Feature activation | -5.02e-03 |
Pos logit contributions | |
z | +0.012 |
ats | +0.011 |
ew | +0.011 |
zag | +0.011 |
om | +0.011 |
Neg logit contributions | |
bean | -0.007 |
Prince | -0.007 |
narrative | -0.006 |
thank | -0.006 |
reef | -0.006 |
Token | if |
Token ID | 611 |
Feature activation | -2.39e-03 |
Pos logit contributions | |
z | +0.012 |
ats | +0.011 |
zag | +0.011 |
ew | +0.010 |
om | +0.010 |
Neg logit contributions | |
bean | -0.007 |
Prince | -0.006 |
thank | -0.006 |
narrative | -0.006 |
reef | -0.005 |
Token | ready |
Token ID | 3492 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
z | +0.005 |
ats | +0.005 |
ew | +0.005 |
zag | +0.005 |
om | +0.005 |
Neg logit contributions | |
bean | -0.005 |
narrative | -0.005 |
Prince | -0.005 |
reef | -0.004 |
thank | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | +3.02e-03 |
Pos logit contributions | |
z | +0.025 |
ats | +0.024 |
ew | +0.024 |
zag | +0.022 |
attered | +0.020 |
Neg logit contributions | |
bean | -0.035 |
Prince | -0.033 |
thank | -0.033 |
reef | -0.032 |
cuc | -0.031 |
Token | take |
Token ID | 1011 |
Feature activation | +5.92e-04 |
Pos logit contributions | |
narrative | +0.005 |
bean | +0.005 |
Prince | +0.005 |
reef | +0.005 |
pearl | +0.004 |
Neg logit contributions | |
ats | -0.005 |
z | -0.005 |
zag | -0.005 |
ew | -0.005 |
om | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | -1.69e-02 |
Pos logit contributions | |
bean | +0.001 |
Prince | +0.001 |
narrative | +0.001 |
reef | +0.001 |
thank | +0.001 |
Neg logit contributions | |
z | -0.001 |
ats | -0.001 |
ew | -0.001 |
zag | -0.001 |
om | -0.001 |
Token | bath |
Token ID | 7837 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
z | +0.032 |
ats | +0.031 |
ew | +0.030 |
zag | +0.029 |
om | +0.029 |
Neg logit contributions | |
bean | -0.027 |
Prince | -0.025 |
narrative | -0.024 |
reef | -0.024 |
thank | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | -2.58e-03 |
Pos logit contributions | |
z | +0.018 |
ew | +0.018 |
ats | +0.018 |
om | +0.017 |
zag | +0.016 |
Neg logit contributions | |
bean | -0.019 |
Prince | -0.018 |
reef | -0.017 |
narrative | -0.017 |
rice | -0.016 |
Token | He |
Token ID | 679 |
Feature activation | +6.86e-04 |
Pos logit contributions | |
z | +0.005 |
ats | +0.005 |
ew | +0.005 |
zag | +0.004 |
om | +0.004 |
Neg logit contributions | |
bean | -0.004 |
Prince | -0.004 |
reef | -0.004 |
narrative | -0.004 |
thank | -0.004 |
Token | gathered |
Token ID | 9272 |
Feature activation | -5.48e-03 |
Pos logit contributions | |
bean | +0.001 |
reef | +0.001 |
sailor | +0.001 |
Prince | +0.001 |
seaw | +0.001 |
Neg logit contributions | |
z | -0.001 |
ew | -0.001 |
ats | -0.001 |
zag | -0.001 |
om | -0.001 |
Token | all |
Token ID | 477 |
Feature activation | -9.94e-03 |
Pos logit contributions | |
z | +0.012 |
zag | +0.012 |
ats | +0.011 |
ew | +0.011 |
uddy | +0.010 |
Neg logit contributions | |
bean | -0.008 |
Prince | -0.007 |
reef | -0.007 |
rice | -0.007 |
seaw | -0.007 |
Token | of |
Token ID | 286 |
Feature activation | -1.82e-02 |
Pos logit contributions | |
z | +0.021 |
ats | +0.020 |
ew | +0.020 |
zag | +0.020 |
om | +0.019 |
Neg logit contributions | |
bean | -0.014 |
Prince | -0.012 |
narrative | -0.012 |
reef | -0.012 |
rice | -0.011 |
Token | his |
Token ID | 465 |
Feature activation | +8.73e-03 |
Pos logit contributions | |
z | +0.041 |
ew | +0.038 |
ats | +0.038 |
zag | +0.038 |
om | +0.036 |
Neg logit contributions | |
bean | -0.026 |
Prince | -0.023 |
reef | -0.022 |
seaw | -0.021 |
rice | -0.021 |
Token | like |
Token ID | 588 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
z | +0.033 |
ats | +0.031 |
ew | +0.031 |
om | +0.030 |
zag | +0.029 |
Neg logit contributions | |
bean | -0.017 |
thank | -0.016 |
Prince | -0.015 |
narrative | -0.014 |
relief | -0.014 |
Token | to |
Token ID | 284 |
Feature activation | -3.83e-03 |
Pos logit contributions | |
z | +0.032 |
ats | +0.030 |
ew | +0.029 |
zag | +0.029 |
om | +0.027 |
Neg logit contributions | |
bean | -0.023 |
Prince | -0.021 |
thank | -0.020 |
beans | -0.020 |
rice | -0.019 |
Token | listen |
Token ID | 6004 |
Feature activation | +2.09e-03 |
Pos logit contributions | |
z | +0.009 |
ew | +0.008 |
ats | +0.008 |
om | +0.008 |
zag | +0.008 |
Neg logit contributions | |
bean | -0.005 |
thank | -0.005 |
Prince | -0.005 |
narrative | -0.004 |
reef | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | +6.92e-03 |
Pos logit contributions | |
bean | +0.003 |
thank | +0.003 |
Prince | +0.003 |
rice | +0.003 |
Claire | +0.003 |
Neg logit contributions | |
z | -0.004 |
ew | -0.004 |
ats | -0.004 |
zag | -0.003 |
icycle | -0.003 |
Token | his |
Token ID | 465 |
Feature activation | -5.50e-03 |
Pos logit contributions | |
bean | +0.008 |
Prince | +0.008 |
thank | +0.008 |
God | +0.007 |
relief | +0.007 |
Neg logit contributions | |
z | -0.017 |
ew | -0.016 |
ats | -0.016 |
zag | -0.015 |
om | -0.015 |
Token | owner |
Token ID | 4870 |
Feature activation | +4.92e-03 |
Pos logit contributions | |
z | +0.013 |
ats | +0.013 |
ew | +0.013 |
attered | +0.012 |
zag | +0.012 |
Neg logit contributions | |
bean | -0.007 |
Prince | -0.006 |
narrative | -0.006 |
thank | -0.006 |
reef | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -4.72e-03 |
Pos logit contributions | |
bean | +0.008 |
Prince | +0.008 |
narrative | +0.007 |
thank | +0.007 |
reef | +0.007 |
Neg logit contributions | |
z | -0.009 |
ew | -0.009 |
ats | -0.009 |
zag | -0.008 |
om | -0.008 |
Token | One |
Token ID | 1881 |
Feature activation | +7.16e-04 |
Pos logit contributions | |
z | +0.010 |
ats | +0.010 |
ew | +0.009 |
zag | +0.009 |
om | +0.008 |
Neg logit contributions | |
bean | -0.007 |
Prince | -0.007 |
narrative | -0.006 |
Av | -0.006 |
Claire | -0.006 |
Token | day |
Token ID | 1110 |
Feature activation | +9.46e-03 |
Pos logit contributions | |
bean | +0.001 |
Prince | +0.001 |
narrative | +0.001 |
reef | +0.001 |
thank | +0.001 |
Neg logit contributions | |
z | -0.002 |
ats | -0.002 |
ew | -0.002 |
zag | -0.002 |
om | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
bean | +0.014 |
Prince | +0.014 |
thank | +0.013 |
Av | +0.012 |
Claire | +0.012 |
Neg logit contributions | |
z | -0.019 |
ats | -0.019 |
ew | -0.018 |
zag | -0.018 |
attered | -0.017 |
Token | Jack |
Token ID | 3619 |
Feature activation | -5.75e-03 |
Pos logit contributions | |
bean | +0.014 |
Prince | +0.014 |
Av | +0.012 |
reef | +0.012 |
cuc | +0.011 |
Neg logit contributions | |
ats | -0.027 |
z | -0.027 |
ew | -0.026 |
zag | -0.025 |
om | -0.025 |
Token | every |
Token ID | 790 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
bean | +0.021 |
reef | +0.018 |
Prince | +0.018 |
thank | +0.017 |
Av | +0.017 |
Neg logit contributions | |
ats | -0.025 |
ew | -0.024 |
z | -0.023 |
uddy | -0.022 |
om | -0.021 |
Token | day |
Token ID | 1110 |
Feature activation | +5.31e-03 |
Pos logit contributions | |
z | +0.035 |
ats | +0.035 |
ew | +0.034 |
zag | +0.033 |
om | +0.032 |
Neg logit contributions | |
bean | -0.021 |
Prince | -0.017 |
reef | -0.017 |
narrative | -0.016 |
thank | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | +6.18e-03 |
Pos logit contributions | |
bean | +0.009 |
Prince | +0.008 |
thank | +0.008 |
Av | +0.007 |
narrative | +0.007 |
Neg logit contributions | |
ats | -0.010 |
z | -0.010 |
ew | -0.009 |
zag | -0.009 |
ahs | -0.009 |
Token | She |
Token ID | 1375 |
Feature activation | +7.85e-03 |
Pos logit contributions | |
bean | +0.010 |
Prince | +0.009 |
narrative | +0.009 |
Av | +0.008 |
reef | +0.008 |
Neg logit contributions | |
z | -0.012 |
ats | -0.012 |
ew | -0.011 |
zag | -0.011 |
om | -0.010 |
Token | was |
Token ID | 373 |
Feature activation | +3.85e-03 |
Pos logit contributions | |
bean | +0.012 |
Prince | +0.011 |
reef | +0.010 |
narrative | +0.010 |
Av | +0.010 |
Neg logit contributions | |
z | -0.016 |
ew | -0.016 |
ats | -0.015 |
zag | -0.015 |
uddy | -0.014 |
Token | still |
Token ID | 991 |
Feature activation | +8.28e-04 |
Pos logit contributions | |
Prince | +0.005 |
refreshed | +0.005 |
bean | +0.005 |
Av | +0.005 |
thank | +0.005 |
Neg logit contributions | |
ats | -0.008 |
z | -0.008 |
ew | -0.008 |
uddy | -0.007 |
zag | -0.007 |
Token | proud |
Token ID | 6613 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
bean | +0.001 |
Prince | +0.001 |
reef | +0.001 |
Av | +0.001 |
narrative | +0.001 |
Neg logit contributions | |
ats | -0.002 |
z | -0.002 |
ew | -0.002 |
zag | -0.002 |
ches | -0.002 |
Token | of |
Token ID | 286 |
Feature activation | -7.90e-03 |
Pos logit contributions | |
bean | +0.020 |
Prince | +0.019 |
thank | +0.017 |
beans | +0.017 |
reef | +0.017 |
Neg logit contributions | |
z | -0.021 |
ats | -0.021 |
zag | -0.020 |
ew | -0.020 |
om | -0.018 |
Token | herself |
Token ID | 5223 |
Feature activation | +4.65e-03 |
Pos logit contributions | |
z | +0.016 |
ats | +0.016 |
ew | +0.015 |
zag | +0.015 |
om | +0.014 |
Neg logit contributions | |
bean | -0.012 |
Prince | -0.011 |
narrative | -0.011 |
reef | -0.010 |
thank | -0.010 |
Token | for |
Token ID | 329 |
Feature activation | -2.22e-02 |
Pos logit contributions | |
bean | +0.008 |
Prince | +0.008 |
narrative | +0.007 |
thank | +0.007 |
reef | +0.007 |
Neg logit contributions | |
z | -0.008 |
ats | -0.008 |
ew | -0.008 |
zag | -0.007 |
om | -0.007 |
Token | finding |
Token ID | 4917 |
Feature activation | +4.92e-03 |
Pos logit contributions | |
z | +0.039 |
ats | +0.038 |
ew | +0.037 |
zag | +0.036 |
om | +0.035 |
Neg logit contributions | |
bean | -0.038 |
Prince | -0.036 |
narrative | -0.036 |
reef | -0.034 |
cuc | -0.032 |
Token |
|
Token ID | 198 |
Feature activation | -9.68e-03 |
Pos logit contributions | |
ats | +0.035 |
z | +0.034 |
ew | +0.033 |
attered | +0.033 |
zag | +0.032 |
Neg logit contributions | |
bean | -0.020 |
Prince | -0.019 |
narrative | -0.018 |
thank | -0.018 |
reef | -0.017 |
Token | At |
Token ID | 2953 |
Feature activation | +2.44e-02 |
Pos logit contributions | |
ats | +0.019 |
ew | +0.017 |
oses | +0.016 |
attered | +0.016 |
z | +0.016 |
Neg logit contributions | |
narrative | -0.015 |
bean | -0.014 |
Prince | -0.013 |
thank | -0.013 |
Av | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | +8.37e-03 |
Pos logit contributions | |
bean | +0.041 |
narrative | +0.040 |
Prince | +0.038 |
cuc | +0.037 |
seaw | +0.035 |
Neg logit contributions | |
z | -0.045 |
ats | -0.042 |
zag | -0.042 |
om | -0.039 |
ew | -0.038 |
Token | end |
Token ID | 886 |
Feature activation | -5.25e-03 |
Pos logit contributions | |
bean | +0.011 |
Prince | +0.010 |
narrative | +0.010 |
reef | +0.009 |
cuc | +0.009 |
Neg logit contributions | |
z | -0.018 |
ats | -0.018 |
zag | -0.017 |
ew | -0.017 |
om | -0.016 |
Token | of |
Token ID | 286 |
Feature activation | -1.16e-03 |
Pos logit contributions | |
ats | +0.011 |
erved | +0.011 |
z | +0.011 |
ches | +0.010 |
attered | +0.010 |
Neg logit contributions | |
thank | -0.006 |
bean | -0.006 |
Av | -0.006 |
Prince | -0.006 |
Claire | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | +6.52e-03 |
Pos logit contributions | |
z | +0.002 |
zag | +0.002 |
ats | +0.002 |
om | +0.002 |
ew | +0.002 |
Neg logit contributions | |
bean | -0.002 |
narrative | -0.002 |
cuc | -0.002 |
Prince | -0.002 |
seaw | -0.002 |
Token | adventure |
Token ID | 8855 |
Feature activation | +9.78e-03 |
Pos logit contributions | |
bean | +0.011 |
Prince | +0.011 |
cuc | +0.010 |
reef | +0.010 |
seaw | +0.010 |
Neg logit contributions | |
z | -0.012 |
ats | -0.011 |
zag | -0.011 |
ew | -0.010 |
om | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | -4.15e-03 |
Pos logit contributions | |
bean | +0.012 |
thank | +0.012 |
Prince | +0.011 |
Av | +0.011 |
Claire | +0.011 |
Neg logit contributions | |
ats | -0.021 |
z | -0.021 |
ew | -0.020 |
zag | -0.019 |
attered | -0.019 |
Token | her |
Token ID | 607 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
ats | +0.009 |
z | +0.009 |
ew | +0.009 |
zag | +0.008 |
om | +0.008 |
Neg logit contributions | |
bean | -0.005 |
Prince | -0.005 |
narrative | -0.005 |
Av | -0.005 |
thank | -0.005 |
Token | mum |
Token ID | 25682 |
Feature activation | +8.43e-03 |
Pos logit contributions | |
narrative | +0.014 |
bean | +0.014 |
Prince | +0.013 |
cuc | +0.012 |
Cr | +0.012 |
Neg logit contributions | |
z | -0.020 |
ats | -0.020 |
ew | -0.019 |
zag | -0.019 |
om | -0.019 |
Token | arrived |
Token ID | 5284 |
Feature activation | +1.83e-02 |
Pos logit contributions | |
bean | +0.012 |
Prince | +0.011 |
thank | +0.010 |
sailor | +0.010 |
narrative | +0.010 |
Neg logit contributions | |
z | -0.017 |
ew | -0.017 |
ats | -0.017 |
zag | -0.016 |
attered | -0.016 |
Token | want |
Token ID | 765 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
bean | +0.019 |
thank | +0.017 |
Prince | +0.016 |
reef | +0.016 |
refreshed | +0.016 |
Neg logit contributions | |
ats | -0.039 |
ew | -0.039 |
z | -0.038 |
ud | -0.036 |
uddy | -0.036 |
Token | to |
Token ID | 284 |
Feature activation | +5.54e-03 |
Pos logit contributions | |
Prince | +0.028 |
thank | +0.028 |
bean | +0.027 |
Av | +0.025 |
Princess | +0.025 |
Neg logit contributions | |
z | -0.026 |
ats | -0.026 |
zag | -0.025 |
ew | -0.024 |
attered | -0.022 |
Token | zoom |
Token ID | 19792 |
Feature activation | -7.83e-03 |
Pos logit contributions | |
bean | +0.008 |
thank | +0.008 |
Prince | +0.007 |
narrative | +0.007 |
reef | +0.007 |
Neg logit contributions | |
z | -0.011 |
ats | -0.011 |
ew | -0.011 |
om | -0.010 |
attered | -0.010 |
Token | too |
Token ID | 1165 |
Feature activation | -1.46e-02 |
Pos logit contributions | |
ats | +0.015 |
ew | +0.015 |
z | +0.014 |
attered | +0.013 |
uddy | +0.013 |
Neg logit contributions | |
thank | -0.011 |
bean | -0.011 |
Prince | -0.010 |
Av | -0.010 |
Princess | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -6.39e-03 |
Pos logit contributions | |
ats | +0.030 |
z | +0.029 |
ew | +0.028 |
attered | +0.027 |
tr | +0.026 |
Neg logit contributions | |
thank | -0.019 |
bean | -0.018 |
Prince | -0.016 |
reef | -0.016 |
sailor | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | -1.88e-02 |
Pos logit contributions | |
z | +0.013 |
ats | +0.013 |
ew | +0.012 |
zag | +0.012 |
om | +0.011 |
Neg logit contributions | |
bean | -0.009 |
Prince | -0.009 |
narrative | -0.008 |
reef | -0.008 |
thank | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -8.08e-03 |
Pos logit contributions | |
z | +0.038 |
ats | +0.037 |
ew | +0.036 |
zag | +0.035 |
attered | +0.035 |
Neg logit contributions | |
bean | -0.025 |
Prince | -0.024 |
narrative | -0.023 |
reef | -0.022 |
thank | -0.022 |
Token | So |
Token ID | 2396 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
z | +0.014 |
ats | +0.014 |
ew | +0.014 |
zag | +0.013 |
om | +0.013 |
Neg logit contributions | |
bean | -0.013 |
narrative | -0.013 |
Prince | -0.013 |
reef | -0.012 |
thank | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | -1.77e-03 |
Pos logit contributions | |
z | +0.013 |
ew | +0.012 |
ats | +0.012 |
om | +0.012 |
zag | +0.012 |
Neg logit contributions | |
bean | -0.027 |
Prince | -0.026 |
narrative | -0.026 |
cuc | -0.025 |
reef | -0.025 |
Token | the |
Token ID | 262 |
Feature activation | +1.42e-03 |
Pos logit contributions | |
z | +0.003 |
ew | +0.003 |
ats | +0.003 |
om | +0.003 |
zag | +0.003 |
Neg logit contributions | |
narrative | -0.003 |
bean | -0.003 |
Prince | -0.003 |
reef | -0.003 |
pearl | -0.003 |
Token | wise |
Token ID | 10787 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
bean | +0.002 |
narrative | +0.002 |
Prince | +0.002 |
Av | +0.002 |
reef | +0.002 |
Neg logit contributions | |
z | -0.002 |
ats | -0.002 |
zag | -0.002 |
ew | -0.002 |
om | -0.002 |
Token | One |
Token ID | 1881 |
Feature activation | -4.98e-03 |
Pos logit contributions | |
z | +0.029 |
ats | +0.029 |
ew | +0.027 |
zag | +0.026 |
attered | +0.025 |
Neg logit contributions | |
bean | -0.019 |
Prince | -0.017 |
narrative | -0.016 |
reef | -0.016 |
thank | -0.016 |
Token | day |
Token ID | 1110 |
Feature activation | -1.29e-02 |
Pos logit contributions | |
z | +0.010 |
ats | +0.010 |
zag | +0.010 |
ew | +0.010 |
om | +0.009 |
Neg logit contributions | |
bean | -0.007 |
Prince | -0.007 |
narrative | -0.007 |
cuc | -0.006 |
reef | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | -5.18e-03 |
Pos logit contributions | |
z | +0.025 |
ats | +0.025 |
zag | +0.023 |
ew | +0.023 |
ches | +0.022 |
Neg logit contributions | |
bean | -0.019 |
Prince | -0.017 |
thank | -0.017 |
narrative | -0.016 |
reef | -0.016 |
Token | Tim |
Token ID | 5045 |
Feature activation | -6.18e-03 |
Pos logit contributions | |
ats | +0.012 |
z | +0.012 |
ew | +0.011 |
zag | +0.011 |
om | +0.010 |
Neg logit contributions | |
bean | -0.007 |
Prince | -0.006 |
thank | -0.006 |
reef | -0.005 |
cuc | -0.005 |
Token | was |
Token ID | 373 |
Feature activation | -2.89e-03 |
Pos logit contributions | |
z | +0.012 |
ew | +0.012 |
ats | +0.011 |
zag | +0.011 |
oses | +0.010 |
Neg logit contributions | |
bean | -0.010 |
Prince | -0.009 |
reef | -0.008 |
sailor | -0.008 |
narrative | -0.008 |
Token | waiting |
Token ID | 4953 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
z | +0.006 |
ats | +0.006 |
ew | +0.006 |
jo | +0.006 |
ches | +0.006 |
Neg logit contributions | |
bean | -0.003 |
refreshed | -0.003 |
energ | -0.003 |
Prince | -0.003 |
gard | -0.003 |
Token | for |
Token ID | 329 |
Feature activation | -2.19e-02 |
Pos logit contributions | |
z | +0.028 |
ew | +0.028 |
ats | +0.027 |
zag | +0.026 |
om | +0.025 |
Neg logit contributions | |
bean | -0.022 |
narrative | -0.020 |
thank | -0.020 |
Prince | -0.020 |
reef | -0.019 |
Token | his |
Token ID | 465 |
Feature activation | -8.10e-03 |
Pos logit contributions | |
z | +0.041 |
ats | +0.040 |
ew | +0.039 |
zag | +0.037 |
om | +0.036 |
Neg logit contributions | |
bean | -0.036 |
Prince | -0.034 |
narrative | -0.033 |
reef | -0.031 |
cuc | -0.030 |
Token | friend |
Token ID | 1545 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
z | +0.017 |
ats | +0.017 |
ew | +0.017 |
ches | +0.016 |
rol | +0.016 |
Neg logit contributions | |
bean | -0.012 |
poppy | -0.010 |
narrative | -0.010 |
Prince | -0.010 |
beans | -0.010 |
Token | to |
Token ID | 284 |
Feature activation | +2.80e-03 |
Pos logit contributions | |
z | +0.041 |
ew | +0.039 |
ats | +0.038 |
zag | +0.037 |
om | +0.036 |
Neg logit contributions | |
Prince | -0.026 |
bean | -0.026 |
Av | -0.022 |
thank | -0.021 |
Penny | -0.021 |
Token | come |
Token ID | 1282 |
Feature activation | -9.71e-03 |
Pos logit contributions | |
narrative | +0.005 |
bean | +0.005 |
Prince | +0.005 |
reef | +0.005 |
pearl | +0.005 |
Neg logit contributions | |
ats | -0.004 |
z | -0.004 |
zag | -0.004 |
ew | -0.004 |
om | -0.004 |
Token | share |
Token ID | 2648 |
Feature activation | -7.13e-04 |
Pos logit contributions | |
bean | +0.018 |
thank | +0.017 |
poppy | +0.015 |
Av | +0.015 |
Prince | +0.014 |
Neg logit contributions | |
z | -0.031 |
ables | -0.030 |
attered | -0.030 |
ew | -0.030 |
ats | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | -9.95e-03 |
Pos logit contributions | |
z | +0.001 |
ats | +0.001 |
ew | +0.001 |
zag | +0.001 |
om | +0.001 |
Neg logit contributions | |
bean | -0.001 |
Prince | -0.001 |
narrative | -0.001 |
Av | -0.001 |
reef | -0.001 |
Token | He |
Token ID | 679 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
ats | +0.023 |
z | +0.023 |
zag | +0.021 |
ew | +0.021 |
om | +0.020 |
Neg logit contributions | |
bean | -0.012 |
Prince | -0.011 |
Av | -0.010 |
thank | -0.010 |
narrative | -0.010 |
Token | was |
Token ID | 373 |
Feature activation | +2.06e-03 |
Pos logit contributions | |
z | +0.024 |
ew | +0.023 |
ables | +0.023 |
ats | +0.023 |
ings | +0.023 |
Neg logit contributions | |
bean | -0.013 |
Prince | -0.011 |
prince | -0.011 |
poppy | -0.011 |
Av | -0.010 |
Token | ignorant |
Token ID | 20109 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
bean | +0.003 |
Prince | +0.003 |
narrative | +0.003 |
reef | +0.003 |
thank | +0.003 |
Neg logit contributions | |
z | -0.004 |
ats | -0.004 |
ew | -0.004 |
zag | -0.003 |
om | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
bean | +0.018 |
Prince | +0.018 |
thank | +0.017 |
beans | +0.016 |
narrative | +0.016 |
Neg logit contributions | |
z | -0.032 |
ats | -0.029 |
zag | -0.029 |
ew | -0.027 |
gy | -0.027 |
Token | Tim |
Token ID | 5045 |
Feature activation | +6.20e-03 |
Pos logit contributions | |
z | +0.032 |
ats | +0.031 |
zag | +0.029 |
ew | +0.029 |
om | +0.027 |
Neg logit contributions | |
bean | -0.018 |
Prince | -0.017 |
narrative | -0.016 |
Av | -0.015 |
thank | -0.014 |
Token | said |
Token ID | 531 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
bean | +0.007 |
Prince | +0.006 |
prince | +0.005 |
thank | +0.005 |
sailor | +0.005 |
Neg logit contributions | |
z | -0.014 |
ew | -0.014 |
zag | -0.013 |
ats | -0.013 |
ings | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | -7.22e-03 |
Pos logit contributions | |
z | +0.023 |
ats | +0.023 |
ew | +0.022 |
zag | +0.021 |
om | +0.020 |
Neg logit contributions | |
bean | -0.020 |
Prince | -0.018 |
narrative | -0.017 |
thank | -0.017 |
reef | -0.016 |
Token | " |
Token ID | 366 |
Feature activation | -2.31e-02 |
Pos logit contributions | |
ats | +0.016 |
z | +0.016 |
zag | +0.014 |
ew | +0.014 |
attered | +0.013 |
Neg logit contributions | |
bean | -0.010 |
Prince | -0.010 |
thank | -0.009 |
cuc | -0.009 |
Av | -0.008 |
Token | I |
Token ID | 40 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
ats | +0.054 |
zag | +0.050 |
ew | +0.049 |
z | +0.049 |
om | +0.048 |
Neg logit contributions | |
narrative | -0.026 |
bean | -0.026 |
Prince | -0.023 |
Thank | -0.023 |
Cr | -0.022 |
Token | He |
Token ID | 679 |
Feature activation | -1.53e-02 |
Pos logit contributions | |
z | +0.006 |
ats | +0.006 |
ew | +0.006 |
zag | +0.005 |
om | +0.005 |
Neg logit contributions | |
bean | -0.007 |
Prince | -0.006 |
narrative | -0.006 |
reef | -0.006 |
thank | -0.006 |
Token | loved |
Token ID | 6151 |
Feature activation | -1.69e-03 |
Pos logit contributions | |
z | +0.036 |
ats | +0.034 |
zag | +0.033 |
ew | +0.033 |
om | +0.031 |
Neg logit contributions | |
bean | -0.019 |
Prince | -0.018 |
narrative | -0.018 |
thank | -0.017 |
prince | -0.016 |
Token | his |
Token ID | 465 |
Feature activation | -1.99e-03 |
Pos logit contributions | |
z | +0.004 |
ats | +0.004 |
ew | +0.004 |
zag | +0.004 |
atter | +0.004 |
Neg logit contributions | |
bean | -0.002 |
Prince | -0.002 |
beans | -0.002 |
Av | -0.002 |
thank | -0.002 |
Token | cars |
Token ID | 5006 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
z | +0.003 |
ats | +0.003 |
ew | +0.003 |
zag | +0.003 |
om | +0.003 |
Neg logit contributions | |
bean | -0.004 |
narrative | -0.003 |
Prince | -0.003 |
reef | -0.003 |
pearl | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | -1.27e-02 |
Pos logit contributions | |
z | +0.021 |
ats | +0.021 |
ew | +0.020 |
zag | +0.019 |
om | +0.018 |
Neg logit contributions | |
bean | -0.020 |
narrative | -0.019 |
thank | -0.019 |
Prince | -0.018 |
reef | -0.017 |
Token | did |
Token ID | 750 |
Feature activation | -8.12e-03 |
Pos logit contributions | |
z | +0.025 |
ew | +0.024 |
ats | +0.024 |
zag | +0.023 |
om | +0.022 |
Neg logit contributions | |
bean | -0.021 |
Prince | -0.020 |
narrative | -0.019 |
thank | -0.018 |
reef | -0.018 |
Token | not |
Token ID | 407 |
Feature activation | -6.76e-03 |
Pos logit contributions | |
ew | +0.015 |
z | +0.015 |
ats | +0.015 |
attered | +0.014 |
atter | +0.014 |
Neg logit contributions | |
thank | -0.014 |
bean | -0.012 |
narrative | -0.012 |
Prince | -0.012 |
relief | -0.011 |
Token | want |
Token ID | 765 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
z | +0.015 |
ats | +0.014 |
ew | +0.014 |
zag | +0.013 |
om | +0.013 |
Neg logit contributions | |
bean | -0.009 |
Prince | -0.009 |
narrative | -0.008 |
thank | -0.008 |
reef | -0.008 |
Token | to |
Token ID | 284 |
Feature activation | -7.06e-03 |
Pos logit contributions | |
z | +0.030 |
ats | +0.027 |
ew | +0.027 |
zag | +0.026 |
icycle | +0.024 |
Neg logit contributions | |
bean | -0.028 |
Prince | -0.026 |
thank | -0.025 |
Av | -0.025 |
beans | -0.025 |
Token | lose |
Token ID | 4425 |
Feature activation | -5.63e-03 |
Pos logit contributions | |
z | +0.017 |
ats | +0.016 |
ew | +0.016 |
zag | +0.015 |
om | +0.015 |
Neg logit contributions | |
bean | -0.008 |
thank | -0.007 |
Prince | -0.007 |
narrative | -0.007 |
Av | -0.007 |
Token | them |
Token ID | 606 |
Feature activation | -8.10e-03 |
Pos logit contributions | |
z | +0.012 |
ats | +0.011 |
ew | +0.011 |
zag | +0.011 |
om | +0.010 |
Neg logit contributions | |
bean | -0.009 |
Prince | -0.009 |
thank | -0.008 |
Av | -0.007 |
narrative | -0.007 |
Token | to |
Token ID | 284 |
Feature activation | +8.21e-03 |
Pos logit contributions | |
ats | +0.007 |
z | +0.007 |
ew | +0.007 |
om | +0.006 |
zag | +0.006 |
Neg logit contributions | |
bean | -0.013 |
Prince | -0.013 |
thank | -0.012 |
Av | -0.012 |
narrative | -0.012 |
Token | be |
Token ID | 307 |
Feature activation | -2.20e-03 |
Pos logit contributions | |
bean | +0.011 |
Prince | +0.010 |
thank | +0.009 |
narrative | +0.009 |
reef | +0.009 |
Neg logit contributions | |
z | -0.019 |
ew | -0.018 |
ats | -0.018 |
om | -0.017 |
zag | -0.017 |
Token | brave |
Token ID | 14802 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
z | +0.004 |
ats | +0.004 |
ew | +0.004 |
zag | +0.004 |
om | +0.004 |
Neg logit contributions | |
bean | -0.003 |
Prince | -0.003 |
narrative | -0.003 |
reef | -0.003 |
cuc | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | -2.25e-03 |
Pos logit contributions | |
bean | +0.031 |
Prince | +0.030 |
narrative | +0.027 |
thank | +0.026 |
sailor | +0.026 |
Neg logit contributions | |
ats | -0.033 |
z | -0.033 |
ew | -0.033 |
zag | -0.032 |
om | -0.029 |
Token | She |
Token ID | 1375 |
Feature activation | +3.75e-03 |
Pos logit contributions | |
z | +0.004 |
ats | +0.004 |
ew | +0.004 |
zag | +0.004 |
om | +0.004 |
Neg logit contributions | |
bean | -0.004 |
Prince | -0.003 |
narrative | -0.003 |
Av | -0.003 |
thank | -0.003 |
Token | played |
Token ID | 2826 |
Feature activation | -7.35e-03 |
Pos logit contributions | |
bean | +0.006 |
Prince | +0.006 |
narrative | +0.006 |
reef | +0.005 |
thank | +0.005 |
Neg logit contributions | |
z | -0.007 |
ats | -0.007 |
ew | -0.007 |
zag | -0.006 |
om | -0.006 |
Token | with |
Token ID | 351 |
Feature activation | -6.49e-03 |
Pos logit contributions | |
z | +0.010 |
ats | +0.010 |
ew | +0.009 |
zag | +0.009 |
om | +0.009 |
Neg logit contributions | |
bean | -0.015 |
narrative | -0.015 |
Prince | -0.015 |
reef | -0.014 |
cuc | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | -1.21e-03 |
Pos logit contributions | |
z | +0.016 |
ats | +0.015 |
ew | +0.015 |
zag | +0.015 |
om | +0.014 |
Neg logit contributions | |
bean | -0.007 |
Prince | -0.007 |
narrative | -0.006 |
reef | -0.006 |
thank | -0.006 |
Token | skeleton |
Token ID | 18328 |
Feature activation | +1.95e-02 |
Pos logit contributions | |
z | +0.002 |
ats | +0.002 |
ew | +0.002 |
zag | +0.002 |
om | +0.002 |
Neg logit contributions | |
bean | -0.002 |
narrative | -0.002 |
Prince | -0.002 |
reef | -0.002 |
cuc | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | +3.45e-03 |
Pos logit contributions | |
bean | +0.034 |
Prince | +0.030 |
reef | +0.030 |
narrative | +0.028 |
beans | +0.028 |
Neg logit contributions | |
ew | -0.036 |
z | -0.034 |
ats | -0.034 |
om | -0.031 |
attered | -0.030 |
Token | had |
Token ID | 550 |
Feature activation | +1.90e-03 |
Pos logit contributions | |
bean | +0.006 |
narrative | +0.006 |
Prince | +0.005 |
reef | +0.005 |
pearl | +0.005 |
Neg logit contributions | |
z | -0.006 |
ats | -0.006 |
ew | -0.006 |
zag | -0.006 |
om | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | +7.51e-03 |
Pos logit contributions | |
z | +0.019 |
ats | +0.019 |
ew | +0.018 |
zag | +0.018 |
om | +0.017 |
Neg logit contributions | |
bean | -0.019 |
narrative | -0.018 |
Prince | -0.018 |
reef | -0.017 |
cuc | -0.017 |
Token | time |
Token ID | 640 |
Feature activation | -1.49e-03 |
Pos logit contributions | |
bean | +0.013 |
narrative | +0.012 |
Prince | +0.012 |
reef | +0.011 |
thank | +0.011 |
Neg logit contributions | |
z | -0.013 |
ats | -0.012 |
ew | -0.012 |
zag | -0.012 |
om | -0.011 |
Token | there |
Token ID | 612 |
Feature activation | -6.90e-03 |
Pos logit contributions | |
ats | +0.003 |
z | +0.003 |
ew | +0.003 |
zag | +0.002 |
om | +0.002 |
Neg logit contributions | |
bean | -0.002 |
Prince | -0.002 |
narrative | -0.002 |
reef | -0.002 |
thank | -0.002 |
Token | were |
Token ID | 547 |
Feature activation | +2.70e-03 |
Pos logit contributions | |
z | +0.010 |
ats | +0.009 |
ew | +0.009 |
zag | +0.009 |
om | +0.008 |
Neg logit contributions | |
bean | -0.015 |
Prince | -0.014 |
narrative | -0.013 |
reef | -0.013 |
thank | -0.013 |
Token | two |
Token ID | 734 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
narrative | +0.004 |
bean | +0.004 |
Prince | +0.004 |
relief | +0.004 |
thank | +0.004 |
Neg logit contributions | |
z | -0.005 |
ew | -0.004 |
om | -0.004 |
ats | -0.004 |
o | -0.004 |
Token | best |
Token ID | 1266 |
Feature activation | -4.66e-02 |
Pos logit contributions | |
z | +0.029 |
zag | +0.027 |
ew | +0.026 |
ats | +0.026 |
tr | +0.024 |
Neg logit contributions | |
bean | -0.015 |
Prince | -0.014 |
narrative | -0.013 |
beans | -0.013 |
rice | -0.013 |
Token | friends |
Token ID | 2460 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
z | +0.103 |
zag | +0.097 |
ats | +0.095 |
ew | +0.094 |
ches | +0.090 |
Neg logit contributions | |
bean | -0.062 |
narrative | -0.056 |
Prince | -0.054 |
thank | -0.054 |
reef | -0.052 |
Token | named |
Token ID | 3706 |
Feature activation | -5.72e-03 |
Pos logit contributions | |
z | +0.026 |
ats | +0.025 |
zag | +0.024 |
ew | +0.024 |
om | +0.022 |
Neg logit contributions | |
bean | -0.022 |
Prince | -0.021 |
narrative | -0.020 |
reef | -0.019 |
thank | -0.019 |
Token | Jane |
Token ID | 12091 |
Feature activation | -2.08e-03 |
Pos logit contributions | |
z | +0.013 |
ats | +0.012 |
ew | +0.012 |
zag | +0.012 |
om | +0.011 |
Neg logit contributions | |
bean | -0.008 |
Prince | -0.007 |
Av | -0.007 |
reef | -0.006 |
narrative | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | -4.55e-03 |
Pos logit contributions | |
z | +0.004 |
ew | +0.004 |
zag | +0.004 |
ats | +0.004 |
rol | +0.004 |
Neg logit contributions | |
bean | -0.003 |
Prince | -0.003 |
prince | -0.002 |
sailor | -0.002 |
rice | -0.002 |
Token | Luke |
Token ID | 11336 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
z | +0.009 |
ats | +0.008 |
ew | +0.008 |
zag | +0.008 |
om | +0.008 |
Neg logit contributions | |
bean | -0.007 |
narrative | -0.007 |
Prince | -0.006 |
reef | -0.006 |
pearl | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -9.32e-03 |
Pos logit contributions | |
z | +0.016 |
ats | +0.016 |
ew | +0.015 |
zag | +0.015 |
om | +0.014 |
Neg logit contributions | |
bean | -0.021 |
Prince | -0.020 |
narrative | -0.020 |
reef | -0.019 |
thank | -0.019 |
Token | " |
Token ID | 366 |
Feature activation | -1.85e-02 |
Pos logit contributions | |
z | +0.014 |
ew | +0.014 |
ats | +0.014 |
zag | +0.013 |
om | +0.013 |
Neg logit contributions | |
bean | -0.018 |
narrative | -0.017 |
Prince | -0.017 |
reef | -0.016 |
pearl | -0.015 |
Token | You |
Token ID | 1639 |
Feature activation | -2.38e-02 |
Pos logit contributions | |
z | +0.036 |
ats | +0.035 |
ew | +0.034 |
zag | +0.033 |
om | +0.032 |
Neg logit contributions | |
bean | -0.029 |
Prince | -0.027 |
narrative | -0.026 |
reef | -0.025 |
thank | -0.024 |
Token | are |
Token ID | 389 |
Feature activation | -1.54e-02 |
Pos logit contributions | |
z | +0.057 |
ew | +0.050 |
zag | +0.050 |
ats | +0.050 |
om | +0.049 |
Neg logit contributions | |
bean | -0.030 |
Prince | -0.025 |
thank | -0.024 |
reef | -0.024 |
sailor | -0.022 |
Token | not |
Token ID | 407 |
Feature activation | -1.68e-03 |
Pos logit contributions | |
z | +0.033 |
ats | +0.030 |
zag | +0.029 |
ew | +0.028 |
eth | +0.027 |
Neg logit contributions | |
Prince | -0.025 |
bean | -0.024 |
Av | -0.021 |
prince | -0.021 |
reef | -0.020 |
Token | supposed |
Token ID | 4385 |
Feature activation | -6.10e-02 |
Pos logit contributions | |
z | +0.004 |
ats | +0.003 |
ew | +0.003 |
zag | +0.003 |
attered | +0.003 |
Neg logit contributions | |
bean | -0.002 |
Prince | -0.002 |
thank | -0.002 |
Av | -0.002 |
prince | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | -1.58e-03 |
Pos logit contributions | |
z | +0.123 |
ew | +0.115 |
ats | +0.110 |
aned | +0.109 |
zag | +0.107 |
Neg logit contributions | |
bean | -0.099 |
Prince | -0.093 |
poppy | -0.092 |
shrimp | -0.092 |
crab | -0.091 |
Token | touch |
Token ID | 3638 |
Feature activation | -9.61e-03 |
Pos logit contributions | |
z | +0.003 |
ats | +0.003 |
ew | +0.003 |
om | +0.003 |
zag | +0.003 |
Neg logit contributions | |
bean | -0.002 |
Prince | -0.002 |
thank | -0.002 |
reef | -0.002 |
narrative | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | +6.49e-04 |
Pos logit contributions | |
z | +0.023 |
zag | +0.022 |
ats | +0.022 |
ew | +0.021 |
uddy | +0.021 |
Neg logit contributions | |
bean | -0.012 |
Prince | -0.011 |
rice | -0.010 |
poppy | -0.010 |
reef | -0.009 |
Token | clock |
Token ID | 8801 |
Feature activation | -3.78e-03 |
Pos logit contributions | |
bean | +0.001 |
narrative | +0.001 |
Prince | +0.001 |
reef | +0.001 |
rice | +0.001 |
Neg logit contributions | |
z | -0.001 |
ats | -0.001 |
ew | -0.001 |
zag | -0.001 |
om | -0.001 |
Token | ! |
Token ID | 0 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
z | +0.007 |
ats | +0.007 |
ew | +0.007 |
om | +0.006 |
zag | +0.006 |
Neg logit contributions | |
bean | -0.006 |
Prince | -0.006 |
reef | -0.005 |
narrative | -0.005 |
thank | -0.005 |
Token | tag |
Token ID | 7621 |
Feature activation | -6.18e-03 |
Pos logit contributions | |
z | +0.005 |
ats | +0.005 |
ew | +0.005 |
zag | +0.005 |
om | +0.005 |
Neg logit contributions | |
bean | -0.007 |
Prince | -0.007 |
narrative | -0.007 |
reef | -0.006 |
cuc | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | +8.31e-03 |
Pos logit contributions | |
ew | +0.012 |
z | +0.011 |
ats | +0.011 |
aned | +0.011 |
attered | +0.011 |
Neg logit contributions | |
bean | -0.010 |
reef | -0.009 |
beans | -0.009 |
Prince | -0.008 |
thank | -0.008 |
Token | hop |
Token ID | 1725 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
bean | +0.013 |
Prince | +0.012 |
narrative | +0.012 |
reef | +0.011 |
Av | +0.011 |
Neg logit contributions | |
z | -0.016 |
ats | -0.016 |
ew | -0.016 |
zag | -0.015 |
om | -0.015 |
Token | sc |
Token ID | 1416 |
Feature activation | -3.71e-02 |
Pos logit contributions | |
ew | +0.017 |
ats | +0.016 |
z | +0.016 |
oses | +0.015 |
om | +0.015 |
Neg logit contributions | |
bean | -0.020 |
reef | -0.018 |
beans | -0.018 |
Prince | -0.017 |
thank | -0.017 |
Token | ot |
Token ID | 313 |
Feature activation | -2.03e-02 |
Pos logit contributions | |
chairs | +0.077 |
zag | +0.076 |
ahs | +0.075 |
z | +0.073 |
ning | +0.072 |
Neg logit contributions | |
bean | -0.047 |
kin | -0.037 |
beans | -0.036 |
Av | -0.036 |
rice | -0.035 |
Token | ch |
Token ID | 354 |
Feature activation | -4.70e-02 |
Pos logit contributions | |
oses | +0.022 |
icycle | +0.022 |
attered | +0.022 |
zag | +0.021 |
ew | +0.021 |
Neg logit contributions | |
bean | -0.042 |
thank | -0.038 |
Prince | -0.038 |
beans | -0.037 |
Av | -0.037 |
Token | . |
Token ID | 13 |
Feature activation | +8.30e-03 |
Pos logit contributions | |
attered | +0.072 |
icycle | +0.070 |
ew | +0.066 |
z | +0.066 |
ats | +0.065 |
Neg logit contributions | |
bean | -0.078 |
kin | -0.070 |
thank | -0.069 |
beans | -0.067 |
coc | -0.065 |
Token | They |
Token ID | 1119 |
Feature activation | +4.70e-03 |
Pos logit contributions | |
bean | +0.012 |
Prince | +0.011 |
narrative | +0.011 |
Av | +0.010 |
reef | +0.010 |
Neg logit contributions | |
z | -0.018 |
ats | -0.017 |
ew | -0.016 |
zag | -0.016 |
co | -0.015 |
Token | laughed |
Token ID | 13818 |
Feature activation | -1.31e-03 |
Pos logit contributions | |
bean | +0.007 |
Prince | +0.007 |
narrative | +0.007 |
reef | +0.007 |
cuc | +0.006 |
Neg logit contributions | |
z | -0.009 |
ew | -0.009 |
ats | -0.009 |
zag | -0.008 |
om | -0.008 |
Token | a |
Token ID | 257 |
Feature activation | -7.70e-03 |
Pos logit contributions | |
ats | +0.003 |
ew | +0.002 |
z | +0.002 |
zag | +0.002 |
om | +0.002 |
Neg logit contributions | |
bean | -0.002 |
Prince | -0.002 |
thank | -0.002 |
reef | -0.002 |
Av | -0.002 |
Token | lot |
Token ID | 1256 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
ats | +0.012 |
z | +0.012 |
ew | +0.011 |
zag | +0.011 |
oses | +0.011 |
Neg logit contributions | |
bean | -0.015 |
thank | -0.014 |
Prince | -0.014 |
reef | -0.013 |
narrative | -0.013 |
Token | loud |
Token ID | 7812 |
Feature activation | -7.26e-03 |
Pos logit contributions | |
bean | +0.002 |
narrative | +0.002 |
Prince | +0.002 |
reef | +0.002 |
pearl | +0.002 |
Neg logit contributions | |
z | -0.002 |
ats | -0.002 |
ew | -0.002 |
zag | -0.001 |
om | -0.001 |
Token | noise |
Token ID | 7838 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
ats | +0.015 |
z | +0.015 |
icycle | +0.014 |
zag | +0.014 |
ew | +0.014 |
Neg logit contributions | |
thank | -0.010 |
bean | -0.009 |
Prince | -0.009 |
relief | -0.009 |
agreement | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -2.72e-03 |
Pos logit contributions | |
bean | +0.014 |
thank | +0.013 |
Prince | +0.013 |
sailor | +0.012 |
mer | +0.012 |
Neg logit contributions | |
ats | -0.023 |
z | -0.023 |
ew | -0.021 |
zag | -0.021 |
icycle | -0.021 |
Token | He |
Token ID | 679 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
ats | +0.006 |
z | +0.006 |
zag | +0.005 |
ew | +0.005 |
om | +0.005 |
Neg logit contributions | |
bean | -0.004 |
Prince | -0.004 |
Av | -0.003 |
narrative | -0.003 |
Claire | -0.003 |
Token | sc |
Token ID | 629 |
Feature activation | -3.30e-02 |
Pos logit contributions | |
z | +0.023 |
ew | +0.021 |
ats | +0.021 |
zag | +0.021 |
ippy | +0.020 |
Neg logit contributions | |
thank | -0.013 |
bean | -0.013 |
Prince | -0.013 |
narrative | -0.013 |
reef | -0.012 |
Token | run |
Token ID | 5143 |
Feature activation | -5.08e-02 |
Pos logit contributions | |
z | +0.058 |
zag | +0.046 |
ning | +0.045 |
ables | +0.044 |
gy | +0.044 |
Neg logit contributions | |
thank | -0.056 |
narrative | -0.051 |
Cr | -0.046 |
relief | -0.044 |
generosity | -0.044 |
Token | ched |
Token ID | 1740 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
oses | +0.066 |
z | +0.066 |
attered | +0.066 |
ew | +0.065 |
zag | +0.063 |
Neg logit contributions | |
bean | -0.086 |
narrative | -0.079 |
Cr | -0.079 |
Honey | -0.078 |
Penny | -0.078 |
Token | his |
Token ID | 465 |
Feature activation | -9.10e-03 |
Pos logit contributions | |
z | +0.028 |
ats | +0.028 |
zag | +0.028 |
ew | +0.027 |
attered | +0.026 |
Neg logit contributions | |
Prince | -0.014 |
bean | -0.013 |
Penny | -0.011 |
Honey | -0.011 |
Av | -0.011 |
Token | eyes |
Token ID | 2951 |
Feature activation | -2.18e-03 |
Pos logit contributions | |
ats | +0.019 |
z | +0.019 |
ew | +0.018 |
ines | +0.017 |
rol | +0.017 |
Neg logit contributions | |
bean | -0.014 |
pearl | -0.012 |
Prince | -0.012 |
poppy | -0.012 |
reef | -0.012 |
Token | tightly |
Token ID | 17707 |
Feature activation | -9.11e-03 |
Pos logit contributions | |
ats | +0.004 |
z | +0.004 |
ew | +0.004 |
zag | +0.004 |
uddy | +0.004 |
Neg logit contributions | |
bean | -0.003 |
thank | -0.003 |
refreshed | -0.003 |
Prince | -0.003 |
seaw | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | -6.69e-03 |
Pos logit contributions | |
ats | +0.021 |
ew | +0.019 |
z | +0.019 |
ups | +0.018 |
zag | +0.018 |
Neg logit contributions | |
bean | -0.012 |
thank | -0.010 |
Prince | -0.009 |
Honey | -0.009 |
rice | -0.009 |
Token | Max |
Token ID | 11518 |
Feature activation | -1.79e-03 |
Pos logit contributions | |
ats | +0.002 |
ew | +0.002 |
z | +0.002 |
om | +0.002 |
zag | +0.002 |
Neg logit contributions | |
bean | -0.002 |
Prince | -0.002 |
narrative | -0.002 |
thank | -0.002 |
relief | -0.002 |
Token | sat |
Token ID | 3332 |
Feature activation | +3.59e-03 |
Pos logit contributions | |
ats | +0.003 |
z | +0.003 |
ew | +0.003 |
zag | +0.003 |
om | +0.003 |
Neg logit contributions | |
bean | -0.003 |
Prince | -0.003 |
thank | -0.002 |
reef | -0.002 |
Av | -0.002 |
Token | down |
Token ID | 866 |
Feature activation | -7.60e-03 |
Pos logit contributions | |
bean | +0.008 |
narrative | +0.008 |
Prince | +0.008 |
reef | +0.007 |
cuc | +0.007 |
Neg logit contributions | |
z | -0.005 |
ats | -0.004 |
ew | -0.004 |
zag | -0.004 |
om | -0.004 |
Token | on |
Token ID | 319 |
Feature activation | -8.80e-03 |
Pos logit contributions | |
z | +0.011 |
ats | +0.010 |
ew | +0.010 |
zag | +0.009 |
om | +0.009 |
Neg logit contributions | |
bean | -0.016 |
Prince | -0.015 |
narrative | -0.015 |
reef | -0.015 |
thank | -0.014 |
Token | a |
Token ID | 257 |
Feature activation | -9.60e-03 |
Pos logit contributions | |
z | +0.019 |
ats | +0.019 |
ew | +0.018 |
zag | +0.018 |
om | +0.017 |
Neg logit contributions | |
bean | -0.012 |
Prince | -0.011 |
narrative | -0.011 |
reef | -0.010 |
cuc | -0.009 |
Token | log |
Token ID | 2604 |
Feature activation | -4.39e-02 |
Pos logit contributions | |
z | +0.019 |
ats | +0.018 |
ew | +0.018 |
om | +0.017 |
zag | +0.017 |
Neg logit contributions | |
bean | -0.015 |
Prince | -0.014 |
reef | -0.014 |
narrative | -0.013 |
pearl | -0.012 |
Token | to |
Token ID | 284 |
Feature activation | -1.77e-03 |
Pos logit contributions | |
ats | +0.081 |
z | +0.080 |
ew | +0.079 |
om | +0.070 |
attered | +0.070 |
Neg logit contributions | |
bean | -0.072 |
reef | -0.067 |
Prince | -0.066 |
thank | -0.064 |
refreshed | -0.060 |
Token | watch |
Token ID | 2342 |
Feature activation | -4.57e-03 |
Pos logit contributions | |
ats | +0.003 |
z | +0.003 |
zag | +0.003 |
ches | +0.003 |
ew | +0.003 |
Neg logit contributions | |
narrative | -0.003 |
bean | -0.003 |
Prince | -0.003 |
rice | -0.003 |
cuc | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
z | +0.010 |
ats | +0.010 |
ew | +0.010 |
zag | +0.010 |
attered | +0.009 |
Neg logit contributions | |
bean | -0.006 |
Prince | -0.006 |
thank | -0.005 |
reef | -0.005 |
rice | -0.005 |
Token | rabbit |
Token ID | 22746 |
Feature activation | -2.54e-03 |
Pos logit contributions | |
z | +0.031 |
ats | +0.031 |
ew | +0.030 |
zag | +0.029 |
om | +0.028 |
Neg logit contributions | |
bean | -0.018 |
Prince | -0.016 |
narrative | -0.016 |
reef | -0.015 |
cuc | -0.014 |
Token | until |
Token ID | 1566 |
Feature activation | -2.91e-03 |
Pos logit contributions | |
ats | +0.005 |
z | +0.005 |
ew | +0.004 |
zag | +0.004 |
om | +0.004 |
Neg logit contributions | |
bean | -0.005 |
Prince | -0.004 |
reef | -0.004 |
thank | -0.004 |
cuc | -0.004 |