Token | John |
Token ID | 1757 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
works | +0.033 |
clock | +0.033 |
ABC | +0.031 |
numbers | +0.031 |
bows | +0.031 |
Neg logit contributions | |
bed | -0.031 |
aroo | -0.027 |
ging | -0.026 |
ged | -0.026 |
bly | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | +7.10e-01 |
Pos logit contributions | |
clock | +0.044 |
works | +0.043 |
ABC | +0.040 |
numbers | +0.040 |
bows | +0.040 |
Neg logit contributions | |
bed | -0.046 |
aroo | -0.042 |
ged | -0.041 |
ging | -0.040 |
bly | -0.039 |
Token | John |
Token ID | 1757 |
Feature activation | +8.17e-01 |
Pos logit contributions | |
works | +0.024 |
clock | +0.023 |
ABC | +0.022 |
statues | +0.022 |
paintings | +0.021 |
Neg logit contributions | |
bed | -0.022 |
aroo | -0.018 |
ged | -0.018 |
ging | -0.017 |
oned | -0.016 |
Token | was |
Token ID | 373 |
Feature activation | -2.88e-02 |
Pos logit contributions | |
clock | +0.025 |
works | +0.025 |
numbers | +0.023 |
bows | +0.023 |
ABC | +0.023 |
Neg logit contributions | |
bed | -0.030 |
aroo | -0.026 |
ged | -0.026 |
ging | -0.025 |
bly | -0.025 |
Token | three |
Token ID | 1115 |
Feature activation | +9.47e-01 |
Pos logit contributions | |
bed | +0.001 |
ged | +0.001 |
aroo | +0.001 |
ging | +0.001 |
bly | +0.001 |
Neg logit contributions | |
clock | -0.001 |
works | -0.001 |
ABC | -0.001 |
numbers | -0.001 |
library | -0.001 |
Token | years |
Token ID | 812 |
Feature activation | +6.57e+00 |
Pos logit contributions | |
works | +0.031 |
clock | +0.031 |
bows | +0.030 |
library | +0.028 |
ABC | +0.028 |
Neg logit contributions | |
bed | -0.032 |
aroo | -0.029 |
ging | -0.028 |
ged | -0.028 |
bly | -0.027 |
Token | old |
Token ID | 1468 |
Feature activation | +7.98e-01 |
Pos logit contributions | |
works | +0.183 |
clock | +0.182 |
bows | +0.172 |
ABC | +0.166 |
numbers | +0.164 |
Neg logit contributions | |
bed | -0.246 |
aroo | -0.237 |
ging | -0.222 |
ged | -0.218 |
bly | -0.217 |
Token | and |
Token ID | 290 |
Feature activation | +8.15e-01 |
Pos logit contributions | |
works | +0.031 |
clock | +0.030 |
ABC | +0.028 |
restaurants | +0.028 |
bows | +0.028 |
Neg logit contributions | |
bed | -0.023 |
aroo | -0.019 |
ged | -0.019 |
ging | -0.018 |
bly | -0.017 |
Token | had |
Token ID | 550 |
Feature activation | +6.06e-01 |
Pos logit contributions | |
clock | +0.030 |
bows | +0.028 |
works | +0.028 |
tours | +0.027 |
ABC | +0.027 |
Neg logit contributions | |
bed | -0.025 |
aroo | -0.023 |
bly | -0.022 |
ged | -0.021 |
ging | -0.020 |
Token | been |
Token ID | 587 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
works | +0.025 |
bows | +0.023 |
clock | +0.022 |
pays | +0.021 |
aris | +0.021 |
Neg logit contributions | |
bed | -0.016 |
bly | -0.013 |
aroo | -0.012 |
luckily | -0.012 |
dd | -0.012 |
Token | learning |
Token ID | 4673 |
Feature activation | +2.87e+00 |
Pos logit contributions | |
bed | +0.010 |
aroo | +0.009 |
ging | +0.009 |
ged | +0.009 |
bly | +0.009 |
Neg logit contributions | |
works | -0.010 |
clock | -0.010 |
bows | -0.009 |
ABC | -0.009 |
numbers | -0.009 |
Token | Mark |
Token ID | 2940 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
works | +0.033 |
clock | +0.033 |
ABC | +0.030 |
numbers | +0.030 |
bows | +0.030 |
Neg logit contributions | |
bed | -0.029 |
aroo | -0.026 |
ging | -0.025 |
ged | -0.025 |
bly | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | +6.69e-01 |
Pos logit contributions | |
works | +0.007 |
clock | +0.007 |
ABC | +0.006 |
numbers | +0.006 |
bows | +0.006 |
Neg logit contributions | |
bed | -0.008 |
aroo | -0.007 |
ging | -0.007 |
ged | -0.007 |
bly | -0.007 |
Token | Mark |
Token ID | 2940 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
works | +0.022 |
ews | +0.021 |
restaurants | +0.021 |
statues | +0.021 |
hairc | +0.021 |
Neg logit contributions | |
bed | -0.019 |
aroo | -0.016 |
ged | -0.015 |
inn | -0.014 |
pered | -0.014 |
Token | was |
Token ID | 373 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
bed | +0.008 |
aroo | +0.007 |
ged | +0.007 |
ging | +0.007 |
bly | +0.006 |
Neg logit contributions | |
clock | -0.007 |
works | -0.007 |
numbers | -0.006 |
bows | -0.006 |
ABC | -0.006 |
Token | three |
Token ID | 1115 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
clock | +0.002 |
works | +0.002 |
ABC | +0.002 |
library | +0.002 |
numbers | +0.002 |
Neg logit contributions | |
bed | -0.005 |
ged | -0.004 |
aroo | -0.004 |
ging | -0.004 |
oned | -0.004 |
Token | years |
Token ID | 812 |
Feature activation | +6.50e+00 |
Pos logit contributions | |
works | +0.033 |
clock | +0.033 |
bows | +0.031 |
ABC | +0.030 |
numbers | +0.030 |
Neg logit contributions | |
bed | -0.035 |
aroo | -0.032 |
ging | -0.031 |
ged | -0.031 |
bly | -0.030 |
Token | old |
Token ID | 1468 |
Feature activation | +9.07e-01 |
Pos logit contributions | |
works | +0.180 |
clock | +0.180 |
bows | +0.168 |
ABC | +0.163 |
numbers | +0.162 |
Neg logit contributions | |
bed | -0.245 |
aroo | -0.235 |
ging | -0.222 |
ged | -0.217 |
bly | -0.216 |
Token | . |
Token ID | 13 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
works | +0.036 |
clock | +0.035 |
ABC | +0.032 |
bows | +0.032 |
restaurants | +0.032 |
Neg logit contributions | |
bed | -0.026 |
aroo | -0.022 |
ged | -0.021 |
ging | -0.021 |
bly | -0.019 |
Token | One |
Token ID | 1881 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
works | +0.008 |
bows | +0.008 |
statues | +0.008 |
flavors | +0.008 |
clock | +0.008 |
Neg logit contributions | |
bed | -0.006 |
aroo | -0.006 |
inn | -0.005 |
oned | -0.005 |
pered | -0.005 |
Token | day |
Token ID | 1110 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
clock | +0.069 |
works | +0.069 |
numbers | +0.064 |
ABC | +0.064 |
bows | +0.064 |
Neg logit contributions | |
bed | -0.071 |
aroo | -0.065 |
ging | -0.062 |
ged | -0.062 |
bly | -0.061 |
Token | Mark |
Token ID | 2940 |
Feature activation | -6.37e-01 |
Pos logit contributions | |
bed | +0.040 |
aroo | +0.036 |
ged | +0.034 |
ging | +0.032 |
bly | +0.029 |
Neg logit contributions | |
clock | -0.048 |
works | -0.046 |
bows | -0.045 |
ABC | -0.043 |
flavors | -0.043 |
Token | Jane |
Token ID | 12091 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
clock | +0.023 |
library | +0.022 |
works | +0.022 |
bows | +0.022 |
brushes | +0.022 |
Neg logit contributions | |
bed | -0.027 |
ging | -0.026 |
aroo | -0.025 |
ged | -0.025 |
bly | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | +9.10e-01 |
Pos logit contributions | |
works | +0.058 |
clock | +0.056 |
ABC | +0.053 |
library | +0.052 |
looks | +0.052 |
Neg logit contributions | |
bed | -0.086 |
aroo | -0.081 |
ging | -0.079 |
bly | -0.079 |
ged | -0.077 |
Token | Jane |
Token ID | 12091 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
works | +0.028 |
clock | +0.028 |
ABC | +0.026 |
numbers | +0.025 |
jobs | +0.025 |
Neg logit contributions | |
bed | -0.033 |
aroo | -0.028 |
ged | -0.028 |
oned | -0.026 |
ging | -0.026 |
Token | was |
Token ID | 373 |
Feature activation | +4.66e-02 |
Pos logit contributions | |
works | +0.043 |
clock | +0.042 |
ABC | +0.039 |
bows | +0.038 |
numbers | +0.038 |
Neg logit contributions | |
bed | -0.063 |
aroo | -0.058 |
ging | -0.057 |
ged | -0.056 |
bly | -0.055 |
Token | three |
Token ID | 1115 |
Feature activation | +9.76e-01 |
Pos logit contributions | |
clock | +0.001 |
works | +0.001 |
ABC | +0.001 |
library | +0.001 |
numbers | +0.001 |
Neg logit contributions | |
bed | -0.002 |
ged | -0.002 |
aroo | -0.002 |
ging | -0.002 |
bly | -0.002 |
Token | years |
Token ID | 812 |
Feature activation | +6.49e+00 |
Pos logit contributions | |
works | +0.031 |
clock | +0.031 |
bows | +0.029 |
numbers | +0.028 |
ABC | +0.028 |
Neg logit contributions | |
bed | -0.034 |
aroo | -0.031 |
ging | -0.030 |
ged | -0.030 |
bly | -0.029 |
Token | old |
Token ID | 1468 |
Feature activation | +9.96e-01 |
Pos logit contributions | |
works | +0.176 |
clock | +0.176 |
bows | +0.162 |
ABC | +0.159 |
numbers | +0.158 |
Neg logit contributions | |
bed | -0.251 |
aroo | -0.238 |
ging | -0.226 |
ged | -0.223 |
bly | -0.221 |
Token | and |
Token ID | 290 |
Feature activation | +8.90e-01 |
Pos logit contributions | |
works | +0.038 |
clock | +0.037 |
ABC | +0.035 |
restaurants | +0.034 |
numbers | +0.034 |
Neg logit contributions | |
bed | -0.030 |
aroo | -0.025 |
ged | -0.024 |
ging | -0.024 |
bly | -0.022 |
Token | she |
Token ID | 673 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
clock | +0.033 |
works | +0.032 |
bows | +0.030 |
ABC | +0.030 |
restaurants | +0.030 |
Neg logit contributions | |
bed | -0.028 |
aroo | -0.025 |
bly | -0.024 |
ged | -0.023 |
ging | -0.022 |
Token | enjoyed |
Token ID | 8359 |
Feature activation | +6.94e-01 |
Pos logit contributions | |
clock | +0.034 |
works | +0.034 |
numbers | +0.032 |
ABC | +0.032 |
restaurants | +0.032 |
Neg logit contributions | |
bed | -0.034 |
aroo | -0.030 |
ged | -0.029 |
bly | -0.028 |
ging | -0.028 |
Token | playing |
Token ID | 2712 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
works | +0.028 |
clock | +0.028 |
bows | +0.026 |
looks | +0.025 |
ABC | +0.025 |
Neg logit contributions | |
bed | -0.020 |
ged | -0.016 |
aroo | -0.016 |
ging | -0.016 |
bly | -0.015 |
Token | Fiona |
Token ID | 42207 |
Feature activation | +7.96e-01 |
Pos logit contributions | |
clock | +0.027 |
works | +0.026 |
library | +0.026 |
ABC | +0.025 |
bows | +0.025 |
Neg logit contributions | |
bed | -0.029 |
aroo | -0.027 |
ging | -0.027 |
ged | -0.026 |
bly | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | +7.02e-01 |
Pos logit contributions | |
works | +0.017 |
looks | +0.015 |
bows | +0.015 |
ABC | +0.015 |
smells | +0.015 |
Neg logit contributions | |
bed | -0.034 |
ging | -0.033 |
aroo | -0.033 |
bly | -0.032 |
bled | -0.032 |
Token | Fiona |
Token ID | 42207 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
works | +0.015 |
clock | +0.015 |
bows | +0.014 |
numbers | +0.014 |
ABC | +0.014 |
Neg logit contributions | |
bed | -0.031 |
aroo | -0.029 |
ging | -0.029 |
ged | -0.028 |
bly | -0.028 |
Token | was |
Token ID | 373 |
Feature activation | -8.03e-02 |
Pos logit contributions | |
works | +0.008 |
clock | +0.008 |
ABC | +0.008 |
bows | +0.007 |
numbers | +0.007 |
Neg logit contributions | |
bed | -0.011 |
aroo | -0.010 |
ging | -0.010 |
ged | -0.009 |
bly | -0.009 |
Token | 3 |
Token ID | 513 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
bed | +0.004 |
ged | +0.003 |
aroo | +0.003 |
ging | +0.003 |
bly | +0.003 |
Neg logit contributions | |
clock | -0.002 |
works | -0.002 |
ABC | -0.002 |
library | -0.002 |
numbers | -0.001 |
Token | years |
Token ID | 812 |
Feature activation | +6.48e+00 |
Pos logit contributions | |
bed | +0.006 |
aroo | +0.006 |
ging | +0.006 |
ged | +0.006 |
bly | +0.005 |
Neg logit contributions | |
clock | -0.005 |
works | -0.005 |
ABC | -0.004 |
numbers | -0.004 |
bows | -0.004 |
Token | old |
Token ID | 1468 |
Feature activation | +9.85e-01 |
Pos logit contributions | |
works | +0.165 |
clock | +0.165 |
bows | +0.150 |
ABC | +0.149 |
numbers | +0.148 |
Neg logit contributions | |
bed | -0.266 |
aroo | -0.250 |
ging | -0.240 |
ged | -0.238 |
bly | -0.234 |
Token | and |
Token ID | 290 |
Feature activation | +7.54e-01 |
Pos logit contributions | |
works | +0.037 |
clock | +0.037 |
ABC | +0.034 |
numbers | +0.034 |
bows | +0.034 |
Neg logit contributions | |
bed | -0.030 |
aroo | -0.026 |
ged | -0.025 |
ging | -0.025 |
bly | -0.023 |
Token | she |
Token ID | 673 |
Feature activation | +8.92e-01 |
Pos logit contributions | |
clock | +0.026 |
works | +0.025 |
bows | +0.024 |
ABC | +0.024 |
numbers | +0.024 |
Neg logit contributions | |
bed | -0.025 |
aroo | -0.023 |
bly | -0.022 |
ged | -0.021 |
ging | -0.021 |
Token | liked |
Token ID | 8288 |
Feature activation | +6.79e-01 |
Pos logit contributions | |
clock | +0.030 |
works | +0.029 |
numbers | +0.028 |
ABC | +0.027 |
bows | +0.027 |
Neg logit contributions | |
bed | -0.031 |
aroo | -0.028 |
ged | -0.027 |
ging | -0.026 |
bly | -0.026 |
Token | to |
Token ID | 284 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
works | +0.024 |
clock | +0.022 |
bows | +0.022 |
pays | +0.021 |
total | +0.020 |
Neg logit contributions | |
bed | -0.021 |
aroo | -0.018 |
ged | -0.017 |
spraying | -0.015 |
bing | -0.015 |
Token | Jack |
Token ID | 3619 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
works | +0.029 |
clock | +0.029 |
bows | +0.027 |
ABC | +0.027 |
numbers | +0.027 |
Neg logit contributions | |
bed | -0.026 |
aroo | -0.024 |
ged | -0.022 |
ging | -0.022 |
bly | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | +6.97e-01 |
Pos logit contributions | |
works | +0.034 |
clock | +0.034 |
ABC | +0.031 |
numbers | +0.031 |
bows | +0.031 |
Neg logit contributions | |
bed | -0.042 |
aroo | -0.038 |
ging | -0.037 |
ged | -0.037 |
bly | -0.036 |
Token | He |
Token ID | 679 |
Feature activation | +9.10e-01 |
Pos logit contributions | |
clock | +0.024 |
works | +0.024 |
ABC | +0.023 |
bows | +0.022 |
numbers | +0.022 |
Neg logit contributions | |
bed | -0.023 |
aroo | -0.020 |
ged | -0.019 |
ging | -0.019 |
bly | -0.019 |
Token | was |
Token ID | 373 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
clock | +0.027 |
works | +0.027 |
numbers | +0.025 |
ABC | +0.025 |
bows | +0.024 |
Neg logit contributions | |
bed | -0.035 |
aroo | -0.031 |
ged | -0.030 |
ging | -0.030 |
bly | -0.030 |
Token | 3 |
Token ID | 513 |
Feature activation | -9.25e-02 |
Pos logit contributions | |
bed | +0.009 |
aroo | +0.009 |
ged | +0.009 |
ging | +0.009 |
bly | +0.008 |
Neg logit contributions | |
clock | -0.005 |
works | -0.005 |
ABC | -0.004 |
numbers | -0.004 |
library | -0.004 |
Token | years |
Token ID | 812 |
Feature activation | +6.48e+00 |
Pos logit contributions | |
bed | +0.003 |
aroo | +0.003 |
ging | +0.003 |
ged | +0.003 |
bly | +0.003 |
Neg logit contributions | |
works | -0.003 |
clock | -0.003 |
bows | -0.003 |
ABC | -0.003 |
numbers | -0.003 |
Token | old |
Token ID | 1468 |
Feature activation | +9.30e-01 |
Pos logit contributions | |
works | +0.169 |
clock | +0.168 |
bows | +0.156 |
ABC | +0.153 |
numbers | +0.151 |
Neg logit contributions | |
bed | -0.260 |
aroo | -0.244 |
ging | -0.234 |
ged | -0.232 |
bly | -0.229 |
Token | and |
Token ID | 290 |
Feature activation | +7.76e-01 |
Pos logit contributions | |
works | +0.037 |
clock | +0.036 |
ABC | +0.034 |
restaurants | +0.033 |
bows | +0.033 |
Neg logit contributions | |
bed | -0.026 |
aroo | -0.022 |
ged | -0.021 |
ging | -0.021 |
bly | -0.019 |
Token | very |
Token ID | 845 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
clock | +0.028 |
works | +0.026 |
bows | +0.026 |
ABC | +0.025 |
tours | +0.025 |
Neg logit contributions | |
bed | -0.025 |
aroo | -0.023 |
bly | -0.022 |
ged | -0.021 |
ging | -0.021 |
Token | persistent |
Token ID | 16218 |
Feature activation | +4.94e-01 |
Pos logit contributions | |
clock | +0.109 |
bows | +0.105 |
works | +0.102 |
flavors | +0.101 |
numbers | +0.101 |
Neg logit contributions | |
bed | -0.079 |
aroo | -0.078 |
bly | -0.072 |
ging | -0.070 |
ged | -0.067 |
Token | . |
Token ID | 13 |
Feature activation | +6.71e-02 |
Pos logit contributions | |
works | +0.020 |
clock | +0.019 |
bows | +0.018 |
ABC | +0.018 |
smells | +0.018 |
Neg logit contributions | |
bed | -0.013 |
aroo | -0.011 |
ging | -0.011 |
ged | -0.011 |
bly | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +5.24e-01 |
Pos logit contributions | |
works | +0.046 |
clock | +0.045 |
ABC | +0.043 |
bows | +0.043 |
numbers | +0.043 |
Neg logit contributions | |
bed | -0.060 |
aroo | -0.055 |
ging | -0.055 |
ged | -0.054 |
bly | -0.053 |
Token | M |
Token ID | 337 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
works | +0.019 |
clock | +0.018 |
ABC | +0.017 |
numbers | +0.017 |
flavors | +0.017 |
Neg logit contributions | |
bed | -0.017 |
ged | -0.013 |
aroo | -0.013 |
inn | -0.013 |
bly | -0.013 |
Token | illy |
Token ID | 6548 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
works | +0.111 |
clock | +0.111 |
numbers | +0.105 |
bows | +0.104 |
ABC | +0.103 |
Neg logit contributions | |
bed | -0.057 |
aroo | -0.045 |
ged | -0.043 |
ging | -0.043 |
bly | -0.042 |
Token | was |
Token ID | 373 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
clock | +0.036 |
works | +0.035 |
numbers | +0.033 |
restaurants | +0.033 |
ABC | +0.032 |
Neg logit contributions | |
bed | -0.038 |
aroo | -0.034 |
ged | -0.032 |
ging | -0.031 |
bly | -0.031 |
Token | 3 |
Token ID | 513 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
clock | +0.006 |
works | +0.006 |
ABC | +0.005 |
numbers | +0.005 |
library | +0.005 |
Neg logit contributions | |
bed | -0.010 |
aroo | -0.009 |
ged | -0.009 |
ging | -0.009 |
bly | -0.009 |
Token | years |
Token ID | 812 |
Feature activation | +6.47e+00 |
Pos logit contributions | |
bed | +0.013 |
aroo | +0.012 |
ging | +0.011 |
ged | +0.011 |
bly | +0.011 |
Neg logit contributions | |
works | -0.011 |
clock | -0.011 |
bows | -0.010 |
ABC | -0.010 |
numbers | -0.010 |
Token | old |
Token ID | 1468 |
Feature activation | +6.91e-01 |
Pos logit contributions | |
works | +0.167 |
clock | +0.166 |
bows | +0.153 |
ABC | +0.150 |
numbers | +0.149 |
Neg logit contributions | |
bed | -0.264 |
aroo | -0.247 |
ging | -0.236 |
ged | -0.235 |
bly | -0.232 |
Token | and |
Token ID | 290 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
works | +0.027 |
clock | +0.026 |
ABC | +0.024 |
restaurants | +0.024 |
bows | +0.024 |
Neg logit contributions | |
bed | -0.020 |
aroo | -0.017 |
ged | -0.017 |
ging | -0.017 |
bly | -0.016 |
Token | loved |
Token ID | 6151 |
Feature activation | +7.59e-01 |
Pos logit contributions | |
clock | +0.013 |
works | +0.013 |
bows | +0.012 |
ABC | +0.012 |
numbers | +0.012 |
Neg logit contributions | |
bed | -0.014 |
aroo | -0.012 |
bly | -0.012 |
ged | -0.012 |
ging | -0.011 |
Token | to |
Token ID | 284 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
works | +0.026 |
bows | +0.025 |
clock | +0.024 |
ven | +0.023 |
total | +0.023 |
Neg logit contributions | |
bed | -0.024 |
ged | -0.019 |
aroo | -0.019 |
ging | -0.018 |
spraying | -0.018 |
Token | chew |
Token ID | 34722 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
clock | +0.077 |
works | +0.072 |
bows | +0.070 |
aris | +0.067 |
pays | +0.067 |
Neg logit contributions | |
bed | -0.070 |
aroo | -0.059 |
bly | -0.056 |
ged | -0.054 |
swat | -0.053 |
Token | Alex |
Token ID | 4422 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
works | +0.032 |
clock | +0.032 |
numbers | +0.030 |
ABC | +0.030 |
bows | +0.030 |
Neg logit contributions | |
bed | -0.030 |
aroo | -0.027 |
ging | -0.026 |
ged | -0.026 |
bly | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | +5.95e-01 |
Pos logit contributions | |
works | +0.004 |
clock | +0.004 |
ABC | +0.004 |
looks | +0.003 |
numbers | +0.003 |
Neg logit contributions | |
bed | -0.006 |
aroo | -0.006 |
ging | -0.006 |
bly | -0.006 |
ged | -0.006 |
Token | He |
Token ID | 679 |
Feature activation | +7.96e-01 |
Pos logit contributions | |
clock | +0.017 |
works | +0.017 |
ABC | +0.016 |
bows | +0.016 |
numbers | +0.016 |
Neg logit contributions | |
bed | -0.023 |
aroo | -0.020 |
ged | -0.020 |
ging | -0.020 |
bly | -0.019 |
Token | was |
Token ID | 373 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
works | +0.022 |
clock | +0.022 |
ABC | +0.020 |
numbers | +0.020 |
bows | +0.020 |
Neg logit contributions | |
bed | -0.031 |
aroo | -0.029 |
ging | -0.028 |
ged | -0.028 |
bly | -0.028 |
Token | three |
Token ID | 1115 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
bed | +0.012 |
aroo | +0.011 |
ged | +0.011 |
ging | +0.011 |
bly | +0.010 |
Neg logit contributions | |
clock | -0.006 |
works | -0.006 |
ABC | -0.006 |
numbers | -0.006 |
library | -0.006 |
Token | years |
Token ID | 812 |
Feature activation | +6.47e+00 |
Pos logit contributions | |
works | +0.037 |
clock | +0.037 |
bows | +0.035 |
ABC | +0.034 |
library | +0.033 |
Neg logit contributions | |
bed | -0.038 |
aroo | -0.034 |
ging | -0.033 |
ged | -0.032 |
bly | -0.032 |
Token | old |
Token ID | 1468 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
works | +0.182 |
clock | +0.180 |
bows | +0.172 |
ABC | +0.166 |
flavors | +0.165 |
Neg logit contributions | |
bed | -0.239 |
aroo | -0.229 |
ging | -0.218 |
ged | -0.212 |
bly | -0.211 |
Token | and |
Token ID | 290 |
Feature activation | +9.07e-01 |
Pos logit contributions | |
works | +0.040 |
clock | +0.039 |
ABC | +0.037 |
restaurants | +0.037 |
bows | +0.036 |
Neg logit contributions | |
bed | -0.029 |
aroo | -0.024 |
ged | -0.023 |
ging | -0.023 |
bly | -0.020 |
Token | always |
Token ID | 1464 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
clock | +0.032 |
works | +0.031 |
bows | +0.030 |
ABC | +0.029 |
numbers | +0.029 |
Neg logit contributions | |
bed | -0.029 |
aroo | -0.027 |
bly | -0.026 |
ged | -0.025 |
ging | -0.024 |
Token | looking |
Token ID | 2045 |
Feature activation | +3.23e+00 |
Pos logit contributions | |
clock | +0.071 |
ABC | +0.071 |
works | +0.070 |
numbers | +0.068 |
library | +0.067 |
Neg logit contributions | |
bed | -0.078 |
ged | -0.068 |
ging | -0.068 |
aroo | -0.066 |
bly | -0.064 |
Token | for |
Token ID | 329 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
clock | +0.147 |
flavors | +0.144 |
bows | +0.143 |
works | +0.141 |
brushes | +0.136 |
Neg logit contributions | |
bed | -0.061 |
ging | -0.059 |
ged | -0.054 |
ling | -0.051 |
aroo | -0.049 |
Token | . |
Token ID | 13 |
Feature activation | +7.03e-01 |
Pos logit contributions | |
bed | +0.016 |
ging | +0.015 |
bly | +0.015 |
ged | +0.015 |
aroo | +0.015 |
Neg logit contributions | |
works | -0.008 |
clock | -0.008 |
library | -0.008 |
ABC | -0.008 |
books | -0.007 |
Token | Mill |
Token ID | 9212 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
clock | +0.022 |
works | +0.021 |
ABC | +0.020 |
numbers | +0.020 |
flavors | +0.020 |
Neg logit contributions | |
bed | -0.026 |
aroo | -0.022 |
ged | -0.022 |
ging | -0.021 |
bly | -0.021 |
Token | ie |
Token ID | 494 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
works | +0.054 |
clock | +0.053 |
ABC | +0.050 |
numbers | +0.050 |
bows | +0.050 |
Neg logit contributions | |
bed | -0.038 |
aroo | -0.034 |
ging | -0.032 |
ged | -0.032 |
bly | -0.031 |
Token | was |
Token ID | 373 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
bed | +0.045 |
aroo | +0.040 |
ged | +0.039 |
ging | +0.038 |
bly | +0.038 |
Neg logit contributions | |
clock | -0.039 |
works | -0.039 |
numbers | -0.036 |
ABC | -0.036 |
bows | -0.036 |
Token | 3 |
Token ID | 513 |
Feature activation | -4.60e-01 |
Pos logit contributions | |
bed | +0.007 |
ged | +0.007 |
aroo | +0.007 |
ging | +0.007 |
bly | +0.006 |
Neg logit contributions | |
clock | -0.004 |
works | -0.003 |
ABC | -0.003 |
library | -0.003 |
numbers | -0.003 |
Token | years |
Token ID | 812 |
Feature activation | +6.45e+00 |
Pos logit contributions | |
bed | +0.018 |
aroo | +0.016 |
ging | +0.016 |
ged | +0.016 |
bly | +0.015 |
Neg logit contributions | |
works | -0.013 |
clock | -0.013 |
ABC | -0.012 |
numbers | -0.012 |
bows | -0.012 |
Token | old |
Token ID | 1468 |
Feature activation | +7.92e-01 |
Pos logit contributions | |
works | +0.161 |
clock | +0.161 |
bows | +0.146 |
ABC | +0.145 |
numbers | +0.145 |
Neg logit contributions | |
bed | -0.269 |
aroo | -0.250 |
ging | -0.242 |
ged | -0.240 |
bly | -0.236 |
Token | and |
Token ID | 290 |
Feature activation | +5.42e-01 |
Pos logit contributions | |
works | +0.030 |
clock | +0.030 |
ABC | +0.028 |
restaurants | +0.027 |
numbers | +0.027 |
Neg logit contributions | |
bed | -0.024 |
aroo | -0.020 |
ged | -0.020 |
ging | -0.019 |
bly | -0.018 |
Token | loved |
Token ID | 6151 |
Feature activation | +9.53e-01 |
Pos logit contributions | |
clock | +0.019 |
works | +0.018 |
bows | +0.017 |
ABC | +0.017 |
restaurants | +0.017 |
Neg logit contributions | |
bed | -0.018 |
aroo | -0.017 |
bly | -0.016 |
ged | -0.016 |
ging | -0.015 |
Token | to |
Token ID | 284 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
works | +0.032 |
bows | +0.030 |
clock | +0.030 |
ven | +0.028 |
pays | +0.028 |
Neg logit contributions | |
bed | -0.030 |
ged | -0.025 |
aroo | -0.024 |
ging | -0.023 |
bing | -0.023 |
Token | explore |
Token ID | 7301 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
clock | +0.080 |
works | +0.075 |
bows | +0.072 |
aris | +0.071 |
pays | +0.070 |
Neg logit contributions | |
bed | -0.071 |
aroo | -0.061 |
bly | -0.056 |
swat | -0.054 |
ged | -0.054 |
Token | Jimmy |
Token ID | 12963 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
clock | +0.030 |
works | +0.030 |
numbers | +0.029 |
ABC | +0.028 |
library | +0.028 |
Neg logit contributions | |
bed | -0.031 |
aroo | -0.028 |
ging | -0.027 |
ged | -0.027 |
bly | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | +7.75e-01 |
Pos logit contributions | |
works | +0.037 |
clock | +0.037 |
ABC | +0.034 |
numbers | +0.034 |
bows | +0.034 |
Neg logit contributions | |
bed | -0.045 |
aroo | -0.042 |
ging | -0.040 |
ged | -0.040 |
bly | -0.039 |
Token | Jimmy |
Token ID | 12963 |
Feature activation | +5.96e-01 |
Pos logit contributions | |
works | +0.025 |
clock | +0.025 |
ABC | +0.023 |
bows | +0.023 |
numbers | +0.023 |
Neg logit contributions | |
bed | -0.027 |
ged | -0.023 |
aroo | -0.023 |
ging | -0.023 |
bly | -0.022 |
Token | was |
Token ID | 373 |
Feature activation | -3.02e-02 |
Pos logit contributions | |
clock | +0.018 |
works | +0.018 |
numbers | +0.017 |
ABC | +0.017 |
bows | +0.017 |
Neg logit contributions | |
bed | -0.022 |
aroo | -0.020 |
ged | -0.019 |
ging | -0.019 |
bly | -0.019 |
Token | three |
Token ID | 1115 |
Feature activation | +8.63e-01 |
Pos logit contributions | |
bed | +0.001 |
ged | +0.001 |
aroo | +0.001 |
ging | +0.001 |
bly | +0.001 |
Neg logit contributions | |
clock | -0.001 |
works | -0.001 |
ABC | -0.001 |
library | -0.001 |
numbers | -0.001 |
Token | years |
Token ID | 812 |
Feature activation | +6.44e+00 |
Pos logit contributions | |
works | +0.027 |
clock | +0.026 |
bows | +0.025 |
ABC | +0.024 |
numbers | +0.024 |
Neg logit contributions | |
bed | -0.031 |
aroo | -0.028 |
ging | -0.027 |
ged | -0.027 |
bly | -0.027 |
Token | old |
Token ID | 1468 |
Feature activation | +9.27e-01 |
Pos logit contributions | |
works | +0.175 |
clock | +0.174 |
bows | +0.162 |
ABC | +0.158 |
numbers | +0.156 |
Neg logit contributions | |
bed | -0.250 |
aroo | -0.237 |
ging | -0.226 |
ged | -0.222 |
bly | -0.220 |
Token | , |
Token ID | 11 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
works | +0.036 |
clock | +0.035 |
ABC | +0.033 |
bows | +0.032 |
restaurants | +0.032 |
Neg logit contributions | |
bed | -0.027 |
aroo | -0.023 |
ging | -0.022 |
ged | -0.022 |
bly | -0.020 |
Token | and |
Token ID | 290 |
Feature activation | +5.70e-01 |
Pos logit contributions | |
works | +0.014 |
clock | +0.014 |
numbers | +0.013 |
ABC | +0.013 |
bows | +0.013 |
Neg logit contributions | |
bed | -0.012 |
aroo | -0.011 |
ging | -0.011 |
ged | -0.011 |
bly | -0.011 |
Token | very |
Token ID | 845 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
clock | +0.019 |
works | +0.019 |
bows | +0.018 |
ABC | +0.017 |
numbers | +0.017 |
Neg logit contributions | |
bed | -0.020 |
aroo | -0.018 |
bly | -0.017 |
ged | -0.017 |
ging | -0.017 |
Token | healthy |
Token ID | 5448 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
clock | +0.100 |
works | +0.097 |
bows | +0.096 |
numbers | +0.092 |
ABC | +0.092 |
Neg logit contributions | |
bed | -0.082 |
aroo | -0.077 |
bly | -0.072 |
ging | -0.072 |
ged | -0.071 |
Token | Bob |
Token ID | 5811 |
Feature activation | +6.61e-01 |
Pos logit contributions | |
clock | +0.028 |
works | +0.028 |
bows | +0.026 |
ABC | +0.026 |
flavors | +0.026 |
Neg logit contributions | |
bed | -0.024 |
aroo | -0.022 |
ged | -0.020 |
ging | -0.020 |
bly | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +4.55e-01 |
Pos logit contributions | |
clock | +0.021 |
works | +0.021 |
ABC | +0.019 |
numbers | +0.019 |
bows | +0.019 |
Neg logit contributions | |
bed | -0.023 |
aroo | -0.021 |
ged | -0.021 |
ging | -0.020 |
bly | -0.020 |
Token | Bob |
Token ID | 5811 |
Feature activation | +5.82e-01 |
Pos logit contributions | |
works | +0.017 |
clock | +0.017 |
ABC | +0.016 |
bows | +0.016 |
numbers | +0.016 |
Neg logit contributions | |
bed | -0.013 |
aroo | -0.012 |
ged | -0.011 |
ging | -0.010 |
bly | -0.010 |
Token | was |
Token ID | 373 |
Feature activation | -3.27e-02 |
Pos logit contributions | |
clock | +0.019 |
works | +0.018 |
numbers | +0.017 |
bows | +0.017 |
ABC | +0.017 |
Neg logit contributions | |
bed | -0.021 |
aroo | -0.018 |
ged | -0.018 |
ging | -0.017 |
bly | -0.017 |
Token | three |
Token ID | 1115 |
Feature activation | +8.91e-01 |
Pos logit contributions | |
bed | +0.001 |
ged | +0.001 |
ging | +0.001 |
aroo | +0.001 |
bly | +0.001 |
Neg logit contributions | |
clock | -0.001 |
works | -0.001 |
ABC | -0.001 |
numbers | -0.001 |
library | -0.001 |
Token | years |
Token ID | 812 |
Feature activation | +6.44e+00 |
Pos logit contributions | |
works | +0.029 |
clock | +0.029 |
bows | +0.028 |
ABC | +0.027 |
library | +0.026 |
Neg logit contributions | |
bed | -0.030 |
aroo | -0.027 |
ging | -0.026 |
ged | -0.026 |
bly | -0.025 |
Token | old |
Token ID | 1468 |
Feature activation | +7.56e-01 |
Pos logit contributions | |
works | +0.176 |
clock | +0.174 |
bows | +0.164 |
ABC | +0.159 |
numbers | +0.157 |
Neg logit contributions | |
bed | -0.247 |
aroo | -0.237 |
ging | -0.223 |
ged | -0.220 |
bly | -0.217 |
Token | and |
Token ID | 290 |
Feature activation | +6.36e-01 |
Pos logit contributions | |
works | +0.030 |
clock | +0.029 |
ABC | +0.027 |
bows | +0.027 |
restaurants | +0.027 |
Neg logit contributions | |
bed | -0.022 |
aroo | -0.018 |
ged | -0.017 |
ging | -0.017 |
bly | -0.015 |
Token | loved |
Token ID | 6151 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
clock | +0.022 |
works | +0.021 |
bows | +0.021 |
ABC | +0.020 |
numbers | +0.020 |
Neg logit contributions | |
bed | -0.021 |
aroo | -0.020 |
bly | -0.018 |
ged | -0.018 |
ging | -0.017 |
Token | to |
Token ID | 284 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
bows | +0.034 |
works | +0.034 |
clock | +0.032 |
ven | +0.030 |
pays | +0.030 |
Neg logit contributions | |
bed | -0.031 |
aroo | -0.026 |
ged | -0.026 |
ging | -0.024 |
bing | -0.024 |
Token | be |
Token ID | 307 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
clock | +0.083 |
works | +0.077 |
bows | +0.075 |
meanings | +0.073 |
pays | +0.073 |
Neg logit contributions | |
bed | -0.070 |
aroo | -0.059 |
bly | -0.054 |
swat | -0.052 |
ged | -0.052 |
Token | Jack |
Token ID | 3619 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
works | +0.038 |
clock | +0.038 |
ABC | +0.035 |
bows | +0.035 |
numbers | +0.035 |
Neg logit contributions | |
bed | -0.033 |
aroo | -0.029 |
ged | -0.028 |
ging | -0.028 |
bly | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
works | +0.039 |
clock | +0.039 |
ABC | +0.036 |
numbers | +0.036 |
bows | +0.035 |
Neg logit contributions | |
bed | -0.048 |
aroo | -0.044 |
ging | -0.043 |
ged | -0.042 |
bly | -0.042 |
Token | He |
Token ID | 679 |
Feature activation | +8.31e-01 |
Pos logit contributions | |
works | +0.018 |
clock | +0.018 |
ABC | +0.016 |
numbers | +0.016 |
bows | +0.016 |
Neg logit contributions | |
bed | -0.018 |
aroo | -0.016 |
ging | -0.015 |
ged | -0.015 |
bly | -0.015 |
Token | was |
Token ID | 373 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
works | +0.023 |
clock | +0.023 |
ABC | +0.021 |
numbers | +0.021 |
library | +0.021 |
Neg logit contributions | |
bed | -0.033 |
aroo | -0.030 |
ging | -0.030 |
ged | -0.029 |
bly | -0.029 |
Token | three |
Token ID | 1115 |
Feature activation | +9.82e-01 |
Pos logit contributions | |
bed | +0.012 |
ged | +0.011 |
aroo | +0.011 |
ging | +0.011 |
bly | +0.010 |
Neg logit contributions | |
clock | -0.006 |
works | -0.006 |
ABC | -0.005 |
numbers | -0.005 |
library | -0.005 |
Token | years |
Token ID | 812 |
Feature activation | +6.43e+00 |
Pos logit contributions | |
works | +0.032 |
clock | +0.031 |
bows | +0.030 |
ABC | +0.029 |
numbers | +0.029 |
Neg logit contributions | |
bed | -0.034 |
aroo | -0.030 |
ging | -0.029 |
ged | -0.029 |
bly | -0.029 |
Token | old |
Token ID | 1468 |
Feature activation | +9.30e-01 |
Pos logit contributions | |
works | +0.174 |
clock | +0.173 |
bows | +0.164 |
ABC | +0.158 |
numbers | +0.157 |
Neg logit contributions | |
bed | -0.247 |
aroo | -0.236 |
ging | -0.224 |
ged | -0.220 |
bly | -0.219 |
Token | and |
Token ID | 290 |
Feature activation | +8.24e-01 |
Pos logit contributions | |
works | +0.037 |
clock | +0.036 |
ABC | +0.034 |
restaurants | +0.034 |
bows | +0.033 |
Neg logit contributions | |
bed | -0.026 |
aroo | -0.022 |
ged | -0.021 |
ging | -0.021 |
bly | -0.018 |
Token | he |
Token ID | 339 |
Feature activation | +4.66e-01 |
Pos logit contributions | |
clock | +0.030 |
works | +0.028 |
bows | +0.028 |
ABC | +0.027 |
numbers | +0.026 |
Neg logit contributions | |
bed | -0.026 |
aroo | -0.024 |
bly | -0.023 |
ged | -0.022 |
ging | -0.021 |
Token | loved |
Token ID | 6151 |
Feature activation | +5.08e-01 |
Pos logit contributions | |
clock | +0.017 |
works | +0.016 |
bows | +0.016 |
numbers | +0.015 |
ABC | +0.015 |
Neg logit contributions | |
bed | -0.015 |
aroo | -0.013 |
ged | -0.013 |
bly | -0.012 |
ging | -0.012 |
Token | to |
Token ID | 284 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
bows | +0.017 |
works | +0.017 |
clock | +0.016 |
pays | +0.015 |
ven | +0.015 |
Neg logit contributions | |
bed | -0.016 |
aroo | -0.013 |
ged | -0.013 |
ging | -0.012 |
under | -0.012 |
Token | Tom |
Token ID | 4186 |
Feature activation | +6.12e-01 |
Pos logit contributions | |
clock | +0.032 |
works | +0.032 |
numbers | +0.030 |
ABC | +0.029 |
library | +0.029 |
Neg logit contributions | |
bed | -0.032 |
aroo | -0.029 |
ging | -0.028 |
ged | -0.028 |
bly | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | +7.02e-01 |
Pos logit contributions | |
works | +0.018 |
clock | +0.017 |
ABC | +0.016 |
numbers | +0.016 |
library | +0.016 |
Neg logit contributions | |
bed | -0.023 |
aroo | -0.022 |
ging | -0.021 |
bly | -0.021 |
ged | -0.021 |
Token | He |
Token ID | 679 |
Feature activation | +8.63e-01 |
Pos logit contributions | |
works | +0.022 |
clock | +0.021 |
ABC | +0.020 |
bows | +0.020 |
statues | +0.020 |
Neg logit contributions | |
bed | -0.024 |
aroo | -0.021 |
ged | -0.021 |
ging | -0.020 |
inn | -0.019 |
Token | was |
Token ID | 373 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
works | +0.024 |
clock | +0.023 |
ABC | +0.021 |
numbers | +0.021 |
library | +0.021 |
Neg logit contributions | |
bed | -0.035 |
aroo | -0.032 |
ging | -0.031 |
ged | -0.031 |
bly | -0.031 |
Token | three |
Token ID | 1115 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
bed | +0.010 |
ged | +0.009 |
aroo | +0.009 |
ging | +0.009 |
bly | +0.009 |
Neg logit contributions | |
clock | -0.005 |
works | -0.004 |
ABC | -0.004 |
numbers | -0.004 |
library | -0.004 |
Token | years |
Token ID | 812 |
Feature activation | +6.43e+00 |
Pos logit contributions | |
works | +0.035 |
clock | +0.034 |
bows | +0.033 |
ABC | +0.031 |
numbers | +0.031 |
Neg logit contributions | |
bed | -0.036 |
aroo | -0.032 |
ging | -0.031 |
ged | -0.031 |
bly | -0.030 |
Token | old |
Token ID | 1468 |
Feature activation | +9.54e-01 |
Pos logit contributions | |
works | +0.178 |
clock | +0.176 |
bows | +0.167 |
ABC | +0.161 |
numbers | +0.160 |
Neg logit contributions | |
bed | -0.243 |
aroo | -0.232 |
ging | -0.221 |
ged | -0.216 |
bly | -0.215 |
Token | and |
Token ID | 290 |
Feature activation | +8.34e-01 |
Pos logit contributions | |
works | +0.038 |
clock | +0.037 |
ABC | +0.034 |
bows | +0.034 |
restaurants | +0.034 |
Neg logit contributions | |
bed | -0.027 |
aroo | -0.022 |
ged | -0.021 |
ging | -0.021 |
bly | -0.019 |
Token | liked |
Token ID | 8288 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
clock | +0.030 |
bows | +0.028 |
works | +0.028 |
ABC | +0.027 |
numbers | +0.027 |
Neg logit contributions | |
bed | -0.026 |
aroo | -0.024 |
bly | -0.023 |
ged | -0.022 |
ging | -0.022 |
Token | to |
Token ID | 284 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
bows | +0.046 |
works | +0.046 |
clock | +0.043 |
pays | +0.041 |
meanings | +0.040 |
Neg logit contributions | |
bed | -0.039 |
aroo | -0.035 |
ged | -0.033 |
ging | -0.030 |
under | -0.030 |
Token | explore |
Token ID | 7301 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
clock | +0.075 |
works | +0.072 |
bows | +0.069 |
aris | +0.069 |
pays | +0.068 |
Neg logit contributions | |
bed | -0.071 |
aroo | -0.062 |
bly | -0.056 |
ged | -0.055 |
swat | -0.053 |
Token | John |
Token ID | 1757 |
Feature activation | +9.81e-01 |
Pos logit contributions | |
clock | +0.030 |
works | +0.030 |
bows | +0.028 |
ABC | +0.028 |
numbers | +0.028 |
Neg logit contributions | |
bed | -0.024 |
aroo | -0.022 |
ged | -0.021 |
ging | -0.020 |
bly | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | +3.00e-01 |
Pos logit contributions | |
clock | +0.034 |
works | +0.034 |
bows | +0.032 |
ABC | +0.032 |
numbers | +0.032 |
Neg logit contributions | |
bed | -0.032 |
aroo | -0.028 |
ged | -0.028 |
ging | -0.027 |
bly | -0.026 |
Token | John |
Token ID | 1757 |
Feature activation | +6.88e-01 |
Pos logit contributions | |
works | +0.010 |
bows | +0.010 |
clock | +0.010 |
ABC | +0.010 |
statues | +0.010 |
Neg logit contributions | |
bed | -0.008 |
ged | -0.007 |
aroo | -0.006 |
inn | -0.006 |
ging | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
clock | +0.022 |
works | +0.021 |
numbers | +0.020 |
bows | +0.020 |
ABC | +0.020 |
Neg logit contributions | |
bed | -0.025 |
aroo | -0.022 |
ged | -0.021 |
ging | -0.021 |
bly | -0.020 |
Token | three |
Token ID | 1115 |
Feature activation | +9.62e-01 |
Pos logit contributions | |
bed | +0.005 |
ged | +0.005 |
aroo | +0.005 |
ging | +0.005 |
bly | +0.004 |
Neg logit contributions | |
clock | -0.002 |
works | -0.002 |
ABC | -0.002 |
library | -0.002 |
numbers | -0.002 |
Token | years |
Token ID | 812 |
Feature activation | +6.43e+00 |
Pos logit contributions | |
works | +0.031 |
clock | +0.031 |
bows | +0.029 |
ABC | +0.028 |
numbers | +0.028 |
Neg logit contributions | |
bed | -0.033 |
aroo | -0.030 |
ging | -0.029 |
ged | -0.029 |
bly | -0.028 |
Token | old |
Token ID | 1468 |
Feature activation | +7.49e-01 |
Pos logit contributions | |
works | +0.173 |
clock | +0.173 |
bows | +0.162 |
ABC | +0.157 |
numbers | +0.156 |
Neg logit contributions | |
bed | -0.250 |
aroo | -0.237 |
ging | -0.226 |
ged | -0.223 |
bly | -0.219 |
Token | and |
Token ID | 290 |
Feature activation | +5.89e-01 |
Pos logit contributions | |
works | +0.029 |
clock | +0.028 |
ABC | +0.027 |
bows | +0.026 |
restaurants | +0.026 |
Neg logit contributions | |
bed | -0.022 |
aroo | -0.018 |
ged | -0.018 |
ging | -0.018 |
bly | -0.016 |
Token | he |
Token ID | 339 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
clock | +0.021 |
works | +0.020 |
bows | +0.020 |
ABC | +0.019 |
numbers | +0.019 |
Neg logit contributions | |
bed | -0.019 |
aroo | -0.017 |
bly | -0.016 |
ged | -0.016 |
ging | -0.015 |
Token | really |
Token ID | 1107 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
clock | +0.006 |
works | +0.005 |
numbers | +0.005 |
bows | +0.005 |
ABC | +0.005 |
Neg logit contributions | |
bed | -0.005 |
aroo | -0.005 |
ged | -0.004 |
bly | -0.004 |
ging | -0.004 |
Token | loved |
Token ID | 6151 |
Feature activation | +5.48e-01 |
Pos logit contributions | |
clock | +0.048 |
restaurants | +0.046 |
numbers | +0.045 |
tours | +0.045 |
works | +0.045 |
Neg logit contributions | |
bed | -0.037 |
aroo | -0.033 |
ged | -0.031 |
bly | -0.030 |
ging | -0.029 |
Token | Lucy |
Token ID | 22162 |
Feature activation | +8.87e-01 |
Pos logit contributions | |
works | +0.023 |
clock | +0.023 |
flavors | +0.021 |
numbers | +0.021 |
ABC | +0.021 |
Neg logit contributions | |
bed | -0.019 |
aroo | -0.017 |
ged | -0.015 |
ging | -0.015 |
bly | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
works | +0.027 |
clock | +0.027 |
ABC | +0.025 |
numbers | +0.025 |
bows | +0.024 |
Neg logit contributions | |
bed | -0.033 |
aroo | -0.030 |
ging | -0.029 |
ged | -0.029 |
bly | -0.028 |
Token | Lucy |
Token ID | 22162 |
Feature activation | +6.06e-01 |
Pos logit contributions | |
works | +0.012 |
clock | +0.012 |
ABC | +0.011 |
numbers | +0.011 |
flavors | +0.011 |
Neg logit contributions | |
bed | -0.014 |
aroo | -0.012 |
ged | -0.011 |
oned | -0.011 |
bly | -0.011 |
Token | was |
Token ID | 373 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
clock | +0.020 |
works | +0.019 |
numbers | +0.018 |
ABC | +0.018 |
restaurants | +0.018 |
Neg logit contributions | |
bed | -0.021 |
aroo | -0.019 |
ged | -0.018 |
ging | -0.017 |
bly | -0.017 |
Token | 3 |
Token ID | 513 |
Feature activation | -5.29e-01 |
Pos logit contributions | |
bed | +0.008 |
aroo | +0.008 |
ged | +0.007 |
ging | +0.007 |
bly | +0.007 |
Neg logit contributions | |
works | -0.005 |
clock | -0.005 |
ABC | -0.005 |
numbers | -0.005 |
bows | -0.005 |
Token | years |
Token ID | 812 |
Feature activation | +6.43e+00 |
Pos logit contributions | |
bed | +0.019 |
aroo | +0.018 |
ging | +0.017 |
ged | +0.017 |
bly | +0.017 |
Neg logit contributions | |
works | -0.016 |
clock | -0.016 |
ABC | -0.015 |
numbers | -0.015 |
bows | -0.015 |
Token | old |
Token ID | 1468 |
Feature activation | +5.76e-01 |
Pos logit contributions | |
works | +0.167 |
clock | +0.167 |
bows | +0.154 |
ABC | +0.151 |
numbers | +0.150 |
Neg logit contributions | |
bed | -0.258 |
aroo | -0.242 |
ging | -0.232 |
ged | -0.230 |
bly | -0.226 |
Token | and |
Token ID | 290 |
Feature activation | +5.56e-01 |
Pos logit contributions | |
works | +0.023 |
clock | +0.022 |
ABC | +0.021 |
restaurants | +0.021 |
bows | +0.020 |
Neg logit contributions | |
bed | -0.017 |
aroo | -0.014 |
ged | -0.014 |
ging | -0.013 |
bly | -0.013 |
Token | she |
Token ID | 673 |
Feature activation | +7.15e-01 |
Pos logit contributions | |
clock | +0.019 |
works | +0.018 |
bows | +0.018 |
ABC | +0.017 |
numbers | +0.017 |
Neg logit contributions | |
bed | -0.019 |
aroo | -0.017 |
bly | -0.016 |
ged | -0.016 |
ging | -0.016 |
Token | lived |
Token ID | 5615 |
Feature activation | -6.42e-01 |
Pos logit contributions | |
clock | +0.024 |
works | +0.023 |
numbers | +0.022 |
ABC | +0.022 |
bows | +0.021 |
Neg logit contributions | |
bed | -0.025 |
aroo | -0.022 |
ged | -0.021 |
ging | -0.021 |
bly | -0.021 |
Token | in |
Token ID | 287 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
bed | +0.018 |
aroo | +0.017 |
ged | +0.016 |
ging | +0.016 |
oned | +0.016 |
Neg logit contributions | |
works | -0.023 |
clock | -0.022 |
books | -0.022 |
numbers | -0.022 |
library | -0.021 |
Token | Tim |
Token ID | 5045 |
Feature activation | +6.01e-01 |
Pos logit contributions | |
works | +0.028 |
clock | +0.028 |
numbers | +0.026 |
ABC | +0.026 |
library | +0.026 |
Neg logit contributions | |
bed | -0.028 |
aroo | -0.025 |
ging | -0.024 |
ged | -0.024 |
bly | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | +9.44e-01 |
Pos logit contributions | |
works | +0.011 |
clock | +0.011 |
numbers | +0.010 |
ABC | +0.010 |
bows | +0.010 |
Neg logit contributions | |
bed | -0.029 |
aroo | -0.027 |
ging | -0.027 |
ged | -0.026 |
bly | -0.026 |
Token | He |
Token ID | 679 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
works | +0.035 |
clock | +0.034 |
ABC | +0.032 |
numbers | +0.032 |
bows | +0.032 |
Neg logit contributions | |
bed | -0.029 |
aroo | -0.026 |
ged | -0.025 |
ging | -0.025 |
bly | -0.024 |
Token | was |
Token ID | 373 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
works | +0.027 |
clock | +0.026 |
ABC | +0.024 |
numbers | +0.024 |
library | +0.024 |
Neg logit contributions | |
bed | -0.040 |
aroo | -0.037 |
ging | -0.037 |
ged | -0.036 |
bly | -0.036 |
Token | 3 |
Token ID | 513 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
bed | +0.006 |
ged | +0.006 |
aroo | +0.006 |
ging | +0.006 |
bly | +0.005 |
Neg logit contributions | |
clock | -0.003 |
works | -0.003 |
ABC | -0.003 |
numbers | -0.003 |
library | -0.003 |
Token | years |
Token ID | 812 |
Feature activation | +6.42e+00 |
Pos logit contributions | |
bed | +0.007 |
aroo | +0.006 |
ging | +0.006 |
ged | +0.006 |
bly | +0.006 |
Neg logit contributions | |
clock | -0.005 |
works | -0.005 |
ABC | -0.005 |
numbers | -0.005 |
bows | -0.005 |
Token | old |
Token ID | 1468 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
works | +0.162 |
clock | +0.161 |
bows | +0.148 |
ABC | +0.146 |
numbers | +0.145 |
Neg logit contributions | |
bed | -0.265 |
aroo | -0.248 |
ging | -0.238 |
ged | -0.237 |
bly | -0.234 |
Token | and |
Token ID | 290 |
Feature activation | +7.85e-01 |
Pos logit contributions | |
works | +0.039 |
clock | +0.039 |
ABC | +0.036 |
bows | +0.036 |
restaurants | +0.036 |
Neg logit contributions | |
bed | -0.029 |
aroo | -0.024 |
ged | -0.023 |
ging | -0.023 |
bly | -0.021 |
Token | very |
Token ID | 845 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
clock | +0.028 |
works | +0.027 |
bows | +0.026 |
ABC | +0.026 |
numbers | +0.025 |
Neg logit contributions | |
bed | -0.025 |
aroo | -0.023 |
bly | -0.022 |
ged | -0.021 |
ging | -0.021 |
Token | eager |
Token ID | 11069 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
clock | +0.110 |
bows | +0.106 |
works | +0.103 |
flavors | +0.102 |
numbers | +0.102 |
Neg logit contributions | |
bed | -0.081 |
aroo | -0.080 |
bly | -0.074 |
ging | -0.072 |
ged | -0.069 |
Token | to |
Token ID | 284 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
works | +0.034 |
bows | +0.030 |
total | +0.030 |
ven | +0.030 |
ABC | +0.029 |
Neg logit contributions | |
bed | -0.035 |
ged | -0.029 |
aroo | -0.028 |
ging | -0.027 |
under | -0.026 |
Token | Jack |
Token ID | 3619 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
works | +0.033 |
clock | +0.033 |
bows | +0.031 |
ABC | +0.031 |
numbers | +0.031 |
Neg logit contributions | |
bed | -0.026 |
aroo | -0.023 |
ged | -0.022 |
ging | -0.022 |
bly | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | +6.13e-01 |
Pos logit contributions | |
works | +0.034 |
clock | +0.034 |
ABC | +0.031 |
numbers | +0.031 |
bows | +0.031 |
Neg logit contributions | |
bed | -0.040 |
aroo | -0.037 |
ging | -0.035 |
ged | -0.035 |
bly | -0.035 |
Token | He |
Token ID | 679 |
Feature activation | +8.14e-01 |
Pos logit contributions | |
works | +0.022 |
clock | +0.022 |
ABC | +0.021 |
bows | +0.020 |
numbers | +0.020 |
Neg logit contributions | |
bed | -0.019 |
aroo | -0.017 |
ged | -0.016 |
ging | -0.016 |
bly | -0.016 |
Token | was |
Token ID | 373 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
works | +0.023 |
clock | +0.023 |
ABC | +0.022 |
numbers | +0.021 |
bows | +0.021 |
Neg logit contributions | |
bed | -0.031 |
aroo | -0.029 |
ging | -0.028 |
ged | -0.028 |
bly | -0.027 |
Token | three |
Token ID | 1115 |
Feature activation | +9.19e-01 |
Pos logit contributions | |
bed | +0.011 |
ged | +0.010 |
aroo | +0.010 |
ging | +0.010 |
bly | +0.010 |
Neg logit contributions | |
clock | -0.006 |
works | -0.005 |
ABC | -0.005 |
numbers | -0.005 |
library | -0.005 |
Token | years |
Token ID | 812 |
Feature activation | +6.42e+00 |
Pos logit contributions | |
works | +0.031 |
clock | +0.030 |
bows | +0.029 |
ABC | +0.028 |
numbers | +0.028 |
Neg logit contributions | |
bed | -0.031 |
aroo | -0.028 |
ging | -0.026 |
ged | -0.026 |
bly | -0.026 |
Token | old |
Token ID | 1468 |
Feature activation | +7.91e-01 |
Pos logit contributions | |
works | +0.178 |
clock | +0.177 |
bows | +0.168 |
ABC | +0.161 |
numbers | +0.160 |
Neg logit contributions | |
bed | -0.241 |
aroo | -0.231 |
ging | -0.217 |
ged | -0.213 |
bly | -0.212 |
Token | and |
Token ID | 290 |
Feature activation | +7.69e-01 |
Pos logit contributions | |
works | +0.031 |
clock | +0.031 |
bows | +0.028 |
restaurants | +0.028 |
ABC | +0.028 |
Neg logit contributions | |
bed | -0.022 |
aroo | -0.019 |
ged | -0.018 |
ging | -0.018 |
bly | -0.016 |
Token | he |
Token ID | 339 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
clock | +0.028 |
bows | +0.026 |
works | +0.026 |
ABC | +0.025 |
numbers | +0.025 |
Neg logit contributions | |
bed | -0.024 |
aroo | -0.022 |
bly | -0.021 |
ged | -0.020 |
ging | -0.020 |
Token | was |
Token ID | 373 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
clock | +0.011 |
works | +0.011 |
numbers | +0.010 |
bows | +0.010 |
ABC | +0.010 |
Neg logit contributions | |
bed | -0.010 |
aroo | -0.009 |
ged | -0.009 |
bly | -0.008 |
ging | -0.008 |
Token | very |
Token ID | 845 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
bed | +0.015 |
aroo | +0.014 |
ging | +0.013 |
ged | +0.013 |
bly | +0.013 |
Neg logit contributions | |
works | -0.011 |
clock | -0.011 |
bows | -0.010 |
numbers | -0.010 |
ABC | -0.010 |
Token | Daisy |
Token ID | 40355 |
Feature activation | +9.98e-01 |
Pos logit contributions | |
works | +0.026 |
clock | +0.026 |
numbers | +0.024 |
ABC | +0.024 |
flavors | +0.024 |
Neg logit contributions | |
bed | -0.022 |
aroo | -0.019 |
ged | -0.018 |
ging | -0.018 |
bly | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | +5.30e-01 |
Pos logit contributions | |
works | +0.029 |
clock | +0.028 |
ABC | +0.026 |
library | +0.026 |
numbers | +0.026 |
Neg logit contributions | |
bed | -0.038 |
aroo | -0.035 |
ging | -0.035 |
ged | -0.034 |
bly | -0.034 |
Token | Daisy |
Token ID | 40355 |
Feature activation | +5.54e-01 |
Pos logit contributions | |
works | +0.013 |
clock | +0.013 |
bows | +0.013 |
smells | +0.013 |
library | +0.013 |
Neg logit contributions | |
bed | -0.021 |
ging | -0.020 |
aroo | -0.020 |
ged | -0.020 |
bly | -0.020 |
Token | was |
Token ID | 373 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
clock | +0.018 |
works | +0.017 |
numbers | +0.016 |
ABC | +0.016 |
bows | +0.016 |
Neg logit contributions | |
bed | -0.020 |
aroo | -0.018 |
ged | -0.017 |
ging | -0.017 |
bly | -0.016 |
Token | three |
Token ID | 1115 |
Feature activation | +9.78e-01 |
Pos logit contributions | |
bed | +0.005 |
ged | +0.004 |
aroo | +0.004 |
ging | +0.004 |
bly | +0.004 |
Neg logit contributions | |
clock | -0.002 |
works | -0.002 |
ABC | -0.002 |
library | -0.002 |
numbers | -0.002 |
Token | years |
Token ID | 812 |
Feature activation | +6.41e+00 |
Pos logit contributions | |
works | +0.031 |
clock | +0.031 |
bows | +0.029 |
ABC | +0.028 |
numbers | +0.028 |
Neg logit contributions | |
bed | -0.034 |
aroo | -0.031 |
ging | -0.030 |
ged | -0.030 |
bly | -0.029 |
Token | old |
Token ID | 1468 |
Feature activation | +9.05e-01 |
Pos logit contributions | |
works | +0.174 |
clock | +0.173 |
bows | +0.159 |
ABC | +0.156 |
numbers | +0.155 |
Neg logit contributions | |
bed | -0.249 |
aroo | -0.236 |
ging | -0.224 |
ged | -0.221 |
bly | -0.219 |
Token | and |
Token ID | 290 |
Feature activation | +7.37e-01 |
Pos logit contributions | |
works | +0.036 |
clock | +0.035 |
ABC | +0.032 |
restaurants | +0.032 |
bows | +0.032 |
Neg logit contributions | |
bed | -0.026 |
aroo | -0.022 |
ged | -0.020 |
ging | -0.020 |
bly | -0.019 |
Token | she |
Token ID | 673 |
Feature activation | +8.54e-01 |
Pos logit contributions | |
clock | +0.026 |
works | +0.025 |
bows | +0.024 |
ABC | +0.023 |
numbers | +0.023 |
Neg logit contributions | |
bed | -0.025 |
aroo | -0.022 |
bly | -0.021 |
ged | -0.021 |
ging | -0.020 |
Token | was |
Token ID | 373 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
clock | +0.029 |
works | +0.028 |
numbers | +0.027 |
bows | +0.027 |
ABC | +0.027 |
Neg logit contributions | |
bed | -0.029 |
aroo | -0.026 |
ged | -0.025 |
bly | -0.024 |
ging | -0.024 |
Token | very |
Token ID | 845 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
bed | +0.011 |
aroo | +0.010 |
ging | +0.010 |
ged | +0.010 |
bly | +0.010 |
Neg logit contributions | |
works | -0.008 |
clock | -0.008 |
ABC | -0.007 |
numbers | -0.007 |
bows | -0.007 |
Token | Sophia |
Token ID | 39953 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
clock | +0.044 |
works | +0.043 |
bows | +0.043 |
ABC | +0.042 |
flavors | +0.042 |
Neg logit contributions | |
bed | -0.022 |
aroo | -0.019 |
ged | -0.018 |
bly | -0.017 |
ging | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | +6.84e-01 |
Pos logit contributions | |
clock | +0.065 |
works | +0.062 |
bows | +0.060 |
numbers | +0.059 |
ABC | +0.059 |
Neg logit contributions | |
bed | -0.054 |
aroo | -0.048 |
ged | -0.047 |
ging | -0.045 |
bly | -0.044 |
Token | Sophia |
Token ID | 39953 |
Feature activation | +9.53e-01 |
Pos logit contributions | |
works | +0.022 |
clock | +0.021 |
ABC | +0.020 |
bows | +0.019 |
jobs | +0.019 |
Neg logit contributions | |
bed | -0.024 |
ged | -0.020 |
aroo | -0.020 |
ging | -0.020 |
inn | -0.019 |
Token | was |
Token ID | 373 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
clock | +0.032 |
works | +0.030 |
bows | +0.029 |
numbers | +0.029 |
restaurants | +0.029 |
Neg logit contributions | |
bed | -0.033 |
aroo | -0.029 |
ged | -0.028 |
ging | -0.027 |
bly | -0.027 |
Token | three |
Token ID | 1115 |
Feature activation | +8.25e-01 |
Pos logit contributions | |
bed | +0.014 |
aroo | +0.012 |
ged | +0.012 |
ging | +0.012 |
bly | +0.012 |
Neg logit contributions | |
clock | -0.008 |
works | -0.008 |
ABC | -0.008 |
numbers | -0.008 |
bows | -0.008 |
Token | years |
Token ID | 812 |
Feature activation | +6.41e+00 |
Pos logit contributions | |
works | +0.027 |
clock | +0.027 |
bows | +0.026 |
numbers | +0.025 |
ABC | +0.025 |
Neg logit contributions | |
bed | -0.028 |
aroo | -0.025 |
ging | -0.024 |
ged | -0.024 |
bly | -0.023 |
Token | old |
Token ID | 1468 |
Feature activation | +9.10e-01 |
Pos logit contributions | |
works | +0.190 |
clock | +0.188 |
bows | +0.179 |
flavors | +0.175 |
ABC | +0.173 |
Neg logit contributions | |
bed | -0.223 |
aroo | -0.215 |
ging | -0.204 |
ged | -0.197 |
bly | -0.196 |
Token | and |
Token ID | 290 |
Feature activation | +7.52e-01 |
Pos logit contributions | |
works | +0.038 |
clock | +0.037 |
ABC | +0.035 |
restaurants | +0.035 |
numbers | +0.034 |
Neg logit contributions | |
bed | -0.024 |
aroo | -0.019 |
ged | -0.018 |
ging | -0.018 |
bly | -0.016 |
Token | loved |
Token ID | 6151 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
clock | +0.027 |
works | +0.026 |
bows | +0.025 |
ABC | +0.025 |
numbers | +0.024 |
Neg logit contributions | |
bed | -0.023 |
aroo | -0.022 |
bly | -0.021 |
ged | -0.019 |
ging | -0.019 |
Token | exploring |
Token ID | 13504 |
Feature activation | +3.15e+00 |
Pos logit contributions | |
works | +0.036 |
bows | +0.035 |
ven | +0.034 |
clock | +0.033 |
cases | +0.032 |
Neg logit contributions | |
bed | -0.030 |
ged | -0.024 |
aroo | -0.023 |
spraying | -0.023 |
under | -0.023 |
Token | the |
Token ID | 262 |
Feature activation | +5.86e-01 |
Pos logit contributions | |
clock | +0.116 |
works | +0.107 |
bows | +0.106 |
meanings | +0.104 |
ABC | +0.102 |
Neg logit contributions | |
bed | -0.097 |
ging | -0.083 |
ged | -0.081 |
aroo | -0.079 |
bly | -0.078 |
Token | Jake |
Token ID | 14757 |
Feature activation | +8.43e-01 |
Pos logit contributions | |
clock | +0.038 |
works | +0.038 |
bows | +0.036 |
ABC | +0.036 |
numbers | +0.036 |
Neg logit contributions | |
bed | -0.030 |
aroo | -0.027 |
ged | -0.025 |
ging | -0.025 |
bly | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | +5.17e-01 |
Pos logit contributions | |
works | +0.025 |
clock | +0.025 |
ABC | +0.023 |
numbers | +0.023 |
bows | +0.022 |
Neg logit contributions | |
bed | -0.032 |
aroo | -0.029 |
ging | -0.028 |
ged | -0.028 |
bly | -0.028 |
Token | He |
Token ID | 679 |
Feature activation | +7.20e-01 |
Pos logit contributions | |
bows | +0.018 |
statues | +0.018 |
works | +0.018 |
flavors | +0.018 |
paintings | +0.018 |
Neg logit contributions | |
bed | -0.014 |
inn | -0.011 |
ged | -0.010 |
bing | -0.009 |
under | -0.009 |
Token | was |
Token ID | 373 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
works | +0.021 |
clock | +0.021 |
ABC | +0.019 |
numbers | +0.019 |
bows | +0.019 |
Neg logit contributions | |
bed | -0.028 |
aroo | -0.025 |
ging | -0.025 |
ged | -0.025 |
bly | -0.024 |
Token | three |
Token ID | 1115 |
Feature activation | +9.24e-01 |
Pos logit contributions | |
bed | +0.011 |
aroo | +0.010 |
ged | +0.010 |
ging | +0.010 |
bly | +0.010 |
Neg logit contributions | |
clock | -0.006 |
works | -0.006 |
ABC | -0.005 |
numbers | -0.005 |
library | -0.005 |
Token | years |
Token ID | 812 |
Feature activation | +6.40e+00 |
Pos logit contributions | |
works | +0.029 |
clock | +0.029 |
bows | +0.028 |
ABC | +0.027 |
numbers | +0.027 |
Neg logit contributions | |
bed | -0.032 |
aroo | -0.029 |
ging | -0.028 |
ged | -0.028 |
bly | -0.027 |
Token | old |
Token ID | 1468 |
Feature activation | +7.77e-01 |
Pos logit contributions | |
works | +0.173 |
clock | +0.172 |
bows | +0.163 |
ABC | +0.157 |
numbers | +0.156 |
Neg logit contributions | |
bed | -0.248 |
aroo | -0.235 |
ging | -0.224 |
ged | -0.221 |
bly | -0.218 |
Token | and |
Token ID | 290 |
Feature activation | +7.13e-01 |
Pos logit contributions | |
works | +0.031 |
clock | +0.030 |
bows | +0.028 |
restaurants | +0.028 |
ABC | +0.028 |
Neg logit contributions | |
bed | -0.022 |
aroo | -0.018 |
ged | -0.018 |
ging | -0.018 |
bly | -0.016 |
Token | he |
Token ID | 339 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
clock | +0.025 |
works | +0.024 |
bows | +0.024 |
ABC | +0.023 |
restaurants | +0.023 |
Neg logit contributions | |
bed | -0.023 |
aroo | -0.021 |
bly | -0.020 |
ged | -0.019 |
ging | -0.019 |
Token | was |
Token ID | 373 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
clock | +0.009 |
works | +0.009 |
bows | +0.008 |
numbers | +0.008 |
ABC | +0.008 |
Neg logit contributions | |
bed | -0.009 |
aroo | -0.008 |
ged | -0.007 |
bly | -0.007 |
ging | -0.007 |
Token | always |
Token ID | 1464 |
Feature activation | +8.47e-01 |
Pos logit contributions | |
bed | +0.015 |
aroo | +0.013 |
ging | +0.013 |
ged | +0.013 |
bly | +0.013 |
Neg logit contributions | |
works | -0.010 |
clock | -0.010 |
bows | -0.010 |
numbers | -0.009 |
ABC | -0.009 |
Token | Molly |
Token ID | 30236 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
works | +0.040 |
clock | +0.040 |
ABC | +0.038 |
numbers | +0.037 |
bows | +0.037 |
Neg logit contributions | |
bed | -0.043 |
aroo | -0.039 |
ging | -0.038 |
ged | -0.038 |
bly | -0.037 |
Token | . |
Token ID | 13 |
Feature activation | +7.55e-01 |
Pos logit contributions | |
works | +0.055 |
clock | +0.055 |
ABC | +0.051 |
numbers | +0.051 |
bows | +0.051 |
Neg logit contributions | |
bed | -0.073 |
aroo | -0.067 |
ging | -0.066 |
ged | -0.065 |
bly | -0.064 |
Token | She |
Token ID | 1375 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
clock | +0.014 |
works | +0.014 |
library | +0.013 |
smells | +0.013 |
looks | +0.013 |
Neg logit contributions | |
aroo | -0.035 |
bed | -0.035 |
ging | -0.034 |
ged | -0.034 |
bly | -0.033 |
Token | was |
Token ID | 373 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
works | +0.044 |
clock | +0.041 |
ABC | +0.040 |
looks | +0.039 |
library | +0.039 |
Neg logit contributions | |
bed | -0.072 |
ging | -0.067 |
aroo | -0.067 |
ged | -0.065 |
bly | -0.065 |
Token | 3 |
Token ID | 513 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
bed | +0.015 |
ged | +0.014 |
ging | +0.014 |
aroo | +0.014 |
bly | +0.013 |
Neg logit contributions | |
clock | -0.007 |
works | -0.007 |
ABC | -0.006 |
library | -0.006 |
numbers | -0.006 |
Token | years |
Token ID | 812 |
Feature activation | +6.40e+00 |
Pos logit contributions | |
bed | +0.009 |
aroo | +0.008 |
ging | +0.008 |
ged | +0.008 |
bly | +0.008 |
Neg logit contributions | |
clock | -0.007 |
works | -0.007 |
ABC | -0.007 |
numbers | -0.007 |
bows | -0.006 |
Token | old |
Token ID | 1468 |
Feature activation | +8.86e-01 |
Pos logit contributions | |
works | +0.155 |
clock | +0.154 |
ABC | +0.139 |
numbers | +0.139 |
bows | +0.139 |
Neg logit contributions | |
bed | -0.274 |
aroo | -0.253 |
ging | -0.246 |
ged | -0.245 |
bly | -0.241 |
Token | and |
Token ID | 290 |
Feature activation | +6.72e-01 |
Pos logit contributions | |
works | +0.035 |
clock | +0.034 |
ABC | +0.032 |
restaurants | +0.032 |
numbers | +0.032 |
Neg logit contributions | |
bed | -0.025 |
aroo | -0.021 |
ged | -0.020 |
ging | -0.020 |
bly | -0.018 |
Token | loved |
Token ID | 6151 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
clock | +0.022 |
works | +0.022 |
bows | +0.021 |
ABC | +0.020 |
numbers | +0.020 |
Neg logit contributions | |
bed | -0.023 |
aroo | -0.021 |
bly | -0.020 |
ged | -0.020 |
ging | -0.020 |
Token | to |
Token ID | 284 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
works | +0.038 |
bows | +0.036 |
clock | +0.036 |
ven | +0.034 |
pays | +0.034 |
Neg logit contributions | |
bed | -0.034 |
ged | -0.028 |
aroo | -0.027 |
ging | -0.026 |
spraying | -0.026 |
Token | explore |
Token ID | 7301 |
Feature activation | +2.77e+00 |
Pos logit contributions | |
clock | +0.079 |
works | +0.075 |
bows | +0.072 |
aris | +0.070 |
meanings | +0.068 |
Neg logit contributions | |
bed | -0.074 |
aroo | -0.063 |
bly | -0.059 |
ged | -0.058 |
swat | -0.056 |
Token | Max |
Token ID | 5436 |
Feature activation | -9.16e-01 |
Pos logit contributions | |
works | +0.015 |
clock | +0.015 |
numbers | +0.014 |
ABC | +0.014 |
bows | +0.013 |
Neg logit contributions | |
bed | -0.013 |
aroo | -0.011 |
ging | -0.011 |
ged | -0.011 |
bly | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
bed | +0.036 |
aroo | +0.034 |
ging | +0.033 |
bly | +0.033 |
ged | +0.032 |
Neg logit contributions | |
works | -0.025 |
clock | -0.024 |
library | -0.023 |
looks | -0.022 |
numbers | -0.022 |
Token | Max |
Token ID | 5436 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
bed | +0.003 |
ged | +0.002 |
aroo | +0.002 |
ging | +0.002 |
bly | +0.002 |
Neg logit contributions | |
clock | -0.005 |
works | -0.005 |
statues | -0.005 |
paintings | -0.005 |
flavors | -0.005 |
Token | had |
Token ID | 550 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
bed | +0.043 |
aroo | +0.038 |
ged | +0.037 |
ging | +0.037 |
bly | +0.036 |
Neg logit contributions | |
clock | -0.037 |
works | -0.036 |
numbers | -0.034 |
ABC | -0.034 |
bows | -0.034 |
Token | a |
Token ID | 257 |
Feature activation | -6.99e-01 |
Pos logit contributions | |
bed | +0.007 |
aroo | +0.006 |
ging | +0.006 |
ged | +0.006 |
bly | +0.006 |
Neg logit contributions | |
clock | -0.003 |
works | -0.003 |
numbers | -0.003 |
ABC | -0.003 |
library | -0.003 |
Token | fle |
Token ID | 5104 |
Feature activation | -5.64e+00 |
Pos logit contributions | |
bed | +0.031 |
aroo | +0.029 |
ging | +0.028 |
ged | +0.028 |
bly | +0.028 |
Neg logit contributions | |
works | -0.016 |
clock | -0.016 |
ABC | -0.014 |
numbers | -0.014 |
library | -0.014 |
Token | a |
Token ID | 64 |
Feature activation | -3.07e+00 |
Pos logit contributions | |
bed | +0.224 |
oned | +0.220 |
bing | +0.217 |
ging | +0.208 |
swat | +0.204 |
Neg logit contributions | |
bows | -0.115 |
names | -0.113 |
books | -0.110 |
aris | -0.106 |
works | -0.102 |
Token | on |
Token ID | 319 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
bed | +0.080 |
bly | +0.076 |
bled | +0.073 |
ging | +0.072 |
aroo | +0.072 |
Neg logit contributions | |
books | -0.118 |
library | -0.117 |
works | -0.117 |
clock | -0.113 |
ABC | -0.113 |
Token | his |
Token ID | 465 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
bed | +0.074 |
ging | +0.069 |
aroo | +0.069 |
ged | +0.068 |
bly | +0.067 |
Neg logit contributions | |
works | -0.054 |
clock | -0.054 |
numbers | -0.052 |
ABC | -0.052 |
library | -0.052 |
Token | back |
Token ID | 736 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
bed | +0.044 |
ging | +0.044 |
bly | +0.044 |
ged | +0.043 |
aroo | +0.042 |
Neg logit contributions | |
clock | -0.034 |
ABC | -0.032 |
library | -0.032 |
books | -0.032 |
numbers | -0.031 |
Token | that |
Token ID | 326 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
bed | +0.049 |
ging | +0.048 |
bly | +0.048 |
ged | +0.047 |
bled | +0.046 |
Neg logit contributions | |
clock | -0.031 |
library | -0.031 |
works | -0.030 |
books | -0.029 |
restaurants | -0.028 |
Token | his |
Token ID | 465 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
works | +0.029 |
clock | +0.026 |
smells | +0.025 |
restaurants | +0.025 |
numbers | +0.025 |
Neg logit contributions | |
bed | -0.050 |
ging | -0.047 |
ged | -0.047 |
bly | -0.045 |
bled | -0.045 |
Token | friends |
Token ID | 2460 |
Feature activation | -5.29e-01 |
Pos logit contributions | |
bed | +0.013 |
aroo | +0.012 |
ging | +0.012 |
ged | +0.012 |
bly | +0.012 |
Neg logit contributions | |
works | -0.011 |
clock | -0.011 |
ABC | -0.010 |
numbers | -0.010 |
bows | -0.010 |
Token | when |
Token ID | 618 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
bed | +0.018 |
aroo | +0.017 |
ged | +0.016 |
ging | +0.016 |
bly | +0.016 |
Neg logit contributions | |
works | -0.017 |
clock | -0.016 |
ABC | -0.016 |
numbers | -0.016 |
bows | -0.016 |
Token | they |
Token ID | 484 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
bed | +0.036 |
aroo | +0.033 |
ged | +0.031 |
ging | +0.031 |
bly | +0.029 |
Neg logit contributions | |
clock | -0.043 |
works | -0.042 |
bows | -0.041 |
ABC | -0.039 |
numbers | -0.039 |
Token | had |
Token ID | 550 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
clock | +0.045 |
works | +0.042 |
ABC | +0.041 |
bows | +0.041 |
numbers | +0.040 |
Neg logit contributions | |
bed | -0.058 |
ged | -0.052 |
aroo | -0.052 |
ging | -0.050 |
bly | -0.048 |
Token | fle |
Token ID | 5104 |
Feature activation | -5.40e+00 |
Pos logit contributions | |
bed | +0.012 |
ged | +0.010 |
aroo | +0.010 |
ging | +0.010 |
bly | +0.009 |
Neg logit contributions | |
works | -0.008 |
clock | -0.008 |
ABC | -0.008 |
bows | -0.008 |
library | -0.008 |
Token | as |
Token ID | 292 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
bed | +0.230 |
aroo | +0.218 |
ging | +0.212 |
luckily | +0.205 |
ged | +0.205 |
Neg logit contributions | |
clock | -0.111 |
works | -0.110 |
bows | -0.105 |
aris | -0.099 |
names | -0.099 |
Token | . |
Token ID | 13 |
Feature activation | -7.02e-01 |
Pos logit contributions | |
bed | +0.052 |
aroo | +0.047 |
ging | +0.046 |
ged | +0.046 |
bly | +0.045 |
Neg logit contributions | |
works | -0.046 |
clock | -0.046 |
ABC | -0.043 |
numbers | -0.043 |
bows | -0.042 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +9.49e-01 |
Pos logit contributions | |
bed | +0.024 |
aroo | +0.021 |
ged | +0.021 |
ging | +0.020 |
bly | +0.020 |
Neg logit contributions | |
works | -0.023 |
clock | -0.023 |
numbers | -0.022 |
ABC | -0.022 |
bows | -0.021 |
Token | Once |
Token ID | 7454 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
works | +0.026 |
clock | +0.026 |
ABC | +0.024 |
numbers | +0.024 |
library | +0.024 |
Neg logit contributions | |
bed | -0.037 |
aroo | -0.035 |
ging | -0.035 |
ged | -0.034 |
bly | -0.034 |
Token | upon |
Token ID | 2402 |
Feature activation | +9.65e-01 |
Pos logit contributions | |
bed | +0.089 |
aroo | +0.082 |
ging | +0.081 |
bly | +0.081 |
ged | +0.080 |
Neg logit contributions | |
works | -0.032 |
clock | -0.031 |
ABC | -0.028 |
numbers | -0.027 |
library | -0.027 |
Token | time |
Token ID | 640 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
bed | +0.044 |
aroo | +0.043 |
ging | +0.041 |
bly | +0.040 |
ged | +0.039 |
Neg logit contributions | |
works | -0.025 |
clock | -0.024 |
numbers | -0.023 |
flavors | -0.023 |
books | -0.023 |
Token | with |
Token ID | 351 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
bed | +0.007 |
aroo | +0.007 |
bly | +0.007 |
ged | +0.007 |
ging | +0.006 |
Neg logit contributions | |
clock | -0.008 |
works | -0.008 |
numbers | -0.008 |
bows | -0.008 |
books | -0.008 |
Token | his |
Token ID | 465 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
bed | +0.042 |
aroo | +0.038 |
ging | +0.037 |
ged | +0.037 |
bly | +0.036 |
Neg logit contributions | |
clock | -0.036 |
works | -0.036 |
numbers | -0.034 |
ABC | -0.034 |
bows | -0.033 |
Token | new |
Token ID | 649 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
bed | +0.008 |
aroo | +0.008 |
ging | +0.007 |
ged | +0.007 |
bly | +0.007 |
Neg logit contributions | |
works | -0.006 |
clock | -0.006 |
ABC | -0.006 |
numbers | -0.006 |
bows | -0.006 |
Token | k |
Token ID | 479 |
Feature activation | -3.28e+00 |
Pos logit contributions | |
bed | +0.066 |
aroo | +0.060 |
ging | +0.058 |
ged | +0.058 |
bly | +0.056 |
Neg logit contributions | |
clock | -0.062 |
works | -0.062 |
ABC | -0.057 |
numbers | -0.057 |
bows | -0.057 |
Token | ang |
Token ID | 648 |
Feature activation | -5.37e+00 |
Pos logit contributions | |
bed | +0.060 |
ged | +0.046 |
ging | +0.045 |
aroo | +0.044 |
bly | +0.043 |
Neg logit contributions | |
clock | -0.152 |
works | -0.150 |
bows | -0.146 |
numbers | -0.145 |
ABC | -0.145 |
Token | aroo |
Token ID | 38049 |
Feature activation | -3.35e+00 |
Pos logit contributions | |
bed | +0.069 |
oned | +0.045 |
ged | +0.041 |
ging | +0.041 |
bly | +0.038 |
Neg logit contributions | |
ABC | -0.253 |
numbers | -0.253 |
works | -0.245 |
names | -0.241 |
looks | -0.239 |
Token | buddy |
Token ID | 24407 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
bed | +0.128 |
ged | +0.120 |
ging | +0.120 |
bly | +0.118 |
aroo | +0.117 |
Neg logit contributions | |
clock | -0.087 |
works | -0.085 |
numbers | -0.081 |
books | -0.080 |
library | -0.080 |
Token | . |
Token ID | 13 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
bed | +0.075 |
aroo | +0.069 |
ged | +0.068 |
ging | +0.067 |
bly | +0.067 |
Neg logit contributions | |
clock | -0.053 |
works | -0.052 |
numbers | -0.049 |
bows | -0.048 |
library | -0.047 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
bed | +0.033 |
aroo | +0.029 |
ged | +0.028 |
ging | +0.027 |
oned | +0.026 |
Neg logit contributions | |
works | -0.041 |
clock | -0.040 |
bows | -0.038 |
ABC | -0.038 |
statues | -0.038 |
Token | Once |
Token ID | 7454 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
works | +0.030 |
clock | +0.030 |
library | +0.027 |
numbers | +0.027 |
ABC | +0.027 |
Neg logit contributions | |
bed | -0.052 |
aroo | -0.048 |
ging | -0.047 |
bly | -0.047 |
ged | -0.046 |
Token | wanted |
Token ID | 2227 |
Feature activation | -3.68e-01 |
Pos logit contributions | |
bed | +0.001 |
aroo | +0.001 |
ged | +0.001 |
ging | +0.001 |
bly | +0.001 |
Neg logit contributions | |
clock | -0.001 |
numbers | -0.001 |
works | -0.001 |
bows | -0.001 |
restaurants | -0.001 |
Token | to |
Token ID | 284 |
Feature activation | +8.50e-01 |
Pos logit contributions | |
bed | +0.013 |
aroo | +0.012 |
ged | +0.011 |
ging | +0.011 |
bly | +0.010 |
Neg logit contributions | |
bows | -0.011 |
works | -0.011 |
clock | -0.010 |
meanings | -0.010 |
smells | -0.010 |
Token | find |
Token ID | 1064 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
clock | +0.026 |
bows | +0.026 |
works | +0.026 |
smells | +0.023 |
meanings | +0.023 |
Neg logit contributions | |
bed | -0.029 |
aroo | -0.028 |
bly | -0.024 |
swat | -0.024 |
oned | -0.024 |
Token | a |
Token ID | 257 |
Feature activation | -6.73e-01 |
Pos logit contributions | |
clock | +0.009 |
works | +0.009 |
bows | +0.008 |
ABC | +0.008 |
library | +0.008 |
Neg logit contributions | |
bed | -0.012 |
aroo | -0.011 |
ged | -0.011 |
ging | -0.011 |
bly | -0.010 |
Token | k |
Token ID | 479 |
Feature activation | -3.80e+00 |
Pos logit contributions | |
bed | +0.025 |
aroo | +0.024 |
ging | +0.022 |
bly | +0.022 |
ged | +0.021 |
Neg logit contributions | |
clock | -0.019 |
works | -0.018 |
bows | -0.018 |
numbers | -0.017 |
meanings | -0.017 |
Token | ang |
Token ID | 648 |
Feature activation | -5.37e+00 |
Pos logit contributions | |
bed | +0.166 |
ged | +0.148 |
oned | +0.148 |
ging | +0.147 |
bled | +0.145 |
Neg logit contributions | |
clock | -0.082 |
works | -0.077 |
library | -0.073 |
books | -0.071 |
looks | -0.070 |
Token | aroo |
Token ID | 38049 |
Feature activation | -3.82e+00 |
Pos logit contributions | |
bed | +0.097 |
oned | +0.066 |
bing | +0.058 |
ged | +0.058 |
ging | +0.056 |
Neg logit contributions | |
look | -0.237 |
looks | -0.235 |
works | -0.235 |
books | -0.233 |
numbers | -0.229 |
Token | . |
Token ID | 13 |
Feature activation | -6.54e-01 |
Pos logit contributions | |
bed | +0.153 |
bly | +0.142 |
ged | +0.141 |
ging | +0.140 |
bled | +0.139 |
Neg logit contributions | |
clock | -0.096 |
works | -0.096 |
library | -0.096 |
books | -0.092 |
looks | -0.089 |
Token | He |
Token ID | 679 |
Feature activation | -5.79e-01 |
Pos logit contributions | |
bed | +0.017 |
aroo | +0.014 |
ged | +0.012 |
inn | +0.012 |
oned | +0.012 |
Neg logit contributions | |
works | -0.025 |
bows | -0.025 |
statues | -0.025 |
restaurants | -0.024 |
Bible | -0.024 |
Token | looked |
Token ID | 3114 |
Feature activation | +7.34e-01 |
Pos logit contributions | |
bed | +0.023 |
aroo | +0.021 |
ged | +0.020 |
ging | +0.020 |
bly | +0.019 |
Neg logit contributions | |
clock | -0.016 |
works | -0.016 |
bows | -0.015 |
ABC | -0.015 |
numbers | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
works | +0.028 |
clock | +0.027 |
numbers | +0.026 |
looks | +0.026 |
smells | +0.026 |
Neg logit contributions | |
bed | -0.022 |
aroo | -0.019 |
ging | -0.018 |
bly | -0.018 |
ged | -0.018 |
Token | idea |
Token ID | 2126 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
works | +0.004 |
clock | +0.003 |
numbers | +0.003 |
ABC | +0.003 |
jobs | +0.003 |
Neg logit contributions | |
bed | -0.010 |
ged | -0.009 |
ging | -0.009 |
aroo | -0.009 |
bly | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -6.07e-01 |
Pos logit contributions | |
bed | +0.084 |
bly | +0.079 |
aroo | +0.077 |
ging | +0.077 |
bled | +0.073 |
Neg logit contributions | |
works | -0.047 |
clock | -0.042 |
numbers | -0.042 |
looks | -0.041 |
books | -0.040 |
Token | He |
Token ID | 679 |
Feature activation | -4.46e-01 |
Pos logit contributions | |
bed | +0.025 |
aroo | +0.023 |
ged | +0.022 |
ging | +0.022 |
bly | +0.021 |
Neg logit contributions | |
works | -0.016 |
clock | -0.016 |
ABC | -0.015 |
bows | -0.014 |
numbers | -0.014 |
Token | took |
Token ID | 1718 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
bed | +0.016 |
aroo | +0.015 |
ged | +0.014 |
ging | +0.014 |
bly | +0.014 |
Neg logit contributions | |
clock | -0.014 |
works | -0.013 |
ABC | -0.013 |
bows | -0.012 |
numbers | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | -5.69e-01 |
Pos logit contributions | |
bed | +0.065 |
ging | +0.062 |
ged | +0.061 |
aroo | +0.060 |
bly | +0.059 |
Neg logit contributions | |
works | -0.036 |
numbers | -0.034 |
clock | -0.034 |
books | -0.032 |
names | -0.032 |
Token | fle |
Token ID | 5104 |
Feature activation | -5.36e+00 |
Pos logit contributions | |
bed | +0.019 |
ged | +0.017 |
aroo | +0.016 |
ging | +0.016 |
bly | +0.016 |
Neg logit contributions | |
works | -0.020 |
clock | -0.019 |
ABC | -0.019 |
numbers | -0.019 |
library | -0.018 |
Token | a |
Token ID | 64 |
Feature activation | -3.29e+00 |
Pos logit contributions | |
bed | +0.215 |
ged | +0.198 |
ging | +0.198 |
luckily | +0.194 |
oned | +0.194 |
Neg logit contributions | |
names | -0.109 |
bows | -0.105 |
clock | -0.104 |
works | -0.102 |
ABC | -0.101 |
Token | to |
Token ID | 284 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
bed | +0.132 |
aroo | +0.122 |
bly | +0.121 |
ging | +0.119 |
ged | +0.119 |
Neg logit contributions | |
works | -0.084 |
clock | -0.082 |
numbers | -0.078 |
looks | -0.077 |
books | -0.077 |
Token | meet |
Token ID | 1826 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
works | +0.000 |
clock | +0.000 |
numbers | +0.000 |
restaurants | +0.000 |
ABC | +0.000 |
Neg logit contributions | |
bed | -0.001 |
ging | -0.001 |
ged | -0.001 |
bly | -0.001 |
aroo | -0.001 |
Token | other |
Token ID | 584 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
books | +0.008 |
works | +0.008 |
numbers | +0.008 |
names | +0.008 |
history | +0.008 |
Neg logit contributions | |
bed | -0.016 |
ging | -0.015 |
bly | -0.015 |
ged | -0.015 |
aroo | -0.015 |
Token | small |
Token ID | 1402 |
Feature activation | -9.34e-01 |
Pos logit contributions | |
works | +0.009 |
clock | +0.009 |
ABC | +0.009 |
numbers | +0.009 |
library | +0.009 |
Neg logit contributions | |
bed | -0.014 |
aroo | -0.012 |
ged | -0.012 |
ging | -0.012 |
bly | -0.012 |
Token | has |
Token ID | 468 |
Feature activation | -6.27e-01 |
Pos logit contributions | |
bed | +0.062 |
aroo | +0.058 |
ged | +0.056 |
ging | +0.056 |
bly | +0.055 |
Neg logit contributions | |
clock | -0.023 |
works | -0.021 |
ABC | -0.020 |
restaurants | -0.019 |
bows | -0.019 |
Token | made |
Token ID | 925 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
bed | +0.019 |
ged | +0.016 |
bly | +0.015 |
bled | +0.015 |
aroo | +0.015 |
Neg logit contributions | |
works | -0.021 |
clock | -0.020 |
restaurants | -0.020 |
aris | -0.020 |
ABC | -0.020 |
Token | a |
Token ID | 257 |
Feature activation | -8.09e-01 |
Pos logit contributions | |
bed | +0.007 |
aroo | +0.006 |
bly | +0.006 |
ging | +0.006 |
ged | +0.006 |
Neg logit contributions | |
works | -0.008 |
clock | -0.008 |
restaurants | -0.008 |
library | -0.008 |
ABC | -0.008 |
Token | big |
Token ID | 1263 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
bed | +0.037 |
aroo | +0.034 |
ging | +0.033 |
ged | +0.033 |
bly | +0.033 |
Neg logit contributions | |
works | -0.017 |
clock | -0.017 |
ABC | -0.016 |
numbers | -0.015 |
bows | -0.015 |
Token | sm |
Token ID | 895 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
bed | +0.061 |
aroo | +0.057 |
ged | +0.055 |
ging | +0.055 |
bly | +0.054 |
Neg logit contributions | |
works | -0.033 |
clock | -0.033 |
numbers | -0.030 |
ABC | -0.030 |
bows | -0.029 |
Token | udge |
Token ID | 12587 |
Feature activation | -5.36e+00 |
Pos logit contributions | |
bed | +0.007 |
aroo | +0.006 |
ged | +0.006 |
ging | +0.006 |
bly | +0.006 |
Neg logit contributions | |
clock | -0.005 |
works | -0.005 |
bows | -0.005 |
smells | -0.005 |
numbers | -0.005 |
Token | on |
Token ID | 319 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
bed | +0.189 |
aroo | +0.171 |
ged | +0.165 |
ging | +0.162 |
bly | +0.162 |
Neg logit contributions | |
works | -0.166 |
clock | -0.157 |
numbers | -0.156 |
smells | -0.153 |
looks | -0.152 |
Token | the |
Token ID | 262 |
Feature activation | -8.09e-01 |
Pos logit contributions | |
bed | +0.054 |
aroo | +0.049 |
ging | +0.047 |
ged | +0.047 |
bly | +0.046 |
Neg logit contributions | |
works | -0.053 |
clock | -0.053 |
numbers | -0.050 |
ABC | -0.049 |
bows | -0.049 |
Token | rainbow |
Token ID | 27223 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
bed | +0.032 |
aroo | +0.029 |
ged | +0.029 |
ging | +0.029 |
bly | +0.028 |
Neg logit contributions | |
clock | -0.023 |
works | -0.022 |
numbers | -0.021 |
ABC | -0.021 |
library | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
clock | +0.004 |
works | +0.004 |
numbers | +0.004 |
ABC | +0.004 |
bows | +0.004 |
Neg logit contributions | |
bed | -0.005 |
aroo | -0.004 |
ging | -0.004 |
ged | -0.004 |
bly | -0.004 |
Token | She |
Token ID | 1375 |
Feature activation | +8.60e-01 |
Pos logit contributions | |
works | +0.011 |
clock | +0.011 |
bows | +0.010 |
restaurants | +0.010 |
flavors | +0.010 |
Neg logit contributions | |
bed | -0.015 |
aroo | -0.014 |
ged | -0.013 |
ging | -0.013 |
bly | -0.012 |
Token | you |
Token ID | 345 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
works | +0.014 |
clock | +0.014 |
numbers | +0.013 |
ABC | +0.013 |
library | +0.012 |
Neg logit contributions | |
bed | -0.022 |
ged | -0.020 |
aroo | -0.020 |
ging | -0.020 |
bly | -0.020 |
Token | ." |
Token ID | 526 |
Feature activation | +7.16e-01 |
Pos logit contributions | |
bed | +0.010 |
ged | +0.009 |
aroo | +0.009 |
ging | +0.009 |
bly | +0.009 |
Neg logit contributions | |
works | -0.008 |
clock | -0.007 |
ABC | -0.007 |
numbers | -0.007 |
bows | -0.007 |
Token | Spot |
Token ID | 15899 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
works | +0.023 |
clock | +0.023 |
numbers | +0.021 |
ABC | +0.021 |
bows | +0.021 |
Neg logit contributions | |
bed | -0.025 |
aroo | -0.023 |
ged | -0.022 |
ging | -0.022 |
bly | -0.021 |
Token | picked |
Token ID | 6497 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
bed | +0.040 |
aroo | +0.035 |
ged | +0.034 |
ging | +0.032 |
bly | +0.032 |
Neg logit contributions | |
clock | -0.034 |
works | -0.033 |
restaurants | -0.032 |
ABC | -0.031 |
numbers | -0.031 |
Token | the |
Token ID | 262 |
Feature activation | -8.49e-01 |
Pos logit contributions | |
bed | +0.012 |
bly | +0.011 |
aroo | +0.011 |
ging | +0.011 |
ged | +0.011 |
Neg logit contributions | |
works | -0.009 |
numbers | -0.008 |
looks | -0.008 |
smells | -0.008 |
ABC | -0.008 |
Token | fle |
Token ID | 5104 |
Feature activation | -5.30e+00 |
Pos logit contributions | |
bed | +0.029 |
ged | +0.026 |
ging | +0.026 |
bly | +0.026 |
aroo | +0.026 |
Neg logit contributions | |
works | -0.028 |
clock | -0.027 |
ABC | -0.026 |
numbers | -0.026 |
library | -0.025 |
Token | a |
Token ID | 64 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
bed | +0.197 |
ging | +0.189 |
ged | +0.189 |
oned | +0.185 |
luckily | +0.185 |
Neg logit contributions | |
bows | -0.111 |
names | -0.110 |
works | -0.106 |
ABC | -0.104 |
clock | -0.101 |
Token | off |
Token ID | 572 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
bed | +0.114 |
aroo | +0.107 |
ged | +0.105 |
bly | +0.105 |
ging | +0.104 |
Neg logit contributions | |
works | -0.097 |
looks | -0.093 |
clock | -0.093 |
smells | -0.091 |
numbers | -0.091 |
Token | the |
Token ID | 262 |
Feature activation | -7.00e-02 |
Pos logit contributions | |
bed | +0.078 |
bly | +0.071 |
ging | +0.071 |
ged | +0.069 |
aroo | +0.068 |
Neg logit contributions | |
works | -0.040 |
clock | -0.040 |
numbers | -0.040 |
books | -0.040 |
ABC | -0.038 |
Token | bird |
Token ID | 6512 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
bed | +0.003 |
ged | +0.003 |
ging | +0.003 |
bly | +0.003 |
dd | +0.003 |
Neg logit contributions | |
library | -0.002 |
ABC | -0.002 |
works | -0.002 |
numbers | -0.002 |
clock | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -6.32e-01 |
Pos logit contributions | |
bly | +0.098 |
ging | +0.098 |
bed | +0.096 |
aroo | +0.096 |
bled | +0.096 |
Neg logit contributions | |
clock | -0.048 |
works | -0.047 |
looks | -0.046 |
library | -0.043 |
books | -0.043 |
Token | y |
Token ID | 88 |
Feature activation | -4.23e-01 |
Pos logit contributions | |
clock | +0.039 |
works | +0.037 |
restaurants | +0.037 |
ABC | +0.037 |
library | +0.036 |
Neg logit contributions | |
bed | -0.035 |
aroo | -0.033 |
ging | -0.032 |
ged | -0.032 |
bly | -0.030 |
Token | was |
Token ID | 373 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
bed | +0.015 |
aroo | +0.014 |
ged | +0.013 |
ging | +0.013 |
bly | +0.012 |
Neg logit contributions | |
clock | -0.013 |
restaurants | -0.012 |
ABC | -0.012 |
works | -0.012 |
numbers | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
bed | +0.039 |
aroo | +0.036 |
ging | +0.034 |
bly | +0.034 |
ged | +0.034 |
Neg logit contributions | |
clock | -0.034 |
works | -0.034 |
ABC | -0.031 |
bows | -0.031 |
numbers | -0.031 |
Token | best |
Token ID | 1266 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
bed | +0.017 |
aroo | +0.017 |
ging | +0.016 |
bly | +0.016 |
ged | +0.015 |
Neg logit contributions | |
works | -0.015 |
clock | -0.015 |
bows | -0.014 |
smells | -0.014 |
ABC | -0.013 |
Token | k |
Token ID | 479 |
Feature activation | -3.66e+00 |
Pos logit contributions | |
bed | +0.045 |
aroo | +0.042 |
ging | +0.040 |
ged | +0.040 |
bly | +0.039 |
Neg logit contributions | |
clock | -0.034 |
works | -0.033 |
bows | -0.031 |
ABC | -0.031 |
numbers | -0.031 |
Token | ang |
Token ID | 648 |
Feature activation | -5.29e+00 |
Pos logit contributions | |
bed | +0.116 |
ging | +0.097 |
ged | +0.097 |
aroo | +0.094 |
bly | +0.093 |
Neg logit contributions | |
works | -0.129 |
clock | -0.127 |
bows | -0.119 |
numbers | -0.118 |
ABC | -0.118 |
Token | aroo |
Token ID | 38049 |
Feature activation | -4.11e+00 |
Pos logit contributions | |
bed | +0.061 |
ging | +0.029 |
ged | +0.028 |
oned | +0.027 |
bly | +0.021 |
Neg logit contributions | |
works | -0.286 |
clock | -0.278 |
numbers | -0.275 |
ABC | -0.275 |
looks | -0.270 |
Token | ever |
Token ID | 1683 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
bed | +0.158 |
ging | +0.141 |
ged | +0.140 |
aroo | +0.140 |
bly | +0.137 |
Neg logit contributions | |
works | -0.117 |
clock | -0.116 |
numbers | -0.106 |
bows | -0.106 |
ABC | -0.105 |
Token | !" |
Token ID | 2474 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
bed | +0.009 |
aroo | +0.008 |
ged | +0.008 |
ging | +0.008 |
bly | +0.008 |
Neg logit contributions | |
clock | -0.006 |
works | -0.006 |
ABC | -0.006 |
numbers | -0.005 |
library | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
clock | +0.005 |
looks | +0.005 |
numbers | +0.005 |
names | +0.005 |
works | +0.005 |
Neg logit contributions | |
ging | -0.016 |
bed | -0.016 |
bly | -0.016 |
ged | -0.015 |
aroo | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
ABC | +0.000 |
works | +0.000 |
clock | +0.000 |
history | +0.000 |
names | +0.000 |
Neg logit contributions | |
bed | -0.001 |
ging | -0.001 |
ged | -0.000 |
bly | -0.000 |
aroo | -0.000 |
Token | He |
Token ID | 679 |
Feature activation | -7.72e-01 |
Pos logit contributions | |
bed | +0.025 |
aroo | +0.023 |
ging | +0.023 |
ged | +0.023 |
bly | +0.022 |
Neg logit contributions | |
clock | -0.021 |
works | -0.021 |
numbers | -0.020 |
ABC | -0.019 |
looks | -0.019 |
Token | was |
Token ID | 373 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
bed | +0.030 |
aroo | +0.027 |
ging | +0.027 |
ged | +0.026 |
bly | +0.026 |
Neg logit contributions | |
works | -0.022 |
clock | -0.022 |
numbers | -0.020 |
ABC | -0.020 |
bows | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | -6.34e-01 |
Pos logit contributions | |
bed | +0.057 |
aroo | +0.052 |
ging | +0.050 |
ged | +0.050 |
bly | +0.049 |
Neg logit contributions | |
works | -0.048 |
clock | -0.048 |
ABC | -0.045 |
numbers | -0.045 |
bows | -0.044 |
Token | happiest |
Token ID | 49414 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
bed | +0.024 |
aroo | +0.023 |
ging | +0.022 |
bly | +0.021 |
ged | +0.021 |
Neg logit contributions | |
works | -0.018 |
clock | -0.018 |
bows | -0.016 |
ABC | -0.016 |
restaurants | -0.016 |
Token | k |
Token ID | 479 |
Feature activation | -3.22e+00 |
Pos logit contributions | |
bed | +0.037 |
ged | +0.032 |
aroo | +0.032 |
ging | +0.032 |
bly | +0.031 |
Neg logit contributions | |
works | -0.033 |
clock | -0.033 |
numbers | -0.031 |
ABC | -0.031 |
bows | -0.031 |
Token | ang |
Token ID | 648 |
Feature activation | -5.26e+00 |
Pos logit contributions | |
bed | +0.066 |
ged | +0.049 |
oned | +0.047 |
ging | +0.047 |
bly | +0.045 |
Neg logit contributions | |
works | -0.145 |
clock | -0.143 |
bows | -0.139 |
numbers | -0.136 |
library | -0.134 |
Token | aroo |
Token ID | 38049 |
Feature activation | -3.75e+00 |
Pos logit contributions | |
bed | +0.071 |
oned | +0.038 |
ged | +0.034 |
ging | +0.030 |
pered | +0.028 |
Neg logit contributions | |
works | -0.258 |
numbers | -0.253 |
clock | -0.249 |
ABC | -0.249 |
statues | -0.248 |
Token | in |
Token ID | 287 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
bed | +0.132 |
ged | +0.116 |
ging | +0.115 |
bly | +0.115 |
aroo | +0.114 |
Neg logit contributions | |
works | -0.115 |
clock | -0.111 |
looks | -0.106 |
numbers | -0.104 |
library | -0.103 |
Token | the |
Token ID | 262 |
Feature activation | +8.69e-01 |
Pos logit contributions | |
bed | +0.013 |
aroo | +0.012 |
ging | +0.012 |
ged | +0.012 |
bly | +0.011 |
Neg logit contributions | |
works | -0.008 |
clock | -0.007 |
numbers | -0.007 |
restaurants | -0.007 |
library | -0.007 |
Token | bush |
Token ID | 24484 |
Feature activation | +5.74e-01 |
Pos logit contributions | |
works | +0.022 |
clock | +0.021 |
ABC | +0.020 |
bows | +0.020 |
numbers | +0.020 |
Neg logit contributions | |
bed | -0.035 |
aroo | -0.032 |
ging | -0.031 |
ged | -0.030 |
bly | -0.030 |
Token | ! |
Token ID | 0 |
Feature activation | -9.15e-01 |
Pos logit contributions | |
works | +0.019 |
clock | +0.019 |
ABC | +0.017 |
numbers | +0.017 |
bows | +0.017 |
Neg logit contributions | |
bed | -0.019 |
aroo | -0.018 |
ging | -0.017 |
ged | -0.017 |
bly | -0.017 |
Token | One |
Token ID | 1881 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
bed | +0.043 |
aroo | +0.038 |
ged | +0.037 |
ging | +0.036 |
oned | +0.035 |
Neg logit contributions | |
works | -0.028 |
clock | -0.028 |
bows | -0.026 |
statues | -0.025 |
numbers | -0.025 |
Token | day |
Token ID | 1110 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
works | +0.030 |
clock | +0.030 |
library | +0.029 |
ABC | +0.028 |
books | +0.028 |
Neg logit contributions | |
bed | -0.050 |
ging | -0.045 |
ged | -0.045 |
bly | -0.044 |
aroo | -0.043 |
Token | , |
Token ID | 11 |
Feature activation | -9.43e-01 |
Pos logit contributions | |
bed | +0.077 |
aroo | +0.071 |
ging | +0.069 |
bly | +0.068 |
ged | +0.068 |
Neg logit contributions | |
works | -0.058 |
clock | -0.057 |
numbers | -0.053 |
ABC | -0.053 |
bows | -0.052 |
Token | Max |
Token ID | 5436 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
bed | +0.032 |
aroo | +0.029 |
ging | +0.028 |
bly | +0.028 |
ged | +0.028 |
Neg logit contributions | |
works | -0.031 |
clock | -0.031 |
numbers | -0.030 |
ABC | -0.029 |
library | -0.029 |
Token | got |
Token ID | 1392 |
Feature activation | -4.63e-03 |
Pos logit contributions | |
bed | +0.074 |
aroo | +0.068 |
ging | +0.066 |
ged | +0.066 |
bly | +0.065 |
Neg logit contributions | |
works | -0.051 |
clock | -0.051 |
ABC | -0.046 |
numbers | -0.046 |
bows | -0.046 |
Token | fle |
Token ID | 5104 |
Feature activation | -5.25e+00 |
Pos logit contributions | |
bed | +0.000 |
aroo | +0.000 |
ging | +0.000 |
ged | +0.000 |
bly | +0.000 |
Neg logit contributions | |
clock | -0.000 |
works | -0.000 |
numbers | -0.000 |
ABC | -0.000 |
restaurants | -0.000 |
Token | as |
Token ID | 292 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
bed | +0.215 |
aroo | +0.200 |
ging | +0.191 |
ged | +0.189 |
luckily | +0.189 |
Neg logit contributions | |
clock | -0.117 |
works | -0.114 |
bows | -0.111 |
aris | -0.107 |
books | -0.102 |
Token | all |
Token ID | 477 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
bed | +0.070 |
aroo | +0.065 |
bly | +0.061 |
ging | +0.060 |
ged | +0.060 |
Neg logit contributions | |
works | -0.075 |
clock | -0.072 |
numbers | -0.069 |
ABC | -0.068 |
bows | -0.067 |
Token | over |
Token ID | 625 |
Feature activation | -8.70e-01 |
Pos logit contributions | |
works | +0.014 |
clock | +0.014 |
ABC | +0.013 |
numbers | +0.013 |
bows | +0.013 |
Neg logit contributions | |
bed | -0.011 |
aroo | -0.009 |
ging | -0.009 |
ged | -0.009 |
bly | -0.009 |
Token | his |
Token ID | 465 |
Feature activation | -6.00e-01 |
Pos logit contributions | |
bed | +0.034 |
aroo | +0.031 |
ging | +0.030 |
ged | +0.030 |
bly | +0.029 |
Neg logit contributions | |
clock | -0.025 |
works | -0.025 |
numbers | -0.023 |
ABC | -0.023 |
bows | -0.022 |
Token | fur |
Token ID | 9230 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
bed | +0.024 |
aroo | +0.022 |
ging | +0.021 |
ged | +0.021 |
bly | +0.021 |
Neg logit contributions | |
works | -0.017 |
clock | -0.017 |
ABC | -0.015 |
numbers | -0.015 |
bows | -0.015 |
Token | hurt |
Token ID | 5938 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
bed | +0.050 |
ged | +0.046 |
aroo | +0.046 |
ging | +0.045 |
bly | +0.044 |
Neg logit contributions | |
clock | -0.030 |
works | -0.028 |
numbers | -0.028 |
library | -0.027 |
ABC | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
bed | +0.068 |
aroo | +0.061 |
ging | +0.059 |
ged | +0.058 |
bly | +0.057 |
Neg logit contributions | |
works | -0.077 |
clock | -0.077 |
ABC | -0.072 |
bows | -0.072 |
numbers | -0.072 |
Token | It |
Token ID | 632 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
bed | +0.032 |
aroo | +0.028 |
ged | +0.027 |
ging | +0.025 |
oned | +0.024 |
Neg logit contributions | |
works | -0.041 |
clock | -0.040 |
bows | -0.039 |
ABC | -0.038 |
flavors | -0.038 |
Token | had |
Token ID | 550 |
Feature activation | -9.04e-01 |
Pos logit contributions | |
bed | +0.015 |
ging | +0.014 |
aroo | +0.013 |
bly | +0.013 |
ged | +0.013 |
Neg logit contributions | |
works | -0.008 |
clock | -0.007 |
looks | -0.007 |
smells | -0.007 |
numbers | -0.006 |
Token | a |
Token ID | 257 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
bed | +0.035 |
aroo | +0.031 |
ged | +0.031 |
ging | +0.030 |
bly | +0.030 |
Neg logit contributions | |
works | -0.026 |
clock | -0.026 |
bows | -0.024 |
ABC | -0.024 |
restaurants | -0.023 |
Token | thorn |
Token ID | 38999 |
Feature activation | -5.24e+00 |
Pos logit contributions | |
bed | +0.046 |
aroo | +0.043 |
ging | +0.042 |
ged | +0.042 |
bly | +0.041 |
Neg logit contributions | |
works | -0.026 |
clock | -0.026 |
numbers | -0.024 |
ABC | -0.024 |
bows | -0.023 |
Token | in |
Token ID | 287 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
aroo | +0.154 |
bed | +0.150 |
bly | +0.149 |
oned | +0.144 |
bled | +0.143 |
Neg logit contributions | |
looks | -0.161 |
works | -0.158 |
smells | -0.156 |
books | -0.154 |
bows | -0.151 |
Token | its |
Token ID | 663 |
Feature activation | -7.90e-01 |
Pos logit contributions | |
bed | +0.040 |
aroo | +0.035 |
ging | +0.034 |
ged | +0.034 |
bly | +0.033 |
Neg logit contributions | |
works | -0.059 |
clock | -0.058 |
numbers | -0.056 |
ABC | -0.055 |
smells | -0.055 |
Token | paw |
Token ID | 41827 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
bed | +0.028 |
aroo | +0.026 |
ging | +0.026 |
ged | +0.026 |
bly | +0.026 |
Neg logit contributions | |
clock | -0.024 |
works | -0.023 |
numbers | -0.022 |
looks | -0.022 |
ABC | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | -9.11e-01 |
Pos logit contributions | |
bed | +0.110 |
aroo | +0.103 |
ging | +0.101 |
bly | +0.100 |
ged | +0.100 |
Neg logit contributions | |
clock | -0.085 |
works | -0.083 |
numbers | -0.079 |
bows | -0.078 |
library | -0.077 |
Token |
|
Token ID | 198 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
bed | +0.031 |
aroo | +0.028 |
ged | +0.027 |
ging | +0.026 |
bly | +0.026 |
Neg logit contributions | |
works | -0.031 |
clock | -0.030 |
ABC | -0.028 |
numbers | -0.028 |
bows | -0.028 |
Token | she |
Token ID | 673 |
Feature activation | -9.28e-01 |
Pos logit contributions | |
bed | +0.018 |
aroo | +0.016 |
ging | +0.016 |
ged | +0.016 |
bly | +0.015 |
Neg logit contributions | |
works | -0.014 |
clock | -0.014 |
numbers | -0.013 |
ABC | -0.013 |
library | -0.013 |
Token | had |
Token ID | 550 |
Feature activation | -9.76e-01 |
Pos logit contributions | |
bed | +0.035 |
aroo | +0.031 |
ged | +0.030 |
ging | +0.029 |
bly | +0.029 |
Neg logit contributions | |
clock | -0.029 |
works | -0.028 |
restaurants | -0.026 |
ABC | -0.026 |
bows | -0.026 |
Token | never |
Token ID | 1239 |
Feature activation | -5.15e-01 |
Pos logit contributions | |
bed | +0.029 |
ged | +0.026 |
aroo | +0.024 |
ging | +0.024 |
luckily | +0.024 |
Neg logit contributions | |
works | -0.034 |
clock | -0.033 |
bows | -0.032 |
ABC | -0.032 |
restaurants | -0.030 |
Token | had |
Token ID | 550 |
Feature activation | -8.05e-01 |
Pos logit contributions | |
bed | +0.017 |
ged | +0.016 |
ging | +0.015 |
aroo | +0.015 |
bly | +0.014 |
Neg logit contributions | |
clock | -0.016 |
works | -0.015 |
ABC | -0.015 |
numbers | -0.015 |
bows | -0.015 |
Token | a |
Token ID | 257 |
Feature activation | -4.74e-01 |
Pos logit contributions | |
bed | +0.028 |
aroo | +0.026 |
ged | +0.025 |
ging | +0.024 |
bly | +0.024 |
Neg logit contributions | |
works | -0.025 |
clock | -0.025 |
bows | -0.023 |
ABC | -0.023 |
restaurants | -0.022 |
Token | lizard |
Token ID | 42406 |
Feature activation | -5.22e+00 |
Pos logit contributions | |
bed | +0.019 |
aroo | +0.017 |
ging | +0.017 |
ged | +0.017 |
bly | +0.017 |
Neg logit contributions | |
works | -0.013 |
clock | -0.013 |
ABC | -0.012 |
numbers | -0.012 |
library | -0.012 |
Token | before |
Token ID | 878 |
Feature activation | -6.36e-01 |
Pos logit contributions | |
bed | +0.177 |
bly | +0.163 |
ged | +0.161 |
aroo | +0.160 |
ging | +0.158 |
Neg logit contributions | |
library | -0.158 |
clock | -0.157 |
works | -0.156 |
books | -0.155 |
numbers | -0.149 |
Token | , |
Token ID | 11 |
Feature activation | -3.49e-02 |
Pos logit contributions | |
bed | +0.024 |
aroo | +0.022 |
ging | +0.021 |
bly | +0.021 |
ged | +0.021 |
Neg logit contributions | |
clock | -0.018 |
works | -0.018 |
numbers | -0.017 |
ABC | -0.017 |
library | -0.017 |
Token | but |
Token ID | 475 |
Feature activation | -2.76e+00 |
Pos logit contributions | |
bed | +0.001 |
aroo | +0.001 |
ging | +0.001 |
bly | +0.001 |
ged | +0.001 |
Neg logit contributions | |
works | -0.001 |
clock | -0.001 |
numbers | -0.001 |
library | -0.001 |
ABC | -0.001 |
Token | Lily |
Token ID | 20037 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
bed | +0.103 |
ging | +0.094 |
aroo | +0.093 |
ged | +0.091 |
bly | +0.090 |
Neg logit contributions | |
works | -0.083 |
clock | -0.081 |
numbers | -0.076 |
library | -0.076 |
looks | -0.075 |
Token | assured |
Token ID | 13933 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
bed | +0.044 |
aroo | +0.040 |
ged | +0.039 |
ging | +0.038 |
bly | +0.037 |
Neg logit contributions | |
clock | -0.037 |
works | -0.036 |
ABC | -0.034 |
numbers | -0.034 |
bows | -0.033 |
Token | to |
Token ID | 284 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
bed | +0.009 |
aroo | +0.008 |
bly | +0.008 |
ged | +0.008 |
ging | +0.008 |
Neg logit contributions | |
clock | -0.008 |
works | -0.008 |
numbers | -0.007 |
library | -0.007 |
ABC | -0.007 |
Token | find |
Token ID | 1064 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
works | +0.007 |
clock | +0.007 |
numbers | +0.006 |
restaurants | +0.006 |
library | +0.006 |
Neg logit contributions | |
bed | -0.011 |
aroo | -0.010 |
ging | -0.010 |
ged | -0.010 |
bly | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
bed | +0.014 |
ging | +0.012 |
ged | +0.012 |
aroo | +0.012 |
oned | +0.012 |
Neg logit contributions | |
works | -0.007 |
numbers | -0.007 |
books | -0.006 |
clock | -0.006 |
names | -0.006 |
Token | big |
Token ID | 1263 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
bed | +0.015 |
aroo | +0.014 |
ging | +0.013 |
ged | +0.013 |
bly | +0.013 |
Neg logit contributions | |
clock | -0.013 |
works | -0.013 |
ABC | -0.012 |
restaurants | -0.012 |
bows | -0.011 |
Token | k |
Token ID | 479 |
Feature activation | -3.22e+00 |
Pos logit contributions | |
bed | +0.043 |
aroo | +0.038 |
ging | +0.037 |
ged | +0.037 |
bly | +0.034 |
Neg logit contributions | |
clock | -0.037 |
works | -0.036 |
ABC | -0.034 |
bows | -0.033 |
restaurants | -0.033 |
Token | ang |
Token ID | 648 |
Feature activation | -5.21e+00 |
Pos logit contributions | |
bed | +0.079 |
ged | +0.068 |
ging | +0.066 |
oned | +0.062 |
bly | +0.062 |
Neg logit contributions | |
clock | -0.127 |
works | -0.125 |
bows | -0.121 |
library | -0.119 |
numbers | -0.119 |
Token | aroo |
Token ID | 38049 |
Feature activation | -3.54e+00 |
Pos logit contributions | |
bed | +0.079 |
oned | +0.054 |
ged | +0.053 |
bly | +0.049 |
ging | +0.049 |
Neg logit contributions | |
numbers | -0.232 |
works | -0.229 |
looks | -0.226 |
ABC | -0.224 |
statues | -0.220 |
Token | and |
Token ID | 290 |
Feature activation | -5.50e-01 |
Pos logit contributions | |
bed | +0.127 |
bly | +0.118 |
aroo | +0.118 |
ged | +0.118 |
ging | +0.117 |
Neg logit contributions | |
works | -0.104 |
clock | -0.101 |
looks | -0.097 |
numbers | -0.096 |
library | -0.096 |
Token | asked |
Token ID | 1965 |
Feature activation | -5.84e-01 |
Pos logit contributions | |
bed | +0.020 |
aroo | +0.018 |
ging | +0.018 |
ged | +0.017 |
bly | +0.017 |
Neg logit contributions | |
works | -0.017 |
clock | -0.017 |
numbers | -0.016 |
library | -0.015 |
looks | -0.015 |
Token | for |
Token ID | 329 |
Feature activation | -5.46e-01 |
Pos logit contributions | |
bed | +0.022 |
aroo | +0.020 |
ging | +0.019 |
bly | +0.019 |
ged | +0.019 |
Neg logit contributions | |
works | -0.017 |
clock | -0.017 |
numbers | -0.016 |
ABC | -0.016 |
restaurants | -0.015 |
Token | his |
Token ID | 465 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
bed | +0.022 |
ging | +0.020 |
aroo | +0.020 |
ged | +0.020 |
bly | +0.019 |
Neg logit contributions | |
works | -0.014 |
clock | -0.014 |
numbers | -0.013 |
ABC | -0.013 |
books | -0.013 |
Token | yes |
Token ID | 3763 |
Feature activation | +9.91e-01 |
Pos logit contributions | |
bed | +0.109 |
aroo | +0.100 |
ging | +0.099 |
bly | +0.096 |
ged | +0.096 |
Neg logit contributions | |
works | -0.072 |
clock | -0.072 |
numbers | -0.068 |
ABC | -0.067 |
bows | -0.067 |
Token | and |
Token ID | 290 |
Feature activation | -5.79e-01 |
Pos logit contributions | |
works | +0.033 |
clock | +0.031 |
restaurants | +0.030 |
library | +0.030 |
ABC | +0.030 |
Neg logit contributions | |
bed | -0.035 |
aroo | -0.031 |
ging | -0.030 |
ged | -0.029 |
bly | -0.029 |
Token | gave |
Token ID | 2921 |
Feature activation | -6.51e-01 |
Pos logit contributions | |
bed | +0.020 |
aroo | +0.018 |
ging | +0.018 |
ged | +0.018 |
bly | +0.018 |
Neg logit contributions | |
works | -0.018 |
clock | -0.018 |
numbers | -0.017 |
bows | -0.017 |
ABC | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | -9.55e-01 |
Pos logit contributions | |
bed | +0.025 |
ging | +0.023 |
aroo | +0.023 |
bly | +0.023 |
ged | +0.022 |
Neg logit contributions | |
works | -0.017 |
numbers | -0.017 |
clock | -0.016 |
books | -0.016 |
looks | -0.016 |
Token | k |
Token ID | 479 |
Feature activation | -3.42e+00 |
Pos logit contributions | |
bed | +0.031 |
ged | +0.027 |
ging | +0.027 |
aroo | +0.026 |
bly | +0.026 |
Neg logit contributions | |
works | -0.033 |
clock | -0.033 |
numbers | -0.032 |
ABC | -0.032 |
library | -0.031 |
Token | ang |
Token ID | 648 |
Feature activation | -5.19e+00 |
Pos logit contributions | |
bed | +0.135 |
ged | +0.120 |
ging | +0.120 |
oned | +0.116 |
bled | +0.116 |
Neg logit contributions | |
clock | -0.085 |
works | -0.081 |
bows | -0.080 |
numbers | -0.077 |
ABC | -0.077 |
Token | aroo |
Token ID | 38049 |
Feature activation | -4.22e+00 |
Pos logit contributions | |
bed | +0.065 |
ging | +0.035 |
oned | +0.034 |
ged | +0.032 |
bly | +0.031 |
Neg logit contributions | |
numbers | -0.256 |
works | -0.252 |
clock | -0.251 |
ABC | -0.251 |
looks | -0.249 |
Token | a |
Token ID | 257 |
Feature activation | -9.15e-01 |
Pos logit contributions | |
bed | +0.160 |
aroo | +0.147 |
ging | +0.141 |
ged | +0.141 |
bly | +0.138 |
Neg logit contributions | |
works | -0.123 |
clock | -0.123 |
ABC | -0.113 |
bows | -0.112 |
numbers | -0.111 |
Token | big |
Token ID | 1263 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
bed | +0.037 |
aroo | +0.035 |
ged | +0.033 |
ging | +0.033 |
bly | +0.033 |
Neg logit contributions | |
clock | -0.024 |
works | -0.024 |
bows | -0.021 |
ABC | -0.021 |
numbers | -0.021 |
Token | hug |
Token ID | 16225 |
Feature activation | +7.49e-01 |
Pos logit contributions | |
bed | +0.055 |
aroo | +0.050 |
ging | +0.049 |
ged | +0.049 |
bly | +0.048 |
Neg logit contributions | |
clock | -0.040 |
works | -0.039 |
ABC | -0.036 |
numbers | -0.036 |
bows | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | -7.25e-01 |
Pos logit contributions | |
clock | +0.023 |
works | +0.023 |
numbers | +0.021 |
bows | +0.021 |
ABC | +0.021 |
Neg logit contributions | |
bed | -0.027 |
aroo | -0.024 |
ging | -0.024 |
ged | -0.024 |
bly | -0.023 |
Token | She |
Token ID | 1375 |
Feature activation | +5.02e-01 |
Pos logit contributions | |
bed | +0.003 |
aroo | +0.003 |
ged | +0.003 |
ging | +0.003 |
bly | +0.003 |
Neg logit contributions | |
works | -0.002 |
clock | -0.002 |
bows | -0.002 |
ABC | -0.002 |
restaurants | -0.002 |
Token | made |
Token ID | 925 |
Feature activation | -5.91e-01 |
Pos logit contributions | |
works | +0.014 |
clock | +0.014 |
numbers | +0.013 |
ABC | +0.013 |
bows | +0.012 |
Neg logit contributions | |
bed | -0.020 |
aroo | -0.018 |
ging | -0.018 |
ged | -0.018 |
bly | -0.017 |
Token | a |
Token ID | 257 |
Feature activation | -8.76e-01 |
Pos logit contributions | |
bed | +0.021 |
ged | +0.017 |
ging | +0.017 |
bly | +0.017 |
aroo | +0.016 |
Neg logit contributions | |
clock | -0.019 |
works | -0.019 |
library | -0.019 |
restaurants | -0.018 |
bows | -0.018 |
Token | big |
Token ID | 1263 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
bed | +0.038 |
aroo | +0.035 |
ging | +0.034 |
ged | +0.034 |
bly | +0.033 |
Neg logit contributions | |
works | -0.021 |
clock | -0.021 |
bows | -0.019 |
ABC | -0.018 |
restaurants | -0.018 |
Token | green |
Token ID | 4077 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
bed | +0.058 |
aroo | +0.053 |
ged | +0.052 |
ging | +0.052 |
bly | +0.051 |
Neg logit contributions | |
works | -0.040 |
clock | -0.039 |
numbers | -0.036 |
ABC | -0.036 |
bows | -0.036 |
Token | dot |
Token ID | 16605 |
Feature activation | -5.18e+00 |
Pos logit contributions | |
bed | +0.076 |
aroo | +0.071 |
ging | +0.069 |
ged | +0.069 |
bly | +0.068 |
Neg logit contributions | |
works | -0.054 |
clock | -0.054 |
numbers | -0.051 |
ABC | -0.050 |
bows | -0.049 |
Token | and |
Token ID | 290 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
bed | +0.163 |
aroo | +0.150 |
ging | +0.147 |
ged | +0.146 |
bly | +0.142 |
Neg logit contributions | |
works | -0.174 |
clock | -0.170 |
numbers | -0.167 |
bows | -0.165 |
looks | -0.163 |
Token | a |
Token ID | 257 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
clock | +0.003 |
works | +0.003 |
ABC | +0.003 |
numbers | +0.003 |
bows | +0.003 |
Neg logit contributions | |
bed | -0.004 |
aroo | -0.004 |
ged | -0.004 |
ging | -0.004 |
bly | -0.004 |
Token | yellow |
Token ID | 7872 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
bed | +0.015 |
aroo | +0.014 |
ging | +0.014 |
ged | +0.014 |
bly | +0.014 |
Neg logit contributions | |
works | -0.009 |
clock | -0.009 |
ABC | -0.008 |
bows | -0.008 |
numbers | -0.008 |
Token | swirl |
Token ID | 42835 |
Feature activation | +5.07e-01 |
Pos logit contributions | |
bed | +0.040 |
aroo | +0.037 |
ging | +0.036 |
ged | +0.036 |
bly | +0.035 |
Neg logit contributions | |
works | -0.029 |
clock | -0.028 |
numbers | -0.027 |
ABC | -0.026 |
bows | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
works | +0.019 |
clock | +0.019 |
numbers | +0.017 |
bows | +0.017 |
ABC | +0.017 |
Neg logit contributions | |
bed | -0.015 |
aroo | -0.014 |
ging | -0.013 |
ged | -0.013 |
bly | -0.013 |
Token | He |
Token ID | 679 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
bed | +0.016 |
aroo | +0.015 |
ged | +0.014 |
ging | +0.013 |
oned | +0.013 |
Neg logit contributions | |
works | -0.015 |
clock | -0.014 |
bows | -0.014 |
ABC | -0.013 |
restaurants | -0.013 |
Token | had |
Token ID | 550 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
bed | +0.018 |
aroo | +0.017 |
ging | +0.017 |
bly | +0.016 |
ged | +0.016 |
Neg logit contributions | |
works | -0.012 |
clock | -0.012 |
numbers | -0.011 |
ABC | -0.011 |
looks | -0.011 |
Token | never |
Token ID | 1239 |
Feature activation | -4.03e-01 |
Pos logit contributions | |
bed | +0.031 |
ged | +0.026 |
aroo | +0.026 |
luckily | +0.024 |
ched | +0.024 |
Neg logit contributions | |
bows | -0.039 |
works | -0.039 |
clock | -0.037 |
ABC | -0.037 |
restaurants | -0.035 |
Token | seen |
Token ID | 1775 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
bed | +0.012 |
ged | +0.011 |
ging | +0.010 |
aroo | +0.010 |
behind | +0.009 |
Neg logit contributions | |
ABC | -0.014 |
clock | -0.014 |
works | -0.014 |
bows | -0.013 |
numbers | -0.013 |
Token | a |
Token ID | 257 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
bed | +0.013 |
aroo | +0.012 |
ging | +0.011 |
ged | +0.011 |
bly | +0.011 |
Neg logit contributions | |
works | -0.008 |
clock | -0.008 |
bows | -0.007 |
ABC | -0.007 |
numbers | -0.007 |
Token | fle |
Token ID | 5104 |
Feature activation | -5.17e+00 |
Pos logit contributions | |
bed | +0.014 |
aroo | +0.012 |
ging | +0.012 |
ged | +0.012 |
bly | +0.012 |
Neg logit contributions | |
clock | -0.011 |
works | -0.011 |
bows | -0.010 |
numbers | -0.010 |
ABC | -0.010 |
Token | a |
Token ID | 64 |
Feature activation | -3.06e+00 |
Pos logit contributions | |
bed | +0.193 |
ged | +0.179 |
ging | +0.174 |
ishly | +0.171 |
oned | +0.169 |
Neg logit contributions | |
bows | -0.118 |
clock | -0.111 |
library | -0.111 |
total | -0.110 |
ABC | -0.110 |
Token | before |
Token ID | 878 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
bed | +0.107 |
aroo | +0.100 |
bly | +0.100 |
ged | +0.098 |
ging | +0.095 |
Neg logit contributions | |
clock | -0.088 |
works | -0.087 |
library | -0.086 |
numbers | -0.086 |
ABC | -0.085 |
Token | and |
Token ID | 290 |
Feature activation | -4.93e-01 |
Pos logit contributions | |
bed | +0.018 |
aroo | +0.016 |
ging | +0.016 |
ged | +0.016 |
bly | +0.015 |
Neg logit contributions | |
works | -0.016 |
clock | -0.016 |
numbers | -0.015 |
ABC | -0.015 |
bows | -0.014 |
Token | he |
Token ID | 339 |
Feature activation | -6.00e-01 |
Pos logit contributions | |
bed | +0.018 |
aroo | +0.016 |
ged | +0.016 |
ging | +0.015 |
bly | +0.015 |
Neg logit contributions | |
clock | -0.015 |
works | -0.015 |
ABC | -0.014 |
bows | -0.014 |
numbers | -0.014 |
Token | wanted |
Token ID | 2227 |
Feature activation | -9.45e-01 |
Pos logit contributions | |
bed | +0.024 |
aroo | +0.022 |
ged | +0.021 |
ging | +0.021 |
bly | +0.020 |
Neg logit contributions | |
clock | -0.017 |
works | -0.017 |
ABC | -0.015 |
bows | -0.015 |
numbers | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | -6.09e-01 |
Pos logit contributions | |
bed | +0.049 |
aroo | +0.049 |
ging | +0.046 |
bly | +0.046 |
ged | +0.045 |
Neg logit contributions | |
works | -0.029 |
numbers | -0.027 |
clock | -0.027 |
looks | -0.026 |
books | -0.026 |
Token | Emily |
Token ID | 17608 |
Feature activation | -6.16e-01 |
Pos logit contributions | |
bed | +0.020 |
aroo | +0.019 |
ging | +0.018 |
ged | +0.018 |
bly | +0.017 |
Neg logit contributions | |
works | -0.020 |
clock | -0.020 |
numbers | -0.019 |
books | -0.019 |
ABC | -0.019 |
Token | saw |
Token ID | 2497 |
Feature activation | -7.58e-02 |
Pos logit contributions | |
bed | +0.022 |
ged | +0.019 |
aroo | +0.019 |
ging | +0.018 |
bly | +0.017 |
Neg logit contributions | |
clock | -0.019 |
works | -0.019 |
numbers | -0.018 |
ABC | -0.018 |
bows | -0.018 |
Token | a |
Token ID | 257 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
bed | +0.003 |
ging | +0.003 |
aroo | +0.003 |
ged | +0.003 |
bly | +0.003 |
Neg logit contributions | |
works | -0.002 |
numbers | -0.002 |
clock | -0.002 |
library | -0.002 |
books | -0.002 |
Token | do |
Token ID | 466 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
bed | +0.013 |
aroo | +0.012 |
ging | +0.011 |
ged | +0.011 |
bly | +0.011 |
Neg logit contributions | |
clock | -0.010 |
works | -0.010 |
bows | -0.009 |
ABC | -0.009 |
restaurants | -0.009 |
Token | ggy |
Token ID | 19970 |
Feature activation | -5.15e+00 |
Pos logit contributions | |
bed | +0.065 |
aroo | +0.056 |
ging | +0.055 |
ged | +0.054 |
bly | +0.053 |
Neg logit contributions | |
works | -0.104 |
clock | -0.103 |
ABC | -0.099 |
numbers | -0.098 |
bows | -0.098 |
Token | walking |
Token ID | 6155 |
Feature activation | +1.73e-02 |
Pos logit contributions | |
bed | +0.183 |
bly | +0.179 |
aroo | +0.174 |
ging | +0.168 |
bled | +0.166 |
Neg logit contributions | |
library | -0.150 |
works | -0.148 |
clock | -0.146 |
books | -0.141 |
numbers | -0.139 |
Token | up |
Token ID | 510 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
clock | +0.001 |
works | +0.001 |
numbers | +0.001 |
library | +0.001 |
bows | +0.001 |
Neg logit contributions | |
bed | -0.001 |
bly | -0.000 |
aroo | -0.000 |
ged | -0.000 |
ging | -0.000 |
Token | and |
Token ID | 290 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
bed | +0.070 |
aroo | +0.063 |
ged | +0.061 |
ging | +0.061 |
bly | +0.059 |
Neg logit contributions | |
works | -0.062 |
clock | -0.061 |
ABC | -0.058 |
bows | -0.057 |
numbers | -0.057 |
Token | down |
Token ID | 866 |
Feature activation | -5.58e-01 |
Pos logit contributions | |
clock | +0.008 |
works | +0.008 |
ABC | +0.007 |
bows | +0.007 |
numbers | +0.007 |
Neg logit contributions | |
bed | -0.008 |
aroo | -0.007 |
ged | -0.007 |
ging | -0.007 |
bly | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
bed | +0.017 |
aroo | +0.015 |
ging | +0.015 |
ged | +0.015 |
bly | +0.014 |
Neg logit contributions | |
works | -0.020 |
clock | -0.020 |
ABC | -0.019 |
bows | -0.019 |
numbers | -0.019 |
Token | ! |
Token ID | 0 |
Feature activation | -7.96e-01 |
Pos logit contributions | |
works | +0.008 |
clock | +0.008 |
ABC | +0.007 |
bows | +0.007 |
numbers | +0.007 |
Neg logit contributions | |
bed | -0.010 |
aroo | -0.009 |
ging | -0.009 |
ged | -0.009 |
bly | -0.009 |
Token | It |
Token ID | 632 |
Feature activation | -9.71e-01 |
Pos logit contributions | |
bed | +0.028 |
aroo | +0.025 |
ged | +0.024 |
ging | +0.024 |
bly | +0.023 |
Neg logit contributions | |
works | -0.026 |
clock | -0.025 |
ABC | -0.024 |
bows | -0.024 |
numbers | -0.024 |
Token | snatched |
Token ID | 43276 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
bed | +0.038 |
aroo | +0.035 |
ging | +0.034 |
ged | +0.034 |
bly | +0.033 |
Neg logit contributions | |
works | -0.027 |
clock | -0.027 |
numbers | -0.024 |
ABC | -0.024 |
bows | -0.024 |
Token | the |
Token ID | 262 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
bed | +0.068 |
aroo | +0.064 |
bly | +0.061 |
ging | +0.061 |
ged | +0.060 |
Neg logit contributions | |
works | -0.049 |
clock | -0.048 |
numbers | -0.046 |
smells | -0.043 |
looks | -0.043 |
Token | paper |
Token ID | 3348 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
bed | +0.063 |
ged | +0.056 |
bly | +0.056 |
ging | +0.055 |
aroo | +0.054 |
Neg logit contributions | |
works | -0.047 |
numbers | -0.046 |
books | -0.045 |
library | -0.045 |
looks | -0.044 |
Token | lizard |
Token ID | 42406 |
Feature activation | -5.15e+00 |
Pos logit contributions | |
bed | +0.054 |
aroo | +0.048 |
ged | +0.046 |
ging | +0.045 |
bly | +0.044 |
Neg logit contributions | |
works | -0.076 |
clock | -0.075 |
numbers | -0.071 |
ABC | -0.071 |
bows | -0.070 |
Token | away |
Token ID | 1497 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
bed | +0.152 |
aroo | +0.135 |
ged | +0.133 |
ging | +0.131 |
bly | +0.129 |
Neg logit contributions | |
works | -0.188 |
clock | -0.183 |
looks | -0.177 |
numbers | -0.175 |
smells | -0.175 |
Token | and |
Token ID | 290 |
Feature activation | -7.44e-01 |
Pos logit contributions | |
bed | +0.060 |
aroo | +0.055 |
ged | +0.053 |
ging | +0.053 |
bly | +0.051 |
Neg logit contributions | |
works | -0.059 |
clock | -0.059 |
numbers | -0.056 |
bows | -0.056 |
ABC | -0.054 |
Token | ran |
Token ID | 4966 |
Feature activation | -7.89e-01 |
Pos logit contributions | |
bed | +0.026 |
aroo | +0.024 |
ging | +0.023 |
ged | +0.023 |
bly | +0.023 |
Neg logit contributions | |
works | -0.023 |
clock | -0.023 |
numbers | -0.022 |
ABC | -0.021 |
bows | -0.021 |
Token | off |
Token ID | 572 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
bed | +0.023 |
aroo | +0.021 |
bly | +0.020 |
ging | +0.019 |
ged | +0.019 |
Neg logit contributions | |
clock | -0.029 |
works | -0.028 |
numbers | -0.027 |
books | -0.027 |
names | -0.026 |
Token | ! |
Token ID | 0 |
Feature activation | -8.46e-01 |
Pos logit contributions | |
bed | +0.052 |
aroo | +0.050 |
bly | +0.049 |
ging | +0.047 |
ged | +0.046 |
Neg logit contributions | |
clock | -0.029 |
works | -0.029 |
numbers | -0.029 |
books | -0.026 |
bows | -0.026 |
Token | is |
Token ID | 318 |
Feature activation | -7.67e-01 |
Pos logit contributions | |
bed | +0.030 |
aroo | +0.027 |
ged | +0.027 |
ging | +0.026 |
bly | +0.026 |
Neg logit contributions | |
clock | -0.022 |
works | -0.021 |
ABC | -0.021 |
bows | -0.020 |
restaurants | -0.020 |
Token | normal |
Token ID | 3487 |
Feature activation | -8.77e-01 |
Pos logit contributions | |
bed | +0.030 |
aroo | +0.028 |
ging | +0.027 |
ged | +0.027 |
bly | +0.027 |
Neg logit contributions | |
works | -0.021 |
clock | -0.021 |
numbers | -0.019 |
ABC | -0.019 |
bows | -0.019 |
Token | for |
Token ID | 329 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
bed | +0.029 |
aroo | +0.025 |
ging | +0.024 |
ged | +0.024 |
bly | +0.024 |
Neg logit contributions | |
clock | -0.029 |
works | -0.029 |
ABC | -0.028 |
restaurants | -0.028 |
library | -0.028 |
Token | old |
Token ID | 1468 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
bed | +0.046 |
aroo | +0.041 |
ging | +0.040 |
ged | +0.040 |
bly | +0.039 |
Neg logit contributions | |
works | -0.039 |
clock | -0.039 |
numbers | -0.036 |
ABC | -0.036 |
bows | -0.035 |
Token | k |
Token ID | 479 |
Feature activation | -3.76e+00 |
Pos logit contributions | |
bed | +0.075 |
aroo | +0.068 |
ging | +0.066 |
ged | +0.066 |
bly | +0.062 |
Neg logit contributions | |
clock | -0.055 |
works | -0.055 |
ABC | -0.051 |
bows | -0.050 |
numbers | -0.049 |
Token | ang |
Token ID | 648 |
Feature activation | -5.14e+00 |
Pos logit contributions | |
bed | +0.117 |
ged | +0.101 |
ging | +0.100 |
aroo | +0.100 |
bly | +0.098 |
Neg logit contributions | |
clock | -0.130 |
works | -0.126 |
bows | -0.121 |
numbers | -0.118 |
library | -0.118 |
Token | aro |
Token ID | 12022 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
bed | +0.113 |
ging | +0.088 |
ged | +0.087 |
bly | +0.085 |
aroo | +0.083 |
Neg logit contributions | |
works | -0.221 |
clock | -0.217 |
numbers | -0.213 |
ABC | -0.208 |
bows | -0.206 |
Token | os |
Token ID | 418 |
Feature activation | +7.58e-02 |
Pos logit contributions | |
bed | +0.048 |
aroo | +0.045 |
ged | +0.044 |
ging | +0.043 |
bly | +0.042 |
Neg logit contributions | |
works | -0.023 |
clock | -0.023 |
numbers | -0.021 |
ABC | -0.021 |
library | -0.020 |
Token | ." |
Token ID | 526 |
Feature activation | -7.85e-01 |
Pos logit contributions | |
clock | +0.003 |
works | +0.003 |
ABC | +0.002 |
numbers | +0.002 |
library | +0.002 |
Neg logit contributions | |
bed | -0.002 |
aroo | -0.002 |
ging | -0.002 |
ged | -0.002 |
bly | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
bed | +0.032 |
ging | +0.030 |
bly | +0.030 |
aroo | +0.029 |
ged | +0.029 |
Neg logit contributions | |
clock | -0.020 |
works | -0.018 |
library | -0.018 |
numbers | -0.018 |
ABC | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | -9.58e-01 |
Pos logit contributions | |
bed | +0.057 |
ging | +0.052 |
ged | +0.050 |
bly | +0.050 |
aroo | +0.050 |
Neg logit contributions | |
clock | -0.030 |
works | -0.029 |
library | -0.028 |
numbers | -0.028 |
ABC | -0.027 |
Token | to |
Token ID | 284 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
bed | +0.002 |
ged | +0.002 |
ging | +0.002 |
aroo | +0.002 |
then | +0.002 |
Neg logit contributions | |
works | -0.002 |
clock | -0.002 |
bows | -0.002 |
ABC | -0.002 |
total | -0.002 |
Token | take |
Token ID | 1011 |
Feature activation | -9.08e-01 |
Pos logit contributions | |
clock | +0.009 |
works | +0.009 |
bows | +0.008 |
ABC | +0.008 |
statues | +0.008 |
Neg logit contributions | |
bed | -0.010 |
aroo | -0.009 |
bly | -0.008 |
oned | -0.008 |
swat | -0.008 |
Token | a |
Token ID | 257 |
Feature activation | -7.74e-01 |
Pos logit contributions | |
bed | +0.027 |
ged | +0.025 |
ging | +0.024 |
aroo | +0.023 |
bly | +0.022 |
Neg logit contributions | |
clock | -0.034 |
works | -0.034 |
bows | -0.032 |
ABC | -0.031 |
library | -0.030 |
Token | pol |
Token ID | 755 |
Feature activation | -9.69e-01 |
Pos logit contributions | |
bed | +0.033 |
aroo | +0.031 |
ged | +0.030 |
ging | +0.030 |
bly | +0.029 |
Neg logit contributions | |
clock | -0.019 |
works | -0.018 |
bows | -0.017 |
numbers | -0.017 |
ABC | -0.016 |
Token | ka |
Token ID | 4914 |
Feature activation | -8.08e-01 |
Pos logit contributions | |
bed | +0.023 |
ging | +0.019 |
ged | +0.019 |
aroo | +0.019 |
bly | +0.019 |
Neg logit contributions | |
clock | -0.043 |
library | -0.042 |
ABC | -0.041 |
works | -0.041 |
restaurants | -0.041 |
Token | dot |
Token ID | 16605 |
Feature activation | -5.14e+00 |
Pos logit contributions | |
bed | +0.029 |
aroo | +0.027 |
ging | +0.026 |
ged | +0.026 |
bly | +0.025 |
Neg logit contributions | |
clock | -0.025 |
works | -0.025 |
ABC | -0.023 |
numbers | -0.023 |
bows | -0.023 |
Token | umbrella |
Token ID | 25510 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
bed | +0.167 |
ging | +0.151 |
bly | +0.150 |
aroo | +0.149 |
ged | +0.145 |
Neg logit contributions | |
clock | -0.158 |
books | -0.157 |
works | -0.156 |
bows | -0.153 |
numbers | -0.151 |
Token | . |
Token ID | 13 |
Feature activation | -6.39e-01 |
Pos logit contributions | |
bed | +0.011 |
aroo | +0.010 |
ged | +0.009 |
ging | +0.009 |
bly | +0.009 |
Neg logit contributions | |
works | -0.011 |
clock | -0.011 |
ABC | -0.011 |
numbers | -0.010 |
restaurants | -0.010 |
Token | |
Token ID | 220 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
bed | +0.015 |
ged | +0.012 |
oned | +0.012 |
aroo | +0.011 |
luckily | +0.009 |
Neg logit contributions | |
works | -0.028 |
clock | -0.025 |
jobs | -0.025 |
bows | -0.025 |
statues | -0.025 |
Token |
|
Token ID | 198 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
clock | +0.076 |
works | +0.076 |
ABC | +0.071 |
numbers | +0.070 |
bows | +0.069 |
Neg logit contributions | |
bed | -0.088 |
aroo | -0.080 |
ging | -0.078 |
ged | -0.078 |
bly | -0.076 |
Token |
|
Token ID | 198 |
Feature activation | -6.81e-01 |
Pos logit contributions | |
bed | +0.051 |
aroo | +0.046 |
ging | +0.046 |
bly | +0.046 |
ged | +0.045 |
Neg logit contributions | |
clock | -0.032 |
works | -0.032 |
ABC | -0.031 |
library | -0.030 |
numbers | -0.030 |
Token | to |
Token ID | 284 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
bed | +0.032 |
aroo | +0.027 |
ged | +0.026 |
bly | +0.025 |
ging | +0.025 |
Neg logit contributions | |
works | -0.029 |
bows | -0.029 |
clock | -0.027 |
library | -0.025 |
ABC | -0.025 |
Token | draw |
Token ID | 3197 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
works | +0.042 |
clock | +0.041 |
aris | +0.039 |
bows | +0.039 |
smells | +0.039 |
Neg logit contributions | |
bed | -0.042 |
aroo | -0.037 |
bly | -0.035 |
oned | -0.033 |
swat | -0.033 |
Token | lots |
Token ID | 6041 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
clock | +0.047 |
works | +0.046 |
ABC | +0.044 |
library | +0.043 |
restaurants | +0.043 |
Neg logit contributions | |
bed | -0.037 |
aroo | -0.031 |
bly | -0.031 |
ging | -0.030 |
ged | -0.030 |
Token | of |
Token ID | 286 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
clock | +0.103 |
works | +0.103 |
ABC | +0.097 |
bows | +0.096 |
library | +0.096 |
Neg logit contributions | |
bed | -0.045 |
aroo | -0.041 |
bly | -0.036 |
ging | -0.036 |
ged | -0.034 |
Token | pretty |
Token ID | 2495 |
Feature activation | +7.80e-01 |
Pos logit contributions | |
clock | +0.004 |
works | +0.004 |
bows | +0.004 |
ABC | +0.003 |
total | +0.003 |
Neg logit contributions | |
bed | -0.009 |
aroo | -0.008 |
ging | -0.008 |
ged | -0.007 |
bly | -0.007 |
Token | pictures |
Token ID | 5986 |
Feature activation | +3.24e+00 |
Pos logit contributions | |
clock | +0.019 |
works | +0.017 |
ABC | +0.016 |
Sale | +0.016 |
total | +0.016 |
Neg logit contributions | |
bed | -0.033 |
ged | -0.027 |
ging | -0.027 |
ling | -0.026 |
aroo | -0.026 |
Token | ." |
Token ID | 526 |
Feature activation | +8.44e-01 |
Pos logit contributions | |
works | +0.120 |
clock | +0.119 |
ABC | +0.113 |
meanings | +0.110 |
restaurants | +0.110 |
Neg logit contributions | |
bed | -0.095 |
aroo | -0.085 |
bly | -0.079 |
ging | -0.078 |
ged | -0.077 |
Token |
|
Token ID | 198 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
clock | +0.023 |
works | +0.021 |
ABC | +0.021 |
library | +0.021 |
bows | +0.020 |
Neg logit contributions | |
bed | -0.033 |
aroo | -0.032 |
ging | -0.032 |
bly | -0.032 |
ged | -0.030 |
Token |
|
Token ID | 198 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
bed | +0.018 |
ging | +0.017 |
bly | +0.017 |
aroo | +0.017 |
ged | +0.016 |
Neg logit contributions | |
ABC | -0.007 |
clock | -0.007 |
numbers | -0.007 |
works | -0.007 |
library | -0.007 |
Token | Her |
Token ID | 9360 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
bed | +0.005 |
aroo | +0.004 |
ged | +0.004 |
ging | +0.004 |
bly | +0.004 |
Neg logit contributions | |
clock | -0.004 |
works | -0.004 |
library | -0.004 |
ABC | -0.004 |
numbers | -0.004 |
Token | mom |
Token ID | 1995 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
clock | +0.049 |
works | +0.049 |
numbers | +0.047 |
ABC | +0.047 |
library | +0.044 |
Neg logit contributions | |
bed | -0.076 |
aroo | -0.071 |
ging | -0.070 |
ged | -0.069 |
bly | -0.069 |
Token | one |
Token ID | 530 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
bed | +0.005 |
aroo | +0.004 |
ged | +0.004 |
ging | +0.004 |
bly | +0.004 |
Neg logit contributions | |
works | -0.004 |
clock | -0.004 |
bows | -0.004 |
library | -0.004 |
ABC | -0.004 |
Token | home |
Token ID | 1363 |
Feature activation | +7.15e-01 |
Pos logit contributions | |
bed | +0.067 |
ging | +0.061 |
ged | +0.061 |
bly | +0.058 |
aroo | +0.057 |
Neg logit contributions | |
clock | -0.054 |
works | -0.052 |
library | -0.049 |
flavors | -0.049 |
looks | -0.049 |
Token | ?" |
Token ID | 1701 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
works | +0.021 |
clock | +0.021 |
ABC | +0.020 |
bows | +0.020 |
numbers | +0.020 |
Neg logit contributions | |
bed | -0.027 |
aroo | -0.024 |
ged | -0.023 |
ging | -0.023 |
bly | -0.023 |
Token |
|
Token ID | 198 |
Feature activation | +2.27e-02 |
Pos logit contributions | |
clock | +0.032 |
works | +0.030 |
ABC | +0.030 |
library | +0.030 |
numbers | +0.030 |
Neg logit contributions | |
bed | -0.051 |
aroo | -0.049 |
bly | -0.048 |
ging | -0.048 |
ged | -0.047 |
Token |
|
Token ID | 198 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
clock | +0.000 |
ABC | +0.000 |
grand | +0.000 |
numbers | +0.000 |
brushes | +0.000 |
Neg logit contributions | |
bed | -0.001 |
aroo | -0.001 |
ging | -0.001 |
bly | -0.001 |
ged | -0.001 |
Token | Mom |
Token ID | 29252 |
Feature activation | +3.22e+00 |
Pos logit contributions | |
clock | +0.003 |
brushes | +0.003 |
library | +0.003 |
numbers | +0.003 |
ABC | +0.003 |
Neg logit contributions | |
bed | -0.005 |
aroo | -0.005 |
ged | -0.005 |
ging | -0.005 |
bly | -0.005 |
Token | laughed |
Token ID | 13818 |
Feature activation | +5.07e-01 |
Pos logit contributions | |
clock | +0.101 |
works | +0.100 |
ABC | +0.093 |
bows | +0.093 |
restaurants | +0.093 |
Neg logit contributions | |
bed | -0.115 |
aroo | -0.104 |
ged | -0.101 |
ging | -0.099 |
bly | -0.097 |
Token | and |
Token ID | 290 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
clock | +0.012 |
works | +0.012 |
looks | +0.011 |
numbers | +0.011 |
books | +0.011 |
Neg logit contributions | |
aroo | -0.022 |
bed | -0.021 |
bly | -0.020 |
ging | -0.019 |
ged | -0.019 |
Token | said |
Token ID | 531 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
works | +0.051 |
clock | +0.049 |
numbers | +0.046 |
looks | +0.046 |
smells | +0.045 |
Neg logit contributions | |
bed | -0.065 |
aroo | -0.059 |
ging | -0.058 |
bly | -0.057 |
ged | -0.056 |
Token | , |
Token ID | 11 |
Feature activation | +7.22e-01 |
Pos logit contributions | |
works | +0.011 |
clock | +0.011 |
numbers | +0.011 |
ABC | +0.011 |
bows | +0.010 |
Neg logit contributions | |
bed | -0.015 |
aroo | -0.013 |
ging | -0.013 |
ged | -0.013 |
bly | -0.013 |
Token | " |
Token ID | 366 |
Feature activation | +8.99e-01 |
Pos logit contributions | |
works | +0.019 |
clock | +0.019 |
ABC | +0.017 |
numbers | +0.017 |
bows | +0.017 |
Neg logit contributions | |
bed | -0.030 |
aroo | -0.027 |
ging | -0.027 |
ged | -0.027 |
bly | -0.026 |
Token | We |
Token ID | 775 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
clock | +0.022 |
works | +0.020 |
ABC | +0.019 |
names | +0.019 |
library | +0.019 |
Neg logit contributions | |
bed | -0.032 |
ged | -0.031 |
ging | -0.030 |
aroo | -0.030 |
bly | -0.029 |
Token | can |
Token ID | 460 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
bed | +0.016 |
aroo | +0.015 |
ging | +0.015 |
ged | +0.015 |
bly | +0.014 |
Neg logit contributions | |
clock | -0.005 |
works | -0.005 |
ABC | -0.004 |
numbers | -0.004 |
bows | -0.004 |
Token | come |
Token ID | 1282 |
Feature activation | +9.57e-01 |
Pos logit contributions | |
works | +0.004 |
clock | +0.004 |
numbers | +0.003 |
ABC | +0.003 |
bows | +0.003 |
Neg logit contributions | |
bed | -0.006 |
aroo | -0.006 |
ged | -0.005 |
ging | -0.005 |
bly | -0.005 |
Token | back |
Token ID | 736 |
Feature activation | -2.24e-02 |
Pos logit contributions | |
works | +0.036 |
clock | +0.036 |
ABC | +0.034 |
bows | +0.034 |
numbers | +0.034 |
Neg logit contributions | |
bed | -0.028 |
aroo | -0.025 |
ging | -0.024 |
ged | -0.024 |
bly | -0.023 |
Token | before |
Token ID | 878 |
Feature activation | +7.66e-01 |
Pos logit contributions | |
bed | +0.001 |
aroo | +0.001 |
ged | +0.001 |
ging | +0.001 |
bly | +0.001 |
Neg logit contributions | |
works | -0.001 |
clock | -0.001 |
ABC | -0.001 |
bows | -0.001 |
numbers | -0.001 |
Token | mom |
Token ID | 1995 |
Feature activation | +3.96e+00 |
Pos logit contributions | |
works | +0.022 |
clock | +0.022 |
numbers | +0.020 |
ABC | +0.020 |
bows | +0.020 |
Neg logit contributions | |
bed | -0.030 |
aroo | -0.027 |
ging | -0.026 |
ged | -0.026 |
bly | -0.026 |
Token | sees |
Token ID | 7224 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
ABC | +0.107 |
clock | +0.107 |
meanings | +0.103 |
numbers | +0.102 |
statues | +0.102 |
Neg logit contributions | |
bed | -0.145 |
aroo | -0.134 |
ged | -0.133 |
ging | -0.129 |
oned | -0.122 |
Token | us |
Token ID | 514 |
Feature activation | +6.37e-01 |
Pos logit contributions | |
works | +0.044 |
clock | +0.044 |
numbers | +0.041 |
ABC | +0.041 |
bows | +0.040 |
Neg logit contributions | |
bed | -0.054 |
aroo | -0.049 |
ging | -0.048 |
ged | -0.048 |
bly | -0.046 |
Token | ." |
Token ID | 526 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
clock | +0.021 |
works | +0.021 |
ABC | +0.019 |
numbers | +0.019 |
bows | +0.019 |
Neg logit contributions | |
bed | -0.022 |
aroo | -0.019 |
ging | -0.019 |
ged | -0.019 |
bly | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | -4.81e-01 |
Pos logit contributions | |
bed | +0.004 |
bly | +0.004 |
ging | +0.004 |
aroo | +0.004 |
ged | +0.004 |
Neg logit contributions | |
clock | -0.003 |
works | -0.003 |
numbers | -0.003 |
ABC | -0.003 |
library | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
bed | +0.023 |
ging | +0.021 |
aroo | +0.021 |
ged | +0.021 |
bly | +0.020 |
Neg logit contributions | |
works | -0.009 |
clock | -0.009 |
looks | -0.008 |
books | -0.008 |
ABC | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -7.49e-01 |
Pos logit contributions | |
clock | +0.028 |
works | +0.028 |
ABC | +0.026 |
numbers | +0.026 |
bows | +0.026 |
Neg logit contributions | |
bed | -0.030 |
aroo | -0.027 |
ging | -0.026 |
ged | -0.026 |
bly | -0.025 |
Token |
|
Token ID | 198 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
bed | +0.033 |
bly | +0.031 |
ging | +0.031 |
aroo | +0.031 |
ged | +0.030 |
Neg logit contributions | |
clock | -0.016 |
works | -0.015 |
ABC | -0.015 |
numbers | -0.014 |
library | -0.014 |
Token | " |
Token ID | 1 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
bed | +0.013 |
aroo | +0.012 |
ged | +0.012 |
ging | +0.012 |
bly | +0.011 |
Neg logit contributions | |
clock | -0.012 |
works | -0.011 |
library | -0.011 |
numbers | -0.011 |
ABC | -0.011 |
Token | No |
Token ID | 2949 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
clock | +0.033 |
works | +0.032 |
numbers | +0.031 |
ABC | +0.030 |
library | +0.030 |
Neg logit contributions | |
bed | -0.040 |
aroo | -0.036 |
ging | -0.035 |
ged | -0.035 |
bly | -0.034 |
Token | , |
Token ID | 11 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
bed | +0.027 |
aroo | +0.025 |
ged | +0.023 |
ging | +0.022 |
luckily | +0.020 |
Neg logit contributions | |
clock | -0.046 |
bows | -0.043 |
works | -0.043 |
aris | -0.041 |
restaurants | -0.040 |
Token | mom |
Token ID | 1995 |
Feature activation | +3.15e+00 |
Pos logit contributions | |
clock | +0.012 |
works | +0.012 |
ABC | +0.011 |
bows | +0.011 |
numbers | +0.011 |
Neg logit contributions | |
bed | -0.015 |
aroo | -0.013 |
ging | -0.013 |
ged | -0.013 |
bly | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
ABC | +0.137 |
restaurants | +0.136 |
clock | +0.134 |
tours | +0.131 |
museums | +0.129 |
Neg logit contributions | |
bed | -0.067 |
aroo | -0.055 |
ged | -0.053 |
ging | -0.051 |
behind | -0.045 |
Token | I |
Token ID | 314 |
Feature activation | +8.02e-01 |
Pos logit contributions | |
clock | +0.006 |
works | +0.006 |
bows | +0.006 |
ABC | +0.006 |
flavors | +0.006 |
Neg logit contributions | |
bed | -0.007 |
aroo | -0.007 |
ged | -0.006 |
ging | -0.006 |
bly | -0.006 |
Token | want |
Token ID | 765 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
clock | +0.025 |
ABC | +0.022 |
bows | +0.022 |
statues | +0.022 |
numbers | +0.022 |
Neg logit contributions | |
bed | -0.029 |
ged | -0.027 |
aroo | -0.027 |
ging | -0.027 |
dd | -0.024 |
Token | to |
Token ID | 284 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
bed | +0.007 |
aroo | +0.006 |
ged | +0.006 |
ging | +0.006 |
bly | +0.006 |
Neg logit contributions | |
works | -0.006 |
bows | -0.006 |
clock | -0.006 |
ABC | -0.006 |
aris | -0.006 |
Token | go |
Token ID | 467 |
Feature activation | +2.94e-02 |
Pos logit contributions | |
works | +0.055 |
clock | +0.054 |
ABC | +0.050 |
bows | +0.049 |
numbers | +0.049 |
Neg logit contributions | |
bed | -0.066 |
aroo | -0.061 |
bly | -0.055 |
ged | -0.054 |
swat | -0.054 |
Token | you |
Token ID | 345 |
Feature activation | +6.87e-01 |
Pos logit contributions | |
clock | +0.024 |
works | +0.024 |
bows | +0.022 |
smells | +0.021 |
restaurants | +0.021 |
Neg logit contributions | |
bed | -0.024 |
aroo | -0.022 |
ged | -0.021 |
ging | -0.020 |
bly | -0.020 |
Token | understand |
Token ID | 1833 |
Feature activation | +6.06e-01 |
Pos logit contributions | |
clock | +0.020 |
works | +0.020 |
ABC | +0.019 |
numbers | +0.019 |
bows | +0.018 |
Neg logit contributions | |
bed | -0.026 |
aroo | -0.023 |
ging | -0.023 |
ged | -0.023 |
bly | -0.022 |
Token | ?" |
Token ID | 1701 |
Feature activation | +8.50e-01 |
Pos logit contributions | |
clock | +0.014 |
works | +0.014 |
ABC | +0.013 |
bows | +0.013 |
numbers | +0.013 |
Neg logit contributions | |
bed | -0.027 |
aroo | -0.024 |
ging | -0.024 |
ged | -0.024 |
bly | -0.023 |
Token |
|
Token ID | 198 |
Feature activation | -8.45e-02 |
Pos logit contributions | |
clock | +0.021 |
works | +0.020 |
ABC | +0.020 |
numbers | +0.019 |
library | +0.019 |
Neg logit contributions | |
bed | -0.037 |
ging | -0.034 |
bly | -0.034 |
ged | -0.033 |
aroo | -0.033 |
Token |
|
Token ID | 198 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
bed | +0.004 |
ging | +0.004 |
bly | +0.004 |
aroo | +0.004 |
ged | +0.004 |
Neg logit contributions | |
works | -0.002 |
clock | -0.002 |
ABC | -0.002 |
numbers | -0.002 |
library | -0.002 |
Token | S |
Token ID | 50 |
Feature activation | +3.31e+00 |
Pos logit contributions | |
clock | +0.000 |
works | +0.000 |
numbers | +0.000 |
library | +0.000 |
ABC | +0.000 |
Neg logit contributions | |
bed | -0.000 |
aroo | -0.000 |
ged | -0.000 |
ging | -0.000 |
bly | -0.000 |
Token | ara |
Token ID | 3301 |
Feature activation | +7.04e-01 |
Pos logit contributions | |
clock | +0.123 |
restaurants | +0.118 |
works | +0.116 |
packages | +0.115 |
ABC | +0.114 |
Neg logit contributions | |
bed | -0.090 |
aroo | -0.075 |
ged | -0.074 |
ging | -0.071 |
inn | -0.067 |
Token | and |
Token ID | 290 |
Feature activation | +7.20e-01 |
Pos logit contributions | |
clock | +0.020 |
works | +0.019 |
restaurants | +0.018 |
bows | +0.018 |
ABC | +0.018 |
Neg logit contributions | |
bed | -0.027 |
aroo | -0.024 |
ged | -0.024 |
ging | -0.023 |
bly | -0.022 |
Token | Ben |
Token ID | 3932 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
clock | +0.026 |
works | +0.026 |
bows | +0.024 |
ABC | +0.024 |
numbers | +0.024 |
Neg logit contributions | |
bed | -0.022 |
aroo | -0.020 |
ged | -0.019 |
ging | -0.019 |
bly | -0.018 |
Token | nod |
Token ID | 18666 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
clock | +0.004 |
works | +0.004 |
ABC | +0.004 |
restaurants | +0.004 |
library | +0.004 |
Neg logit contributions | |
bed | -0.005 |
aroo | -0.005 |
ged | -0.005 |
ging | -0.005 |
bly | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
clock | +0.056 |
works | +0.055 |
ABC | +0.051 |
numbers | +0.051 |
bows | +0.050 |
Neg logit contributions | |
bed | -0.077 |
aroo | -0.075 |
ging | -0.069 |
ged | -0.069 |
bly | -0.068 |
Token | " |
Token ID | 1 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
bed | +0.011 |
aroo | +0.010 |
ged | +0.010 |
ging | +0.009 |
bly | +0.009 |
Neg logit contributions | |
clock | -0.009 |
works | -0.009 |
library | -0.009 |
numbers | -0.009 |
ABC | -0.009 |
Token | Wow |
Token ID | 22017 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
clock | +0.014 |
works | +0.013 |
numbers | +0.013 |
bows | +0.013 |
ABC | +0.013 |
Neg logit contributions | |
bed | -0.015 |
aroo | -0.014 |
ging | -0.013 |
ged | -0.013 |
bly | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
bed | +0.036 |
ged | +0.030 |
ging | +0.030 |
aroo | +0.030 |
bly | +0.028 |
Neg logit contributions | |
clock | -0.048 |
ABC | -0.043 |
meanings | -0.043 |
works | -0.042 |
flavors | -0.042 |
Token | you |
Token ID | 345 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
clock | +0.036 |
works | +0.033 |
ABC | +0.032 |
bows | +0.032 |
flavors | +0.031 |
Neg logit contributions | |
bed | -0.032 |
aroo | -0.031 |
ged | -0.028 |
bly | -0.028 |
ging | -0.027 |
Token | look |
Token ID | 804 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
clock | +0.044 |
ABC | +0.038 |
facts | +0.038 |
clocks | +0.038 |
restaurants | +0.037 |
Neg logit contributions | |
bed | -0.057 |
bly | -0.049 |
aroo | -0.047 |
ged | -0.046 |
ched | -0.046 |
Token | so |
Token ID | 523 |
Feature activation | +8.75e-01 |
Pos logit contributions | |
clock | +0.081 |
works | +0.080 |
ABC | +0.075 |
bows | +0.075 |
flavors | +0.073 |
Neg logit contributions | |
bed | -0.081 |
ging | -0.073 |
ged | -0.071 |
bly | -0.070 |
aroo | -0.069 |
Token | pretty |
Token ID | 2495 |
Feature activation | +9.18e-01 |
Pos logit contributions | |
clock | +0.029 |
clocks | +0.027 |
rays | +0.026 |
meanings | +0.026 |
ABC | +0.026 |
Neg logit contributions | |
bed | -0.028 |
bly | -0.027 |
aroo | -0.024 |
ging | -0.024 |
ling | -0.023 |
Token | , |
Token ID | 11 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
clock | +0.027 |
works | +0.027 |
ABC | +0.027 |
library | +0.025 |
restaurants | +0.025 |
Neg logit contributions | |
bed | -0.034 |
aroo | -0.031 |
ging | -0.030 |
ged | -0.030 |
bly | -0.030 |
Token | Lily |
Token ID | 20037 |
Feature activation | -6.04e-02 |
Pos logit contributions | |
clock | +0.040 |
works | +0.039 |
bows | +0.036 |
ABC | +0.036 |
restaurants | +0.035 |
Neg logit contributions | |
bed | -0.040 |
aroo | -0.037 |
ging | -0.034 |
bly | -0.034 |
ged | -0.034 |
Token | !" |
Token ID | 2474 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
bed | +0.002 |
aroo | +0.002 |
ging | +0.002 |
ged | +0.002 |
bly | +0.002 |
Neg logit contributions | |
clock | -0.002 |
works | -0.002 |
ABC | -0.002 |
numbers | -0.002 |
restaurants | -0.002 |
Token | her |
Token ID | 607 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
bed | +0.007 |
bly | +0.007 |
ging | +0.007 |
aroo | +0.006 |
bled | +0.006 |
Neg logit contributions | |
works | -0.003 |
clock | -0.003 |
numbers | -0.003 |
library | -0.003 |
brushes | -0.003 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
bed | +0.010 |
ged | +0.010 |
ging | +0.010 |
aroo | +0.010 |
bly | +0.009 |
Neg logit contributions | |
clock | -0.008 |
works | -0.007 |
ABC | -0.007 |
numbers | -0.007 |
library | -0.007 |
Token | Once |
Token ID | 7454 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
works | +0.037 |
clock | +0.037 |
ABC | +0.034 |
numbers | +0.034 |
library | +0.033 |
Neg logit contributions | |
bed | -0.049 |
aroo | -0.045 |
ging | -0.045 |
ged | -0.044 |
bly | -0.044 |
Token | upon |
Token ID | 2402 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
bed | +0.065 |
aroo | +0.060 |
ging | +0.059 |
ged | +0.059 |
bly | +0.058 |
Neg logit contributions | |
works | -0.025 |
clock | -0.025 |
ABC | -0.022 |
numbers | -0.022 |
bows | -0.022 |
Token | a |
Token ID | 257 |
Feature activation | +8.72e-01 |
Pos logit contributions | |
clock | +0.029 |
works | +0.029 |
ABC | +0.026 |
numbers | +0.026 |
bows | +0.026 |
Neg logit contributions | |
bed | -0.046 |
aroo | -0.042 |
ged | -0.041 |
ging | -0.041 |
bly | -0.040 |
Token | time |
Token ID | 640 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
works | +0.020 |
clock | +0.019 |
ABC | +0.018 |
library | +0.017 |
looks | +0.017 |
Neg logit contributions | |
bed | -0.039 |
aroo | -0.037 |
ging | -0.036 |
ged | -0.036 |
bly | -0.035 |
Token | , |
Token ID | 11 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
bed | +0.005 |
aroo | +0.004 |
ging | +0.004 |
ged | +0.004 |
bly | +0.004 |
Neg logit contributions | |
clock | -0.004 |
works | -0.004 |
ABC | -0.004 |
numbers | -0.004 |
bows | -0.004 |
Token | there |
Token ID | 612 |
Feature activation | -2.65e-03 |
Pos logit contributions | |
works | +0.002 |
looks | +0.002 |
look | +0.002 |
books | +0.002 |
smells | +0.002 |
Neg logit contributions | |
bed | -0.005 |
ging | -0.004 |
ged | -0.004 |
oned | -0.004 |
bly | -0.004 |
Token | was |
Token ID | 373 |
Feature activation | +6.94e-01 |
Pos logit contributions | |
bed | +0.000 |
ging | +0.000 |
aroo | +0.000 |
bly | +0.000 |
ged | +0.000 |
Neg logit contributions | |
works | -0.000 |
clock | -0.000 |
ABC | -0.000 |
numbers | -0.000 |
looks | -0.000 |
Token | a |
Token ID | 257 |
Feature activation | +7.15e-01 |
Pos logit contributions | |
library | +0.008 |
books | +0.008 |
numbers | +0.008 |
works | +0.008 |
clock | +0.008 |
Neg logit contributions | |
bed | -0.037 |
ging | -0.037 |
aroo | -0.036 |
ged | -0.035 |
bly | -0.034 |
Token | little |
Token ID | 1310 |
Feature activation | -6.97e-01 |
Pos logit contributions | |
works | +0.019 |
clock | +0.019 |
ABC | +0.017 |
numbers | +0.017 |
library | +0.017 |
Neg logit contributions | |
bed | -0.029 |
aroo | -0.026 |
ged | -0.026 |
ging | -0.026 |
bly | -0.025 |
Token | orange |
Token ID | 10912 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
bed | +0.026 |
aroo | +0.023 |
ged | +0.023 |
ging | +0.023 |
bly | +0.023 |
Neg logit contributions | |
works | -0.021 |
clock | -0.020 |
numbers | -0.019 |
ABC | -0.019 |
library | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | -8.61e-02 |
Pos logit contributions | |
works | +0.039 |
clock | +0.039 |
ABC | +0.038 |
flavors | +0.037 |
meanings | +0.037 |
Neg logit contributions | |
bed | -0.022 |
aroo | -0.018 |
bly | -0.016 |
ging | -0.016 |
ged | -0.016 |
Token | a |
Token ID | 257 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
bed | +0.003 |
aroo | +0.003 |
ged | +0.003 |
ging | +0.003 |
bly | +0.003 |
Neg logit contributions | |
clock | -0.002 |
works | -0.002 |
ABC | -0.002 |
bows | -0.002 |
numbers | -0.002 |
Token | magic |
Token ID | 5536 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
clock | +0.004 |
works | +0.004 |
bows | +0.004 |
ABC | +0.004 |
numbers | +0.004 |
Neg logit contributions | |
bed | -0.006 |
aroo | -0.006 |
ging | -0.005 |
ged | -0.005 |
bly | -0.005 |
Token | wand |
Token ID | 11569 |
Feature activation | -2.57e+00 |
Pos logit contributions | |
bed | +0.003 |
aroo | +0.003 |
ged | +0.003 |
ging | +0.003 |
bly | +0.003 |
Neg logit contributions | |
clock | -0.004 |
works | -0.004 |
ABC | -0.004 |
numbers | -0.004 |
restaurants | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
bed | +0.089 |
aroo | +0.081 |
ging | +0.079 |
ged | +0.078 |
bly | +0.077 |
Neg logit contributions | |
works | -0.082 |
clock | -0.081 |
bows | -0.076 |
numbers | -0.076 |
ABC | -0.076 |
Token | a |
Token ID | 257 |
Feature activation | +3.21e-02 |
Pos logit contributions | |
clock | +0.004 |
works | +0.004 |
ABC | +0.004 |
bows | +0.004 |
numbers | +0.004 |
Neg logit contributions | |
bed | -0.004 |
aroo | -0.004 |
ged | -0.004 |
ging | -0.004 |
bly | -0.004 |
Token | st |
Token ID | 336 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
works | +0.001 |
clock | +0.001 |
numbers | +0.001 |
ABC | +0.001 |
bows | +0.001 |
Neg logit contributions | |
bed | -0.001 |
aroo | -0.001 |
ging | -0.001 |
ged | -0.001 |
bly | -0.001 |
Token | eth |
Token ID | 2788 |
Feature activation | +7.13e-01 |
Pos logit contributions | |
works | +0.061 |
restaurants | +0.059 |
clock | +0.058 |
flavors | +0.057 |
numbers | +0.055 |
Neg logit contributions | |
bed | -0.070 |
aroo | -0.060 |
ging | -0.059 |
ged | -0.058 |
bly | -0.057 |
Token | oscope |
Token ID | 40326 |
Feature activation | -8.14e-01 |
Pos logit contributions | |
works | +0.024 |
clock | +0.023 |
bows | +0.023 |
ABC | +0.022 |
numbers | +0.022 |
Neg logit contributions | |
bed | -0.023 |
aroo | -0.021 |
bly | -0.021 |
ging | -0.021 |
ged | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
bed | +0.025 |
ging | +0.021 |
ged | +0.021 |
aroo | +0.021 |
bly | +0.020 |
Neg logit contributions | |
works | -0.030 |
clock | -0.030 |
restaurants | -0.028 |
flavors | -0.028 |
ABC | -0.028 |
Token | or |
Token ID | 393 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
clock | +0.009 |
works | +0.009 |
ABC | +0.008 |
restaurants | +0.008 |
bows | +0.008 |
Neg logit contributions | |
bed | -0.007 |
aroo | -0.006 |
ged | -0.006 |
ging | -0.005 |
bly | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | -6.83e-02 |
Pos logit contributions | |
clock | +0.028 |
ABC | +0.026 |
works | +0.025 |
bows | +0.025 |
numbers | +0.025 |
Neg logit contributions | |
bed | -0.029 |
ged | -0.025 |
aroo | -0.024 |
ging | -0.023 |
bly | -0.022 |
Token | Tom |
Token ID | 4186 |
Feature activation | +4.74e-01 |
Pos logit contributions | |
bed | +0.003 |
aroo | +0.002 |
ging | +0.002 |
ged | +0.002 |
bly | +0.002 |
Neg logit contributions | |
works | -0.002 |
clock | -0.002 |
numbers | -0.002 |
ABC | -0.002 |
library | -0.002 |
Token | are |
Token ID | 389 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
clock | +0.016 |
ABC | +0.015 |
numbers | +0.013 |
statues | +0.013 |
meanings | +0.013 |
Neg logit contributions | |
bed | -0.016 |
ged | -0.015 |
ging | -0.014 |
aroo | -0.013 |
dd | -0.013 |
Token | friends |
Token ID | 2460 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
clock | +0.051 |
works | +0.050 |
numbers | +0.047 |
ABC | +0.046 |
restaurants | +0.046 |
Neg logit contributions | |
bed | -0.053 |
aroo | -0.049 |
ging | -0.047 |
ged | -0.046 |
bly | -0.045 |
Token | . |
Token ID | 13 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
bed | +0.011 |
aroo | +0.011 |
ging | +0.011 |
ged | +0.011 |
bly | +0.010 |
Neg logit contributions | |
clock | -0.005 |
books | -0.005 |
works | -0.005 |
library | -0.004 |
looks | -0.004 |
Token | They |
Token ID | 1119 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
clock | +0.008 |
works | +0.008 |
library | +0.007 |
bows | +0.007 |
numbers | +0.007 |
Neg logit contributions | |
bed | -0.018 |
aroo | -0.018 |
ging | -0.017 |
ged | -0.017 |
bly | -0.017 |
Token | like |
Token ID | 588 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
clock | +0.055 |
works | +0.051 |
ABC | +0.049 |
flavors | +0.048 |
numbers | +0.048 |
Neg logit contributions | |
bed | -0.057 |
aroo | -0.051 |
ged | -0.050 |
ging | -0.049 |
bly | -0.048 |
Token | to |
Token ID | 284 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
clock | +0.035 |
works | +0.035 |
bows | +0.032 |
flavors | +0.031 |
meanings | +0.031 |
Neg logit contributions | |
bed | -0.031 |
aroo | -0.029 |
ged | -0.027 |
ging | -0.024 |
under | -0.024 |
Token | play |
Token ID | 711 |
Feature activation | +7.35e-01 |
Pos logit contributions | |
clock | +0.084 |
works | +0.080 |
meanings | +0.076 |
bows | +0.074 |
flavors | +0.074 |
Neg logit contributions | |
bed | -0.080 |
aroo | -0.068 |
ged | -0.063 |
bly | -0.062 |
ging | -0.060 |
Token | together |
Token ID | 1978 |
Feature activation | +5.50e-01 |
Pos logit contributions | |
books | +0.025 |
works | +0.025 |
numbers | +0.024 |
jobs | +0.023 |
library | +0.023 |
Neg logit contributions | |
ging | -0.023 |
aroo | -0.023 |
ged | -0.022 |
bed | -0.021 |
oned | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | -2.36e-02 |
Pos logit contributions | |
numbers | +0.013 |
clock | +0.013 |
books | +0.013 |
works | +0.012 |
ABC | +0.012 |
Neg logit contributions | |
ging | -0.023 |
bed | -0.022 |
aroo | -0.022 |
bly | -0.022 |
ged | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | -6.19e-01 |
Pos logit contributions | |
bed | +0.047 |
ging | +0.044 |
aroo | +0.043 |
bly | +0.043 |
ged | +0.042 |
Neg logit contributions | |
works | -0.025 |
clock | -0.025 |
ABC | -0.024 |
numbers | -0.023 |
library | -0.023 |
Token | But |
Token ID | 1537 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
bed | +0.018 |
aroo | +0.016 |
ging | +0.015 |
ged | +0.015 |
bly | +0.015 |
Neg logit contributions | |
works | -0.024 |
clock | -0.023 |
bows | -0.022 |
ABC | -0.022 |
numbers | -0.022 |
Token | then |
Token ID | 788 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
bly | +0.057 |
aroo | +0.057 |
ging | +0.056 |
bed | +0.055 |
oned | +0.055 |
Neg logit contributions | |
clock | -0.039 |
books | -0.036 |
numbers | -0.036 |
works | -0.036 |
library | -0.036 |
Token | , |
Token ID | 11 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
bed | +0.046 |
aroo | +0.041 |
ged | +0.040 |
ging | +0.039 |
bly | +0.037 |
Neg logit contributions | |
clock | -0.049 |
works | -0.048 |
bows | -0.046 |
ABC | -0.045 |
numbers | -0.044 |
Token | the |
Token ID | 262 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
bed | +0.009 |
aroo | +0.008 |
ging | +0.008 |
bly | +0.008 |
ged | +0.008 |
Neg logit contributions | |
works | -0.004 |
clock | -0.004 |
numbers | -0.004 |
restaurants | -0.004 |
library | -0.004 |
Token | sun |
Token ID | 4252 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
works | +0.035 |
clock | +0.035 |
numbers | +0.033 |
ABC | +0.032 |
library | +0.032 |
Neg logit contributions | |
bed | -0.059 |
aroo | -0.054 |
ged | -0.053 |
ging | -0.052 |
bly | -0.051 |
Token | came |
Token ID | 1625 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
works | +0.045 |
clock | +0.044 |
looks | +0.039 |
numbers | +0.039 |
smells | +0.038 |
Neg logit contributions | |
bed | -0.084 |
aroo | -0.079 |
ging | -0.079 |
bly | -0.077 |
ged | -0.077 |
Token | out |
Token ID | 503 |
Feature activation | +4.08e-01 |
Pos logit contributions | |
clock | +0.083 |
works | +0.083 |
ABC | +0.078 |
numbers | +0.078 |
bows | +0.077 |
Neg logit contributions | |
bed | -0.067 |
aroo | -0.060 |
ging | -0.058 |
ged | -0.057 |
bly | -0.056 |
Token | and |
Token ID | 290 |
Feature activation | +6.31e-01 |
Pos logit contributions | |
clock | +0.013 |
works | +0.013 |
numbers | +0.012 |
ABC | +0.012 |
looks | +0.012 |
Neg logit contributions | |
bed | -0.014 |
aroo | -0.013 |
ged | -0.013 |
ging | -0.013 |
bly | -0.012 |
Token | it |
Token ID | 340 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
clock | +0.020 |
works | +0.020 |
ABC | +0.019 |
bows | +0.019 |
numbers | +0.018 |
Neg logit contributions | |
bed | -0.022 |
aroo | -0.020 |
ged | -0.020 |
ging | -0.019 |
bly | -0.019 |
Token | was |
Token ID | 373 |
Feature activation | -7.49e-01 |
Pos logit contributions | |
works | +0.006 |
clock | +0.006 |
numbers | +0.006 |
ABC | +0.006 |
bows | +0.006 |
Neg logit contributions | |
bed | -0.010 |
aroo | -0.009 |
ging | -0.009 |
ged | -0.009 |
bly | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
bed | +0.031 |
ging | +0.028 |
aroo | +0.027 |
ged | +0.027 |
bly | +0.027 |
Neg logit contributions | |
clock | -0.014 |
works | -0.014 |
library | -0.013 |
ABC | -0.013 |
restaurants | -0.013 |
Token | So |
Token ID | 2396 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
bed | +0.008 |
aroo | +0.007 |
ged | +0.007 |
ging | +0.007 |
bly | +0.007 |
Neg logit contributions | |
clock | -0.006 |
works | -0.006 |
library | -0.006 |
numbers | -0.006 |
restaurants | -0.006 |
Token | Tim |
Token ID | 5045 |
Feature activation | -8.11e-01 |
Pos logit contributions | |
clock | +0.004 |
works | +0.004 |
ABC | +0.004 |
bows | +0.004 |
numbers | +0.004 |
Neg logit contributions | |
bed | -0.004 |
aroo | -0.004 |
ged | -0.003 |
ging | -0.003 |
bly | -0.003 |
Token | followed |
Token ID | 3940 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
bed | +0.025 |
aroo | +0.022 |
ged | +0.022 |
ging | +0.021 |
ling | +0.019 |
Neg logit contributions | |
clock | -0.029 |
statues | -0.028 |
works | -0.027 |
ABC | -0.027 |
restaurants | -0.027 |
Token | the |
Token ID | 262 |
Feature activation | +9.97e-01 |
Pos logit contributions | |
bed | +0.050 |
bly | +0.046 |
aroo | +0.046 |
ged | +0.044 |
ging | +0.044 |
Neg logit contributions | |
clock | -0.025 |
works | -0.024 |
numbers | -0.024 |
restaurants | -0.023 |
ABC | -0.023 |
Token | rabbit |
Token ID | 22746 |
Feature activation | -2.66e+00 |
Pos logit contributions | |
clock | +0.033 |
works | +0.032 |
numbers | +0.031 |
library | +0.030 |
smells | +0.030 |
Neg logit contributions | |
bed | -0.035 |
ged | -0.031 |
aroo | -0.031 |
ging | -0.030 |
bly | -0.030 |
Token | â |
Token ID | 22940 |
Feature activation | +9.22e-01 |
Pos logit contributions | |
bed | +0.098 |
bly | +0.095 |
aroo | +0.092 |
ging | +0.091 |
ged | +0.090 |
Neg logit contributions | |
works | -0.075 |
clock | -0.073 |
looks | -0.071 |
numbers | -0.070 |
library | -0.069 |
Token | € |
Token ID | 26391 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
clock | +0.025 |
works | +0.025 |
bows | +0.023 |
ABC | +0.022 |
numbers | +0.022 |
Neg logit contributions | |
bed | -0.037 |
aroo | -0.034 |
ged | -0.033 |
ging | -0.033 |
bly | -0.032 |
Token | â„¢ |
Token ID | 8151 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
bed | +0.050 |
ged | +0.043 |
aroo | +0.042 |
ging | +0.041 |
dd | +0.038 |
Neg logit contributions | |
works | -0.041 |
clock | -0.038 |
numbers | -0.038 |
ABC | -0.037 |
meanings | -0.036 |
Token | s |
Token ID | 82 |
Feature activation | +4.91e-01 |
Pos logit contributions | |
clock | +0.007 |
works | +0.007 |
ABC | +0.007 |
numbers | +0.007 |
bows | +0.007 |
Neg logit contributions | |
bed | -0.009 |
aroo | -0.008 |
ging | -0.008 |
ged | -0.008 |
bly | -0.008 |
Token | advice |
Token ID | 5608 |
Feature activation | +8.09e-01 |
Pos logit contributions | |
clock | +0.015 |
works | +0.014 |
numbers | +0.014 |
ABC | +0.014 |
looks | +0.014 |
Neg logit contributions | |
bed | -0.018 |
aroo | -0.016 |
bly | -0.016 |
ged | -0.016 |
ging | -0.016 |
Token | and |
Token ID | 290 |
Feature activation | -7.14e-01 |
Pos logit contributions | |
bed | +0.048 |
aroo | +0.043 |
ged | +0.041 |
ging | +0.041 |
bly | +0.040 |
Neg logit contributions | |
clock | -0.042 |
works | -0.042 |
ABC | -0.039 |
bows | -0.039 |
numbers | -0.039 |
Token | rabbit |
Token ID | 22746 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
bed | +0.027 |
aroo | +0.025 |
ged | +0.024 |
ging | +0.024 |
bly | +0.023 |
Neg logit contributions | |
clock | -0.021 |
works | -0.021 |
ABC | -0.019 |
bows | -0.019 |
numbers | -0.019 |
Token | listened |
Token ID | 16399 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
bed | +0.066 |
aroo | +0.061 |
ging | +0.059 |
ged | +0.059 |
bly | +0.058 |
Neg logit contributions | |
works | -0.039 |
clock | -0.039 |
numbers | -0.035 |
ABC | -0.035 |
bows | -0.035 |
Token | to |
Token ID | 284 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
clock | +0.023 |
works | +0.022 |
numbers | +0.021 |
looks | +0.019 |
ABC | +0.019 |
Neg logit contributions | |
aroo | -0.057 |
bed | -0.055 |
bly | -0.053 |
ging | -0.051 |
ged | -0.050 |
Token | the |
Token ID | 262 |
Feature activation | +6.14e-01 |
Pos logit contributions | |
works | +0.005 |
clock | +0.005 |
numbers | +0.005 |
ABC | +0.005 |
bows | +0.005 |
Neg logit contributions | |
bed | -0.007 |
aroo | -0.006 |
ging | -0.006 |
ged | -0.006 |
bly | -0.006 |
Token | owl |
Token ID | 39610 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
clock | +0.020 |
works | +0.020 |
bows | +0.018 |
ABC | +0.018 |
flavors | +0.018 |
Neg logit contributions | |
bed | -0.021 |
aroo | -0.019 |
ging | -0.019 |
ged | -0.018 |
bly | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
bed | +0.038 |
aroo | +0.037 |
bly | +0.036 |
ging | +0.035 |
ged | +0.035 |
Neg logit contributions | |
clock | -0.030 |
works | -0.030 |
ABC | -0.028 |
numbers | -0.028 |
bows | -0.028 |
Token | They |
Token ID | 1119 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
bed | +0.019 |
aroo | +0.016 |
ged | +0.015 |
bly | +0.015 |
oned | +0.015 |
Neg logit contributions | |
works | -0.016 |
clock | -0.016 |
restaurants | -0.015 |
flavors | -0.015 |
ABC | -0.015 |
Token | stopped |
Token ID | 5025 |
Feature activation | -7.68e-01 |
Pos logit contributions | |
bed | +0.009 |
aroo | +0.008 |
ged | +0.008 |
ging | +0.008 |
bly | +0.008 |
Neg logit contributions | |
clock | -0.007 |
works | -0.007 |
ABC | -0.007 |
numbers | -0.007 |
bows | -0.007 |
Token | fighting |
Token ID | 4330 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
aroo | +0.029 |
bly | +0.028 |
bed | +0.027 |
bled | +0.025 |
dd | +0.025 |
Neg logit contributions | |
works | -0.022 |
numbers | -0.021 |
clock | -0.021 |
ABC | -0.020 |
paintings | -0.020 |
Token | and |
Token ID | 290 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
works | +0.045 |
clock | +0.045 |
numbers | +0.043 |
ABC | +0.042 |
bows | +0.041 |
Neg logit contributions | |
bed | -0.044 |
aroo | -0.041 |
ging | -0.039 |
ged | -0.039 |
bly | -0.039 |
Token | was |
Token ID | 373 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
clock | +0.023 |
works | +0.022 |
bows | +0.021 |
restaurants | +0.021 |
ABC | +0.021 |
Neg logit contributions | |
bed | -0.027 |
aroo | -0.024 |
ged | -0.024 |
ging | -0.022 |
bly | -0.022 |
Token | very |
Token ID | 845 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
bed | +0.048 |
aroo | +0.044 |
ging | +0.042 |
ged | +0.042 |
bly | +0.041 |
Neg logit contributions | |
works | -0.044 |
clock | -0.043 |
ABC | -0.041 |
bows | -0.040 |
numbers | -0.040 |
Token | careful |
Token ID | 8161 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
clock | +0.039 |
works | +0.039 |
ABC | +0.036 |
bows | +0.036 |
numbers | +0.036 |
Neg logit contributions | |
bed | -0.036 |
aroo | -0.033 |
ging | -0.032 |
ged | -0.032 |
bly | -0.031 |
Token | and |
Token ID | 290 |
Feature activation | -2.59e-02 |
Pos logit contributions | |
bed | +0.011 |
aroo | +0.010 |
ging | +0.010 |
ged | +0.010 |
bly | +0.009 |
Neg logit contributions | |
works | -0.011 |
clock | -0.011 |
library | -0.010 |
ABC | -0.010 |
restaurants | -0.010 |
Token | made |
Token ID | 925 |
Feature activation | +5.14e-01 |
Pos logit contributions | |
bed | +0.001 |
aroo | +0.001 |
ged | +0.001 |
ging | +0.001 |
bly | +0.001 |
Neg logit contributions | |
clock | -0.001 |
works | -0.001 |
ABC | -0.001 |
bows | -0.001 |
numbers | -0.001 |
Token | sure |
Token ID | 1654 |
Feature activation | -7.43e-01 |
Pos logit contributions | |
clock | +0.018 |
works | +0.018 |
ABC | +0.017 |
bows | +0.017 |
library | +0.017 |
Neg logit contributions | |
bed | -0.016 |
aroo | -0.014 |
ging | -0.014 |
ged | -0.013 |
bly | -0.013 |
Token | to |
Token ID | 284 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
bed | +0.025 |
aroo | +0.024 |
ged | +0.022 |
ging | +0.021 |
luckily | +0.021 |
Neg logit contributions | |
works | -0.024 |
clock | -0.023 |
ABC | -0.022 |
bows | -0.022 |
library | -0.021 |
Token | hold |
Token ID | 1745 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
clock | +0.041 |
works | +0.041 |
ABC | +0.037 |
bows | +0.037 |
numbers | +0.037 |
Neg logit contributions | |
bed | -0.057 |
aroo | -0.052 |
ging | -0.050 |
ged | -0.049 |
bly | -0.049 |
Token | on |
Token ID | 319 |
Feature activation | -8.96e-01 |
Pos logit contributions | |
bed | +0.060 |
aroo | +0.052 |
ged | +0.051 |
ging | +0.050 |
bly | +0.050 |
Neg logit contributions | |
works | -0.061 |
numbers | -0.061 |
clock | -0.060 |
books | -0.058 |
looks | -0.057 |
Token | tight |
Token ID | 5381 |
Feature activation | -5.56e-01 |
Pos logit contributions | |
bed | +0.031 |
aroo | +0.027 |
ging | +0.027 |
ged | +0.027 |
bly | +0.026 |
Neg logit contributions | |
works | -0.030 |
clock | -0.030 |
bows | -0.028 |
ABC | -0.027 |
restaurants | -0.027 |
Token | to |
Token ID | 284 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
bed | +0.019 |
aroo | +0.016 |
ging | +0.016 |
ged | +0.016 |
bly | +0.015 |
Neg logit contributions | |
works | -0.019 |
clock | -0.019 |
ABC | -0.018 |
bows | -0.017 |
library | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | +8.87e-01 |
Pos logit contributions | |
works | +0.005 |
clock | +0.005 |
ABC | +0.005 |
numbers | +0.005 |
bows | +0.005 |
Neg logit contributions | |
bed | -0.005 |
aroo | -0.004 |
ged | -0.004 |
ging | -0.004 |
bly | -0.004 |
Token | tree |
Token ID | 5509 |
Feature activation | +6.29e-01 |
Pos logit contributions | |
clock | +0.033 |
works | +0.032 |
restaurants | +0.031 |
bows | +0.031 |
ABC | +0.031 |
Neg logit contributions | |
aroo | -0.024 |
bed | -0.023 |
luckily | -0.020 |
swat | -0.019 |
ging | -0.018 |
Token | was |
Token ID | 373 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
clock | +0.018 |
works | +0.018 |
ABC | +0.017 |
numbers | +0.016 |
restaurants | +0.016 |
Neg logit contributions | |
bed | -0.024 |
aroo | -0.022 |
ged | -0.021 |
ging | -0.021 |
bly | -0.021 |
Token | happy |
Token ID | 3772 |
Feature activation | +3.16e-01 |
Pos logit contributions | |
bed | +0.042 |
aroo | +0.038 |
ging | +0.036 |
ged | +0.036 |
bly | +0.036 |
Neg logit contributions | |
works | -0.037 |
clock | -0.037 |
ABC | -0.034 |
numbers | -0.034 |
bows | -0.034 |
Token | too |
Token ID | 1165 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
works | +0.010 |
clock | +0.010 |
ABC | +0.010 |
numbers | +0.009 |
bows | +0.009 |
Neg logit contributions | |
bed | -0.011 |
aroo | -0.010 |
ged | -0.010 |
ging | -0.010 |
bly | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -5.90e-01 |
Pos logit contributions | |
clock | +0.083 |
works | +0.082 |
ABC | +0.080 |
restaurants | +0.077 |
numbers | +0.077 |
Neg logit contributions | |
bed | -0.078 |
ging | -0.068 |
aroo | -0.067 |
ged | -0.066 |
bly | -0.064 |
Token | It |
Token ID | 632 |
Feature activation | -4.15e-01 |
Pos logit contributions | |
bed | +0.019 |
aroo | +0.014 |
oned | +0.014 |
luckily | +0.014 |
ged | +0.014 |
Neg logit contributions | |
works | -0.021 |
flavors | -0.020 |
restaurants | -0.020 |
clock | -0.020 |
ABC | -0.020 |
Token | made |
Token ID | 925 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
bed | +0.015 |
aroo | +0.014 |
ged | +0.013 |
bly | +0.013 |
ging | +0.013 |
Neg logit contributions | |
clock | -0.013 |
works | -0.012 |
ABC | -0.012 |
restaurants | -0.012 |
numbers | -0.012 |
Token | Maria |
Token ID | 14200 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
bed | +0.012 |
aroo | +0.011 |
bly | +0.010 |
ged | +0.010 |
ging | +0.010 |
Neg logit contributions | |
works | -0.011 |
clock | -0.011 |
library | -0.011 |
ABC | -0.011 |
bows | -0.011 |
Token | laugh |
Token ID | 6487 |
Feature activation | -4.88e-01 |
Pos logit contributions | |
bed | +0.049 |
aroo | +0.043 |
ged | +0.042 |
bly | +0.041 |
ging | +0.041 |
Neg logit contributions | |
clock | -0.040 |
works | -0.039 |
restaurants | -0.038 |
library | -0.038 |
numbers | -0.037 |
Token | and |
Token ID | 290 |
Feature activation | +7.61e-01 |
Pos logit contributions | |
bed | +0.015 |
aroo | +0.014 |
ging | +0.013 |
ged | +0.013 |
bly | +0.013 |
Neg logit contributions | |
works | -0.017 |
clock | -0.017 |
numbers | -0.016 |
bows | -0.016 |
ABC | -0.016 |
Token | was |
Token ID | 373 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
clock | +0.005 |
works | +0.005 |
restaurants | +0.005 |
bows | +0.005 |
ABC | +0.005 |
Neg logit contributions | |
bed | -0.007 |
aroo | -0.006 |
ged | -0.006 |
ging | -0.006 |
bly | -0.006 |
Token | so |
Token ID | 523 |
Feature activation | +5.82e-02 |
Pos logit contributions | |
bed | +0.054 |
aroo | +0.050 |
ged | +0.049 |
ging | +0.049 |
bly | +0.047 |
Neg logit contributions | |
clock | -0.041 |
works | -0.040 |
numbers | -0.037 |
ABC | -0.036 |
looks | -0.036 |
Token | excited |
Token ID | 6568 |
Feature activation | +8.27e-01 |
Pos logit contributions | |
works | +0.002 |
clock | +0.002 |
numbers | +0.002 |
smells | +0.002 |
ABC | +0.002 |
Neg logit contributions | |
bed | -0.002 |
aroo | -0.002 |
ged | -0.002 |
ging | -0.002 |
bly | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
works | +0.027 |
clock | +0.026 |
ABC | +0.026 |
restaurants | +0.024 |
numbers | +0.024 |
Neg logit contributions | |
bed | -0.029 |
aroo | -0.025 |
ged | -0.025 |
ging | -0.025 |
bly | -0.023 |
Token | She |
Token ID | 1375 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
bed | +0.015 |
ged | +0.012 |
aroo | +0.012 |
oned | +0.012 |
ging | +0.012 |
Neg logit contributions | |
works | -0.013 |
clock | -0.012 |
flavors | -0.012 |
restaurants | -0.012 |
ABC | -0.012 |
Token | asked |
Token ID | 1965 |
Feature activation | -3.88e-01 |
Pos logit contributions | |
works | +0.006 |
clock | +0.006 |
ABC | +0.005 |
numbers | +0.005 |
bows | +0.005 |
Neg logit contributions | |
bed | -0.007 |
aroo | -0.007 |
ging | -0.006 |
ged | -0.006 |
bly | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | +8.09e-01 |
Pos logit contributions | |
bed | +0.014 |
aroo | +0.013 |
ging | +0.013 |
ged | +0.013 |
bly | +0.012 |
Neg logit contributions | |
works | -0.012 |
clock | -0.012 |
ABC | -0.011 |
numbers | -0.011 |
bows | -0.011 |
Token | fairy |
Token ID | 25607 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
works | +0.031 |
clock | +0.031 |
ABC | +0.029 |
numbers | +0.029 |
bows | +0.029 |
Neg logit contributions | |
bed | -0.024 |
aroo | -0.021 |
ged | -0.020 |
ging | -0.020 |
bly | -0.019 |
Token | what |
Token ID | 644 |
Feature activation | +3.78e-01 |
Pos logit contributions | |
bed | +0.037 |
aroo | +0.034 |
ging | +0.032 |
ged | +0.032 |
bly | +0.031 |
Neg logit contributions | |
clock | -0.037 |
works | -0.036 |
ABC | -0.034 |
bows | -0.033 |
numbers | -0.033 |
Token | it |
Token ID | 340 |
Feature activation | +7.76e-01 |
Pos logit contributions | |
clock | +0.014 |
works | +0.013 |
bows | +0.012 |
ABC | +0.012 |
restaurants | +0.011 |
Neg logit contributions | |
bed | -0.012 |
aroo | -0.011 |
ged | -0.010 |
ging | -0.010 |
bly | -0.010 |
Token | was |
Token ID | 373 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
clock | +0.023 |
works | +0.022 |
ABC | +0.021 |
numbers | +0.021 |
bows | +0.020 |
Neg logit contributions | |
bed | -0.029 |
aroo | -0.027 |
ged | -0.026 |
ging | -0.026 |
bly | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
works | +0.025 |
clock | +0.025 |
ABC | +0.023 |
bows | +0.023 |
numbers | +0.023 |
Neg logit contributions | |
bed | -0.023 |
aroo | -0.021 |
ging | -0.020 |
ged | -0.020 |
bly | -0.019 |
Token | He |
Token ID | 679 |
Feature activation | -3.95e-01 |
Pos logit contributions | |
bed | +0.016 |
aroo | +0.013 |
inn | +0.013 |
oned | +0.012 |
ged | +0.011 |
Neg logit contributions | |
works | -0.018 |
clock | -0.018 |
statues | -0.018 |
bows | -0.017 |
restaurants | -0.017 |
Token | had |
Token ID | 550 |
Feature activation | -7.77e-01 |
Pos logit contributions | |
bed | +0.017 |
aroo | +0.016 |
ged | +0.015 |
ging | +0.015 |
bly | +0.015 |
Neg logit contributions | |
clock | -0.010 |
works | -0.009 |
bows | -0.009 |
ABC | -0.009 |
numbers | -0.008 |
Token | a |
Token ID | 257 |
Feature activation | -8.99e-01 |
Pos logit contributions | |
bed | +0.023 |
aroo | +0.018 |
ged | +0.018 |
under | +0.017 |
bly | +0.017 |
Neg logit contributions | |
works | -0.028 |
bows | -0.027 |
clock | -0.025 |
ABC | -0.025 |
aris | -0.024 |
Token | small |
Token ID | 1402 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
bed | +0.039 |
aroo | +0.036 |
ging | +0.035 |
ged | +0.035 |
bly | +0.034 |
Neg logit contributions | |
clock | -0.021 |
works | -0.021 |
bows | -0.019 |
ABC | -0.018 |
numbers | -0.018 |
Token | toy |
Token ID | 13373 |
Feature activation | -4.25e+00 |
Pos logit contributions | |
bed | +0.063 |
aroo | +0.056 |
ging | +0.054 |
ged | +0.053 |
bly | +0.051 |
Neg logit contributions | |
clock | -0.053 |
works | -0.052 |
bows | -0.049 |
ABC | -0.048 |
numbers | -0.047 |
Token | grill |
Token ID | 29901 |
Feature activation | -8.78e-01 |
Pos logit contributions | |
bed | +0.158 |
ging | +0.146 |
ged | +0.144 |
aroo | +0.143 |
bly | +0.141 |
Neg logit contributions | |
clock | -0.125 |
works | -0.124 |
numbers | -0.117 |
library | -0.115 |
ABC | -0.115 |
Token | that |
Token ID | 326 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
bed | +0.025 |
aroo | +0.022 |
ging | +0.021 |
ged | +0.021 |
bly | +0.020 |
Neg logit contributions | |
works | -0.034 |
clock | -0.034 |
ABC | -0.032 |
numbers | -0.032 |
bows | -0.032 |
Token | he |
Token ID | 339 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
bed | +0.034 |
aroo | +0.031 |
bly | +0.026 |
ged | +0.026 |
luckily | +0.026 |
Neg logit contributions | |
clock | -0.045 |
bows | -0.043 |
ABC | -0.042 |
tours | -0.042 |
aris | -0.041 |
Token | played |
Token ID | 2826 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
bed | +0.050 |
aroo | +0.045 |
ged | +0.044 |
ging | +0.043 |
bly | +0.043 |
Neg logit contributions | |
clock | -0.037 |
works | -0.037 |
bows | -0.034 |
ABC | -0.034 |
numbers | -0.034 |
Token | with |
Token ID | 351 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
bed | +0.029 |
aroo | +0.028 |
ged | +0.027 |
ging | +0.027 |
bly | +0.025 |
Neg logit contributions | |
works | -0.037 |
numbers | -0.036 |
clock | -0.036 |
books | -0.036 |
ABC | -0.035 |
Token | . |
Token ID | 13 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
works | +0.026 |
clock | +0.026 |
numbers | +0.025 |
smells | +0.024 |
bows | +0.024 |
Neg logit contributions | |
bed | -0.035 |
aroo | -0.033 |
ging | -0.031 |
ged | -0.031 |
bly | -0.031 |
Token | Suddenly |
Token ID | 24975 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
bed | +0.004 |
aroo | +0.004 |
ged | +0.004 |
ging | +0.004 |
bly | +0.004 |
Neg logit contributions | |
works | -0.004 |
clock | -0.004 |
ABC | -0.004 |
numbers | -0.004 |
bows | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
bed | +0.043 |
aroo | +0.039 |
ged | +0.038 |
ging | +0.037 |
bly | +0.035 |
Neg logit contributions | |
clock | -0.045 |
works | -0.044 |
ABC | -0.041 |
bows | -0.041 |
flavors | -0.041 |
Token | the |
Token ID | 262 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
clock | +0.005 |
works | +0.005 |
ABC | +0.005 |
bows | +0.005 |
numbers | +0.005 |
Neg logit contributions | |
bed | -0.007 |
aroo | -0.006 |
ged | -0.006 |
ging | -0.006 |
bly | -0.006 |
Token | k |
Token ID | 479 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
works | +0.036 |
clock | +0.036 |
ABC | +0.033 |
bows | +0.033 |
restaurants | +0.033 |
Neg logit contributions | |
bed | -0.034 |
aroo | -0.032 |
ging | -0.030 |
ged | -0.029 |
bly | -0.029 |
Token | ang |
Token ID | 648 |
Feature activation | -3.98e+00 |
Pos logit contributions | |
bed | +0.041 |
oned | +0.032 |
ged | +0.031 |
rily | +0.030 |
bled | +0.030 |
Neg logit contributions | |
clock | -0.089 |
works | -0.088 |
bows | -0.087 |
library | -0.086 |
numbers | -0.086 |
Token | aroo |
Token ID | 38049 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
bed | +0.060 |
bly | +0.041 |
oned | +0.040 |
afloat | +0.039 |
ging | +0.038 |
Neg logit contributions | |
works | -0.177 |
looks | -0.177 |
numbers | -0.175 |
ABC | -0.170 |
total | -0.168 |
Token | heard |
Token ID | 2982 |
Feature activation | +8.46e-01 |
Pos logit contributions | |
bed | +0.109 |
aroo | +0.102 |
ging | +0.100 |
bly | +0.100 |
ged | +0.098 |
Neg logit contributions | |
clock | -0.069 |
works | -0.069 |
numbers | -0.063 |
ABC | -0.061 |
looks | -0.061 |
Token | a |
Token ID | 257 |
Feature activation | -6.52e-01 |
Pos logit contributions | |
works | +0.026 |
clock | +0.026 |
bows | +0.024 |
ABC | +0.024 |
flavors | +0.023 |
Neg logit contributions | |
bed | -0.031 |
aroo | -0.028 |
ged | -0.027 |
ging | -0.027 |
bly | -0.026 |
Token | voice |
Token ID | 3809 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
bed | +0.025 |
aroo | +0.024 |
ging | +0.023 |
ged | +0.022 |
bly | +0.022 |
Neg logit contributions | |
clock | -0.018 |
works | -0.018 |
bows | -0.017 |
restaurants | -0.016 |
ABC | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -7.63e-01 |
Pos logit contributions | |
bed | +0.022 |
bled | +0.020 |
bly | +0.020 |
aroo | +0.019 |
ging | +0.018 |
Neg logit contributions | |
works | -0.013 |
clock | -0.012 |
looks | -0.012 |
look | -0.012 |
smells | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
works | +0.003 |
clock | +0.003 |
total | +0.003 |
ABC | +0.003 |
library | +0.003 |
Neg logit contributions | |
bed | -0.002 |
ged | -0.002 |
ling | -0.002 |
ging | -0.002 |
aroo | -0.002 |
Token | accidentally |
Token ID | 14716 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
bed | +0.006 |
aroo | +0.005 |
ged | +0.005 |
ging | +0.005 |
bly | +0.005 |
Neg logit contributions | |
clock | -0.006 |
works | -0.006 |
ABC | -0.006 |
bows | -0.006 |
numbers | -0.006 |
Token | got |
Token ID | 1392 |
Feature activation | +2.57e-02 |
Pos logit contributions | |
bed | +0.081 |
aroo | +0.073 |
ging | +0.071 |
ged | +0.070 |
bly | +0.069 |
Neg logit contributions | |
works | -0.081 |
clock | -0.081 |
numbers | -0.075 |
ABC | -0.075 |
bows | -0.074 |
Token | the |
Token ID | 262 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
clock | +0.001 |
works | +0.001 |
bows | +0.001 |
ABC | +0.001 |
library | +0.001 |
Neg logit contributions | |
bed | -0.001 |
aroo | -0.001 |
ged | -0.001 |
ging | -0.001 |
bly | -0.001 |
Token | tape |
Token ID | 9154 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
bed | +0.055 |
aroo | +0.051 |
ged | +0.050 |
ging | +0.050 |
bly | +0.049 |
Neg logit contributions | |
works | -0.030 |
clock | -0.029 |
numbers | -0.027 |
ABC | -0.026 |
bows | -0.026 |
Token | stuck |
Token ID | 7819 |
Feature activation | -4.24e+00 |
Pos logit contributions | |
bed | +0.086 |
aroo | +0.080 |
bly | +0.075 |
ged | +0.075 |
ging | +0.074 |
Neg logit contributions | |
works | -0.083 |
clock | -0.081 |
numbers | -0.078 |
bows | -0.076 |
looks | -0.075 |
Token | all |
Token ID | 477 |
Feature activation | +2.35e-02 |
Pos logit contributions | |
bed | +0.130 |
aroo | +0.126 |
bly | +0.117 |
ging | +0.116 |
ged | +0.113 |
Neg logit contributions | |
clock | -0.141 |
works | -0.141 |
numbers | -0.136 |
bows | -0.129 |
books | -0.129 |
Token | over |
Token ID | 625 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
works | +0.001 |
clock | +0.001 |
numbers | +0.001 |
looks | +0.001 |
bows | +0.001 |
Neg logit contributions | |
bed | -0.001 |
aroo | -0.001 |
ging | -0.001 |
ged | -0.001 |
bly | -0.001 |
Token | his |
Token ID | 465 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
bed | +0.043 |
aroo | +0.041 |
bly | +0.039 |
ging | +0.039 |
ged | +0.038 |
Neg logit contributions | |
works | -0.026 |
clock | -0.026 |
numbers | -0.026 |
restaurants | -0.024 |
flavors | -0.024 |
Token | fur |
Token ID | 9230 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
bed | +0.046 |
aroo | +0.043 |
ged | +0.042 |
ging | +0.042 |
bly | +0.041 |
Neg logit contributions | |
clock | -0.046 |
works | -0.045 |
numbers | -0.043 |
ABC | -0.043 |
library | -0.042 |
Token | . |
Token ID | 13 |
Feature activation | -9.70e-01 |
Pos logit contributions | |
bed | +0.080 |
aroo | +0.074 |
ging | +0.072 |
ged | +0.072 |
bly | +0.071 |
Neg logit contributions | |
clock | -0.061 |
works | -0.060 |
numbers | -0.057 |
bows | -0.056 |
ABC | -0.055 |
Token | The |
Token ID | 383 |
Feature activation | +5.60e-01 |
Pos logit contributions | |
bed | +0.021 |
aroo | +0.019 |
ged | +0.016 |
oned | +0.015 |
ging | +0.014 |
Neg logit contributions | |
works | -0.032 |
clock | -0.031 |
bows | -0.031 |
ABC | -0.030 |
flavors | -0.030 |
Token | mouse |
Token ID | 10211 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
clock | +0.019 |
works | +0.019 |
bows | +0.018 |
ABC | +0.018 |
numbers | +0.018 |
Neg logit contributions | |
bed | -0.019 |
aroo | -0.017 |
ging | -0.016 |
ged | -0.016 |
bly | -0.016 |
Token | had |
Token ID | 550 |
Feature activation | -9.68e-01 |
Pos logit contributions | |
bed | +0.086 |
aroo | +0.079 |
ging | +0.079 |
ged | +0.078 |
bly | +0.077 |
Neg logit contributions | |
works | -0.055 |
clock | -0.053 |
numbers | -0.049 |
ABC | -0.048 |
looks | -0.048 |
Token | a |
Token ID | 257 |
Feature activation | -9.92e-01 |
Pos logit contributions | |
bed | +0.030 |
aroo | +0.026 |
ged | +0.025 |
bly | +0.023 |
pered | +0.023 |
Neg logit contributions | |
works | -0.033 |
bows | -0.033 |
clock | -0.033 |
restaurants | -0.032 |
ABC | -0.031 |
Token | nut |
Token ID | 6701 |
Feature activation | -3.38e+00 |
Pos logit contributions | |
bed | +0.040 |
aroo | +0.037 |
ging | +0.035 |
ged | +0.035 |
bly | +0.034 |
Neg logit contributions | |
clock | -0.026 |
works | -0.025 |
bows | -0.024 |
restaurants | -0.023 |
ABC | -0.023 |
Token | stuck |
Token ID | 7819 |
Feature activation | -4.58e+00 |
Pos logit contributions | |
bed | +0.105 |
bly | +0.095 |
aroo | +0.095 |
ging | +0.093 |
ged | +0.092 |
Neg logit contributions | |
works | -0.119 |
clock | -0.112 |
looks | -0.111 |
numbers | -0.111 |
books | -0.110 |
Token | in |
Token ID | 287 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
bed | +0.119 |
aroo | +0.111 |
bly | +0.106 |
ging | +0.105 |
ged | +0.100 |
Neg logit contributions | |
works | -0.176 |
clock | -0.172 |
numbers | -0.170 |
books | -0.164 |
looks | -0.162 |
Token | its |
Token ID | 663 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
bed | +0.058 |
aroo | +0.052 |
ging | +0.050 |
ged | +0.050 |
bly | +0.049 |
Neg logit contributions | |
clock | -0.048 |
works | -0.048 |
bows | -0.045 |
ABC | -0.044 |
library | -0.043 |
Token | mouth |
Token ID | 5422 |
Feature activation | -4.67e-01 |
Pos logit contributions | |
bed | +0.033 |
aroo | +0.029 |
ged | +0.027 |
ging | +0.027 |
bly | +0.026 |
Neg logit contributions | |
works | -0.036 |
clock | -0.035 |
bows | -0.033 |
ABC | -0.033 |
numbers | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | -9.66e-01 |
Pos logit contributions | |
bed | +0.016 |
aroo | +0.014 |
ging | +0.014 |
ged | +0.014 |
bly | +0.013 |
Neg logit contributions | |
works | -0.016 |
clock | -0.015 |
ABC | -0.014 |
numbers | -0.014 |
bows | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
bed | +0.031 |
aroo | +0.028 |
ged | +0.026 |
ging | +0.025 |
bly | +0.024 |
Neg logit contributions | |
works | -0.034 |
clock | -0.034 |
bows | -0.032 |
ABC | -0.032 |
numbers | -0.031 |
Token | !" |
Token ID | 2474 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
bed | +0.024 |
aroo | +0.022 |
ging | +0.021 |
ged | +0.020 |
bly | +0.020 |
Neg logit contributions | |
clock | -0.021 |
works | -0.020 |
ABC | -0.020 |
numbers | -0.019 |
statues | -0.019 |
Token | Mitt |
Token ID | 16627 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
clock | +0.010 |
works | +0.009 |
numbers | +0.009 |
bows | +0.009 |
ABC | +0.009 |
Neg logit contributions | |
bed | -0.010 |
aroo | -0.010 |
ging | -0.010 |
bly | -0.009 |
ged | -0.009 |
Token | ens |
Token ID | 641 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
works | +0.011 |
clock | +0.011 |
bows | +0.010 |
numbers | +0.010 |
ABC | +0.010 |
Neg logit contributions | |
bed | -0.013 |
aroo | -0.012 |
ging | -0.012 |
ged | -0.012 |
bly | -0.011 |
Token | chased |
Token ID | 26172 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
bed | +0.016 |
aroo | +0.014 |
ged | +0.013 |
ging | +0.013 |
bly | +0.013 |
Neg logit contributions | |
clock | -0.013 |
works | -0.013 |
ABC | -0.012 |
bows | -0.012 |
numbers | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
bly | +0.066 |
bed | +0.065 |
bled | +0.063 |
aroo | +0.062 |
rily | +0.057 |
Neg logit contributions | |
books | -0.041 |
numbers | -0.038 |
jobs | -0.036 |
clock | -0.036 |
names | -0.036 |
Token | fle |
Token ID | 5104 |
Feature activation | -4.04e+00 |
Pos logit contributions | |
works | +0.005 |
clock | +0.005 |
numbers | +0.005 |
ABC | +0.005 |
library | +0.005 |
Neg logit contributions | |
bed | -0.007 |
ged | -0.007 |
ging | -0.006 |
aroo | -0.006 |
bly | -0.006 |
Token | a |
Token ID | 64 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
bed | +0.166 |
ging | +0.157 |
ged | +0.153 |
luckily | +0.152 |
bing | +0.152 |
Neg logit contributions | |
bows | -0.074 |
clock | -0.071 |
names | -0.071 |
works | -0.068 |
aris | -0.066 |
Token | and |
Token ID | 290 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
bed | +0.076 |
bly | +0.074 |
aroo | +0.072 |
bled | +0.069 |
ging | +0.069 |
Neg logit contributions | |
works | -0.065 |
clock | -0.063 |
looks | -0.063 |
books | -0.062 |
numbers | -0.061 |
Token | caught |
Token ID | 4978 |
Feature activation | -6.68e-01 |
Pos logit contributions | |
bed | +0.008 |
bly | +0.008 |
aroo | +0.008 |
ging | +0.008 |
oned | +0.007 |
Neg logit contributions | |
works | -0.007 |
clock | -0.006 |
looks | -0.006 |
books | -0.006 |
smells | -0.006 |
Token | it |
Token ID | 340 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
bed | +0.024 |
aroo | +0.023 |
bly | +0.022 |
oned | +0.022 |
ged | +0.022 |
Neg logit contributions | |
numbers | -0.017 |
works | -0.017 |
books | -0.016 |
smells | -0.016 |
names | -0.016 |
Token | with |
Token ID | 351 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
aroo | +0.008 |
bed | +0.008 |
ging | +0.008 |
ged | +0.008 |
bly | +0.008 |
Neg logit contributions | |
works | -0.007 |
clock | -0.007 |
looks | -0.007 |
numbers | -0.007 |
smells | -0.007 |