TOP ACTIVATIONS
MAX = 13.223

grandma 's house for safe keeping . When
, " I knew you 'd like it !" Emily was
it to me for safe keeping . He told me to
Pick out whatever yogurt you 'd like for a treat ,
here ! Eat whatever you 'd like from the bowl !"
it ? I knew you 'd like it ."
share and that sometimes things can break . <|endoftext|> Once upon
food for you if you 'd like ."
See , I knew you 'd like it !" Alex was
learned that even though things can be hard , she can
, " I knew you 'd keep your promise ."
can help you if you 'd like ." The shell was
he also learned that accidents can happen and it 's important
I don 't think it can talk ," Anna says .
you feel better if you 'd like ." Toby nodded sadly
't it incredible how nature can be so beautiful ?" Lily
I love you and nothing can change that ."
respect them , because things can go wrong very quickly if
He also learned that accidents can happen , but it 's
very happy and knew he 'd never leave the house without

MIN ACTIVATIONS
MIN = -16.988

she got rid of the intr uders . She did not
play without going near the sm elly leaves . Tim and
to get away from the sm elly sock . So ,
was running around on the lush grass , enjoying the sunshine
and ran away from the sm elly jail . And he
farmer who lived on a lush farm with many animals and
her . Tommy saw the sm elly sock and wanted to
home , away from the sm elly man . John never
mouse never suffered from the rud eness of other animals again
not want to touch the sm elly sock . They do
, he noticed that the Sm elly King was cruel and
Fl uffy picked up the sm elly sock with her teeth
car came and hit the sm elly cat and Zero .
Alice saw Lisa with the y ummy cand ies , she
to take a journey to outer space . He hopped into
getting very annoyed with his rud eness and complained that he
Lily were scared of the gr umpy man . They ran
?" asked the rh in oc eros . "
were running away from the sm elly pitch . But one
to roll around with the gr umpy shape and soon ,

INTERVAL 5.670 - 13.223
CONTAINS 11.332%

mom my , " Where did the bird go ?"
why she was crying . She told him about the rope
pumpkin was so long that it reached the sky . One
him a big shed where he could ice - sk ate
had to save some of it . It was a big

INTERVAL -1.882 - 5.670
CONTAINS 60.691%

How did you do that ?" Lily smiled and said ,
They looked and looked for the fl ute . Finally
, " So jail is like a time - out for
the way the curtain moved and kept pushing it . His
. She rides , slides , and plays with a furry

INTERVAL -9.435 - -1.882
CONTAINS 24.695%

<|endoftext|> Tom my was an alert little boy . He was
Tim my . Tim my loved to go to the park
practices every day . The little bird ie was happy to
ran to investigate . When she got there ,
and Ell a was too scared to move .

INTERVAL -16.988 - -9.435
CONTAINS 3.282%

was comfortable . The train started ch ug ging
ucky saw a big , graceful sw an swimming in the
. When he went into the east store , he saw
everywhere she went . The old lady was happy to have
tree . He had a huge bag over his shoulder and
Token grandma
Token ID49890
Feature activation+1.04e+00

Pos logit contributions
igsaw+0.163
aj+0.140
umm+0.134
Whe+0.131
udd+0.128
Neg logit contributions
 never-0.144
 decided-0.144
 tried-0.139
 dropped-0.129
 came-0.129
Token's
Token ID338
Feature activation-5.28e+00

Pos logit contributions
 decided+0.022
 never+0.021
 tried+0.020
 stumbled+0.020
 came+0.019
Neg logit contributions
igsaw-0.036
aj-0.034
 batch-0.031
ummy-0.030
 coll-0.030
Token house
Token ID2156
Feature activation+4.64e+00

Pos logit contributions
igsaw+0.148
aj+0.128
umm+0.115
Whe+0.113
 batch+0.113
Neg logit contributions
 decided-0.154
 never-0.153
 tried-0.147
 came-0.142
 dropped-0.138
Token for
Token ID329
Feature activation+8.91e-01

Pos logit contributions
 decided+0.086
 tried+0.081
 never+0.079
 came+0.077
 stumbled+0.075
Neg logit contributions
igsaw-0.170
aj-0.162
 batch-0.148
ummy-0.145
udd-0.144
Token safe
Token ID3338
Feature activation-1.33e+00

Pos logit contributions
 decided+0.020
 stumbled+0.019
 wouldn+0.018
 tried+0.018
 came+0.018
Neg logit contributions
igsaw-0.028
aj-0.026
 coll-0.024
 batch-0.024
ummy-0.023
Tokenkeeping
Token ID19934
Feature activation+1.32e+01

Pos logit contributions
igsaw+0.044
aj+0.043
 coll+0.038
 batch+0.038
ummy+0.038
Neg logit contributions
 decided-0.027
 tried-0.026
 managed-0.025
 never-0.025
 dropped-0.025
Token.
Token ID13
Feature activation-5.77e-01

Pos logit contributions
 decided+0.302
 tried+0.288
Please+0.280
 managed+0.278
pped+0.270
Neg logit contributions
aj-0.381
igsaw-0.376
 batch-0.326
ummy-0.323
udd-0.320
Token
Token ID220
Feature activation-1.40e+00

Pos logit contributions
igsaw+0.019
aj+0.018
 batch+0.016
 coll+0.016
ummy+0.015
Neg logit contributions
 decided-0.014
 tried-0.013
 never-0.013
 came-0.013
 got-0.012
Token
Token ID198
Feature activation-4.04e+00

Pos logit contributions
igsaw+0.050
aj+0.044
 batch+0.043
umm+0.042
 coll+0.041
Neg logit contributions
 decided-0.029
 never-0.028
 tried-0.027
 came-0.027
 could-0.026
Token
Token ID198
Feature activation-4.44e+00

Pos logit contributions
igsaw+0.135
aj+0.126
 batch+0.113
umm+0.112
ummy+0.111
Neg logit contributions
 decided-0.093
 never-0.090
 tried-0.089
 came-0.086
 stumbled-0.082
TokenWhen
Token ID2215
Feature activation+4.19e+00

Pos logit contributions
igsaw+0.129
aj+0.120
 batch+0.108
udd+0.106
ummy+0.103
Neg logit contributions
 decided-0.111
 tried-0.110
 came-0.108
 never-0.105
 dropped-0.104
Token,
Token ID11
Feature activation-2.28e-01

Pos logit contributions
 decided+0.003
 never+0.003
 tried+0.003
 stumbled+0.003
 came+0.003
Neg logit contributions
igsaw-0.003
aj-0.003
ummy-0.003
 batch-0.003
udd-0.003
Token "
Token ID366
Feature activation+1.29e-01

Pos logit contributions
igsaw+0.008
aj+0.007
 batch+0.007
ummy+0.007
 coll+0.006
Neg logit contributions
 decided-0.005
 tried-0.004
 never-0.004
 came-0.004
 stumbled-0.004
TokenI
Token ID40
Feature activation+8.62e+00

Pos logit contributions
 decided+0.003
 never+0.003
 tried+0.003
 came+0.003
 dropped+0.002
Neg logit contributions
igsaw-0.004
aj-0.004
 batch-0.004
ummy-0.004
 coll-0.004
Token knew
Token ID2993
Feature activation+3.10e+00

Pos logit contributions
pped+0.151
 decided+0.143
 never+0.139
Please+0.131
 stumbled+0.128
Neg logit contributions
aj-0.274
igsaw-0.272
udd-0.250
 batch-0.250
 difference-0.236
Token you
Token ID345
Feature activation+8.46e+00

Pos logit contributions
 decided+0.058
 tried+0.055
 never+0.055
 came+0.053
 stumbled+0.050
Neg logit contributions
igsaw-0.115
aj-0.109
 batch-0.099
ummy-0.097
udd-0.096
Token'd
Token ID1549
Feature activation+1.23e+01

Pos logit contributions
pped+0.119
Please+0.108
 tried+0.099
ged+0.098
 rushed+0.097
Neg logit contributions
igsaw-0.287
aj-0.282
 types-0.265
ummy-0.264
 goals-0.263
Token like
Token ID588
Feature activation+3.07e+00

Pos logit contributions
 decided+0.225
pped+0.207
 tried+0.207
 came+0.198
 stumbled+0.195
Neg logit contributions
igsaw-0.418
aj-0.392
 batch-0.368
 coll-0.360
 difference-0.356
Token it
Token ID340
Feature activation+8.43e+00

Pos logit contributions
 decided+0.053
 tried+0.050
 never+0.049
 came+0.047
 stumbled+0.045
Neg logit contributions
igsaw-0.117
aj-0.111
 batch-0.102
ummy-0.100
udd-0.098
Token!"
Token ID2474
Feature activation-7.10e-01

Pos logit contributions
 decided+0.168
 never+0.158
 tried+0.156
 came+0.152
 almost+0.145
Neg logit contributions
igsaw-0.311
aj-0.291
 batch-0.264
udd-0.258
 coll-0.256
Token Emily
Token ID17608
Feature activation+3.21e+00

Pos logit contributions
igsaw+0.023
aj+0.022
 batch+0.019
ummy+0.019
udd+0.019
Neg logit contributions
 decided-0.017
 tried-0.016
 never-0.016
 came-0.015
 stumbled-0.015
Token was
Token ID373
Feature activation+3.11e+00

Pos logit contributions
 decided+0.060
 tried+0.056
 never+0.056
 came+0.054
 stumbled+0.051
Neg logit contributions
igsaw-0.119
aj-0.113
 batch-0.103
ummy-0.101
udd-0.100
Token it
Token ID340
Feature activation+6.38e+00

Pos logit contributions
igsaw+0.084
aj+0.080
 batch+0.074
ummy+0.074
udd+0.073
Neg logit contributions
 decided-0.020
 tried-0.018
 never-0.018
 came-0.016
 stumbled-0.015
Token to
Token ID284
Feature activation+3.36e+00

Pos logit contributions
 decided+0.092
 never+0.086
 tried+0.082
 came+0.079
 got+0.075
Neg logit contributions
igsaw-0.272
aj-0.256
 batch-0.241
umm-0.238
ummy-0.235
Token me
Token ID502
Feature activation+1.56e+00

Pos logit contributions
 decided+0.075
 never+0.072
 tried+0.071
 came+0.070
 almost+0.065
Neg logit contributions
igsaw-0.115
aj-0.108
 batch-0.096
udd-0.095
ummy-0.094
Token for
Token ID329
Feature activation+2.50e-01

Pos logit contributions
 decided+0.029
 never+0.027
 tried+0.027
 came+0.025
 got+0.024
Neg logit contributions
igsaw-0.060
aj-0.056
 batch-0.051
ummy-0.050
udd-0.050
Token safe
Token ID3338
Feature activation-2.04e+00

Pos logit contributions
 decided+0.006
 tried+0.005
 came+0.005
 never+0.005
 stumbled+0.005
Neg logit contributions
igsaw-0.008
aj-0.008
 batch-0.007
 coll-0.007
ummy-0.007
Tokenkeeping
Token ID19934
Feature activation+1.21e+01

Pos logit contributions
igsaw+0.071
aj+0.068
 batch+0.061
ummy+0.060
 coll+0.060
Neg logit contributions
 decided-0.041
 tried-0.039
 never-0.038
 came-0.037
 stumbled-0.037
Token.
Token ID13
Feature activation-1.77e+00

Pos logit contributions
 decided+0.274
 tried+0.254
 stumbled+0.249
 managed+0.246
pped+0.240
Neg logit contributions
aj-0.376
igsaw-0.358
 batch-0.321
 coll-0.316
udd-0.315
Token He
Token ID679
Feature activation+7.62e+00

Pos logit contributions
igsaw+0.064
aj+0.059
 batch+0.056
udd+0.054
 coll+0.053
Neg logit contributions
 decided-0.037
 never-0.035
 tried-0.035
 came-0.034
 could-0.032
Token told
Token ID1297
Feature activation-5.30e-01

Pos logit contributions
 decided+0.166
 tried+0.157
 never+0.156
 came+0.152
 stumbled+0.150
Neg logit contributions
igsaw-0.245
aj-0.239
 batch-0.213
udd-0.209
 coll-0.206
Token me
Token ID502
Feature activation+2.30e+00

Pos logit contributions
igsaw+0.021
aj+0.020
 batch+0.018
udd+0.018
ummy+0.017
Neg logit contributions
 decided-0.009
 never-0.009
 tried-0.009
 came-0.008
 dropped-0.008
Token to
Token ID284
Feature activation+3.47e+00

Pos logit contributions
 decided+0.047
 tried+0.044
 never+0.042
 came+0.042
 stumbled+0.042
Neg logit contributions
igsaw-0.079
aj-0.076
 batch-0.068
ummy-0.068
udd-0.067
TokenPick
Token ID31686
Feature activation+3.77e+00

Pos logit contributions
igsaw+0.024
aj+0.023
 batch+0.020
ummy+0.020
udd+0.020
Neg logit contributions
 decided-0.015
 never-0.014
 tried-0.014
 came-0.013
 stumbled-0.013
Token out
Token ID503
Feature activation+1.82e+00

Pos logit contributions
 decided+0.085
 tried+0.083
 came+0.080
 never+0.080
 got+0.077
Neg logit contributions
igsaw-0.129
aj-0.118
umm-0.110
ummy-0.107
 batch-0.105
Token whatever
Token ID4232
Feature activation+2.49e+00

Pos logit contributions
 decided+0.043
 never+0.041
 tried+0.041
 came+0.039
 dropped+0.038
Neg logit contributions
igsaw-0.059
aj-0.056
 batch-0.050
ummy-0.049
udd-0.049
Token yogurt
Token ID32132
Feature activation+2.13e+00

Pos logit contributions
 decided+0.053
 tried+0.049
 never+0.049
 came+0.048
 stumbled+0.046
Neg logit contributions
igsaw-0.085
aj-0.081
 batch-0.073
ummy-0.072
udd-0.071
Token you
Token ID345
Feature activation+8.24e+00

Pos logit contributions
 decided+0.053
 tried+0.050
 never+0.050
 came+0.048
 stumbled+0.047
Neg logit contributions
igsaw-0.065
aj-0.061
 batch-0.055
ummy-0.054
udd-0.053
Token'd
Token ID1549
Feature activation+1.20e+01

Pos logit contributions
 decided+0.129
 never+0.128
pped+0.123
 tried+0.118
 stumbled+0.117
Neg logit contributions
igsaw-0.298
aj-0.281
 types-0.259
udd-0.257
 batch-0.257
Token like
Token ID588
Feature activation+2.32e+00

Pos logit contributions
 decided+0.204
pped+0.190
 tried+0.188
 stumbled+0.183
 came+0.180
Neg logit contributions
igsaw-0.421
aj-0.390
 batch-0.374
 types-0.366
 coll-0.359
Token for
Token ID329
Feature activation+1.08e+00

Pos logit contributions
 decided+0.047
 tried+0.044
 never+0.044
 came+0.042
 stumbled+0.040
Neg logit contributions
igsaw-0.083
aj-0.079
 batch-0.071
ummy-0.070
udd-0.069
Token a
Token ID257
Feature activation-6.64e+00

Pos logit contributions
 decided+0.024
 tried+0.023
 never+0.023
 came+0.022
 stumbled+0.022
Neg logit contributions
igsaw-0.036
aj-0.034
 batch-0.030
ummy-0.030
udd-0.029
Token treat
Token ID2190
Feature activation+8.20e-01

Pos logit contributions
igsaw+0.178
aj+0.168
 batch+0.144
udd+0.142
ummy+0.142
Neg logit contributions
 decided-0.192
 tried-0.184
 never-0.183
 came-0.179
 stumbled-0.173
Token,
Token ID11
Feature activation-1.36e+00

Pos logit contributions
 decided+0.018
 tried+0.017
 never+0.017
 came+0.017
 stumbled+0.016
Neg logit contributions
igsaw-0.028
aj-0.026
 batch-0.023
ummy-0.023
udd-0.023
Token here
Token ID994
Feature activation+4.53e+00

Pos logit contributions
pped+0.017
 decided+0.015
 never+0.015
Please+0.014
 wouldn+0.014
Neg logit contributions
aj-0.044
igsaw-0.041
udd-0.040
 batch-0.038
 types-0.037
Token!
Token ID0
Feature activation-1.68e-01

Pos logit contributions
 decided+0.103
 tried+0.098
 never+0.097
 came+0.094
 stumbled+0.091
Neg logit contributions
igsaw-0.150
aj-0.141
 batch-0.126
ummy-0.124
udd-0.123
Token Eat
Token ID27574
Feature activation+3.95e+00

Pos logit contributions
igsaw+0.006
aj+0.005
 batch+0.005
udd+0.005
ummy+0.005
Neg logit contributions
 decided-0.004
 tried-0.004
 never-0.004
 came-0.004
 stumbled-0.003
Token whatever
Token ID4232
Feature activation+3.32e+00

Pos logit contributions
 decided+0.086
 tried+0.082
 never+0.082
 came+0.078
 almost+0.075
Neg logit contributions
igsaw-0.135
aj-0.127
 batch-0.113
ummy-0.112
udd-0.111
Token you
Token ID345
Feature activation+8.66e+00

Pos logit contributions
 decided+0.063
 tried+0.058
 never+0.057
 came+0.055
 stumbled+0.055
Neg logit contributions
igsaw-0.118
aj-0.111
 batch-0.102
ummy-0.101
 coll-0.098
Token'd
Token ID1549
Feature activation+1.19e+01

Pos logit contributions
 never+0.139
 decided+0.137
pped+0.137
 stumbled+0.133
 rushed+0.123
Neg logit contributions
igsaw-0.291
aj-0.280
 types-0.257
 batch-0.255
udd-0.255
Token like
Token ID588
Feature activation+3.02e+00

Pos logit contributions
 decided+0.183
pped+0.177
 stumbled+0.169
 tried+0.166
 wouldn+0.160
Neg logit contributions
igsaw-0.417
aj-0.393
 batch-0.379
 types-0.371
 coll-0.363
Token from
Token ID422
Feature activation-3.04e-01

Pos logit contributions
 decided+0.063
 tried+0.060
 never+0.059
 came+0.058
 stumbled+0.056
Neg logit contributions
igsaw-0.103
aj-0.098
 batch-0.089
ummy-0.088
udd-0.086
Token the
Token ID262
Feature activation-8.43e+00

Pos logit contributions
igsaw+0.010
aj+0.009
 batch+0.008
ummy+0.008
 coll+0.008
Neg logit contributions
 decided-0.007
 tried-0.006
 came-0.006
 never-0.006
 stumbled-0.006
Token bowl
Token ID9396
Feature activation-9.55e-01

Pos logit contributions
igsaw+0.226
aj+0.216
udd+0.182
ummy+0.177
 batch+0.175
Neg logit contributions
 decided-0.247
 never-0.239
 tried-0.236
 came-0.231
 stumbled-0.221
Token!"
Token ID2474
Feature activation-1.54e+00

Pos logit contributions
igsaw+0.034
aj+0.032
 batch+0.029
ummy+0.029
udd+0.028
Neg logit contributions
 decided-0.019
 tried-0.018
 never-0.018
 came-0.017
 stumbled-0.017
Token it
Token ID340
Feature activation+8.50e+00

Pos logit contributions
 decided+0.125
 tried+0.121
 never+0.116
 stumbled+0.115
 came+0.115
Neg logit contributions
igsaw-0.255
aj-0.236
 batch-0.230
ummy-0.227
udd-0.216
Token?
Token ID30
Feature activation+6.97e-01

Pos logit contributions
 decided+0.190
 tried+0.180
 never+0.179
 came+0.175
 dropped+0.166
Neg logit contributions
igsaw-0.289
aj-0.272
 batch-0.244
ummy-0.238
udd-0.236
Token I
Token ID314
Feature activation+8.82e+00

Pos logit contributions
 decided+0.018
 tried+0.017
 never+0.017
 came+0.016
 stumbled+0.016
Neg logit contributions
igsaw-0.021
aj-0.020
 batch-0.018
ummy-0.017
udd-0.017
Token knew
Token ID2993
Feature activation+3.04e+00

Pos logit contributions
pped+0.153
 decided+0.146
 never+0.138
 stumbled+0.137
Please+0.136
Neg logit contributions
igsaw-0.292
aj-0.287
udd-0.270
 batch-0.263
 former-0.249
Token you
Token ID345
Feature activation+7.99e+00

Pos logit contributions
 decided+0.046
 tried+0.043
 never+0.042
 came+0.041
 stumbled+0.038
Neg logit contributions
igsaw-0.123
aj-0.117
 batch-0.108
ummy-0.106
udd-0.105
Token'd
Token ID1549
Feature activation+1.19e+01

Pos logit contributions
pped+0.094
Please+0.088
 rushed+0.088
 tried+0.087
 came+0.082
Neg logit contributions
aj-0.282
igsaw-0.279
udd-0.263
ummy-0.260
 types-0.258
Token like
Token ID588
Feature activation+2.47e+00

Pos logit contributions
 decided+0.221
pped+0.205
 tried+0.201
 came+0.196
 stumbled+0.195
Neg logit contributions
igsaw-0.398
aj-0.369
 batch-0.354
 difference-0.345
 coll-0.343
Token it
Token ID340
Feature activation+8.11e+00

Pos logit contributions
 decided+0.032
 tried+0.028
 never+0.027
 came+0.026
 stumbled+0.026
Neg logit contributions
igsaw-0.104
aj-0.100
 batch-0.094
ummy-0.092
 coll-0.090
Token."
Token ID526
Feature activation-1.51e+00

Pos logit contributions
 decided+0.167
 never+0.156
 tried+0.155
 came+0.151
 almost+0.144
Neg logit contributions
igsaw-0.294
aj-0.275
 batch-0.248
udd-0.242
ummy-0.241
Token
Token ID198
Feature activation-4.35e+00

Pos logit contributions
igsaw+0.050
aj+0.047
udd+0.041
 batch+0.041
umm+0.041
Neg logit contributions
 decided-0.036
 tried-0.034
 never-0.033
 came-0.033
 got-0.031
Token
Token ID198
Feature activation-4.53e+00

Pos logit contributions
igsaw+0.159
aj+0.147
umm+0.142
 batch+0.132
 coll+0.132
Neg logit contributions
 decided-0.089
 never-0.087
 tried-0.082
 came-0.081
 could-0.076
Token share
Token ID2648
Feature activation+2.71e+00

Pos logit contributions
 decided+0.130
 stumbled+0.127
pped+0.121
 came+0.118
 almost+0.118
Neg logit contributions
igsaw-0.204
aj-0.186
 coll-0.180
ummy-0.179
udd-0.178
Token and
Token ID290
Feature activation+1.85e+00

Pos logit contributions
 decided+0.055
 tried+0.052
 never+0.051
 came+0.050
 stumbled+0.050
Neg logit contributions
igsaw-0.094
aj-0.089
ummy-0.080
 batch-0.080
udd-0.079
Token that
Token ID326
Feature activation+3.11e+00

Pos logit contributions
pped+0.034
 decided+0.032
 stumbled+0.032
 almost+0.030
 came+0.030
Neg logit contributions
igsaw-0.061
aj-0.056
 coll-0.054
 batch-0.054
 types-0.054
Token sometimes
Token ID3360
Feature activation+5.18e+00

Pos logit contributions
 decided+0.040
 tried+0.036
 never+0.036
 came+0.035
 stumbled+0.035
Neg logit contributions
igsaw-0.126
aj-0.118
ummy-0.113
 batch-0.111
 goals-0.110
Token things
Token ID1243
Feature activation+7.89e+00

Pos logit contributions
 decided+0.083
 stumbled+0.074
 never+0.074
pped+0.074
 came+0.072
Neg logit contributions
igsaw-0.190
aj-0.177
ummy-0.170
 goals-0.170
 batch-0.166
Token can
Token ID460
Feature activation+1.19e+01

Pos logit contributions
 decided+0.162
 stumbled+0.153
pped+0.142
 never+0.138
 tried+0.137
Neg logit contributions
igsaw-0.258
aj-0.237
udd-0.231
ummy-0.220
 goals-0.218
Token break
Token ID2270
Feature activation+1.75e+00

Pos logit contributions
 decided+0.224
 stumbled+0.214
 came+0.199
 tried+0.198
 managed+0.197
Neg logit contributions
igsaw-0.413
ummy-0.371
aj-0.367
udd-0.350
 coll-0.349
Token.
Token ID13
Feature activation-1.69e-01

Pos logit contributions
 decided+0.036
 tried+0.034
 never+0.033
 stumbled+0.033
 came+0.032
Neg logit contributions
igsaw-0.060
aj-0.057
udd-0.052
ummy-0.052
 coll-0.050
Token<|endoftext|>
Token ID50256
Feature activation-3.21e+00

Pos logit contributions
igsaw+0.006
aj+0.006
 coll+0.005
 batch+0.005
 types+0.005
Neg logit contributions
 decided-0.004
 never-0.004
 tried-0.003
 could-0.003
 came-0.003
TokenOnce
Token ID7454
Feature activation+1.32e+00

Pos logit contributions
igsaw+0.110
aj+0.104
 batch+0.094
 coll+0.092
umm+0.091
Neg logit contributions
 decided-0.070
 tried-0.068
 came-0.068
 never-0.067
 stumbled-0.063
Token upon
Token ID2402
Feature activation-1.53e+00

Pos logit contributions
 decided+0.031
 came+0.031
 tried+0.031
 never+0.030
 got+0.030
Neg logit contributions
igsaw-0.042
aj-0.038
umm-0.036
 coll-0.035
 batch-0.035
Token food
Token ID2057
Feature activation+1.31e+00

Pos logit contributions
igsaw+0.129
aj+0.119
udd+0.104
uff+0.101
 batch+0.099
Neg logit contributions
 decided-0.103
 tried-0.096
 never-0.096
 came-0.093
 it-0.090
Token for
Token ID329
Feature activation+8.84e-01

Pos logit contributions
 decided+0.031
 tried+0.029
 never+0.029
 came+0.028
 stumbled+0.028
Neg logit contributions
igsaw-0.042
aj-0.040
 batch-0.036
ummy-0.035
udd-0.034
Token you
Token ID345
Feature activation+6.61e+00

Pos logit contributions
 decided+0.019
 tried+0.018
 never+0.018
 came+0.017
 stumbled+0.017
Neg logit contributions
igsaw-0.030
aj-0.028
 batch-0.026
ummy-0.025
 coll-0.024
Token if
Token ID611
Feature activation+3.72e+00

Pos logit contributions
 decided+0.159
 tried+0.153
 never+0.149
 came+0.147
 dropped+0.143
Neg logit contributions
igsaw-0.202
aj-0.195
 batch-0.170
ummy-0.170
udd-0.166
Token you
Token ID345
Feature activation+7.70e+00

Pos logit contributions
 decided+0.084
pped+0.083
 managed+0.078
 tried+0.078
 never+0.077
Neg logit contributions
igsaw-0.103
aj-0.100
ummy-0.096
 batch-0.091
 types-0.088
Token'd
Token ID1549
Feature activation+1.18e+01

Pos logit contributions
 decided+0.141
pped+0.139
 never+0.127
 tried+0.127
 stumbled+0.127
Neg logit contributions
igsaw-0.238
aj-0.232
udd-0.210
engu-0.207
 types-0.206
Token like
Token ID588
Feature activation+2.56e+00

Pos logit contributions
 decided+0.221
pped+0.214
 tried+0.194
 stumbled+0.190
 rushed+0.190
Neg logit contributions
igsaw-0.366
aj-0.352
 difference-0.338
 batch-0.332
 coll-0.326
Token."
Token ID526
Feature activation-1.59e+00

Pos logit contributions
 decided+0.061
 tried+0.058
 managed+0.057
 dropped+0.056
 stumbled+0.056
Neg logit contributions
igsaw-0.077
aj-0.073
 batch-0.068
ummy-0.068
 coll-0.064
Token
Token ID220
Feature activation-1.51e+00

Pos logit contributions
igsaw+0.052
aj+0.049
udd+0.044
umm+0.043
 batch+0.043
Neg logit contributions
 decided-0.038
 tried-0.036
 came-0.035
 never-0.035
 got-0.033
Token
Token ID198
Feature activation-4.17e+00

Pos logit contributions
igsaw+0.056
aj+0.051
umm+0.049
 batch+0.049
 coll+0.048
Neg logit contributions
 never-0.026
 decided-0.026
 came-0.026
 tried-0.025
 could-0.025
Token
Token ID198
Feature activation-4.42e+00

Pos logit contributions
igsaw+0.158
aj+0.151
umm+0.142
 goals+0.134
udd+0.134
Neg logit contributions
 decided-0.080
 never-0.076
 tried-0.074
 came-0.070
 could-0.066
TokenSee
Token ID6214
Feature activation+1.57e+00

Pos logit contributions
igsaw+0.017
aj+0.015
 batch+0.014
udd+0.014
ummy+0.014
Neg logit contributions
 decided-0.011
 tried-0.011
 came-0.011
 never-0.010
 dropped-0.010
Token,
Token ID11
Feature activation-6.86e-01

Pos logit contributions
 decided+0.035
 tried+0.034
 never+0.033
 came+0.033
 stumbled+0.031
Neg logit contributions
igsaw-0.053
aj-0.050
 batch-0.045
ummy-0.044
udd-0.044
Token I
Token ID314
Feature activation+9.24e+00

Pos logit contributions
igsaw+0.023
aj+0.021
 batch+0.020
ummy+0.019
udd+0.019
Neg logit contributions
 decided-0.015
 tried-0.014
 never-0.014
 came-0.013
 stumbled-0.013
Token knew
Token ID2993
Feature activation+2.87e+00

Pos logit contributions
 decided+0.141
 never+0.134
pped+0.132
 stumbled+0.128
Please+0.126
Neg logit contributions
aj-0.328
igsaw-0.322
udd-0.306
 batch-0.293
 former-0.275
Token you
Token ID345
Feature activation+7.97e+00

Pos logit contributions
 decided+0.053
 tried+0.050
 never+0.050
 came+0.048
 stumbled+0.046
Neg logit contributions
igsaw-0.107
aj-0.102
 batch-0.092
ummy-0.091
udd-0.090
Token'd
Token ID1549
Feature activation+1.18e+01

Pos logit contributions
 tried+0.106
pped+0.106
 decided+0.103
 rushed+0.102
Please+0.100
Neg logit contributions
aj-0.277
igsaw-0.277
udd-0.258
ummy-0.253
 types-0.247
Token like
Token ID588
Feature activation+2.28e+00

Pos logit contributions
 decided+0.205
 tried+0.188
pped+0.183
 came+0.182
 stumbled+0.177
Neg logit contributions
igsaw-0.417
aj-0.393
 batch-0.367
udd-0.357
 coll-0.356
Token it
Token ID340
Feature activation+8.09e+00

Pos logit contributions
 decided+0.029
 tried+0.026
 never+0.026
 came+0.025
 stumbled+0.024
Neg logit contributions
igsaw-0.097
aj-0.093
 batch-0.086
ummy-0.085
udd-0.084
Token!"
Token ID2474
Feature activation-1.70e+00

Pos logit contributions
 decided+0.174
 never+0.164
 tried+0.163
 came+0.159
 almost+0.151
Neg logit contributions
igsaw-0.283
aj-0.266
 batch-0.239
udd-0.233
 coll-0.232
Token Alex
Token ID4422
Feature activation+3.31e+00

Pos logit contributions
igsaw+0.052
aj+0.048
 batch+0.043
udd+0.042
ummy+0.042
Neg logit contributions
 decided-0.044
 tried-0.042
 never-0.042
 came-0.041
 stumbled-0.039
Token was
Token ID373
Feature activation+3.05e+00

Pos logit contributions
 decided+0.058
 never+0.055
 tried+0.053
 came+0.052
 stumbled+0.051
Neg logit contributions
igsaw-0.120
aj-0.115
 batch-0.106
ummy-0.103
udd-0.103
Token learned
Token ID4499
Feature activation+2.05e+00

Pos logit contributions
igsaw+0.279
aj+0.258
 batch+0.225
ummy+0.220
udd+0.217
Neg logit contributions
 decided-0.291
 tried-0.281
 never-0.278
 came-0.274
 dropped-0.264
Token that
Token ID326
Feature activation+3.98e+00

Pos logit contributions
 decided+0.037
 never+0.035
 tried+0.033
 came+0.032
 dropped+0.030
Neg logit contributions
igsaw-0.080
aj-0.076
 batch-0.070
umm-0.069
ummy-0.068
Token even
Token ID772
Feature activation+4.60e+00

Pos logit contributions
 decided+0.070
 never+0.065
 tried+0.065
 came+0.062
 stumbled+0.058
Neg logit contributions
igsaw-0.154
aj-0.148
 batch-0.133
udd-0.131
ummy-0.131
Token though
Token ID996
Feature activation+4.21e+00

Pos logit contributions
 decided+0.100
 tried+0.095
 never+0.094
 came+0.092
 stumbled+0.088
Neg logit contributions
igsaw-0.156
aj-0.147
 batch-0.132
ummy-0.130
udd-0.129
Token things
Token ID1243
Feature activation+7.87e+00

Pos logit contributions
 decided+0.076
 tried+0.071
 never+0.070
 came+0.068
 stumbled+0.065
Neg logit contributions
igsaw-0.155
aj-0.148
 batch-0.135
ummy-0.134
 coll-0.130
Token can
Token ID460
Feature activation+1.18e+01

Pos logit contributions
 decided+0.158
 stumbled+0.145
pped+0.143
 never+0.141
 tried+0.140
Neg logit contributions
igsaw-0.261
aj-0.241
udd-0.224
ummy-0.221
 types-0.220
Token be
Token ID307
Feature activation+4.12e+00

Pos logit contributions
 decided+0.228
 stumbled+0.210
 tried+0.209
pped+0.206
 managed+0.203
Neg logit contributions
igsaw-0.394
aj-0.360
ummy-0.354
udd-0.335
 coll-0.335
Token hard
Token ID1327
Feature activation-1.16e+00

Pos logit contributions
 decided+0.103
 tried+0.097
 never+0.096
 came+0.095
 stumbled+0.095
Neg logit contributions
igsaw-0.119
aj-0.114
udd-0.099
 batch-0.098
 coll-0.097
Token,
Token ID11
Feature activation-9.91e-01

Pos logit contributions
igsaw+0.038
aj+0.036
ummy+0.033
udd+0.032
 batch+0.032
Neg logit contributions
 decided-0.025
 tried-0.024
 never-0.023
 came-0.023
 stumbled-0.023
Token she
Token ID673
Feature activation+7.98e+00

Pos logit contributions
igsaw+0.038
aj+0.036
 batch+0.033
ummy+0.033
 coll+0.032
Neg logit contributions
 decided-0.016
 tried-0.015
 came-0.015
 never-0.014
 stumbled-0.014
Token can
Token ID460
Feature activation+1.00e+01

Pos logit contributions
pped+0.108
 decided+0.106
 stumbled+0.099
 came+0.099
 dropped+0.096
Neg logit contributions
aj-0.283
igsaw-0.283
udd-0.272
 goals-0.262
 batch-0.256
Token,
Token ID11
Feature activation-4.65e-01

Pos logit contributions
 decided+0.019
 tried+0.018
 never+0.018
 came+0.017
 stumbled+0.017
Neg logit contributions
igsaw-0.029
aj-0.027
ummy-0.025
 batch-0.024
udd-0.024
Token "
Token ID366
Feature activation-6.23e-01

Pos logit contributions
igsaw+0.011
aj+0.011
 batch+0.009
ummy+0.009
 coll+0.008
Neg logit contributions
 decided-0.014
 tried-0.014
 never-0.013
 stumbled-0.013
 managed-0.013
TokenI
Token ID40
Feature activation+8.08e+00

Pos logit contributions
igsaw+0.021
aj+0.020
 batch+0.018
ummy+0.018
udd+0.017
Neg logit contributions
 decided-0.013
 tried-0.013
 never-0.012
 dropped-0.012
 came-0.012
Token knew
Token ID2993
Feature activation+2.96e+00

Pos logit contributions
pped+0.167
 decided+0.146
Please+0.146
 unable+0.140
 tried+0.138
Neg logit contributions
aj-0.248
igsaw-0.234
udd-0.224
 batch-0.216
 former-0.204
Token you
Token ID345
Feature activation+7.91e+00

Pos logit contributions
 decided+0.059
 tried+0.055
 came+0.053
 never+0.052
 stumbled+0.052
Neg logit contributions
igsaw-0.103
aj-0.099
ummy-0.089
 batch-0.087
udd-0.086
Token'd
Token ID1549
Feature activation+1.18e+01

Pos logit contributions
pped+0.112
Please+0.100
 tried+0.098
 rushed+0.094
 decided+0.093
Neg logit contributions
aj-0.277
igsaw-0.266
udd-0.250
ummy-0.247
 types-0.246
Token keep
Token ID1394
Feature activation+2.05e+00

Pos logit contributions
 decided+0.217
 tried+0.204
pped+0.203
 came+0.194
 stumbled+0.189
Neg logit contributions
igsaw-0.392
aj-0.374
 batch-0.345
 difference-0.339
 coll-0.338
Token your
Token ID534
Feature activation-5.02e+00

Pos logit contributions
 decided+0.054
 tried+0.049
 came+0.049
 managed+0.048
 stumbled+0.048
Neg logit contributions
igsaw-0.060
aj-0.057
ummy-0.052
 batch-0.050
 coll-0.049
Token promise
Token ID6991
Feature activation+8.92e-01

Pos logit contributions
igsaw+0.139
aj+0.125
udd+0.113
 batch+0.111
ummy+0.108
Neg logit contributions
 decided-0.139
 tried-0.137
 never-0.136
 came-0.131
 dropped-0.128
Token."
Token ID526
Feature activation-1.57e+00

Pos logit contributions
 decided+0.020
 tried+0.020
 came+0.019
 dropped+0.018
 stumbled+0.018
Neg logit contributions
igsaw-0.028
aj-0.028
ummy-0.025
 batch-0.024
udd-0.024
Token
Token ID220
Feature activation-1.52e+00

Pos logit contributions
igsaw+0.046
aj+0.042
 batch+0.037
udd+0.036
ummy+0.036
Neg logit contributions
 decided-0.043
 tried-0.041
 never-0.041
 came-0.040
 stumbled-0.039
Token can
Token ID460
Feature activation+1.02e+01

Pos logit contributions
 decided+0.151
pped+0.143
 never+0.138
 stumbled+0.132
 tried+0.132
Neg logit contributions
igsaw-0.307
aj-0.299
udd-0.273
 batch-0.270
ay-0.255
Token help
Token ID1037
Feature activation+8.85e-01

Pos logit contributions
 decided+0.205
 came+0.187
 tried+0.185
 stumbled+0.185
 managed+0.178
Neg logit contributions
igsaw-0.356
aj-0.330
ummy-0.306
 batch-0.302
udd-0.292
Token you
Token ID345
Feature activation+7.04e+00

Pos logit contributions
 decided+0.016
 never+0.015
 tried+0.015
 came+0.014
 almost+0.013
Neg logit contributions
igsaw-0.034
aj-0.032
 batch-0.029
udd-0.029
ummy-0.028
Token if
Token ID611
Feature activation+4.10e+00

Pos logit contributions
 decided+0.144
 tried+0.135
 came+0.133
 never+0.132
 stumbled+0.129
Neg logit contributions
igsaw-0.245
aj-0.230
 batch-0.208
ummy-0.207
udd-0.203
Token you
Token ID345
Feature activation+8.02e+00

Pos logit contributions
 decided+0.090
 tried+0.083
 never+0.082
 came+0.081
 managed+0.080
Neg logit contributions
igsaw-0.130
aj-0.125
ummy-0.114
 batch-0.111
 coll-0.105
Token'd
Token ID1549
Feature activation+1.18e+01

Pos logit contributions
 decided+0.140
 never+0.128
 stumbled+0.127
pped+0.126
 tried+0.124
Neg logit contributions
igsaw-0.272
aj-0.263
udd-0.241
ummy-0.232
 goals-0.231
Token like
Token ID588
Feature activation+2.62e+00

Pos logit contributions
 decided+0.212
pped+0.189
 tried+0.188
 came+0.186
 stumbled+0.185
Neg logit contributions
igsaw-0.405
aj-0.384
 batch-0.356
udd-0.346
 coll-0.346
Token."
Token ID526
Feature activation-1.31e+00

Pos logit contributions
 decided+0.045
 tried+0.041
 never+0.041
 came+0.040
 stumbled+0.038
Neg logit contributions
igsaw-0.101
aj-0.097
 batch-0.088
ummy-0.087
udd-0.086
Token The
Token ID383
Feature activation-9.11e+00

Pos logit contributions
igsaw+0.043
aj+0.040
udd+0.037
umm+0.036
 batch+0.036
Neg logit contributions
 decided-0.031
 tried-0.030
 never-0.029
 came-0.028
 stumbled-0.027
Token shell
Token ID7582
Feature activation+8.11e-01

Pos logit contributions
igsaw+0.272
aj+0.258
udd+0.228
 batch+0.218
ummy+0.218
Neg logit contributions
 decided-0.243
 tried-0.233
 came-0.224
 never-0.224
 dropped-0.217
Token was
Token ID373
Feature activation+3.68e+00

Pos logit contributions
 decided+0.015
 tried+0.014
 never+0.014
 came+0.013
 stumbled+0.012
Neg logit contributions
igsaw-0.031
aj-0.029
 batch-0.026
ummy-0.026
udd-0.026
Token he
Token ID339
Feature activation+8.60e+00

Pos logit contributions
 decided+0.074
 tried+0.068
 came+0.066
 never+0.065
 dropped+0.064
Neg logit contributions
igsaw-0.149
aj-0.142
 batch-0.131
ummy-0.129
 coll-0.124
Token also
Token ID635
Feature activation+4.25e+00

Pos logit contributions
 decided+0.120
pped+0.111
 tried+0.107
 came+0.105
 stumbled+0.102
Neg logit contributions
igsaw-0.317
aj-0.317
udd-0.288
 batch-0.288
 goals-0.279
Token learned
Token ID4499
Feature activation+2.67e+00

Pos logit contributions
 decided+0.071
 tried+0.065
 came+0.063
 never+0.063
 stumbled+0.062
Neg logit contributions
igsaw-0.155
aj-0.152
 batch-0.138
udd-0.136
 coll-0.132
Token that
Token ID326
Feature activation+3.62e+00

Pos logit contributions
 decided+0.045
 never+0.042
 tried+0.041
 came+0.038
 dropped+0.036
Neg logit contributions
igsaw-0.106
aj-0.100
 batch-0.093
ummy-0.091
umm-0.090
Token accidents
Token ID17390
Feature activation+5.26e+00

Pos logit contributions
 decided+0.061
 tried+0.057
 never+0.056
 came+0.054
 stumbled+0.051
Neg logit contributions
igsaw-0.141
aj-0.134
 batch-0.123
ummy-0.121
udd-0.120
Token can
Token ID460
Feature activation+1.18e+01

Pos logit contributions
 decided+0.124
 stumbled+0.115
 tried+0.111
 never+0.109
 came+0.106
Neg logit contributions
igsaw-0.163
aj-0.145
udd-0.137
ummy-0.136
 types-0.132
Token happen
Token ID1645
Feature activation+1.06e+00

Pos logit contributions
 decided+0.256
 stumbled+0.244
 tried+0.232
pped+0.231
 came+0.228
Neg logit contributions
igsaw-0.371
ummy-0.329
aj-0.323
 coll-0.319
 difference-0.312
Token and
Token ID290
Feature activation+2.69e+00

Pos logit contributions
 decided+0.022
 tried+0.022
 stumbled+0.021
 dropped+0.021
 came+0.021
Neg logit contributions
igsaw-0.034
aj-0.033
ummy-0.031
udd-0.030
 goals-0.029
Token it
Token ID340
Feature activation+7.99e+00

Pos logit contributions
pped+0.052
 decided+0.051
 stumbled+0.049
 came+0.047
 tried+0.046
Neg logit contributions
igsaw-0.086
aj-0.081
 goals-0.076
 difference-0.076
 types-0.076
Token's
Token ID338
Feature activation-1.90e+00

Pos logit contributions
 decided+0.206
 stumbled+0.195
pped+0.194
 tried+0.188
 came+0.186
Neg logit contributions
igsaw-0.211
aj-0.200
udd-0.184
 goals-0.179
ummy-0.175
Token important
Token ID1593
Feature activation-2.00e+00

Pos logit contributions
aj+0.043
igsaw+0.043
 goals+0.041
 former+0.040
 difference+0.039
Neg logit contributions
 stumbled-0.051
 came-0.050
 decided-0.050
pped-0.048
 bumped-0.048
TokenI
Token ID40
Feature activation+7.94e+00

Pos logit contributions
 decided+0.012
 never+0.011
 tried+0.011
 came+0.011
 stumbled+0.011
Neg logit contributions
igsaw-0.016
aj-0.015
 batch-0.014
ummy-0.013
 coll-0.013
Token don
Token ID836
Feature activation+4.88e+00

Pos logit contributions
pped+0.145
 decided+0.139
 never+0.129
 tried+0.127
 rushed+0.126
Neg logit contributions
aj-0.257
igsaw-0.253
udd-0.236
 batch-0.234
 coll-0.219
Token't
Token ID470
Feature activation+6.95e+00

Pos logit contributions
 decided+0.074
 tried+0.065
 managed+0.062
 stumbled+0.062
 came+0.061
Neg logit contributions
igsaw-0.193
ummy-0.179
aj-0.173
ay-0.172
 batch-0.171
Token think
Token ID892
Feature activation+4.63e+00

Pos logit contributions
pped+0.131
 decided+0.130
 wouldn+0.130
 stumbled+0.123
 never+0.123
Neg logit contributions
igsaw-0.221
aj-0.191
 batch-0.191
udd-0.190
 difference-0.188
Token it
Token ID340
Feature activation+9.13e+00

Pos logit contributions
 decided+0.046
 tried+0.043
 never+0.043
 came+0.040
 almost+0.037
Neg logit contributions
igsaw-0.215
aj-0.206
 batch-0.191
udd-0.189
umm-0.189
Token can
Token ID460
Feature activation+1.17e+01

Pos logit contributions
 decided+0.235
 tried+0.226
 never+0.223
 came+0.219
 got+0.210
Neg logit contributions
igsaw-0.282
aj-0.263
 batch-0.231
ummy-0.229
udd-0.223
Token talk
Token ID1561
Feature activation+1.33e+00

Pos logit contributions
 decided+0.223
 tried+0.206
 stumbled+0.200
 managed+0.199
 never+0.196
Neg logit contributions
igsaw-0.402
aj-0.378
ummy-0.361
 batch-0.356
 coll-0.345
Token,"
Token ID553
Feature activation-2.56e+00

Pos logit contributions
 decided+0.028
 never+0.026
 tried+0.026
 came+0.025
 got+0.024
Neg logit contributions
igsaw-0.049
aj-0.046
 batch-0.041
ummy-0.040
umm-0.040
Token Anna
Token ID11735
Feature activation+1.40e+00

Pos logit contributions
igsaw+0.080
aj+0.075
 batch+0.066
udd+0.066
ummy+0.065
Neg logit contributions
 decided-0.065
 tried-0.063
 never-0.062
 came-0.061
 dropped-0.058
Token says
Token ID1139
Feature activation-7.03e-01

Pos logit contributions
 decided+0.044
 tried+0.043
 never+0.042
 came+0.042
 stumbled+0.040
Neg logit contributions
igsaw-0.035
aj-0.032
 batch-0.027
ummy-0.027
udd-0.026
Token.
Token ID13
Feature activation-1.09e+00

Pos logit contributions
igsaw+0.021
aj+0.020
ummy+0.019
 coll+0.018
 batch+0.018
Neg logit contributions
 decided-0.016
 never-0.015
 stumbled-0.015
 tried-0.014
 managed-0.014
Token you
Token ID345
Feature activation+6.39e+00

Pos logit contributions
igsaw+0.002
aj+0.002
udd+0.002
 batch+0.002
umm+0.002
Neg logit contributions
 decided-0.001
 tried-0.001
 never-0.001
 it-0.001
 almost-0.001
Token feel
Token ID1254
Feature activation+2.23e+00

Pos logit contributions
 decided+0.130
 tried+0.122
 never+0.121
 came+0.117
 dropped+0.112
Neg logit contributions
igsaw-0.227
aj-0.216
 batch-0.195
ummy-0.192
udd-0.190
Token better
Token ID1365
Feature activation-5.32e-01

Pos logit contributions
 decided+0.051
 never+0.048
 tried+0.048
 came+0.047
 stumbled+0.047
Neg logit contributions
igsaw-0.071
aj-0.067
 batch-0.060
udd-0.059
ummy-0.059
Token if
Token ID611
Feature activation+3.41e+00

Pos logit contributions
igsaw+0.017
aj+0.016
ummy+0.015
 batch+0.014
udd+0.014
Neg logit contributions
 decided-0.012
 tried-0.012
 came-0.011
 never-0.011
 stumbled-0.011
Token you
Token ID345
Feature activation+7.51e+00

Pos logit contributions
 decided+0.069
 tried+0.064
 never+0.063
 came+0.062
 dropped+0.060
Neg logit contributions
igsaw-0.119
aj-0.112
ummy-0.102
 batch-0.100
 coll-0.098
Token'd
Token ID1549
Feature activation+1.17e+01

Pos logit contributions
 decided+0.133
pped+0.124
 stumbled+0.122
 never+0.122
 came+0.119
Neg logit contributions
igsaw-0.249
aj-0.238
udd-0.224
 batch-0.211
 types-0.210
Token like
Token ID588
Feature activation+2.16e+00

Pos logit contributions
 decided+0.212
pped+0.196
 tried+0.189
 came+0.187
 stumbled+0.186
Neg logit contributions
igsaw-0.398
aj-0.380
 difference-0.348
 batch-0.347
udd-0.346
Token."
Token ID526
Feature activation-1.50e+00

Pos logit contributions
 decided+0.040
 tried+0.037
 never+0.037
 came+0.036
 stumbled+0.035
Neg logit contributions
igsaw-0.080
aj-0.076
 batch-0.069
ummy-0.068
udd-0.067
Token Toby
Token ID37578
Feature activation+2.80e+00

Pos logit contributions
igsaw+0.042
aj+0.040
 batch+0.035
udd+0.034
ummy+0.033
Neg logit contributions
 decided-0.043
 tried-0.041
 never-0.041
 came-0.040
 stumbled-0.038
Token nodded
Token ID14464
Feature activation+1.18e+00

Pos logit contributions
 decided+0.049
 never+0.047
 tried+0.045
pped+0.044
 stumbled+0.044
Neg logit contributions
igsaw-0.100
aj-0.095
 batch-0.088
udd-0.085
ummy-0.085
Token sadly
Token ID21098
Feature activation+2.91e+00

Pos logit contributions
 never+0.027
 stumbled+0.027
 decided+0.026
 managed+0.025
 tried+0.025
Neg logit contributions
igsaw-0.033
aj-0.031
ummy-0.029
 coll-0.028
 batch-0.028
Token't
Token ID470
Feature activation+7.22e+00

Pos logit contributions
 decided+0.048
 tried+0.042
 never+0.041
 came+0.038
 stumbled+0.035
Neg logit contributions
igsaw-0.241
aj-0.230
 batch-0.214
ummy-0.213
udd-0.210
Token it
Token ID340
Feature activation+9.04e+00

Pos logit contributions
 decided+0.094
 tried+0.087
 never+0.084
 came+0.080
 stumbled+0.077
Neg logit contributions
igsaw-0.310
aj-0.294
 batch-0.274
ummy-0.271
udd-0.268
Token incredible
Token ID8082
Feature activation-4.74e+00

Pos logit contributions
 decided+0.246
 tried+0.235
 never+0.234
 came+0.234
 got+0.226
Neg logit contributions
igsaw-0.268
aj-0.252
 batch-0.220
umm-0.211
ummy-0.208
Token how
Token ID703
Feature activation+3.28e+00

Pos logit contributions
igsaw+0.164
aj+0.154
 batch+0.139
ummy+0.135
udd+0.135
Neg logit contributions
 decided-0.103
 tried-0.098
 never-0.097
 came-0.095
 stumbled-0.090
Token nature
Token ID3450
Feature activation+2.53e+00

Pos logit contributions
 decided+0.069
 tried+0.065
 never+0.064
 came+0.062
 stumbled+0.060
Neg logit contributions
igsaw-0.116
aj-0.110
 batch-0.099
ummy-0.097
udd-0.096
Token can
Token ID460
Feature activation+1.17e+01

Pos logit contributions
 decided+0.062
 never+0.058
 tried+0.057
 stumbled+0.056
 came+0.055
Neg logit contributions
igsaw-0.075
aj-0.069
 batch-0.064
udd-0.064
ummy-0.063
Token be
Token ID307
Feature activation+3.56e+00

Pos logit contributions
 decided+0.229
 tried+0.216
 managed+0.216
 stumbled+0.211
pped+0.210
Neg logit contributions
igsaw-0.374
ummy-0.344
aj-0.343
 batch-0.328
 coll-0.327
Token so
Token ID523
Feature activation+3.15e+00

Pos logit contributions
 decided+0.083
 tried+0.079
 never+0.079
 came+0.076
 stumbled+0.075
Neg logit contributions
igsaw-0.110
aj-0.106
 batch-0.093
udd-0.092
ummy-0.091
Token beautiful
Token ID4950
Feature activation-5.06e+00

Pos logit contributions
 decided+0.105
 tried+0.104
 came+0.101
 never+0.101
pped+0.100
Neg logit contributions
igsaw-0.064
aj-0.059
ummy-0.050
udd-0.050
 batch-0.049
Token?"
Token ID1701
Feature activation-1.56e+00

Pos logit contributions
igsaw+0.166
aj+0.157
 batch+0.141
ummy+0.139
udd+0.137
Neg logit contributions
 decided-0.115
 tried-0.110
 never-0.109
 came-0.106
 stumbled-0.102
Token Lily
Token ID20037
Feature activation+1.44e+00

Pos logit contributions
igsaw+0.053
aj+0.048
umm+0.044
ummy+0.043
 types+0.043
Neg logit contributions
 decided-0.037
 tried-0.036
 came-0.035
 never-0.034
 got-0.033
Token I
Token ID314
Feature activation+9.08e+00

Pos logit contributions
 decided+0.036
 never+0.035
 tried+0.035
 came+0.034
 could+0.033
Neg logit contributions
igsaw-0.046
aj-0.044
 batch-0.040
udd-0.039
 coll-0.039
Token love
Token ID1842
Feature activation-9.75e-02

Pos logit contributions
 decided+0.163
pped+0.162
Please+0.148
 tried+0.148
 stumbled+0.145
Neg logit contributions
igsaw-0.292
aj-0.287
udd-0.266
 batch-0.256
ay-0.251
Token you
Token ID345
Feature activation+7.27e+00

Pos logit contributions
igsaw+0.004
aj+0.003
udd+0.003
 batch+0.003
ummy+0.003
Neg logit contributions
 decided-0.002
 never-0.002
 tried-0.002
 came-0.002
 almost-0.002
Token and
Token ID290
Feature activation+2.35e+00

Pos logit contributions
 decided+0.147
 never+0.142
 tried+0.137
 came+0.131
 almost+0.128
Neg logit contributions
igsaw-0.268
aj-0.248
 batch-0.225
umm-0.222
udd-0.219
Token nothing
Token ID2147
Feature activation+4.19e+00

Pos logit contributions
 decided+0.050
 tried+0.048
 never+0.047
 came+0.046
 stumbled+0.044
Neg logit contributions
igsaw-0.081
aj-0.077
 batch-0.069
ummy-0.068
udd-0.067
Token can
Token ID460
Feature activation+1.16e+01

Pos logit contributions
 decided+0.091
 tried+0.087
 never+0.087
 came+0.084
 dropped+0.080
Neg logit contributions
igsaw-0.146
aj-0.137
 batch-0.124
ummy-0.121
udd-0.119
Token change
Token ID1487
Feature activation+6.55e-01

Pos logit contributions
 decided+0.231
 tried+0.211
 stumbled+0.210
 came+0.205
 managed+0.201
Neg logit contributions
igsaw-0.394
aj-0.363
ummy-0.344
 coll-0.336
 batch-0.333
Token that
Token ID326
Feature activation+3.46e+00

Pos logit contributions
 decided+0.014
 never+0.013
 tried+0.013
 came+0.012
 almost+0.012
Neg logit contributions
igsaw-0.023
aj-0.022
 batch-0.020
ummy-0.019
umm-0.019
Token."
Token ID526
Feature activation-1.33e+00

Pos logit contributions
 decided+0.073
 tried+0.069
 never+0.069
 came+0.067
 got+0.063
Neg logit contributions
igsaw-0.122
aj-0.117
 batch-0.104
ummy-0.102
udd-0.102
Token
Token ID220
Feature activation-1.30e+00

Pos logit contributions
igsaw+0.044
aj+0.040
 batch+0.036
udd+0.036
umm+0.036
Neg logit contributions
 decided-0.032
 tried-0.030
 never-0.030
 came-0.029
 got-0.028
Token
Token ID198
Feature activation-4.07e+00

Pos logit contributions
igsaw+0.049
aj+0.044
umm+0.043
 batch+0.043
 coll+0.042
Neg logit contributions
 decided-0.022
 never-0.022
 came-0.022
 tried-0.021
 could-0.021
Token respect
Token ID2461
Feature activation-2.42e-01

Pos logit contributions
 decided+0.100
 came+0.094
 stumbled+0.093
 managed+0.091
 could+0.091
Neg logit contributions
igsaw-0.170
aj-0.155
ummy-0.147
 coll-0.142
 former-0.142
Token them
Token ID606
Feature activation+5.55e+00

Pos logit contributions
igsaw+0.008
aj+0.008
 batch+0.007
ummy+0.007
udd+0.007
Neg logit contributions
 decided-0.005
 tried-0.005
 never-0.005
 came-0.005
 stumbled-0.005
Token,
Token ID11
Feature activation-8.91e-01

Pos logit contributions
 decided+0.097
 never+0.091
 tried+0.090
 came+0.084
 got+0.080
Neg logit contributions
igsaw-0.216
aj-0.204
 batch-0.187
ummy-0.182
udd-0.181
Token because
Token ID780
Feature activation+4.62e+00

Pos logit contributions
igsaw+0.033
aj+0.032
 batch+0.029
 coll+0.029
ummy+0.029
Neg logit contributions
 decided-0.014
 tried-0.013
 came-0.013
 stumbled-0.013
pped-0.013
Token things
Token ID1243
Feature activation+7.98e+00

Pos logit contributions
 decided+0.076
 tried+0.072
 came+0.069
 never+0.068
 stumbled+0.066
Neg logit contributions
igsaw-0.176
aj-0.166
ummy-0.155
 batch-0.153
 coll-0.148
Token can
Token ID460
Feature activation+1.16e+01

Pos logit contributions
 decided+0.186
 stumbled+0.175
pped+0.172
 tried+0.165
 never+0.164
Neg logit contributions
igsaw-0.238
aj-0.220
udd-0.205
 types-0.201
ummy-0.200
Token go
Token ID467
Feature activation+4.62e+00

Pos logit contributions
 decided+0.238
 stumbled+0.228
pped+0.221
 managed+0.220
 tried+0.215
Neg logit contributions
igsaw-0.368
ummy-0.341
aj-0.331
 coll-0.323
 difference-0.321
Token wrong
Token ID2642
Feature activation-4.98e-01

Pos logit contributions
 decided+0.094
 stumbled+0.092
 tried+0.091
 managed+0.090
 rushed+0.089
Neg logit contributions
igsaw-0.138
aj-0.133
udd-0.123
 new-0.122
 coll-0.122
Token very
Token ID845
Feature activation+8.25e-01

Pos logit contributions
igsaw+0.018
aj+0.018
 batch+0.016
ummy+0.016
udd+0.016
Neg logit contributions
 decided-0.009
 tried-0.009
 never-0.009
 came-0.008
 stumbled-0.008
Token quickly
Token ID2952
Feature activation+6.28e+00

Pos logit contributions
 decided+0.019
 tried+0.019
 came+0.019
 never+0.018
 stumbled+0.018
Neg logit contributions
igsaw-0.025
aj-0.024
ummy-0.022
udd-0.021
 goals-0.021
Token if
Token ID611
Feature activation+3.93e+00

Pos logit contributions
 decided+0.119
 tried+0.112
 never+0.111
 came+0.107
 stumbled+0.104
Neg logit contributions
igsaw-0.227
aj-0.217
 batch-0.196
ummy-0.195
udd-0.193
Token He
Token ID679
Feature activation+8.18e+00

Pos logit contributions
igsaw+0.001
aj+0.001
 coll+0.001
 batch+0.001
 bou+0.001
Neg logit contributions
 decided-0.001
 never-0.001
 tried-0.001
 could-0.001
 came-0.001
Token also
Token ID635
Feature activation+3.23e+00

Pos logit contributions
pped+0.119
 stumbled+0.118
 came+0.117
 decided+0.116
 tried+0.112
Neg logit contributions
aj-0.282
igsaw-0.278
udd-0.270
 batch-0.261
 coll-0.253
Token learned
Token ID4499
Feature activation+2.00e+00

Pos logit contributions
pped+0.054
 stumbled+0.054
 decided+0.053
 came+0.052
 almost+0.052
Neg logit contributions
igsaw-0.109
aj-0.106
udd-0.101
 batch-0.100
 coll-0.097
Token that
Token ID326
Feature activation+3.49e+00

Pos logit contributions
 decided+0.039
 tried+0.037
 came+0.036
 stumbled+0.036
 never+0.035
Neg logit contributions
igsaw-0.071
aj-0.066
 batch-0.061
ummy-0.060
udd-0.060
Token accidents
Token ID17390
Feature activation+5.16e+00

Pos logit contributions
 decided+0.055
 tried+0.051
 came+0.049
 never+0.049
 dropped+0.048
Neg logit contributions
igsaw-0.134
aj-0.126
 batch-0.118
ummy-0.118
 coll-0.114
Token can
Token ID460
Feature activation+1.16e+01

Pos logit contributions
 decided+0.119
 stumbled+0.111
 tried+0.106
 never+0.105
 came+0.102
Neg logit contributions
igsaw-0.162
aj-0.144
udd-0.139
ummy-0.137
 types-0.132
Token happen
Token ID1645
Feature activation+1.19e+00

Pos logit contributions
 decided+0.251
 stumbled+0.233
 tried+0.224
 managed+0.219
 came+0.219
Neg logit contributions
igsaw-0.377
ummy-0.335
aj-0.332
 coll-0.323
udd-0.318
Token,
Token ID11
Feature activation-3.15e-01

Pos logit contributions
 decided+0.027
 tried+0.026
 stumbled+0.025
 dropped+0.025
 came+0.025
Neg logit contributions
igsaw-0.037
aj-0.034
ummy-0.033
udd-0.032
 goals-0.031
Token but
Token ID475
Feature activation+6.90e+00

Pos logit contributions
igsaw+0.011
aj+0.010
ummy+0.009
 batch+0.009
udd+0.009
Neg logit contributions
 decided-0.006
 tried-0.006
 came-0.006
 stumbled-0.006
 dropped-0.006
Token it
Token ID340
Feature activation+7.77e+00

Pos logit contributions
 decided+0.100
 came+0.089
 tried+0.089
pped+0.088
 dropped+0.087
Neg logit contributions
igsaw-0.270
aj-0.252
ummy-0.246
 batch-0.240
 types-0.232
Token's
Token ID338
Feature activation-1.99e+00

Pos logit contributions
 decided+0.203
 stumbled+0.188
 came+0.184
 tried+0.184
 dropped+0.182
Neg logit contributions
igsaw-0.215
aj-0.196
udd-0.182
ummy-0.181
 batch-0.177
Token very
Token ID845
Feature activation+1.31e+00

Pos logit contributions
 decided+0.068
 tried+0.064
 came+0.062
 never+0.062
 stumbled+0.060
Neg logit contributions
igsaw-0.117
aj-0.112
 batch-0.102
ummy-0.099
udd-0.098
Token happy
Token ID3772
Feature activation-3.59e+00

Pos logit contributions
 decided+0.034
 tried+0.033
 never+0.032
 came+0.032
 stumbled+0.031
Neg logit contributions
igsaw-0.039
aj-0.037
 batch-0.033
ummy-0.032
udd-0.032
Token and
Token ID290
Feature activation+2.97e+00

Pos logit contributions
igsaw+0.120
aj+0.113
ummy+0.106
 batch+0.105
udd+0.100
Neg logit contributions
 decided-0.074
 tried-0.070
 dropped-0.067
 never-0.067
 stumbled-0.066
Token knew
Token ID2993
Feature activation+2.73e+00

Pos logit contributions
 decided+0.052
 tried+0.051
pped+0.050
 came+0.049
 stumbled+0.049
Neg logit contributions
igsaw-0.102
aj-0.099
 batch-0.090
ummy-0.088
udd-0.087
Token he
Token ID339
Feature activation+9.34e+00

Pos logit contributions
 decided+0.043
 tried+0.040
 came+0.038
 never+0.038
 stumbled+0.037
Neg logit contributions
igsaw-0.108
aj-0.102
 batch-0.094
ummy-0.093
udd-0.091
Token'd
Token ID1549
Feature activation+1.16e+01

Pos logit contributions
pped+0.144
ged+0.123
Please+0.112
 risking+0.107
 bumped+0.107
Neg logit contributions
 types-0.271
igsaw-0.269
udd-0.261
aj-0.261
 batch-0.249
Token never
Token ID1239
Feature activation+8.81e+00

Pos logit contributions
pped+0.165
 decided+0.164
ged+0.152
 tried+0.150
 stumbled+0.146
Neg logit contributions
igsaw-0.416
aj-0.374
 batch-0.370
 former-0.363
 difference-0.363
Token leave
Token ID2666
Feature activation+9.17e-01

Pos logit contributions
pped+0.135
 decided+0.131
 never+0.127
 almost+0.122
 wouldn+0.119
Neg logit contributions
igsaw-0.320
aj-0.292
 batch-0.274
 types-0.268
 difference-0.265
Token the
Token ID262
Feature activation-9.21e+00

Pos logit contributions
 decided+0.017
 tried+0.016
 came+0.015
 dropped+0.015
 stumbled+0.015
Neg logit contributions
igsaw-0.033
aj-0.030
ummy-0.028
 batch-0.028
 coll-0.027
Token house
Token ID2156
Feature activation+3.60e+00

Pos logit contributions
igsaw+0.245
aj+0.234
udd+0.200
 batch+0.196
ushes+0.196
Neg logit contributions
 decided-0.266
 never-0.260
 tried-0.256
 came-0.249
 stumbled-0.241
Token without
Token ID1231
Feature activation+8.56e-01

Pos logit contributions
 decided+0.076
 tried+0.073
 never+0.069
 came+0.069
 dropped+0.068
Neg logit contributions
igsaw-0.123
aj-0.114
 batch-0.104
ummy-0.103
udd-0.101
Token she
Token ID673
Feature activation+8.32e+00

Pos logit contributions
 decided+0.067
 tried+0.064
 never+0.063
 came+0.061
 stumbled+0.059
Neg logit contributions
igsaw-0.115
aj-0.109
 batch-0.098
ummy-0.097
udd-0.096
Token got
Token ID1392
Feature activation+1.78e+00

Pos logit contributions
pped+0.092
 him+0.089
 decided+0.086
Please+0.083
 possibly+0.082
Neg logit contributions
aj-0.273
udd-0.266
igsaw-0.237
 coll-0.230
 sym-0.229
Token rid
Token ID5755
Feature activation-4.15e+00

Pos logit contributions
 decided+0.035
 stumbled+0.034
 never+0.034
pped+0.034
 tried+0.034
Neg logit contributions
igsaw-0.055
aj-0.054
 batch-0.048
udd-0.047
 coll-0.047
Token of
Token ID286
Feature activation-2.20e+00

Pos logit contributions
igsaw+0.103
aj+0.093
ummy+0.084
udd+0.082
 batch+0.080
Neg logit contributions
 decided-0.124
 never-0.120
 tried-0.119
 stumbled-0.115
 almost-0.114
Token the
Token ID262
Feature activation-9.75e+00

Pos logit contributions
igsaw+0.074
aj+0.069
 batch+0.063
ummy+0.062
 coll+0.061
Neg logit contributions
 decided-0.049
 tried-0.045
 never-0.044
 came-0.044
 stumbled-0.043
Token intr
Token ID9913
Feature activation-1.70e+01

Pos logit contributions
igsaw+0.268
aj+0.252
 batch+0.221
ummy+0.216
udd+0.213
Neg logit contributions
 decided-0.272
 tried-0.260
 never-0.258
 came-0.251
 stumbled-0.246
Tokenuders
Token ID48739
Feature activation+1.54e+00

Pos logit contributions
igsaw+0.431
aj+0.395
 batch+0.343
udd+0.327
ummy+0.326
Neg logit contributions
 decided-0.518
 never-0.501
 tried-0.500
 came-0.488
 stumbled-0.475
Token.
Token ID13
Feature activation-9.12e-01

Pos logit contributions
 decided+0.031
 tried+0.030
 never+0.029
 stumbled+0.028
 managed+0.028
Neg logit contributions
igsaw-0.049
aj-0.047
ummy-0.043
udd-0.042
 batch-0.042
Token She
Token ID1375
Feature activation+7.71e+00

Pos logit contributions
igsaw+0.034
aj+0.032
 batch+0.030
 coll+0.029
umm+0.029
Neg logit contributions
 decided-0.018
 never-0.018
 tried-0.016
 came-0.016
 could-0.016
Token did
Token ID750
Feature activation+5.52e+00

Pos logit contributions
pped+0.105
 decided+0.101
 stumbled+0.095
 tried+0.093
 came+0.089
Neg logit contributions
aj-0.280
igsaw-0.263
udd-0.252
 batch-0.251
 coll-0.245
Token not
Token ID407
Feature activation+6.29e+00

Pos logit contributions
 decided+0.080
 tried+0.070
 stumbled+0.068
 came+0.066
 managed+0.060
Neg logit contributions
igsaw-0.222
aj-0.212
 batch-0.193
udd-0.190
 coll-0.189
Token play
Token ID711
Feature activation-1.25e+00

Pos logit contributions
 decided+0.166
 stumbled+0.153
 came+0.152
 tried+0.148
pped+0.145
Neg logit contributions
igsaw-0.271
aj-0.259
 batch-0.244
ummy-0.233
 stacks-0.231
Token without
Token ID1231
Feature activation+1.32e-01

Pos logit contributions
igsaw+0.046
aj+0.044
 batch+0.039
ummy+0.039
udd+0.038
Neg logit contributions
 decided-0.025
 tried-0.023
 never-0.023
 came-0.022
 stumbled-0.021
Token going
Token ID1016
Feature activation+2.42e+00

Pos logit contributions
 decided+0.003
 never+0.003
 came+0.003
 stumbled+0.003
 tried+0.003
Neg logit contributions
igsaw-0.004
aj-0.004
 batch-0.004
 coll-0.003
 types-0.003
Token near
Token ID1474
Feature activation-2.51e+00

Pos logit contributions
 decided+0.051
 tried+0.050
 managed+0.048
 stumbled+0.047
 dropped+0.047
Neg logit contributions
igsaw-0.079
aj-0.073
ummy-0.070
udd-0.066
 batch-0.065
Token the
Token ID262
Feature activation-1.16e+01

Pos logit contributions
igsaw+0.088
aj+0.083
 batch+0.074
ummy+0.073
udd+0.073
Neg logit contributions
 decided-0.054
 tried-0.051
 never-0.051
 came-0.049
 dropped-0.047
Token sm
Token ID895
Feature activation-1.63e+01

Pos logit contributions
igsaw+0.316
aj+0.306
 batch+0.241
udd+0.238
ummy+0.230
Neg logit contributions
 decided-0.347
 never-0.338
 tried-0.335
 came-0.322
 dropped-0.319
Tokenelly
Token ID6148
Feature activation-1.06e+01

Pos logit contributions
igsaw+0.253
aj+0.236
 batch+0.173
 coll+0.160
udd+0.151
Neg logit contributions
 decided-0.651
 tried-0.630
 never-0.628
 came-0.622
 got-0.604
Token leaves
Token ID5667
Feature activation-5.82e-01

Pos logit contributions
igsaw+0.268
aj+0.249
 batch+0.210
udd+0.204
ummy+0.203
Neg logit contributions
 decided-0.329
 tried-0.319
 never-0.315
 came-0.310
 dropped-0.301
Token.
Token ID13
Feature activation-1.09e+00

Pos logit contributions
igsaw+0.021
aj+0.020
 batch+0.018
ummy+0.018
udd+0.018
Neg logit contributions
 decided-0.011
 tried-0.010
 never-0.010
 came-0.010
 stumbled-0.010
Token Tim
Token ID5045
Feature activation+1.66e+00

Pos logit contributions
igsaw+0.040
aj+0.037
 batch+0.034
 coll+0.034
opl+0.033
Neg logit contributions
 decided-0.023
 tried-0.021
 never-0.021
 came-0.020
 could-0.020
Token and
Token ID290
Feature activation+1.71e+00

Pos logit contributions
 decided+0.029
 tried+0.027
 never+0.027
 came+0.026
 stumbled+0.024
Neg logit contributions
igsaw-0.064
aj-0.061
 batch-0.056
ummy-0.055
udd-0.054
Token to
Token ID284
Feature activation+4.17e+00

Pos logit contributions
 decided+0.051
 tried+0.046
 never+0.046
 came+0.044
 stumbled+0.044
Neg logit contributions
igsaw-0.095
aj-0.090
 batch-0.084
ummy-0.082
 coll-0.080
Token get
Token ID651
Feature activation+1.54e+00

Pos logit contributions
 decided+0.090
 stumbled+0.084
pped+0.084
 wouldn+0.083
 managed+0.082
Neg logit contributions
igsaw-0.132
aj-0.120
 batch-0.113
ummy-0.111
 coll-0.108
Token away
Token ID1497
Feature activation+1.16e+00

Pos logit contributions
'd+0.039
 possibly+0.035
pped+0.035
 managed+0.035
 stumbled+0.034
Neg logit contributions
 new-0.035
aj-0.035
igsaw-0.034
 batch-0.034
 types-0.032
Token from
Token ID422
Feature activation-2.27e+00

Pos logit contributions
 decided+0.026
 tried+0.025
 never+0.024
 came+0.023
 stumbled+0.023
Neg logit contributions
igsaw-0.039
aj-0.036
ummy-0.033
 batch-0.033
udd-0.032
Token the
Token ID262
Feature activation-1.04e+01

Pos logit contributions
igsaw+0.064
aj+0.059
 batch+0.056
ummy+0.055
 goals+0.052
Neg logit contributions
 decided-0.059
 managed-0.054
 stumbled-0.053
 tried-0.053
 came-0.053
Token sm
Token ID895
Feature activation-1.61e+01

Pos logit contributions
igsaw+0.301
aj+0.283
 batch+0.243
ummy+0.234
udd+0.234
Neg logit contributions
 decided-0.289
 tried-0.287
 never-0.282
 came-0.274
 dropped-0.269
Tokenelly
Token ID6148
Feature activation-1.06e+01

Pos logit contributions
igsaw+0.217
aj+0.192
 batch+0.138
 coll+0.122
ummy+0.122
Neg logit contributions
 decided-0.679
 tried-0.658
 never-0.655
 came-0.649
 stumbled-0.634
Token sock
Token ID32263
Feature activation-2.66e+00

Pos logit contributions
igsaw+0.284
aj+0.261
 batch+0.230
udd+0.221
 coll+0.219
Neg logit contributions
 tried-0.308
 decided-0.307
 came-0.299
 never-0.292
 got-0.287
Token.
Token ID13
Feature activation-8.63e-01

Pos logit contributions
igsaw+0.090
aj+0.085
 batch+0.079
ummy+0.079
udd+0.076
Neg logit contributions
 decided-0.053
 tried-0.050
 never-0.049
 stumbled-0.048
 dropped-0.048
Token So
Token ID1406
Feature activation-4.65e-01

Pos logit contributions
igsaw+0.031
aj+0.030
 batch+0.026
 coll+0.026
udd+0.026
Neg logit contributions
 decided-0.019
 tried-0.019
 came-0.018
 never-0.018
 could-0.017
Token,
Token ID11
Feature activation-1.23e-01

Pos logit contributions
igsaw+0.012
aj+0.011
ummy+0.011
 batch+0.010
 goals+0.010
Neg logit contributions
 decided-0.012
pped-0.012
 never-0.011
 tried-0.011
 dropped-0.011
Token was
Token ID373
Feature activation+3.04e+00

Pos logit contributions
 decided+0.089
 tried+0.080
 never+0.080
 came+0.075
 stumbled+0.070
Neg logit contributions
igsaw-0.309
aj-0.303
 batch-0.278
udd-0.275
ummy-0.270
Token running
Token ID2491
Feature activation+7.45e-01

Pos logit contributions
 decided+0.062
 tried+0.059
 never+0.058
 came+0.056
 stumbled+0.054
Neg logit contributions
igsaw-0.106
aj-0.101
 batch-0.092
ummy-0.090
udd-0.089
Token around
Token ID1088
Feature activation+1.82e+00

Pos logit contributions
 decided+0.015
 tried+0.014
 never+0.014
 came+0.013
 stumbled+0.013
Neg logit contributions
igsaw-0.026
aj-0.025
 batch-0.023
udd-0.022
ummy-0.022
Token on
Token ID319
Feature activation-5.65e-01

Pos logit contributions
 decided+0.034
 tried+0.032
 never+0.032
 came+0.030
 stumbled+0.029
Neg logit contributions
igsaw-0.069
aj-0.065
 batch-0.059
ummy-0.058
udd-0.058
Token the
Token ID262
Feature activation-1.07e+01

Pos logit contributions
aj+0.022
igsaw+0.022
udd+0.019
umm+0.019
ummy+0.019
Neg logit contributions
 decided-0.010
 never-0.010
 tried-0.010
 it-0.009
 came-0.009
Token lush
Token ID37408
Feature activation-1.59e+01

Pos logit contributions
igsaw+0.297
aj+0.276
 batch+0.239
ushes+0.230
umm+0.227
Neg logit contributions
 decided-0.316
 never-0.308
 tried-0.295
 came-0.289
 almost-0.288
Token grass
Token ID8701
Feature activation-1.57e+00

Pos logit contributions
aj+0.460
igsaw+0.457
ushes+0.421
umm+0.382
 batch+0.381
Neg logit contributions
 decided-0.406
 came-0.396
 tried-0.390
 got-0.384
 it-0.370
Token,
Token ID11
Feature activation-1.88e+00

Pos logit contributions
igsaw+0.058
aj+0.055
 batch+0.050
ummy+0.049
udd+0.049
Neg logit contributions
 decided-0.030
 never-0.028
 tried-0.028
 came-0.027
 stumbled-0.025
Token enjoying
Token ID13226
Feature activation-2.66e+00

Pos logit contributions
igsaw+0.062
aj+0.060
 batch+0.054
udd+0.053
ummy+0.052
Neg logit contributions
 decided-0.039
 tried-0.036
 never-0.036
 came-0.035
 stumbled-0.034
Token the
Token ID262
Feature activation-9.05e+00

Pos logit contributions
igsaw+0.097
aj+0.093
 batch+0.082
ummy+0.082
udd+0.081
Neg logit contributions
 decided-0.054
 never-0.052
 tried-0.051
 came-0.050
 almost-0.047
Token sunshine
Token ID34488
Feature activation-4.54e-01

Pos logit contributions
igsaw+0.247
aj+0.229
 batch+0.192
ummy+0.184
ushes+0.181
Neg logit contributions
 decided-0.277
 never-0.256
 tried-0.256
 came-0.254
 almost-0.245
Token and
Token ID290
Feature activation+1.04e+00

Pos logit contributions
igsaw+0.008
aj+0.008
ummy+0.008
udd+0.007
 batch+0.007
Neg logit contributions
 decided-0.005
 tried-0.005
 never-0.005
 stumbled-0.005
 dropped-0.005
Token ran
Token ID4966
Feature activation+2.19e+00

Pos logit contributions
 decided+0.014
 tried+0.013
 never+0.013
 came+0.012
pped+0.012
Neg logit contributions
igsaw-0.041
aj-0.039
 batch-0.036
udd-0.035
 coll-0.035
Token away
Token ID1497
Feature activation-2.01e-01

Pos logit contributions
 decided+0.047
 tried+0.043
 wouldn+0.043
'd+0.042
 stumbled+0.041
Neg logit contributions
igsaw-0.072
aj-0.064
udd-0.058
 stacks-0.057
 batch-0.056
Token from
Token ID422
Feature activation-2.54e+00

Pos logit contributions
igsaw+0.007
aj+0.007
 batch+0.006
ummy+0.006
udd+0.006
Neg logit contributions
 decided-0.004
 tried-0.003
 never-0.003
 came-0.003
 stumbled-0.003
Token the
Token ID262
Feature activation-1.05e+01

Pos logit contributions
igsaw+0.081
aj+0.074
 batch+0.069
ummy+0.067
 coll+0.065
Neg logit contributions
 decided-0.059
 tried-0.055
 came-0.053
 never-0.053
 managed-0.052
Token sm
Token ID895
Feature activation-1.59e+01

Pos logit contributions
igsaw+0.275
aj+0.255
 batch+0.224
ummy+0.217
 coll+0.214
Neg logit contributions
 decided-0.308
 tried-0.293
 never-0.289
 came-0.285
 stumbled-0.280
Tokenelly
Token ID6148
Feature activation-1.03e+01

Pos logit contributions
igsaw+0.231
aj+0.196
ummy+0.154
udd+0.152
 batch+0.148
Neg logit contributions
 decided-0.661
 tried-0.649
 never-0.642
 came-0.629
 stumbled-0.623
Token jail
Token ID7356
Feature activation-3.57e+00

Pos logit contributions
igsaw+0.229
aj+0.219
 batch+0.197
 coll+0.192
ummy+0.190
Neg logit contributions
 decided-0.325
 managed-0.304
 tried-0.302
 never-0.300
pped-0.297
Token.
Token ID13
Feature activation-1.52e+00

Pos logit contributions
igsaw+0.131
aj+0.124
 batch+0.114
ummy+0.112
udd+0.111
Neg logit contributions
 decided-0.066
 tried-0.062
 never-0.060
 came-0.058
 stumbled-0.057
Token And
Token ID843
Feature activation-7.90e-02

Pos logit contributions
igsaw+0.052
aj+0.052
 batch+0.047
 coll+0.047
udd+0.044
Neg logit contributions
 never-0.033
 decided-0.032
 came-0.031
 tried-0.031
 could-0.030
Token he
Token ID339
Feature activation+7.55e+00

Pos logit contributions
igsaw+0.003
aj+0.003
 batch+0.003
ummy+0.003
udd+0.003
Neg logit contributions
 decided-0.001
 tried-0.001
 came-0.001
 never-0.001
 dropped-0.001
Token farmer
Token ID18739
Feature activation+6.76e-01

Pos logit contributions
igsaw+0.293
aj+0.283
ushes+0.240
udd+0.240
 batch+0.235
Neg logit contributions
 decided-0.241
 came-0.229
 tried-0.227
 never-0.226
 got-0.217
Token who
Token ID508
Feature activation+4.19e+00

Pos logit contributions
 decided+0.012
 tried+0.012
 managed+0.011
 dropped+0.011
 never+0.011
Neg logit contributions
igsaw-0.023
aj-0.023
 batch-0.021
ummy-0.021
udd-0.020
Token lived
Token ID5615
Feature activation-2.77e+00

Pos logit contributions
pped+0.101
 tried+0.089
 managed+0.089
 stumbled+0.087
 dropped+0.087
Neg logit contributions
igsaw-0.111
aj-0.102
 batch-0.100
 types-0.100
udd-0.098
Token on
Token ID319
Feature activation-1.87e+00

Pos logit contributions
igsaw+0.118
aj+0.113
 batch+0.104
ummy+0.103
udd+0.102
Neg logit contributions
 decided-0.036
 tried-0.033
 never-0.032
 came-0.031
 stumbled-0.029
Token a
Token ID257
Feature activation-9.01e+00

Pos logit contributions
igsaw+0.073
aj+0.072
udd+0.065
ummy+0.063
 batch+0.062
Neg logit contributions
 never-0.032
 decided-0.032
 tried-0.030
 came-0.029
 almost-0.028
Token lush
Token ID37408
Feature activation-1.59e+01

Pos logit contributions
igsaw+0.196
aj+0.183
 batch+0.142
udd+0.142
ummy+0.142
Neg logit contributions
 decided-0.308
 never-0.302
 tried-0.296
 came-0.291
 got-0.285
Token farm
Token ID5318
Feature activation-1.96e+00

Pos logit contributions
igsaw+0.432
aj+0.428
ushes+0.398
Whe+0.369
uff+0.348
Neg logit contributions
 never-0.430
 decided-0.424
 came-0.411
 tried-0.405
 got-0.398
Token with
Token ID351
Feature activation-3.44e+00

Pos logit contributions
igsaw+0.077
aj+0.074
 batch+0.067
ummy+0.066
udd+0.066
Neg logit contributions
 decided-0.032
 never-0.030
 tried-0.030
 came-0.029
 stumbled-0.027
Token many
Token ID867
Feature activation-7.76e+00

Pos logit contributions
igsaw+0.114
aj+0.112
udd+0.094
 batch+0.092
umm+0.091
Neg logit contributions
 decided-0.087
 never-0.082
 came-0.082
 tried-0.080
 got-0.075
Token animals
Token ID4695
Feature activation+9.17e-01

Pos logit contributions
igsaw+0.251
aj+0.225
 batch+0.193
umm+0.189
ummy+0.188
Neg logit contributions
 decided-0.211
 tried-0.194
 came-0.192
 never-0.187
 got-0.179
Token and
Token ID290
Feature activation+6.44e-02

Pos logit contributions
 decided+0.019
 never+0.019
 tried+0.018
 managed+0.018
pped+0.018
Neg logit contributions
igsaw-0.028
aj-0.028
udd-0.025
 batch-0.025
ummy-0.025
Token her
Token ID607
Feature activation-4.50e+00

Pos logit contributions
igsaw+0.066
aj+0.064
 batch+0.060
 coll+0.058
udd+0.058
Neg logit contributions
 decided-0.035
 never-0.032
 stumbled-0.031
 tried-0.031
 managed-0.030
Token.
Token ID13
Feature activation-9.94e-01

Pos logit contributions
igsaw+0.181
aj+0.172
 batch+0.156
ummy+0.155
udd+0.153
Neg logit contributions
 decided-0.074
 tried-0.071
 never-0.068
 came-0.066
 dropped-0.062
Token Tommy
Token ID19919
Feature activation+2.79e+00

Pos logit contributions
igsaw+0.035
aj+0.032
 batch+0.030
udd+0.029
 former+0.029
Neg logit contributions
 tried-0.020
 came-0.020
 decided-0.020
 never-0.019
 got-0.019
Token saw
Token ID2497
Feature activation-1.92e+00

Pos logit contributions
 decided+0.039
 never+0.036
 tried+0.035
 came+0.033
 stumbled+0.033
Neg logit contributions
igsaw-0.109
aj-0.107
 batch-0.099
udd-0.098
ummy-0.095
Token the
Token ID262
Feature activation-9.76e+00

Pos logit contributions
igsaw+0.072
aj+0.068
umm+0.060
ummy+0.059
 batch+0.059
Neg logit contributions
 decided-0.040
 tried-0.038
 never-0.037
 came-0.037
 dropped-0.034
Token sm
Token ID895
Feature activation-1.59e+01

Pos logit contributions
igsaw+0.276
aj+0.261
 batch+0.223
umm+0.219
 former+0.217
Neg logit contributions
 tried-0.279
 decided-0.275
 came-0.261
 never-0.261
 dropped-0.260
Tokenelly
Token ID6148
Feature activation-1.00e+01

Pos logit contributions
igsaw+0.222
aj+0.197
 batch+0.143
 coll+0.128
ummy+0.126
Neg logit contributions
 decided-0.661
 tried-0.642
 never-0.637
 came-0.632
 stumbled-0.616
Token sock
Token ID32263
Feature activation-2.11e+00

Pos logit contributions
igsaw+0.231
aj+0.211
 batch+0.179
udd+0.170
ummy+0.170
Neg logit contributions
 decided-0.330
 tried-0.327
 came-0.317
 never-0.311
 dropped-0.308
Token and
Token ID290
Feature activation+1.34e+00

Pos logit contributions
igsaw+0.069
aj+0.064
 batch+0.061
ummy+0.060
udd+0.058
Neg logit contributions
 decided-0.043
 never-0.040
 tried-0.040
 stumbled-0.039
pped-0.038
Token wanted
Token ID2227
Feature activation+2.50e+00

Pos logit contributions
pped+0.019
 never+0.018
 stumbled+0.017
 decided+0.017
 almost+0.016
Neg logit contributions
aj-0.049
igsaw-0.048
 batch-0.046
 types-0.045
udd-0.044
Token to
Token ID284
Feature activation+4.16e+00

Pos logit contributions
 decided+0.050
pped+0.046
 wouldn+0.045
 stumbled+0.044
 managed+0.044
Neg logit contributions
igsaw-0.079
aj-0.075
 batch-0.072
 coll-0.069
ummy-0.068
Token home
Token ID1363
Feature activation+1.70e+00

Pos logit contributions
 decided+0.012
 tried+0.011
 never+0.011
 came+0.011
 stumbled+0.010
Neg logit contributions
igsaw-0.024
aj-0.023
 batch-0.021
ummy-0.020
udd-0.020
Token,
Token ID11
Feature activation-1.39e+00

Pos logit contributions
 decided+0.031
 tried+0.030
 never+0.029
 came+0.028
 stumbled+0.027
Neg logit contributions
igsaw-0.063
aj-0.059
ummy-0.054
 batch-0.054
udd-0.053
Token away
Token ID1497
Feature activation-4.58e-01

Pos logit contributions
igsaw+0.045
aj+0.044
 batch+0.039
udd+0.039
 coll+0.038
Neg logit contributions
 decided-0.029
 tried-0.027
 came-0.026
 stumbled-0.025
 never-0.025
Token from
Token ID422
Feature activation-3.16e+00

Pos logit contributions
igsaw+0.016
aj+0.015
ummy+0.014
 batch+0.014
udd+0.013
Neg logit contributions
 decided-0.009
 tried-0.009
 never-0.009
 came-0.008
 stumbled-0.008
Token the
Token ID262
Feature activation-1.04e+01

Pos logit contributions
igsaw+0.107
aj+0.100
 batch+0.091
ummy+0.090
 coll+0.087
Neg logit contributions
 decided-0.069
 tried-0.065
 never-0.063
 came-0.063
 stumbled-0.061
Token sm
Token ID895
Feature activation-1.58e+01

Pos logit contributions
igsaw+0.272
aj+0.248
 batch+0.211
ummy+0.207
udd+0.204
Neg logit contributions
 decided-0.323
 never-0.315
 tried-0.314
 came-0.304
 dropped-0.295
Tokenelly
Token ID6148
Feature activation-1.05e+01

Pos logit contributions
igsaw+0.211
aj+0.180
 batch+0.129
ummy+0.122
udd+0.117
Neg logit contributions
 decided-0.675
 tried-0.657
 never-0.655
 came-0.645
 stumbled-0.633
Token man
Token ID582
Feature activation+1.12e+00

Pos logit contributions
igsaw+0.290
aj+0.270
 batch+0.236
ummy+0.230
udd+0.227
Neg logit contributions
 decided-0.300
 tried-0.289
 never-0.286
 came-0.282
 stumbled-0.272
Token.
Token ID13
Feature activation-1.21e+00

Pos logit contributions
 decided+0.024
 tried+0.022
 never+0.022
 came+0.021
 stumbled+0.021
Neg logit contributions
igsaw-0.037
aj-0.035
 batch-0.032
ummy-0.031
 coll-0.031
Token John
Token ID1757
Feature activation+2.94e+00

Pos logit contributions
igsaw+0.038
aj+0.037
 batch+0.033
 coll+0.032
udd+0.032
Neg logit contributions
 decided-0.030
 never-0.029
 tried-0.028
 came-0.027
 stumbled-0.026
Token never
Token ID1239
Feature activation+6.54e+00

Pos logit contributions
 decided+0.040
pped+0.039
 tried+0.037
Please+0.037
 stumbled+0.037
Neg logit contributions
aj-0.097
igsaw-0.092
udd-0.092
 batch-0.090
 coll-0.085
Token mouse
Token ID10211
Feature activation+8.32e-01

Pos logit contributions
igsaw+0.299
aj+0.279
ummy+0.242
udd+0.238
 batch+0.235
Neg logit contributions
 decided-0.231
 tried-0.229
 never-0.222
 came-0.218
 got-0.207
Token never
Token ID1239
Feature activation+7.46e+00

Pos logit contributions
 decided+0.012
 tried+0.011
 never+0.010
 stumbled+0.010
 dropped+0.010
Neg logit contributions
igsaw-0.032
aj-0.031
udd-0.028
 batch-0.028
ummy-0.028
Token suffered
Token ID6989
Feature activation-8.23e-01

Pos logit contributions
 decided+0.081
pped+0.079
 never+0.079
 almost+0.072
 tried+0.067
Neg logit contributions
igsaw-0.302
aj-0.291
udd-0.273
 batch-0.267
 types-0.264
Token from
Token ID422
Feature activation-1.86e+00

Pos logit contributions
igsaw+0.030
aj+0.028
 batch+0.025
ummy+0.025
udd+0.025
Neg logit contributions
 decided-0.016
 tried-0.015
 never-0.015
 came-0.015
 stumbled-0.014
Token the
Token ID262
Feature activation-9.81e+00

Pos logit contributions
igsaw+0.061
aj+0.056
 batch+0.052
ummy+0.050
 coll+0.049
Neg logit contributions
 decided-0.043
 tried-0.040
 came-0.039
 never-0.039
 stumbled-0.038
Token rud
Token ID28906
Feature activation-1.58e+01

Pos logit contributions
igsaw+0.285
aj+0.272
 batch+0.231
udd+0.228
ummy+0.227
Neg logit contributions
 decided-0.266
 tried-0.259
 never-0.259
 came-0.250
 dropped-0.241
Tokeneness
Token ID9449
Feature activation-7.38e-01

Pos logit contributions
igsaw+0.413
aj+0.389
 batch+0.334
ummy+0.316
udd+0.315
Neg logit contributions
 decided-0.465
 tried-0.450
 never-0.447
 came-0.442
 dropped-0.423
Token of
Token ID286
Feature activation-4.31e+00

Pos logit contributions
igsaw+0.024
aj+0.022
ummy+0.021
 batch+0.021
udd+0.020
Neg logit contributions
 decided-0.016
 tried-0.015
 never-0.015
 stumbled-0.015
 came-0.014
Token other
Token ID584
Feature activation-6.59e+00

Pos logit contributions
igsaw+0.131
aj+0.121
 batch+0.110
ummy+0.106
 coll+0.105
Neg logit contributions
 decided-0.110
 tried-0.103
 never-0.102
 came-0.101
 stumbled-0.099
Token animals
Token ID4695
Feature activation+1.78e+00

Pos logit contributions
igsaw+0.191
aj+0.178
 batch+0.155
ummy+0.150
udd+0.149
Neg logit contributions
 decided-0.181
 tried-0.174
 never-0.172
 came-0.171
 dropped-0.162
Token again
Token ID757
Feature activation+3.38e+00

Pos logit contributions
 decided+0.038
 tried+0.036
 stumbled+0.035
 dropped+0.034
 came+0.034
Neg logit contributions
igsaw-0.056
aj-0.050
ummy-0.048
udd-0.047
 batch-0.047
Token not
Token ID407
Feature activation+5.13e+00

Pos logit contributions
 decided+0.032
 stumbled+0.029
 tried+0.027
 came+0.027
 managed+0.025
Neg logit contributions
igsaw-0.083
aj-0.083
 batch-0.076
udd-0.075
 coll-0.074
Token want
Token ID765
Feature activation+3.81e+00

Pos logit contributions
pped+0.123
 wouldn+0.118
ged+0.114
 unable+0.112
 hadn+0.105
Neg logit contributions
igsaw-0.119
udd-0.108
 birthday-0.108
 parties-0.108
 difference-0.107
Token to
Token ID284
Feature activation+4.39e+00

Pos logit contributions
 decided+0.069
 tried+0.064
 never+0.063
 came+0.061
 stumbled+0.059
Neg logit contributions
igsaw-0.142
aj-0.135
 batch-0.124
ummy-0.123
udd-0.120
Token touch
Token ID3638
Feature activation-2.73e+00

Pos logit contributions
 decided+0.096
 wouldn+0.092
 managed+0.091
 stumbled+0.090
 tried+0.087
Neg logit contributions
igsaw-0.134
aj-0.127
ummy-0.117
 batch-0.116
udd-0.113
Token the
Token ID262
Feature activation-1.03e+01

Pos logit contributions
igsaw+0.114
aj+0.108
 batch+0.103
ummy+0.102
 coll+0.100
Neg logit contributions
 decided-0.033
 tried-0.029
 never-0.028
 managed-0.028
 stumbled-0.027
Token sm
Token ID895
Feature activation-1.58e+01

Pos logit contributions
igsaw+0.282
aj+0.260
 batch+0.221
ummy+0.217
udd+0.216
Neg logit contributions
 decided-0.300
 tried-0.291
 never-0.286
 came-0.284
 dropped-0.276
Tokenelly
Token ID6148
Feature activation-1.04e+01

Pos logit contributions
igsaw+0.206
aj+0.176
 batch+0.125
ummy+0.116
udd+0.111
Neg logit contributions
 decided-0.678
 tried-0.660
 never-0.657
 came-0.648
 stumbled-0.635
Token sock
Token ID32263
Feature activation-2.35e+00

Pos logit contributions
igsaw+0.279
aj+0.259
 batch+0.226
ummy+0.221
udd+0.217
Neg logit contributions
 decided-0.302
 tried-0.290
 never-0.289
 came-0.282
 stumbled-0.274
Token.
Token ID13
Feature activation-1.39e+00

Pos logit contributions
igsaw+0.077
aj+0.071
 batch+0.068
ummy+0.067
 coll+0.064
Neg logit contributions
 decided-0.049
 tried-0.048
 stumbled-0.047
 never-0.046
 came-0.045
Token They
Token ID1119
Feature activation+7.57e+00

Pos logit contributions
igsaw+0.045
aj+0.042
 batch+0.038
udd+0.036
ummy+0.036
Neg logit contributions
 decided-0.034
 never-0.032
 tried-0.032
 came-0.031
 stumbled-0.030
Token do
Token ID466
Feature activation+2.46e+00

Pos logit contributions
pped+0.180
 decided+0.173
 managed+0.168
 came+0.167
ged+0.166
Neg logit contributions
 goals-0.181
aj-0.171
igsaw-0.161
udd-0.161
 difference-0.160
Token,
Token ID11
Feature activation-1.48e+00

Pos logit contributions
 decided+0.018
 tried+0.017
 never+0.017
 came+0.016
 stumbled+0.015
Neg logit contributions
igsaw-0.028
aj-0.027
 batch-0.024
ummy-0.024
udd-0.024
Token he
Token ID339
Feature activation+6.80e+00

Pos logit contributions
igsaw+0.061
aj+0.058
 batch+0.053
ummy+0.053
udd+0.052
Neg logit contributions
 decided-0.022
 tried-0.020
 never-0.020
 came-0.019
 stumbled-0.018
Token noticed
Token ID6810
Feature activation-2.96e+00

Pos logit contributions
 decided+0.074
 tried+0.069
 never+0.068
pped+0.066
 dropped+0.063
Neg logit contributions
igsaw-0.266
aj-0.266
udd-0.246
 batch-0.242
 types-0.236
Token that
Token ID326
Feature activation+3.57e-01

Pos logit contributions
igsaw+0.111
aj+0.105
 batch+0.094
ummy+0.093
udd+0.092
Neg logit contributions
 decided-0.058
 tried-0.054
 never-0.054
 came-0.052
 stumbled-0.049
Token the
Token ID262
Feature activation-1.03e+01

Pos logit contributions
 decided+0.007
 never+0.007
 tried+0.007
 came+0.007
 stumbled+0.006
Neg logit contributions
igsaw-0.013
aj-0.013
ummy-0.011
udd-0.011
 batch-0.011
Token Sm
Token ID2439
Feature activation-1.58e+01

Pos logit contributions
igsaw+0.273
aj+0.250
 batch+0.219
ummy+0.214
udd+0.210
Neg logit contributions
 decided-0.301
 tried-0.289
 never-0.286
 came-0.281
 stumbled-0.274
Tokenelly
Token ID6148
Feature activation-8.85e+00

Pos logit contributions
igsaw+0.417
aj+0.376
 batch+0.331
ummy+0.328
udd+0.320
Neg logit contributions
 decided-0.471
 tried-0.455
 never-0.452
 came-0.444
 dropped-0.430
Token King
Token ID2677
Feature activation-8.26e-01

Pos logit contributions
igsaw+0.229
aj+0.203
 batch+0.182
ummy+0.177
 types+0.173
Neg logit contributions
 decided-0.259
 never-0.249
 tried-0.248
pped-0.240
 managed-0.238
Token was
Token ID373
Feature activation+2.55e+00

Pos logit contributions
igsaw+0.032
aj+0.030
 batch+0.029
ummy+0.028
udd+0.028
Neg logit contributions
 decided-0.011
 never-0.010
 tried-0.010
pped-0.009
 stumbled-0.009
Token cruel
Token ID12177
Feature activation-5.42e+00

Pos logit contributions
 decided+0.051
 tried+0.048
 wouldn+0.045
 came+0.045
 never+0.045
Neg logit contributions
igsaw-0.086
aj-0.081
 batch-0.074
ummy-0.072
udd-0.071
Token and
Token ID290
Feature activation+4.94e-01

Pos logit contributions
igsaw+0.171
aj+0.162
ummy+0.151
 batch+0.147
udd+0.145
Neg logit contributions
 decided-0.112
 tried-0.110
 never-0.107
 stumbled-0.104
pped-0.103
TokenFl
Token ID7414
Feature activation-9.60e+00

Pos logit contributions
igsaw+0.114
aj+0.108
 batch+0.094
ummy+0.091
udd+0.091
Neg logit contributions
 decided-0.124
 tried-0.119
 never-0.118
 came-0.116
 stumbled-0.113
Tokenuffy
Token ID15352
Feature activation+2.05e+00

Pos logit contributions
igsaw+0.208
aj+0.156
 batch+0.149
 types+0.146
 coll+0.144
Neg logit contributions
 tried-0.326
 never-0.326
 decided-0.323
 came-0.318
 dropped-0.316
Token picked
Token ID6497
Feature activation+2.79e-02

Pos logit contributions
pped+0.023
 never+0.022
 decided+0.021
 almost+0.020
 wouldn+0.019
Neg logit contributions
aj-0.079
igsaw-0.077
udd-0.073
 batch-0.073
 stacks-0.070
Token up
Token ID510
Feature activation-1.27e+00

Pos logit contributions
 decided+0.001
 tried+0.001
 never+0.001
 came+0.001
 dropped+0.001
Neg logit contributions
igsaw-0.001
aj-0.001
 batch-0.001
ummy-0.001
udd-0.001
Token the
Token ID262
Feature activation-9.83e+00

Pos logit contributions
igsaw+0.048
aj+0.046
umm+0.041
ummy+0.041
udd+0.040
Neg logit contributions
 decided-0.025
 tried-0.024
 never-0.023
 came-0.023
 got-0.022
Token sm
Token ID895
Feature activation-1.58e+01

Pos logit contributions
igsaw+0.240
aj+0.226
 batch+0.195
 former+0.192
umm+0.190
Neg logit contributions
 tried-0.312
 decided-0.307
 came-0.296
 dropped-0.295
 got-0.293
Tokenelly
Token ID6148
Feature activation-1.01e+01

Pos logit contributions
igsaw+0.232
aj+0.211
 batch+0.157
 coll+0.145
udd+0.130
Neg logit contributions
 decided-0.642
 tried-0.620
 never-0.614
 came-0.612
 got-0.595
Token sock
Token ID32263
Feature activation-1.90e+00

Pos logit contributions
igsaw+0.233
aj+0.212
 batch+0.182
udd+0.176
ummy+0.172
Neg logit contributions
 decided-0.330
 tried-0.329
 came-0.319
 got-0.311
 dropped-0.311
Token with
Token ID351
Feature activation-1.38e+00

Pos logit contributions
igsaw+0.066
aj+0.061
 batch+0.057
ummy+0.056
udd+0.054
Neg logit contributions
 decided-0.038
 tried-0.036
 never-0.036
 came-0.035
 stumbled-0.034
Token her
Token ID607
Feature activation-3.52e+00

Pos logit contributions
igsaw+0.045
aj+0.041
 batch+0.039
 coll+0.039
ummy+0.038
Neg logit contributions
 decided-0.029
 never-0.028
 stumbled-0.027
 tried-0.027
 came-0.026
Token teeth
Token ID9941
Feature activation-3.14e-01

Pos logit contributions
igsaw+0.109
aj+0.106
ummy+0.093
 batch+0.093
 coll+0.091
Neg logit contributions
 decided-0.084
 never-0.078
 came-0.076
 tried-0.075
 stumbled-0.075
Token car
Token ID1097
Feature activation-1.48e-01

Pos logit contributions
igsaw+0.348
aj+0.343
udd+0.291
ummy+0.289
ushes+0.284
Neg logit contributions
 tried-0.263
 decided-0.258
 came-0.255
 never-0.253
 got-0.243
Token came
Token ID1625
Feature activation+1.95e+00

Pos logit contributions
igsaw+0.005
aj+0.005
udd+0.005
 batch+0.005
 coll+0.005
Neg logit contributions
 decided-0.002
 never-0.002
 tried-0.002
 stumbled-0.002
pped-0.002
Token and
Token ID290
Feature activation+2.01e+00

Pos logit contributions
 decided+0.039
 tried+0.038
 never+0.036
 dropped+0.035
 managed+0.035
Neg logit contributions
igsaw-0.060
aj-0.059
ummy-0.054
udd-0.054
 coll-0.053
Token hit
Token ID2277
Feature activation-3.91e+00

Pos logit contributions
 decided+0.029
 never+0.027
 tried+0.026
 came+0.025
 stumbled+0.024
Neg logit contributions
igsaw-0.081
aj-0.078
 batch-0.071
udd-0.070
ummy-0.069
Token the
Token ID262
Feature activation-1.10e+01

Pos logit contributions
igsaw+0.120
aj+0.115
 batch+0.100
ummy+0.098
udd+0.097
Neg logit contributions
 decided-0.100
 tried-0.097
 never-0.096
 came-0.094
 dropped-0.089
Token sm
Token ID895
Feature activation-1.58e+01

Pos logit contributions
igsaw+0.314
aj+0.285
 batch+0.244
ummy+0.241
udd+0.233
Neg logit contributions
 decided-0.323
 never-0.317
 tried-0.317
 came-0.304
 dropped-0.302
Tokenelly
Token ID6148
Feature activation-1.01e+01

Pos logit contributions
igsaw+0.235
aj+0.227
 batch+0.164
 coll+0.148
ummy+0.140
Neg logit contributions
 decided-0.636
 tried-0.616
 never-0.614
 came-0.611
 got-0.592
Token cat
Token ID3797
Feature activation-9.61e-01

Pos logit contributions
igsaw+0.288
aj+0.268
 batch+0.229
ummy+0.225
udd+0.224
Neg logit contributions
 decided-0.285
 tried-0.278
 came-0.274
 never-0.273
 dropped-0.263
Token and
Token ID290
Feature activation+1.03e+00

Pos logit contributions
igsaw+0.035
aj+0.033
 batch+0.030
udd+0.029
ummy+0.029
Neg logit contributions
 decided-0.018
 tried-0.016
 never-0.016
 came-0.016
 stumbled-0.015
Token Zero
Token ID12169
Feature activation+2.48e-02

Pos logit contributions
 decided+0.017
 never+0.015
pped+0.015
 tried+0.015
 stumbled+0.014
Neg logit contributions
igsaw-0.036
aj-0.035
 batch-0.032
 coll-0.032
udd-0.032
Token.
Token ID13
Feature activation-1.30e+00

Pos logit contributions
 decided+0.000
 never+0.000
 tried+0.000
 came+0.000
 stumbled+0.000
Neg logit contributions
igsaw-0.001
aj-0.001
udd-0.001
 batch-0.001
 coll-0.001
Token Alice
Token ID14862
Feature activation+1.55e+00

Pos logit contributions
 decided+0.084
 tried+0.080
 never+0.078
 came+0.077
 stumbled+0.075
Neg logit contributions
igsaw-0.108
aj-0.101
 batch-0.091
ummy-0.090
 coll-0.086
Token saw
Token ID2497
Feature activation-1.66e+00

Pos logit contributions
 decided+0.021
 never+0.020
pped+0.018
 wouldn+0.018
 tried+0.018
Neg logit contributions
igsaw-0.057
aj-0.056
 batch-0.052
udd-0.052
ummy-0.050
Token Lisa
Token ID15378
Feature activation+9.82e-01

Pos logit contributions
igsaw+0.060
aj+0.059
udd+0.052
ummy+0.051
umm+0.051
Neg logit contributions
 decided-0.032
 never-0.032
 tried-0.031
 came-0.030
 dropped-0.029
Token with
Token ID351
Feature activation-2.39e+00

Pos logit contributions
 decided+0.021
 tried+0.019
 never+0.019
 came+0.018
 stumbled+0.018
Neg logit contributions
igsaw-0.033
aj-0.032
 batch-0.029
ummy-0.028
udd-0.028
Token the
Token ID262
Feature activation-9.94e+00

Pos logit contributions
igsaw+0.084
aj+0.082
udd+0.072
ummy+0.071
 batch+0.071
Neg logit contributions
 decided-0.050
 tried-0.049
 never-0.048
 came-0.046
 dropped-0.044
Token y
Token ID331
Feature activation-1.58e+01

Pos logit contributions
igsaw+0.242
aj+0.222
 batch+0.184
udd+0.182
ummy+0.179
Neg logit contributions
 decided-0.321
 tried-0.311
 never-0.309
 came-0.304
 dropped-0.295
Tokenummy
Token ID13513
Feature activation-7.58e+00

Pos logit contributions
igsaw+0.117
aj+0.103
 batch+0.038
udd+0.032
 coll+0.025
Neg logit contributions
 decided-0.740
 tried-0.725
 came-0.722
 never-0.717
 got-0.705
Token cand
Token ID2658
Feature activation-4.82e+00

Pos logit contributions
igsaw+0.157
aj+0.143
 batch+0.120
ummy+0.116
udd+0.112
Neg logit contributions
 decided-0.266
 never-0.256
 tried-0.256
 came-0.250
 stumbled-0.246
Tokenies
Token ID444
Feature activation+2.97e+00

Pos logit contributions
igsaw+0.120
aj+0.112
ummy+0.105
 batch+0.098
udd+0.097
Neg logit contributions
 never-0.145
 decided-0.144
 tried-0.140
 stumbled-0.140
Please-0.138
Token,
Token ID11
Feature activation-1.43e+00

Pos logit contributions
 decided+0.068
 never+0.065
 tried+0.063
 stumbled+0.062
pped+0.062
Neg logit contributions
igsaw-0.088
aj-0.078
ummy-0.075
 batch-0.075
udd-0.070
Token she
Token ID673
Feature activation+6.64e+00

Pos logit contributions
igsaw+0.055
aj+0.052
 batch+0.048
ummy+0.047
udd+0.046
Neg logit contributions
 decided-0.024
 tried-0.023
 never-0.022
 came-0.022
 stumbled-0.021
Token to
Token ID284
Feature activation+4.11e+00

Pos logit contributions
pped+0.085
 tried+0.085
 managed+0.081
 decided+0.081
 dropped+0.079
Neg logit contributions
igsaw-0.117
aj-0.113
 new-0.099
ummy-0.099
 coll-0.098
Token take
Token ID1011
Feature activation+4.28e-01

Pos logit contributions
 decided+0.079
 tried+0.075
 came+0.074
pped+0.073
 wouldn+0.073
Neg logit contributions
igsaw-0.142
aj-0.122
ummy-0.116
 batch-0.116
 types-0.114
Token a
Token ID257
Feature activation-7.32e+00

Pos logit contributions
 decided+0.009
 never+0.009
 tried+0.009
 came+0.008
 stumbled+0.008
Neg logit contributions
igsaw-0.015
aj-0.013
 batch-0.012
ummy-0.012
 coll-0.012
Token journey
Token ID7002
Feature activation+1.37e+00

Pos logit contributions
igsaw+0.236
aj+0.219
 batch+0.198
ummy+0.192
udd+0.190
Neg logit contributions
 decided-0.175
 tried-0.165
 never-0.165
 came-0.159
 stumbled-0.154
Token to
Token ID284
Feature activation+2.70e+00

Pos logit contributions
 decided+0.025
 tried+0.024
 never+0.023
 came+0.022
 dropped+0.022
Neg logit contributions
igsaw-0.051
aj-0.048
 batch-0.044
ummy-0.044
udd-0.043
Token outer
Token ID12076
Feature activation-1.57e+01

Pos logit contributions
 decided+0.052
 tried+0.049
 never+0.048
 came+0.047
 stumbled+0.044
Neg logit contributions
igsaw-0.100
aj-0.095
 batch-0.086
ummy-0.085
udd-0.084
Token space
Token ID2272
Feature activation-1.27e+00

Pos logit contributions
igsaw+0.417
aj+0.395
udd+0.345
umm+0.344
 batch+0.340
Neg logit contributions
 never-0.456
 it-0.455
 decided-0.449
 tried-0.427
 him-0.411
Token.
Token ID13
Feature activation-1.29e+00

Pos logit contributions
igsaw+0.048
aj+0.045
 batch+0.041
ummy+0.041
udd+0.040
Neg logit contributions
 decided-0.023
 tried-0.022
 never-0.021
 came-0.020
 stumbled-0.020
Token He
Token ID679
Feature activation+7.15e+00

Pos logit contributions
igsaw+0.040
aj+0.038
 batch+0.034
ummy+0.033
udd+0.032
Neg logit contributions
 decided-0.032
 tried-0.031
 never-0.030
 came-0.030
 stumbled-0.029
Token hopped
Token ID45230
Feature activation+6.69e-01

Pos logit contributions
 decided+0.087
 never+0.082
 tried+0.080
 came+0.075
pped+0.074
Neg logit contributions
igsaw-0.285
aj-0.284
 batch-0.256
udd-0.254
 types-0.251
Token into
Token ID656
Feature activation-2.81e+00

Pos logit contributions
 decided+0.013
 tried+0.012
 never+0.012
 came+0.011
 dropped+0.011
Neg logit contributions
igsaw-0.024
aj-0.023
 batch-0.021
ummy-0.021
udd-0.020
Token getting
Token ID1972
Feature activation+5.71e-01

Pos logit contributions
 decided+0.032
 tried+0.030
 never+0.029
 came+0.029
 stumbled+0.027
Neg logit contributions
igsaw-0.072
aj-0.068
 batch-0.063
ummy-0.061
udd-0.061
Token very
Token ID845
Feature activation+3.55e-01

Pos logit contributions
 decided+0.012
 never+0.012
pped+0.012
 stumbled+0.012
 tried+0.012
Neg logit contributions
aj-0.016
igsaw-0.016
 batch-0.015
udd-0.014
 stacks-0.014
Token annoyed
Token ID25602
Feature activation-3.90e+00

Pos logit contributions
 decided+0.008
 tried+0.008
 never+0.008
 came+0.008
 stumbled+0.007
Neg logit contributions
igsaw-0.012
aj-0.011
 batch-0.010
ummy-0.010
udd-0.010
Token with
Token ID351
Feature activation-1.37e+00

Pos logit contributions
igsaw+0.133
aj+0.124
ummy+0.117
 batch+0.115
udd+0.113
Neg logit contributions
 decided-0.081
 never-0.076
 tried-0.076
 managed-0.074
 stumbled-0.073
Token his
Token ID465
Feature activation-5.73e+00

Pos logit contributions
igsaw+0.051
aj+0.046
 batch+0.044
ummy+0.043
 coll+0.042
Neg logit contributions
 decided-0.026
 tried-0.023
 never-0.023
 came-0.022
 stumbled-0.022
Token rud
Token ID28906
Feature activation-1.57e+01

Pos logit contributions
igsaw+0.169
aj+0.157
udd+0.141
 batch+0.138
umm+0.134
Neg logit contributions
 tried-0.152
 never-0.149
 decided-0.147
 came-0.146
 dropped-0.144
Tokeneness
Token ID9449
Feature activation-5.19e-01

Pos logit contributions
igsaw+0.450
aj+0.413
 batch+0.377
 coll+0.351
udd+0.342
Neg logit contributions
 decided-0.421
 never-0.407
 tried-0.407
 came-0.401
 dropped-0.382
Token and
Token ID290
Feature activation+1.27e+00

Pos logit contributions
igsaw+0.018
aj+0.017
 batch+0.015
ummy+0.015
udd+0.015
Neg logit contributions
 decided-0.010
 tried-0.010
 never-0.010
 stumbled-0.009
 came-0.009
Token complained
Token ID13832
Feature activation-1.82e+00

Pos logit contributions
pped+0.020
 decided+0.018
 stumbled+0.017
 never+0.017
 came+0.016
Neg logit contributions
igsaw-0.045
aj-0.044
 types-0.042
 batch-0.041
 coll-0.041
Token that
Token ID326
Feature activation+1.58e+00

Pos logit contributions
igsaw+0.063
aj+0.060
 batch+0.054
ummy+0.054
udd+0.053
Neg logit contributions
 decided-0.037
 tried-0.035
 never-0.035
 came-0.034
 stumbled-0.033
Token he
Token ID339
Feature activation+7.41e+00

Pos logit contributions
 decided+0.022
 tried+0.020
 never+0.020
 came+0.019
 dropped+0.018
Neg logit contributions
igsaw-0.064
aj-0.061
 batch-0.057
ummy-0.056
 coll-0.055
Token Lily
Token ID20037
Feature activation+1.64e+00

Pos logit contributions
 decided+0.047
 never+0.046
 tried+0.045
 stumbled+0.044
 came+0.043
Neg logit contributions
igsaw-0.036
aj-0.034
 batch-0.029
 coll-0.028
ummy-0.027
Token were
Token ID547
Feature activation+2.07e+00

Pos logit contributions
 never+0.025
pped+0.024
 decided+0.024
 stumbled+0.023
 almost+0.023
Neg logit contributions
udd-0.053
aj-0.053
igsaw-0.048
uddle-0.047
 batch-0.047
Token scared
Token ID12008
Feature activation-4.07e+00

Pos logit contributions
 decided+0.041
 tried+0.037
 came+0.036
 never+0.035
 stumbled+0.035
Neg logit contributions
aj-0.070
igsaw-0.069
udd-0.062
 batch-0.061
 goals-0.060
Token of
Token ID286
Feature activation-2.23e+00

Pos logit contributions
igsaw+0.128
aj+0.123
ummy+0.120
udd+0.114
 batch+0.109
Neg logit contributions
 decided-0.090
 managed-0.086
 never-0.085
 stumbled-0.084
 tried-0.083
Token the
Token ID262
Feature activation-9.91e+00

Pos logit contributions
igsaw+0.077
aj+0.073
 batch+0.065
ummy+0.064
udd+0.063
Neg logit contributions
 decided-0.048
 tried-0.046
 never-0.046
 came-0.045
 dropped-0.042
Token gr
Token ID1036
Feature activation-1.57e+01

Pos logit contributions
igsaw+0.309
aj+0.271
 batch+0.244
ummy+0.240
umm+0.232
Neg logit contributions
 decided-0.264
 tried-0.255
 never-0.251
 came-0.250
 dropped-0.238
Tokenumpy
Token ID32152
Feature activation-9.46e+00

Pos logit contributions
igsaw+0.370
aj+0.340
 batch+0.290
ummy+0.278
udd+0.274
Neg logit contributions
 decided-0.510
 tried-0.491
 never-0.490
 came-0.481
 stumbled-0.467
Token man
Token ID582
Feature activation+1.99e+00

Pos logit contributions
igsaw+0.278
aj+0.262
 batch+0.231
ummy+0.227
udd+0.224
Neg logit contributions
 decided-0.250
 tried-0.238
 never-0.238
 came-0.231
 stumbled-0.224
Token.
Token ID13
Feature activation-1.33e+00

Pos logit contributions
 decided+0.043
 stumbled+0.041
 tried+0.041
 managed+0.040
 never+0.039
Neg logit contributions
igsaw-0.063
aj-0.058
 batch-0.055
 coll-0.055
ummy-0.054
Token They
Token ID1119
Feature activation+7.81e+00

Pos logit contributions
igsaw+0.042
aj+0.039
 batch+0.035
ummy+0.034
udd+0.034
Neg logit contributions
 decided-0.033
 tried-0.032
 never-0.031
 came-0.031
 stumbled-0.030
Token ran
Token ID4966
Feature activation+2.10e+00

Pos logit contributions
pped+0.119
 ever+0.118
can+0.117
 possibly+0.107
Where+0.106
Neg logit contributions
udd-0.209
aj-0.200
 seats-0.184
uddle-0.182
 goals-0.182
Token?"
Token ID1701
Feature activation-1.42e+00

Pos logit contributions
 decided+0.098
 tried+0.097
 came+0.096
 never+0.091
 got+0.088
Neg logit contributions
igsaw-0.200
aj-0.182
umm-0.173
ushes-0.162
udd-0.162
Token asked
Token ID1965
Feature activation+2.37e-01

Pos logit contributions
igsaw+0.052
aj+0.048
 batch+0.046
ummy+0.044
 types+0.044
Neg logit contributions
 decided-0.023
 never-0.023
 managed-0.021
pped-0.021
 wouldn-0.021
Token the
Token ID262
Feature activation-1.05e+01

Pos logit contributions
 decided+0.005
 tried+0.005
 came+0.005
 never+0.005
 got+0.004
Neg logit contributions
igsaw-0.009
aj-0.008
udd-0.007
 batch-0.007
ummy-0.007
Token rh
Token ID9529
Feature activation-1.32e+01

Pos logit contributions
igsaw+0.330
aj+0.307
udd+0.248
ushes+0.243
 batch+0.241
Neg logit contributions
 decided-0.298
 tried-0.293
 never-0.292
 came-0.287
 got-0.275
Tokenin
Token ID259
Feature activation-6.70e+00

Pos logit contributions
igsaw+0.343
aj+0.318
 batch+0.293
ummy+0.286
udd+0.280
Neg logit contributions
 decided-0.379
 tried-0.360
 never-0.356
 stumbled-0.349
 came-0.347
Tokenoc
Token ID420
Feature activation-1.57e+01

Pos logit contributions
igsaw+0.170
aj+0.156
 batch+0.131
ummy+0.129
udd+0.127
Neg logit contributions
 decided-0.210
 tried-0.202
 never-0.200
 came-0.197
 got-0.190
Tokeneros
Token ID27498
Feature activation-4.30e-01

Pos logit contributions
igsaw+0.358
aj+0.330
 batch+0.273
udd+0.266
ummy+0.260
Neg logit contributions
 decided-0.518
 never-0.502
 tried-0.500
 came-0.491
 stumbled-0.474
Token.
Token ID13
Feature activation-9.51e-01

Pos logit contributions
igsaw+0.014
aj+0.014
 batch+0.013
ummy+0.012
udd+0.012
Neg logit contributions
 decided-0.008
 never-0.008
 tried-0.008
 stumbled-0.008
pped-0.008
Token
Token ID198
Feature activation-5.16e+00

Pos logit contributions
igsaw+0.026
aj+0.025
 batch+0.021
ummy+0.021
udd+0.021
Neg logit contributions
 decided-0.027
 tried-0.027
 never-0.026
 came-0.026
 stumbled-0.025
Token
Token ID198
Feature activation-5.42e+00

Pos logit contributions
igsaw+0.167
aj+0.157
 batch+0.140
ummy+0.136
udd+0.135
Neg logit contributions
 decided-0.124
 tried-0.120
 never-0.119
 came-0.117
 stumbled-0.110
Token"
Token ID1
Feature activation+6.35e-03

Pos logit contributions
igsaw+0.186
aj+0.175
 batch+0.158
ummy+0.155
udd+0.154
Neg logit contributions
 decided-0.114
 tried-0.108
 never-0.108
 came-0.105
 stumbled-0.102
Token were
Token ID547
Feature activation+2.55e+00

Pos logit contributions
 decided+0.035
 tried+0.033
 never+0.032
 came+0.030
 stumbled+0.029
Neg logit contributions
igsaw-0.089
aj-0.085
 batch-0.078
ummy-0.077
udd-0.077
Token running
Token ID2491
Feature activation+4.68e-01

Pos logit contributions
 decided+0.058
 tried+0.055
 never+0.054
 came+0.053
 stumbled+0.051
Neg logit contributions
igsaw-0.083
aj-0.079
 batch-0.071
ummy-0.069
udd-0.069
Token away
Token ID1497
Feature activation+4.72e-01

Pos logit contributions
 decided+0.010
 tried+0.009
 never+0.009
 came+0.009
 dropped+0.009
Neg logit contributions
igsaw-0.016
aj-0.014
udd-0.013
 batch-0.013
ummy-0.013
Token from
Token ID422
Feature activation-2.05e+00

Pos logit contributions
 decided+0.009
 tried+0.009
 never+0.009
 came+0.008
 stumbled+0.008
Neg logit contributions
igsaw-0.017
aj-0.016
 batch-0.014
ummy-0.014
udd-0.014
Token the
Token ID262
Feature activation-1.05e+01

Pos logit contributions
igsaw+0.067
aj+0.061
 batch+0.058
ummy+0.056
 coll+0.055
Neg logit contributions
 decided-0.047
 tried-0.044
 never-0.044
 came-0.043
 stumbled-0.041
Token sm
Token ID895
Feature activation-1.57e+01

Pos logit contributions
igsaw+0.266
aj+0.246
 batch+0.213
ummy+0.207
udd+0.204
Neg logit contributions
 decided-0.321
 tried-0.308
 never-0.307
 came-0.301
 stumbled-0.292
Tokenelly
Token ID6148
Feature activation-1.02e+01

Pos logit contributions
igsaw+0.209
aj+0.187
 batch+0.133
 coll+0.117
ummy+0.117
Neg logit contributions
 decided-0.663
 tried-0.642
 never-0.641
 came-0.634
 stumbled-0.619
Token pitch
Token ID7078
Feature activation-2.64e+00

Pos logit contributions
igsaw+0.265
aj+0.241
 batch+0.213
ummy+0.209
udd+0.203
Neg logit contributions
 decided-0.307
 never-0.293
 tried-0.292
 came-0.285
 stumbled-0.278
Token.
Token ID13
Feature activation-9.41e-01

Pos logit contributions
igsaw+0.100
aj+0.095
 batch+0.086
ummy+0.085
udd+0.084
Neg logit contributions
 decided-0.047
 tried-0.044
 never-0.044
 came-0.042
 stumbled-0.040
Token But
Token ID887
Feature activation+2.41e+00

Pos logit contributions
igsaw+0.029
aj+0.028
 batch+0.024
udd+0.024
 coll+0.024
Neg logit contributions
 decided-0.024
 tried-0.023
 never-0.023
 could-0.023
 came-0.023
Token one
Token ID530
Feature activation-3.49e+00

Pos logit contributions
 decided+0.048
 tried+0.044
 never+0.044
 came+0.043
 stumbled+0.041
Neg logit contributions
igsaw-0.086
aj-0.082
 batch-0.075
ummy-0.073
udd-0.072
Token to
Token ID284
Feature activation+4.11e+00

Pos logit contributions
igsaw+0.006
aj+0.005
 batch+0.005
ummy+0.005
 coll+0.005
Neg logit contributions
 decided-0.004
 stumbled-0.004
pped-0.004
 tried-0.004
 dropped-0.004
Token roll
Token ID4836
Feature activation-3.49e-01

Pos logit contributions
 decided+0.083
 stumbled+0.076
 came+0.075
 dropped+0.073
 tried+0.073
Neg logit contributions
igsaw-0.137
aj-0.121
 batch-0.113
 former-0.111
ummy-0.110
Token around
Token ID1088
Feature activation+2.10e+00

Pos logit contributions
igsaw+0.014
aj+0.014
 batch+0.012
ummy+0.012
udd+0.012
Neg logit contributions
 decided-0.006
 tried-0.005
 never-0.005
 came-0.005
 got-0.005
Token with
Token ID351
Feature activation-1.42e+00

Pos logit contributions
 decided+0.043
 tried+0.040
 never+0.040
 came+0.039
 stumbled+0.038
Neg logit contributions
igsaw-0.074
aj-0.069
 batch-0.063
ummy-0.062
udd-0.061
Token the
Token ID262
Feature activation-9.77e+00

Pos logit contributions
igsaw+0.051
aj+0.049
 batch+0.043
ummy+0.043
udd+0.043
Neg logit contributions
 decided-0.030
 tried-0.028
 never-0.028
 came-0.027
 dropped-0.026
Token gr
Token ID1036
Feature activation-1.57e+01

Pos logit contributions
aj+0.259
igsaw+0.256
 batch+0.221
udd+0.211
 coll+0.206
Neg logit contributions
 tried-0.285
 decided-0.283
 never-0.269
 came-0.267
 dropped-0.264
Tokenumpy
Token ID32152
Feature activation-9.48e+00

Pos logit contributions
aj+0.383
igsaw+0.379
 batch+0.331
 coll+0.322
 bou+0.293
Neg logit contributions
 decided-0.464
 tried-0.444
 never-0.440
 came-0.436
 got-0.423
Token shape
Token ID5485
Feature activation-1.11e+00

Pos logit contributions
igsaw+0.255
aj+0.252
 batch+0.221
 coll+0.207
udd+0.207
Neg logit contributions
 decided-0.267
 tried-0.264
 came-0.254
 never-0.251
 dropped-0.247
Token and
Token ID290
Feature activation+1.89e+00

Pos logit contributions
igsaw+0.039
aj+0.037
 batch+0.033
ummy+0.033
udd+0.032
Neg logit contributions
 decided-0.023
 tried-0.021
 never-0.021
 came-0.020
 stumbled-0.020
Token soon
Token ID2582
Feature activation+5.19e+00

Pos logit contributions
 decided+0.033
 tried+0.030
 never+0.030
 came+0.030
 stumbled+0.029
Neg logit contributions
igsaw-0.070
aj-0.066
 batch-0.061
 coll-0.059
udd-0.059
Token,
Token ID11
Feature activation-4.26e-01

Pos logit contributions
 decided+0.087
 tried+0.081
 never+0.080
 came+0.077
 stumbled+0.073
Neg logit contributions
igsaw-0.201
aj-0.191
 batch-0.175
ummy-0.172
udd-0.171
Token mom
Token ID1995
Feature activation+2.66e+00

Pos logit contributions
igsaw+0.180
aj+0.166
udd+0.159
umm+0.153
 batch+0.151
Neg logit contributions
 decided-0.103
 tried-0.098
 never-0.098
 came-0.096
 dropped-0.091
Tokenmy
Token ID1820
Feature activation+4.74e+00

Pos logit contributions
 decided+0.067
 tried+0.065
 never+0.064
 came+0.062
 stumbled+0.061
Neg logit contributions
igsaw-0.080
aj-0.075
 batch-0.067
ummy-0.066
udd-0.065
Token,
Token ID11
Feature activation-1.02e+00

Pos logit contributions
 decided+0.095
 tried+0.090
 never+0.089
 came+0.087
 stumbled+0.082
Neg logit contributions
igsaw-0.169
aj-0.160
 batch-0.145
ummy-0.142
udd-0.141
Token "
Token ID366
Feature activation-1.45e+00

Pos logit contributions
igsaw+0.023
aj+0.021
 batch+0.019
ummy+0.018
 coll+0.017
Neg logit contributions
 decided-0.031
 tried-0.029
 never-0.029
 stumbled-0.029
pped-0.029
TokenWhere
Token ID8496
Feature activation+7.28e+00

Pos logit contributions
aj+0.042
igsaw+0.041
 batch+0.038
ummy+0.036
umm+0.036
Neg logit contributions
 tried-0.031
 dropped-0.030
 never-0.030
 decided-0.030
 came-0.030
Token did
Token ID750
Feature activation+5.69e+00

Pos logit contributions
 decided+0.113
 tried+0.101
 never+0.101
 came+0.094
 stumbled+0.093
Neg logit contributions
igsaw-0.287
aj-0.274
 batch-0.249
ummy-0.247
udd-0.247
Token the
Token ID262
Feature activation-8.55e+00

Pos logit contributions
 decided+0.127
 tried+0.116
 never+0.114
 stumbled+0.113
 managed+0.111
Neg logit contributions
igsaw-0.187
aj-0.170
ummy-0.156
 batch-0.156
 coll-0.150
Token bird
Token ID6512
Feature activation+1.24e+00

Pos logit contributions
igsaw+0.263
aj+0.252
 batch+0.216
udd+0.215
ummy+0.211
Neg logit contributions
 decided-0.221
 never-0.210
 tried-0.210
 came-0.205
 dropped-0.197
Token go
Token ID467
Feature activation+2.70e+00

Pos logit contributions
 decided+0.022
 stumbled+0.020
 never+0.020
pped+0.020
 managed+0.019
Neg logit contributions
igsaw-0.040
aj-0.038
ummy-0.036
 batch-0.036
udd-0.035
Token?"
Token ID1701
Feature activation-2.02e+00

Pos logit contributions
 decided+0.071
 managed+0.068
 tried+0.067
 never+0.067
 stumbled+0.066
Neg logit contributions
igsaw-0.073
aj-0.066
ummy-0.064
 batch-0.062
udd-0.059
Token
Token ID198
Feature activation-5.39e+00

Pos logit contributions
igsaw+0.055
aj+0.051
 batch+0.045
ummy+0.044
udd+0.042
Neg logit contributions
 decided-0.058
 tried-0.055
 never-0.055
 came-0.054
 stumbled-0.052
Token why
Token ID1521
Feature activation+4.44e+00

Pos logit contributions
 decided+0.053
 tried+0.050
 never+0.049
 came+0.047
 stumbled+0.046
Neg logit contributions
igsaw-0.100
aj-0.095
 batch-0.086
ummy-0.085
udd-0.084
Token she
Token ID673
Feature activation+7.69e+00

Pos logit contributions
 decided+0.066
pped+0.062
 tried+0.061
 never+0.059
 stumbled+0.058
Neg logit contributions
igsaw-0.165
aj-0.156
ummy-0.146
 batch-0.143
 types-0.141
Token was
Token ID373
Feature activation+3.00e+00

Pos logit contributions
 decided+0.118
pped+0.116
 never+0.114
Please+0.110
 managed+0.109
Neg logit contributions
aj-0.235
udd-0.231
igsaw-0.227
 types-0.215
 batch-0.212
Token crying
Token ID13774
Feature activation-1.89e-01

Pos logit contributions
 decided+0.063
 tried+0.058
 never+0.057
 came+0.055
 managed+0.055
Neg logit contributions
igsaw-0.099
aj-0.096
 batch-0.086
ummy-0.085
udd-0.084
Token.
Token ID13
Feature activation-1.09e+00

Pos logit contributions
igsaw+0.006
aj+0.006
ummy+0.006
udd+0.005
 batch+0.005
Neg logit contributions
 decided-0.004
 never-0.004
 tried-0.004
 stumbled-0.004
 managed-0.004
Token She
Token ID1375
Feature activation+7.05e+00

Pos logit contributions
igsaw+0.029
aj+0.028
 batch+0.024
udd+0.024
 coll+0.023
Neg logit contributions
 decided-0.032
 tried-0.030
 never-0.030
 came-0.030
 stumbled-0.028
Token told
Token ID1297
Feature activation-7.56e-01

Pos logit contributions
pped+0.131
 decided+0.120
 never+0.119
 stumbled+0.119
 almost+0.117
Neg logit contributions
aj-0.211
 batch-0.199
igsaw-0.194
udd-0.185
 coll-0.183
Token him
Token ID683
Feature activation+3.91e+00

Pos logit contributions
igsaw+0.026
aj+0.024
 batch+0.022
ummy+0.022
 coll+0.021
Neg logit contributions
 decided-0.016
 tried-0.015
 never-0.015
 stumbled-0.014
 came-0.014
Token about
Token ID546
Feature activation+1.84e+00

Pos logit contributions
 decided+0.080
pped+0.078
 tried+0.077
 stumbled+0.077
Please+0.073
Neg logit contributions
igsaw-0.123
aj-0.112
ummy-0.107
 batch-0.105
udd-0.102
Token the
Token ID262
Feature activation-9.55e+00

Pos logit contributions
 decided+0.042
 tried+0.040
 never+0.039
 came+0.039
 stumbled+0.038
Neg logit contributions
igsaw-0.059
aj-0.055
 batch-0.051
ummy-0.050
 coll-0.049
Token rope
Token ID17182
Feature activation-2.63e-01

Pos logit contributions
igsaw+0.301
aj+0.290
ummy+0.253
 batch+0.245
udd+0.244
Neg logit contributions
 tried-0.242
 decided-0.241
 never-0.237
 came-0.229
 dropped-0.223
Token pumpkin
Token ID30089
Feature activation-1.09e+00

Pos logit contributions
igsaw+0.221
aj+0.199
ummy+0.190
 batch+0.186
 coll+0.174
Neg logit contributions
 decided-0.266
 tried-0.262
 never-0.256
 stumbled-0.255
 came-0.252
Token was
Token ID373
Feature activation+2.82e+00

Pos logit contributions
aj+0.037
igsaw+0.037
 batch+0.035
ummy+0.035
udd+0.034
Neg logit contributions
 decided-0.017
pped-0.017
 tried-0.016
 managed-0.016
 dropped-0.016
Token so
Token ID523
Feature activation+2.55e+00

Pos logit contributions
 decided+0.052
 tried+0.048
 never+0.046
 came+0.046
 stumbled+0.046
Neg logit contributions
igsaw-0.101
aj-0.097
 batch-0.091
ummy-0.089
 coll-0.087
Token long
Token ID890
Feature activation-3.75e+00

Pos logit contributions
 decided+0.083
 tried+0.080
 never+0.079
 came+0.078
 stumbled+0.076
Neg logit contributions
igsaw-0.061
aj-0.056
 batch-0.047
ummy-0.046
udd-0.045
Token that
Token ID326
Feature activation+2.77e+00

Pos logit contributions
igsaw+0.113
aj+0.108
ummy+0.102
 batch+0.099
udd+0.097
Neg logit contributions
 decided-0.084
 tried-0.077
 managed-0.076
 never-0.075
 stumbled-0.075
Token it
Token ID340
Feature activation+7.20e+00

Pos logit contributions
 decided+0.024
 tried+0.023
 never+0.020
 came+0.020
 dropped+0.020
Neg logit contributions
igsaw-0.121
aj-0.116
ummy-0.111
 batch-0.111
 types-0.108
Token reached
Token ID4251
Feature activation+4.38e+00

Pos logit contributions
pped+0.095
ged+0.076
 decided+0.072
 rushed+0.070
Please+0.070
Neg logit contributions
aj-0.247
udd-0.239
igsaw-0.230
 batch-0.229
 types-0.229
Token the
Token ID262
Feature activation-8.87e+00

Pos logit contributions
 decided+0.093
 never+0.089
 tried+0.088
 came+0.085
 stumbled+0.081
Neg logit contributions
igsaw-0.153
aj-0.145
 batch-0.130
udd-0.127
ummy-0.127
Token sky
Token ID6766
Feature activation+3.00e+00

Pos logit contributions
igsaw+0.232
aj+0.215
 batch+0.181
udd+0.177
ummy+0.174
Neg logit contributions
 decided-0.272
 never-0.262
 tried-0.259
 came-0.253
 stumbled-0.245
Token.
Token ID13
Feature activation-8.69e-01

Pos logit contributions
 decided+0.052
 tried+0.048
 never+0.048
 came+0.046
 stumbled+0.043
Neg logit contributions
igsaw-0.117
aj-0.111
 batch-0.101
ummy-0.099
udd-0.099
Token One
Token ID1881
Feature activation-4.07e+00

Pos logit contributions
igsaw+0.032
aj+0.031
udd+0.028
 batch+0.027
 coll+0.026
Neg logit contributions
 decided-0.018
 tried-0.018
 came-0.017
 never-0.017
 stumbled-0.016
Token him
Token ID683
Feature activation+4.27e+00

Pos logit contributions
igsaw+0.098
aj+0.093
 batch+0.088
ummy+0.087
udd+0.086
Neg logit contributions
 decided-0.016
 tried-0.014
 never-0.014
 came-0.012
 stumbled-0.012
Token a
Token ID257
Feature activation-6.94e+00

Pos logit contributions
 decided+0.085
 never+0.079
 tried+0.077
 came+0.075
 got+0.072
Neg logit contributions
igsaw-0.156
aj-0.151
umm-0.138
ummy-0.135
 batch-0.133
Token big
Token ID1263
Feature activation-1.06e+01

Pos logit contributions
igsaw+0.175
aj+0.169
udd+0.141
umm+0.139
ummy+0.138
Neg logit contributions
 decided-0.211
 tried-0.204
 never-0.202
 came-0.200
 got-0.197
Token shed
Token ID14999
Feature activation+2.92e+00

Pos logit contributions
aj+0.310
igsaw+0.303
udd+0.266
ushes+0.253
umm+0.243
Neg logit contributions
 tried-0.279
 decided-0.275
 came-0.273
 never-0.264
 got-0.261
Token where
Token ID810
Feature activation+2.50e+00

Pos logit contributions
 tried+0.059
 decided+0.058
 never+0.055
 dropped+0.055
 stumbled+0.054
Neg logit contributions
igsaw-0.096
aj-0.091
 batch-0.086
ummy-0.085
 coll-0.082
Token he
Token ID339
Feature activation+7.98e+00

Pos logit contributions
 decided+0.038
 tried+0.037
 never+0.036
pped+0.036
 almost+0.034
Neg logit contributions
igsaw-0.094
aj-0.087
 batch-0.082
 types-0.081
ummy-0.081
Token could
Token ID714
Feature activation+8.56e+00

Pos logit contributions
 decided+0.082
 never+0.079
pped+0.077
 tried+0.076
 came+0.073
Neg logit contributions
igsaw-0.314
aj-0.307
 types-0.286
 batch-0.286
udd-0.285
Token ice
Token ID4771
Feature activation-3.52e+00

Pos logit contributions
 decided+0.181
 stumbled+0.176
ged+0.175
 came+0.174
 wouldn+0.172
Neg logit contributions
igsaw-0.249
ummy-0.220
 batch-0.219
 stacks-0.210
aj-0.205
Token-
Token ID12
Feature activation-4.08e+00

Pos logit contributions
igsaw+0.097
aj+0.091
 batch+0.081
ummy+0.079
udd+0.078
Neg logit contributions
 decided-0.098
 tried-0.095
 never-0.094
 came-0.092
 stumbled-0.090
Tokensk
Token ID8135
Feature activation-6.83e+00

Pos logit contributions
igsaw+0.113
aj+0.104
 batch+0.097
udd+0.093
ummy+0.092
Neg logit contributions
 decided-0.106
 tried-0.104
 never-0.102
 came-0.100
 stumbled-0.099
Tokenate
Token ID378
Feature activation+2.52e-02

Pos logit contributions
igsaw+0.162
aj+0.148
 batch+0.128
ummy+0.122
 coll+0.121
Neg logit contributions
 decided-0.221
 tried-0.213
 never-0.211
 came-0.209
 stumbled-0.203
Token had
Token ID550
Feature activation+6.32e+00

Pos logit contributions
pped+0.115
Please+0.097
ged+0.089
 stumbled+0.089
 risking+0.085
Neg logit contributions
udd-0.245
 batch-0.236
aj-0.235
igsaw-0.235
 types-0.231
Token to
Token ID284
Feature activation+4.22e+00

Pos logit contributions
 decided+0.110
 tried+0.102
 came+0.098
 never+0.098
pped+0.095
Neg logit contributions
igsaw-0.228
aj-0.219
 batch-0.202
 coll-0.194
udd-0.193
Token save
Token ID3613
Feature activation-7.44e-01

Pos logit contributions
 decided+0.084
 came+0.083
 stumbled+0.082
 could+0.080
 tried+0.080
Neg logit contributions
igsaw-0.138
aj-0.123
ummy-0.118
 batch-0.117
 former-0.115
Token some
Token ID617
Feature activation-4.79e+00

Pos logit contributions
igsaw+0.027
aj+0.026
 batch+0.023
udd+0.023
ummy+0.023
Neg logit contributions
 decided-0.015
 never-0.014
 tried-0.014
 came-0.013
 dropped-0.013
Token of
Token ID286
Feature activation-3.21e+00

Pos logit contributions
igsaw+0.128
aj+0.121
 batch+0.102
udd+0.101
ummy+0.099
Neg logit contributions
 decided-0.140
 tried-0.135
 never-0.134
 came-0.131
 got-0.126
Token it
Token ID340
Feature activation+6.53e+00

Pos logit contributions
igsaw+0.114
aj+0.112
udd+0.099
ummy+0.097
 batch+0.096
Neg logit contributions
 decided-0.064
 never-0.063
 tried-0.062
 came-0.059
 dropped-0.055
Token.
Token ID13
Feature activation-1.16e+00

Pos logit contributions
 decided+0.126
 tried+0.119
 never+0.117
 came+0.114
 stumbled+0.111
Neg logit contributions
igsaw-0.236
aj-0.223
 batch-0.203
ummy-0.200
udd-0.198
Token It
Token ID632
Feature activation+8.82e+00

Pos logit contributions
igsaw+0.037
aj+0.036
opl+0.032
 coll+0.031
udd+0.031
Neg logit contributions
 decided-0.028
 tried-0.026
 never-0.026
 came-0.025
 could-0.025
Token was
Token ID373
Feature activation+2.77e+00

Pos logit contributions
 decided+0.133
 tried+0.123
 never+0.122
 came+0.117
 stumbled+0.116
Neg logit contributions
igsaw-0.342
aj-0.328
 batch-0.305
udd-0.297
ummy-0.294
Token a
Token ID257
Feature activation-6.49e+00

Pos logit contributions
 decided+0.059
 tried+0.056
 never+0.056
 came+0.054
 stumbled+0.052
Neg logit contributions
igsaw-0.096
aj-0.091
 batch-0.082
ummy-0.080
udd-0.079
Token big
Token ID1263
Feature activation-1.05e+01

Pos logit contributions
igsaw+0.185
aj+0.179
udd+0.154
ummy+0.152
 batch+0.149
Neg logit contributions
 decided-0.175
 never-0.173
 tried-0.169
 came-0.164
 got-0.160
Token How
Token ID1374
Feature activation+5.64e+00

Pos logit contributions
igsaw+0.018
aj+0.017
udd+0.016
 batch+0.016
 coll+0.015
Neg logit contributions
 decided-0.013
 tried-0.012
 never-0.012
 came-0.011
 stumbled-0.011
Token did
Token ID750
Feature activation+6.02e+00

Pos logit contributions
 decided+0.076
 tried+0.070
 never+0.067
 came+0.065
 stumbled+0.062
Neg logit contributions
igsaw-0.237
aj-0.227
 batch-0.208
udd-0.206
ummy-0.206
Token you
Token ID345
Feature activation+8.05e+00

Pos logit contributions
 decided+0.122
 tried+0.112
 never+0.111
 stumbled+0.107
 came+0.107
Neg logit contributions
igsaw-0.211
aj-0.196
 batch-0.179
ummy-0.177
 coll-0.174
Token do
Token ID466
Feature activation+4.28e+00

Pos logit contributions
 decided+0.170
 stumbled+0.165
ged+0.158
 managed+0.157
 came+0.157
Neg logit contributions
igsaw-0.230
aj-0.202
ay-0.197
ummy-0.197
udd-0.195
Token that
Token ID326
Feature activation+4.30e+00

Pos logit contributions
 decided+0.091
 tried+0.084
 never+0.081
 came+0.081
 stumbled+0.080
Neg logit contributions
igsaw-0.148
aj-0.138
 batch-0.127
ummy-0.125
udd-0.122
Token?"
Token ID1701
Feature activation-1.11e+00

Pos logit contributions
 decided+0.103
 tried+0.098
 never+0.097
 came+0.094
 stumbled+0.090
Neg logit contributions
igsaw-0.139
aj-0.131
 batch-0.116
ummy-0.114
udd-0.113
Token Lily
Token ID20037
Feature activation+1.70e+00

Pos logit contributions
igsaw+0.036
aj+0.034
 batch+0.030
udd+0.030
ummy+0.029
Neg logit contributions
 decided-0.027
 tried-0.026
 never-0.025
 came-0.025
 stumbled-0.024
Token smiled
Token ID13541
Feature activation-3.32e+00

Pos logit contributions
 decided+0.031
 tried+0.029
 never+0.028
 came+0.028
 stumbled+0.026
Neg logit contributions
igsaw-0.065
aj-0.061
 batch-0.056
ummy-0.055
udd-0.054
Token and
Token ID290
Feature activation+2.40e+00

Pos logit contributions
igsaw+0.121
aj+0.117
ummy+0.105
 batch+0.105
udd+0.104
Neg logit contributions
 decided-0.061
 never-0.059
 tried-0.059
 came-0.055
 stumbled-0.055
Token said
Token ID531
Feature activation+1.79e-01

Pos logit contributions
 decided+0.042
 never+0.041
 tried+0.038
 stumbled+0.038
 came+0.037
Neg logit contributions
igsaw-0.085
aj-0.084
 batch-0.076
udd-0.075
 coll-0.073
Token,
Token ID11
Feature activation-2.82e-01

Pos logit contributions
 decided+0.004
 tried+0.004
 never+0.004
 came+0.004
 stumbled+0.004
Neg logit contributions
igsaw-0.006
aj-0.005
 batch-0.005
ummy-0.005
udd-0.005
Token
Token ID198
Feature activation-5.49e+00

Pos logit contributions
igsaw+0.211
aj+0.194
umm+0.184
 former+0.176
 coll+0.174
Neg logit contributions
 never-0.095
 came-0.095
 decided-0.094
 tried-0.092
 could-0.090
TokenThey
Token ID2990
Feature activation+8.56e+00

Pos logit contributions
igsaw+0.195
aj+0.183
 batch+0.163
ummy+0.160
 coll+0.158
Neg logit contributions
 decided-0.124
 never-0.116
 tried-0.113
 came-0.109
 got-0.105
Token looked
Token ID3114
Feature activation+4.65e+00

Pos logit contributions
pped+0.113
 never+0.112
Please+0.112
 risking+0.108
't+0.107
Neg logit contributions
igsaw-0.272
aj-0.264
udd-0.253
 types-0.249
 stacks-0.249
Token and
Token ID290
Feature activation+3.61e+00

Pos logit contributions
 decided+0.098
 never+0.093
 tried+0.091
 stumbled+0.090
 came+0.088
Neg logit contributions
igsaw-0.151
aj-0.144
 batch-0.131
udd-0.131
ummy-0.129
Token looked
Token ID3114
Feature activation+5.10e+00

Pos logit contributions
pped+0.046
 decided+0.043
 never+0.042
Please+0.041
 dropped+0.039
Neg logit contributions
igsaw-0.129
aj-0.125
udd-0.117
 batch-0.116
 stacks-0.115
Token for
Token ID329
Feature activation+1.57e+00

Pos logit contributions
 decided+0.121
 never+0.118
pped+0.117
 stumbled+0.117
 tried+0.114
Neg logit contributions
igsaw-0.137
aj-0.134
udd-0.125
ummy-0.118
 batch-0.117
Token the
Token ID262
Feature activation-9.23e+00

Pos logit contributions
 decided+0.035
 tried+0.033
 never+0.033
 came+0.032
 stumbled+0.030
Neg logit contributions
igsaw-0.054
aj-0.051
 batch-0.045
ummy-0.045
udd-0.044
Token fl
Token ID781
Feature activation-1.12e+01

Pos logit contributions
igsaw+0.275
aj+0.259
 batch+0.229
ummy+0.225
udd+0.222
Neg logit contributions
 decided-0.239
 tried-0.227
 never-0.226
 came-0.221
 stumbled-0.215
Tokenute
Token ID1133
Feature activation-6.54e-01

Pos logit contributions
igsaw+0.168
aj+0.150
ummy+0.108
 batch+0.107
udd+0.105
Neg logit contributions
 decided-0.463
 tried-0.446
 never-0.443
 came-0.437
 stumbled-0.429
Token.
Token ID13
Feature activation-4.10e-01

Pos logit contributions
igsaw+0.021
aj+0.020
ummy+0.018
 coll+0.018
 batch+0.017
Neg logit contributions
 decided-0.014
 tried-0.013
pped-0.013
 never-0.013
 stumbled-0.012
Token Finally
Token ID9461
Feature activation+3.49e+00

Pos logit contributions
igsaw+0.013
aj+0.013
opl+0.011
 coll+0.011
 batch+0.011
Neg logit contributions
 decided-0.010
 tried-0.010
 came-0.009
 never-0.009
 could-0.009
Token,
Token ID11
Feature activation-6.59e-01

Pos logit contributions
igsaw+0.011
aj+0.010
 batch+0.009
ummy+0.009
udd+0.009
Neg logit contributions
 decided-0.007
 tried-0.007
 never-0.007
 came-0.007
 stumbled-0.007
Token "
Token ID366
Feature activation-9.58e-01

Pos logit contributions
igsaw+0.015
aj+0.014
ummy+0.013
 batch+0.013
 coll+0.012
Neg logit contributions
 decided-0.020
 never-0.019
 tried-0.019
 managed-0.019
 stumbled-0.019
TokenSo
Token ID2396
Feature activation+2.00e+00

Pos logit contributions
igsaw+0.035
aj+0.033
 batch+0.030
ummy+0.030
udd+0.029
Neg logit contributions
 decided-0.018
 tried-0.018
 never-0.017
 came-0.017
 dropped-0.016
Token jail
Token ID7356
Feature activation-2.97e-01

Pos logit contributions
 decided+0.040
 tried+0.038
 never+0.038
 came+0.036
 stumbled+0.035
Neg logit contributions
igsaw-0.072
aj-0.068
 batch-0.062
ummy-0.060
udd-0.060
Token is
Token ID318
Feature activation+3.87e+00

Pos logit contributions
igsaw+0.009
aj+0.009
 batch+0.008
ummy+0.008
udd+0.008
Neg logit contributions
 decided-0.007
 tried-0.007
 never-0.007
 came-0.007
 dropped-0.006
Token like
Token ID588
Feature activation+3.57e-01

Pos logit contributions
 decided+0.084
 tried+0.080
 stumbled+0.077
 came+0.077
 never+0.075
Neg logit contributions
igsaw-0.124
aj-0.117
 batch-0.108
ummy-0.103
 coll-0.102
Token a
Token ID257
Feature activation-7.78e+00

Pos logit contributions
 decided+0.008
 tried+0.007
 never+0.007
 came+0.007
 stumbled+0.007
Neg logit contributions
igsaw-0.012
aj-0.011
 batch-0.010
ummy-0.010
udd-0.010
Token time
Token ID640
Feature activation+2.70e+00

Pos logit contributions
igsaw+0.219
aj+0.205
 batch+0.179
ummy+0.175
udd+0.173
Neg logit contributions
 decided-0.216
 tried-0.207
 never-0.206
 came-0.201
 stumbled-0.194
Token-
Token ID12
Feature activation-5.61e+00

Pos logit contributions
 decided+0.058
 tried+0.055
 never+0.054
 came+0.053
 dropped+0.052
Neg logit contributions
igsaw-0.089
aj-0.085
 batch-0.075
ummy-0.074
udd-0.073
Tokenout
Token ID448
Feature activation-2.60e+00

Pos logit contributions
igsaw+0.166
aj+0.148
 batch+0.136
udd+0.134
ummy+0.129
Neg logit contributions
 tried-0.134
 decided-0.134
 came-0.129
 never-0.129
 stumbled-0.128
Token for
Token ID329
Feature activation+7.88e-02

Pos logit contributions
igsaw+0.085
aj+0.079
 batch+0.073
ummy+0.071
udd+0.069
Neg logit contributions
 decided-0.056
 tried-0.053
 never-0.052
 stumbled-0.050
 managed-0.050
Token the
Token ID262
Feature activation-9.39e+00

Pos logit contributions
igsaw+0.093
aj+0.088
 batch+0.080
ummy+0.078
udd+0.078
Neg logit contributions
 decided-0.050
 tried-0.047
 never-0.047
 came-0.045
 stumbled-0.044
Token way
Token ID835
Feature activation+1.44e+00

Pos logit contributions
igsaw+0.249
aj+0.246
ummy+0.204
umm+0.201
udd+0.201
Neg logit contributions
 decided-0.282
 tried-0.281
 never-0.278
 came-0.277
 almost-0.266
Token the
Token ID262
Feature activation-8.65e+00

Pos logit contributions
 decided+0.024
 tried+0.023
 managed+0.021
pped+0.021
 dropped+0.021
Neg logit contributions
igsaw-0.051
aj-0.047
ummy-0.046
ay-0.044
udd-0.043
Token curtain
Token ID29461
Feature activation+1.69e+00

Pos logit contributions
igsaw+0.205
aj+0.195
 batch+0.161
udd+0.159
ummy+0.159
Neg logit contributions
 decided-0.282
 tried-0.277
 never-0.275
 came-0.271
 almost-0.259
Token moved
Token ID3888
Feature activation-1.68e+00

Pos logit contributions
 decided+0.024
pped+0.022
 tried+0.022
 never+0.021
 stumbled+0.021
Neg logit contributions
igsaw-0.062
aj-0.059
 batch-0.055
udd-0.054
ummy-0.054
Token and
Token ID290
Feature activation+2.39e+00

Pos logit contributions
igsaw+0.058
aj+0.054
ummy+0.050
udd+0.049
 coll+0.049
Neg logit contributions
 decided-0.032
 tried-0.031
 never-0.030
 came-0.029
 dropped-0.029
Token kept
Token ID4030
Feature activation+1.72e+00

Pos logit contributions
 decided+0.037
 tried+0.034
 never+0.033
 came+0.031
 dropped+0.031
Neg logit contributions
igsaw-0.092
aj-0.087
 batch-0.080
udd-0.079
 coll-0.078
Token pushing
Token ID7796
Feature activation-1.22e+00

Pos logit contributions
 decided+0.040
 tried+0.036
 never+0.035
 came+0.035
 got+0.035
Neg logit contributions
igsaw-0.052
aj-0.049
 coll-0.046
 batch-0.045
 goals-0.043
Token it
Token ID340
Feature activation+6.44e+00

Pos logit contributions
igsaw+0.045
aj+0.042
ummy+0.039
 batch+0.038
 coll+0.038
Neg logit contributions
 decided-0.022
 tried-0.020
 never-0.020
 came-0.019
 stumbled-0.019
Token.
Token ID13
Feature activation-8.27e-01

Pos logit contributions
 decided+0.123
 tried+0.115
 never+0.111
 came+0.110
 stumbled+0.107
Neg logit contributions
igsaw-0.232
aj-0.217
 batch-0.195
ummy-0.194
udd-0.194
Token His
Token ID2399
Feature activation-4.32e+00

Pos logit contributions
igsaw+0.028
aj+0.027
 batch+0.025
 coll+0.024
udd+0.023
Neg logit contributions
 decided-0.018
 tried-0.017
 never-0.017
 came-0.017
 could-0.016
Token.
Token ID13
Feature activation-1.54e+00

Pos logit contributions
 decided+0.010
 never+0.010
 came+0.009
 tried+0.009
 got+0.008
Neg logit contributions
igsaw-0.032
aj-0.030
 batch-0.027
ummy-0.027
udd-0.026
Token She
Token ID1375
Feature activation+7.00e+00

Pos logit contributions
igsaw+0.064
aj+0.062
 batch+0.059
udd+0.056
 coll+0.055
Neg logit contributions
 decided-0.021
 never-0.021
 tried-0.021
 could-0.020
 came-0.020
Token rides
Token ID17445
Feature activation+1.61e+00

Pos logit contributions
 decided+0.195
 never+0.188
 tried+0.188
 came+0.182
 dropped+0.175
Neg logit contributions
igsaw-0.207
aj-0.188
 batch-0.168
ummy-0.167
umm-0.160
Token,
Token ID11
Feature activation-1.11e+00

Pos logit contributions
 decided+0.030
 never+0.028
 tried+0.028
 came+0.027
 got+0.025
Neg logit contributions
igsaw-0.062
aj-0.059
 batch-0.053
ummy-0.053
udd-0.052
Token slides
Token ID19392
Feature activation+2.33e+00

Pos logit contributions
igsaw+0.035
aj+0.033
 batch+0.029
ummy+0.029
udd+0.028
Neg logit contributions
 decided-0.028
 tried-0.027
 never-0.027
 came-0.026
 stumbled-0.025
Token,
Token ID11
Feature activation-1.05e+00

Pos logit contributions
 decided+0.039
 tried+0.037
 never+0.037
 came+0.037
 got+0.034
Neg logit contributions
igsaw-0.095
aj-0.088
 batch-0.081
ummy-0.079
umm-0.079
Token and
Token ID290
Feature activation+1.57e+00

Pos logit contributions
igsaw+0.034
aj+0.032
 batch+0.029
ummy+0.028
udd+0.028
Neg logit contributions
 decided-0.025
 tried-0.023
 never-0.023
 came-0.023
 stumbled-0.022
Token plays
Token ID5341
Feature activation-1.33e+00

Pos logit contributions
 decided+0.041
 tried+0.039
 never+0.039
 came+0.038
 stumbled+0.037
Neg logit contributions
igsaw-0.048
aj-0.045
 batch-0.039
ummy-0.039
udd-0.038
Token with
Token ID351
Feature activation-2.30e+00

Pos logit contributions
igsaw+0.052
aj+0.050
ummy+0.046
umm+0.045
 batch+0.043
Neg logit contributions
 decided-0.025
 tried-0.024
 never-0.023
 came-0.023
 almost-0.021
Token a
Token ID257
Feature activation-7.81e+00

Pos logit contributions
igsaw+0.081
aj+0.077
umm+0.068
 batch+0.068
ummy+0.066
Neg logit contributions
 decided-0.049
 tried-0.049
 never-0.049
 came-0.047
 dropped-0.044
Token furry
Token ID40857
Feature activation-1.24e+01

Pos logit contributions
igsaw+0.229
aj+0.213
ummy+0.195
umm+0.189
 types+0.184
Neg logit contributions
 decided-0.209
 tried-0.205
 came-0.204
 dropped-0.198
 never-0.197
Token<|endoftext|>
Token ID50256
Feature activation-3.16e+00

Pos logit contributions
igsaw+0.019
aj+0.019
udd+0.017
 batch+0.017
 coll+0.017
Neg logit contributions
 decided-0.014
 never-0.014
 tried-0.013
 came-0.013
 stumbled-0.013
TokenTom
Token ID13787
Feature activation+2.06e+00

Pos logit contributions
igsaw+0.099
aj+0.093
 batch+0.084
 coll+0.082
ummy+0.081
Neg logit contributions
 decided-0.078
 tried-0.075
 came-0.075
 never-0.074
 stumbled-0.072
Tokenmy
Token ID1820
Feature activation+4.59e+00

Pos logit contributions
 decided+0.050
 tried+0.048
 never+0.047
 came+0.046
 stumbled+0.044
Neg logit contributions
igsaw-0.066
aj-0.061
 batch-0.055
ummy-0.054
 coll-0.053
Token was
Token ID373
Feature activation+2.43e+00

Pos logit contributions
 decided+0.072
 never+0.067
 tried+0.066
 came+0.063
 stumbled+0.060
Neg logit contributions
igsaw-0.177
aj-0.172
 batch-0.157
udd-0.155
ummy-0.154
Token an
Token ID281
Feature activation-9.42e+00

Pos logit contributions
 decided+0.048
 never+0.047
 tried+0.046
 came+0.044
 almost+0.043
Neg logit contributions
igsaw-0.091
aj-0.083
 batch-0.076
ummy-0.076
umm-0.075
Token alert
Token ID7995
Feature activation-7.23e+00

Pos logit contributions
igsaw+0.246
aj+0.245
 batch+0.200
ushes+0.198
 coll+0.196
Neg logit contributions
 decided-0.288
 never-0.269
 tried-0.265
 came-0.251
 almost-0.249
Token little
Token ID1310
Feature activation-7.48e+00

Pos logit contributions
igsaw+0.209
aj+0.200
 batch+0.172
udd+0.168
ushes+0.168
Neg logit contributions
 decided-0.197
 tried-0.190
 came-0.189
 never-0.183
 got-0.178
Token boy
Token ID2933
Feature activation+3.73e+00

Pos logit contributions
igsaw+0.206
aj+0.194
 batch+0.163
udd+0.160
ummy+0.157
Neg logit contributions
 decided-0.218
 tried-0.210
 came-0.204
 never-0.199
 got-0.196
Token.
Token ID13
Feature activation+1.98e-01

Pos logit contributions
 managed+0.077
 decided+0.076
 dropped+0.076
 tried+0.074
 never+0.073
Neg logit contributions
igsaw-0.111
aj-0.110
 batch-0.104
ummy-0.101
 coll-0.099
Token He
Token ID679
Feature activation+7.36e+00

Pos logit contributions
 decided+0.003
 tried+0.003
 never+0.003
 came+0.003
 stumbled+0.003
Neg logit contributions
igsaw-0.008
aj-0.008
 coll-0.007
 batch-0.007
udd-0.007
Token was
Token ID373
Feature activation+2.74e+00

Pos logit contributions
 decided+0.117
 tried+0.110
 never+0.108
pped+0.106
 came+0.105
Neg logit contributions
igsaw-0.265
aj-0.263
udd-0.236
 batch-0.235
ummy-0.227
Token Tim
Token ID5045
Feature activation+1.10e+00

Pos logit contributions
igsaw+0.060
aj+0.057
 batch+0.052
 coll+0.050
udd+0.050
Neg logit contributions
 decided-0.036
 tried-0.035
 never-0.035
 came-0.034
 got-0.032
Tokenmy
Token ID1820
Feature activation+3.85e+00

Pos logit contributions
 decided+0.030
 tried+0.029
 stumbled+0.029
 managed+0.029
 never+0.028
Neg logit contributions
igsaw-0.026
aj-0.026
udd-0.024
ummy-0.023
 batch-0.022
Token.
Token ID13
Feature activation-1.54e-02

Pos logit contributions
 decided+0.081
 managed+0.079
 stumbled+0.078
 tried+0.077
 wouldn+0.076
Neg logit contributions
igsaw-0.114
aj-0.113
udd-0.106
ummy-0.105
 batch-0.104
Token Tim
Token ID5045
Feature activation+1.14e+00

Pos logit contributions
igsaw+0.001
aj+0.001
 batch+0.000
 coll+0.000
udd+0.000
Neg logit contributions
 decided-0.000
 tried-0.000
 never-0.000
 came-0.000
 stumbled-0.000
Tokenmy
Token ID1820
Feature activation+4.39e+00

Pos logit contributions
 decided+0.030
 tried+0.029
 never+0.028
 came+0.028
 stumbled+0.028
Neg logit contributions
igsaw-0.031
aj-0.030
udd-0.026
 batch-0.026
ummy-0.026
Token loved
Token ID6151
Feature activation-3.21e+00

Pos logit contributions
 decided+0.086
 tried+0.082
 managed+0.081
pped+0.080
 wouldn+0.079
Neg logit contributions
igsaw-0.141
aj-0.138
udd-0.126
ummy-0.124
 batch-0.122
Token to
Token ID284
Feature activation+3.33e+00

Pos logit contributions
igsaw+0.128
aj+0.122
 batch+0.110
udd+0.109
ummy+0.109
Neg logit contributions
 decided-0.053
 tried-0.049
 never-0.049
 came-0.047
 got-0.043
Token go
Token ID467
Feature activation+2.32e+00

Pos logit contributions
 decided+0.075
 never+0.071
 tried+0.071
 came+0.068
 stumbled+0.067
Neg logit contributions
igsaw-0.110
aj-0.104
 batch-0.093
ummy-0.091
 coll-0.090
Token to
Token ID284
Feature activation+3.57e+00

Pos logit contributions
 decided+0.041
 never+0.038
 tried+0.038
 came+0.035
 stumbled+0.035
Neg logit contributions
igsaw-0.089
aj-0.085
 batch-0.077
ummy-0.076
udd-0.076
Token the
Token ID262
Feature activation-9.39e+00

Pos logit contributions
 it+0.049
 him+0.045
 tried+0.045
 get+0.042
 came+0.041
Neg logit contributions
igsaw-0.154
aj-0.153
umm-0.152
udd-0.140
ushes-0.139
Token park
Token ID3952
Feature activation+2.62e+00

Pos logit contributions
igsaw+0.277
aj+0.276
ushes+0.243
 types+0.224
 batch+0.211
Neg logit contributions
 decided-0.254
 never-0.249
 came-0.235
 got-0.225
 almost-0.221
Token practices
Token ID6593
Feature activation+4.10e+00

Pos logit contributions
 decided+0.160
 never+0.151
 tried+0.144
pped+0.144
 stumbled+0.143
Neg logit contributions
igsaw-0.273
aj-0.260
udd-0.236
 batch-0.232
 types-0.231
Token every
Token ID790
Feature activation-3.47e+00

Pos logit contributions
 decided+0.083
 tried+0.078
 never+0.076
 came+0.074
 stumbled+0.072
Neg logit contributions
igsaw-0.144
aj-0.137
 batch-0.122
ummy-0.121
udd-0.120
Token day
Token ID1110
Feature activation+4.03e+00

Pos logit contributions
igsaw+0.086
aj+0.079
 batch+0.069
ummy+0.067
udd+0.064
Neg logit contributions
 decided-0.107
 tried-0.102
 never-0.102
 came-0.100
 stumbled-0.097
Token.
Token ID13
Feature activation-7.63e-01

Pos logit contributions
 decided+0.076
 tried+0.072
 never+0.069
 dropped+0.068
 came+0.068
Neg logit contributions
igsaw-0.143
aj-0.134
ummy-0.123
 batch-0.121
 coll-0.120
Token The
Token ID383
Feature activation-8.66e+00

Pos logit contributions
igsaw+0.027
aj+0.026
umm+0.022
 batch+0.022
 coll+0.022
Neg logit contributions
 decided-0.017
 tried-0.016
 could-0.016
 never-0.016
 came-0.016
Token little
Token ID1310
Feature activation-7.75e+00

Pos logit contributions
igsaw+0.275
aj+0.261
 batch+0.227
udd+0.223
ummy+0.222
Neg logit contributions
 decided-0.229
 never-0.222
 tried-0.220
 came-0.211
 dropped-0.204
Token bird
Token ID6512
Feature activation-4.73e-01

Pos logit contributions
igsaw+0.268
aj+0.255
 batch+0.221
udd+0.220
ummy+0.218
Neg logit contributions
 decided-0.181
 tried-0.174
 came-0.166
 never-0.166
 got-0.156
Tokenie
Token ID494
Feature activation+2.89e+00

Pos logit contributions
igsaw+0.015
aj+0.014
 batch+0.013
udd+0.013
ummy+0.013
Neg logit contributions
 decided-0.010
 never-0.010
 tried-0.010
 stumbled-0.009
 came-0.009
Token was
Token ID373
Feature activation+3.39e+00

Pos logit contributions
 decided+0.042
 never+0.039
 tried+0.038
 came+0.037
 stumbled+0.036
Neg logit contributions
igsaw-0.114
aj-0.110
 batch-0.101
udd-0.100
ummy-0.098
Token happy
Token ID3772
Feature activation-3.57e+00

Pos logit contributions
 decided+0.076
 tried+0.072
 came+0.070
 never+0.070
 stumbled+0.068
Neg logit contributions
igsaw-0.110
aj-0.104
 batch-0.094
ummy-0.091
udd-0.091
Token to
Token ID284
Feature activation+4.73e+00

Pos logit contributions
igsaw+0.119
aj+0.110
ummy+0.105
 batch+0.103
udd+0.101
Neg logit contributions
 decided-0.073
 tried-0.067
 dropped-0.067
 stumbled-0.067
pped-0.066
Token ran
Token ID4966
Feature activation+1.88e+00

Pos logit contributions
pped+0.090
 risking+0.087
 never+0.083
 unable+0.073
't+0.071
Neg logit contributions
aj-0.297
igsaw-0.267
udd-0.260
 types-0.246
 stacks-0.245
Token to
Token ID284
Feature activation+2.82e+00

Pos logit contributions
 wouldn+0.044
 decided+0.044
 managed+0.044
'd+0.043
pped+0.043
Neg logit contributions
igsaw-0.055
aj-0.044
 stacks-0.042
 gym-0.041
 math-0.040
Token investigate
Token ID9161
Feature activation+2.79e+00

Pos logit contributions
 decided+0.063
 wouldn+0.058
 managed+0.057
 stumbled+0.056
 never+0.056
Neg logit contributions
igsaw-0.091
aj-0.076
 batch-0.072
ummy-0.071
 types-0.070
Token.
Token ID13
Feature activation-5.27e-01

Pos logit contributions
 decided+0.056
 never+0.054
 tried+0.053
 managed+0.052
 stumbled+0.051
Neg logit contributions
igsaw-0.094
aj-0.088
 batch-0.081
ummy-0.080
udd-0.079
Token
Token ID198
Feature activation-4.40e+00

Pos logit contributions
igsaw+0.016
aj+0.015
 batch+0.013
udd+0.013
ummy+0.013
Neg logit contributions
 decided-0.014
 tried-0.013
 never-0.013
 came-0.013
 stumbled-0.012
Token
Token ID198
Feature activation-4.72e+00

Pos logit contributions
igsaw+0.122
aj+0.115
ummy+0.099
 batch+0.099
udd+0.097
Neg logit contributions
 decided-0.121
 tried-0.115
 never-0.114
 came-0.111
 wouldn-0.109
TokenWhen
Token ID2215
Feature activation+3.71e+00

Pos logit contributions
igsaw+0.139
aj+0.129
 batch+0.110
ummy+0.109
udd+0.109
Neg logit contributions
 decided-0.117
 wouldn-0.113
 tried-0.113
 came-0.110
 never-0.110
Token she
Token ID673
Feature activation+7.22e+00

Pos logit contributions
 decided+0.073
pped+0.069
 managed+0.065
 tried+0.064
 dropped+0.064
Neg logit contributions
igsaw-0.123
aj-0.108
ummy-0.108
 batch-0.106
 puzzle-0.098
Token got
Token ID1392
Feature activation+1.55e+00

Pos logit contributions
 never+0.085
 unable+0.082
 decided+0.074
 risking+0.073
pped+0.072
Neg logit contributions
igsaw-0.260
aj-0.252
ay-0.227
 batch-0.227
udd-0.226
Token there
Token ID612
Feature activation+5.19e+00

Pos logit contributions
 decided+0.031
 wouldn+0.030
'd+0.029
pped+0.029
 dropped+0.029
Neg logit contributions
igsaw-0.049
aj-0.046
ummy-0.041
 batch-0.040
udd-0.039
Token,
Token ID11
Feature activation-7.06e-01

Pos logit contributions
 decided+0.119
 tried+0.113
 never+0.112
 came+0.108
 stumbled+0.105
Neg logit contributions
igsaw-0.169
aj-0.159
 batch-0.143
ummy-0.141
udd-0.139
Token and
Token ID290
Feature activation+1.78e+00

Pos logit contributions
 decided+0.082
 tried+0.078
 never+0.076
 managed+0.074
 stumbled+0.073
Neg logit contributions
igsaw-0.109
aj-0.104
ummy-0.096
udd-0.095
 batch-0.094
Token Ell
Token ID7122
Feature activation-3.64e+00

Pos logit contributions
 decided+0.035
 never+0.033
 tried+0.033
 came+0.032
 managed+0.031
Neg logit contributions
igsaw-0.060
aj-0.058
 batch-0.053
ummy-0.051
 coll-0.051
Tokena
Token ID64
Feature activation-8.39e-01

Pos logit contributions
igsaw+0.110
aj+0.104
 batch+0.093
udd+0.090
ummy+0.090
Neg logit contributions
 decided-0.092
 tried-0.088
 never-0.088
 came-0.085
 stumbled-0.083
Token was
Token ID373
Feature activation+3.16e+00

Pos logit contributions
igsaw+0.032
aj+0.031
 batch+0.029
udd+0.028
 coll+0.028
Neg logit contributions
 decided-0.012
 never-0.011
 tried-0.010
pped-0.010
 almost-0.010
Token too
Token ID1165
Feature activation+6.55e+00

Pos logit contributions
 decided+0.059
 tried+0.055
 never+0.053
 came+0.053
 stumbled+0.050
Neg logit contributions
igsaw-0.114
aj-0.110
 batch-0.099
ummy-0.097
udd-0.096
Token scared
Token ID12008
Feature activation-2.32e+00

Pos logit contributions
 decided+0.139
 tried+0.131
 never+0.131
 came+0.127
 stumbled+0.121
Neg logit contributions
igsaw-0.226
aj-0.215
 batch-0.192
ummy-0.190
udd-0.189
Token to
Token ID284
Feature activation+3.97e+00

Pos logit contributions
igsaw+0.074
ummy+0.069
aj+0.069
udd+0.064
 batch+0.062
Neg logit contributions
 decided-0.050
 tried-0.048
 managed-0.047
 never-0.047
 stumbled-0.046
Token move
Token ID1445
Feature activation-1.19e+00

Pos logit contributions
 decided+0.081
 managed+0.077
pped+0.074
 wouldn+0.073
 stumbled+0.072
Neg logit contributions
igsaw-0.110
aj-0.103
 difference-0.097
 gym-0.095
opl-0.094
Token.
Token ID13
Feature activation-7.70e-01

Pos logit contributions
igsaw+0.038
aj+0.034
ummy+0.032
 coll+0.031
 batch+0.031
Neg logit contributions
 tried-0.024
 decided-0.024
 managed-0.023
 never-0.023
 stumbled-0.022
Token
Token ID198
Feature activation-4.22e+00

Pos logit contributions
igsaw+0.027
aj+0.025
 batch+0.023
 coll+0.023
udd+0.022
Neg logit contributions
 decided-0.017
 tried-0.016
 never-0.016
 came-0.016
 could-0.016
Token
Token ID198
Feature activation-4.61e+00

Pos logit contributions
igsaw+0.148
aj+0.137
 batch+0.126
umm+0.123
 coll+0.122
Neg logit contributions
 decided-0.094
 never-0.091
 tried-0.090
 came-0.087
 stumbled-0.083
Token was
Token ID373
Feature activation+3.33e+00

Pos logit contributions
pped+0.058
 never+0.045
 stumbled+0.044
Please+0.043
 possibly+0.043
Neg logit contributions
 types-0.118
aj-0.116
udd-0.116
igsaw-0.115
 batch-0.113
Token comfortable
Token ID6792
Feature activation-3.30e+00

Pos logit contributions
 decided+0.089
 tried+0.086
 wouldn+0.086
 stumbled+0.085
pped+0.085
Neg logit contributions
aj-0.080
igsaw-0.073
 batch-0.067
udd-0.066
 coll-0.065
Token.
Token ID13
Feature activation-7.56e-01

Pos logit contributions
aj+0.101
igsaw+0.096
udd+0.089
ummy+0.088
 batch+0.086
Neg logit contributions
 tried-0.069
 decided-0.069
 dropped-0.067
 managed-0.066
pped-0.065
Token
Token ID198
Feature activation-4.58e+00

Pos logit contributions
igsaw+0.025
aj+0.025
 batch+0.022
 coll+0.021
udd+0.021
Neg logit contributions
 decided-0.018
 tried-0.017
 came-0.017
 could-0.017
 never-0.016
Token
Token ID198
Feature activation-4.94e+00

Pos logit contributions
igsaw+0.153
aj+0.144
 batch+0.128
umm+0.126
 coll+0.125
Neg logit contributions
 decided-0.107
 never-0.103
 tried-0.101
 came-0.098
 stumbled-0.095
TokenThe
Token ID464
Feature activation-9.61e+00

Pos logit contributions
igsaw+0.136
aj+0.122
 batch+0.111
udd+0.109
ummy+0.107
Neg logit contributions
 decided-0.128
 tried-0.128
 came-0.126
 wouldn-0.125
 never-0.123
Token train
Token ID4512
Feature activation-2.20e+00

Pos logit contributions
igsaw+0.262
aj+0.234
 batch+0.204
ummy+0.201
umm+0.195
Neg logit contributions
 decided-0.296
 never-0.288
 tried-0.285
 came-0.282
 got-0.271
Token started
Token ID2067
Feature activation+1.97e+00

Pos logit contributions
igsaw+0.090
aj+0.088
 batch+0.081
udd+0.080
 coll+0.079
Neg logit contributions
 decided-0.027
 tried-0.025
 never-0.024
 came-0.022
 dropped-0.022
Token ch
Token ID442
Feature activation-8.59e+00

Pos logit contributions
 decided+0.030
 tried+0.028
 never+0.028
 came+0.027
 stumbled+0.025
Neg logit contributions
igsaw-0.081
aj-0.076
 batch-0.070
ummy-0.070
udd-0.068
Tokenug
Token ID1018
Feature activation-3.02e-01

Pos logit contributions
igsaw+0.235
aj+0.216
 batch+0.192
ummy+0.184
 coll+0.178
Neg logit contributions
 decided-0.251
 tried-0.242
 never-0.239
 came-0.236
 dropped-0.228
Tokenging
Token ID2667
Feature activation-9.00e-01

Pos logit contributions
aj+0.010
igsaw+0.009
udd+0.009
 coll+0.009
uff+0.009
Neg logit contributions
 decided-0.006
 never-0.005
 tried-0.005
 stumbled-0.005
 managed-0.005
Tokenucky
Token ID5309
Feature activation+2.34e-01

Pos logit contributions
igsaw+0.154
aj+0.140
 batch+0.114
ummy+0.113
udd+0.110
Neg logit contributions
 decided-0.277
 tried-0.268
 never-0.268
 came-0.262
 stumbled-0.256
Token saw
Token ID2497
Feature activation-1.76e+00

Pos logit contributions
pped+0.003
 never+0.003
 decided+0.003
 tried+0.003
 managed+0.003
Neg logit contributions
aj-0.009
udd-0.008
igsaw-0.008
 batch-0.008
 coll-0.007
Token a
Token ID257
Feature activation-7.75e+00

Pos logit contributions
igsaw+0.059
aj+0.056
 batch+0.051
ummy+0.050
udd+0.050
Neg logit contributions
 decided-0.038
 tried-0.036
 never-0.036
 came-0.034
 stumbled-0.033
Token big
Token ID1263
Feature activation-1.13e+01

Pos logit contributions
igsaw+0.187
aj+0.173
 batch+0.148
ummy+0.144
udd+0.142
Neg logit contributions
 decided-0.245
 tried-0.236
 never-0.235
 came-0.230
 stumbled-0.224
Token,
Token ID11
Feature activation-4.10e+00

Pos logit contributions
igsaw+0.338
aj+0.323
udd+0.272
 batch+0.272
ummy+0.266
Neg logit contributions
 decided-0.293
 tried-0.284
 came-0.277
 never-0.277
 got-0.265
Token graceful
Token ID44363
Feature activation-1.01e+01

Pos logit contributions
igsaw+0.100
aj+0.093
 batch+0.080
ummy+0.077
udd+0.076
Neg logit contributions
 decided-0.128
 tried-0.124
 never-0.123
 came-0.121
 stumbled-0.117
Token sw
Token ID1509
Feature activation-1.12e+01

Pos logit contributions
igsaw+0.319
aj+0.306
udd+0.260
 batch+0.259
ummy+0.252
Neg logit contributions
 decided-0.250
 tried-0.239
 came-0.238
 never-0.232
 got-0.224
Tokenan
Token ID272
Feature activation+5.03e-02

Pos logit contributions
igsaw+0.259
aj+0.245
udd+0.207
 batch+0.206
ummy+0.205
Neg logit contributions
 decided-0.363
 tried-0.348
 never-0.343
 came-0.336
 stumbled-0.330
Token swimming
Token ID14899
Feature activation-2.13e+00

Pos logit contributions
 managed+0.001
 decided+0.001
 tried+0.001
 never+0.001
 finally+0.001
Neg logit contributions
aj-0.001
udd-0.001
 coll-0.001
ummy-0.001
 batch-0.001
Token in
Token ID287
Feature activation-7.31e-01

Pos logit contributions
igsaw+0.075
aj+0.072
udd+0.068
 batch+0.067
ummy+0.067
Neg logit contributions
 never-0.034
 decided-0.033
 tried-0.033
 managed-0.032
 wouldn-0.031
Token the
Token ID262
Feature activation-9.63e+00

Pos logit contributions
igsaw+0.023
aj+0.022
 batch+0.020
ummy+0.019
 coll+0.019
Neg logit contributions
 decided-0.017
 tried-0.016
 never-0.016
 came-0.016
 wouldn-0.015
Token.
Token ID13
Feature activation-5.61e-01

Pos logit contributions
 decided+0.041
 tried+0.041
 never+0.039
 dropped+0.039
 managed+0.038
Neg logit contributions
igsaw-0.065
aj-0.063
ummy-0.059
 batch-0.058
udd-0.057
Token When
Token ID1649
Feature activation+3.51e+00

Pos logit contributions
igsaw+0.019
aj+0.018
 batch+0.016
udd+0.016
 coll+0.016
Neg logit contributions
 decided-0.013
 tried-0.012
 never-0.012
 came-0.012
 stumbled-0.011
Token he
Token ID339
Feature activation+8.15e+00

Pos logit contributions
 decided+0.049
pped+0.046
 tried+0.045
 dropped+0.045
 managed+0.041
Neg logit contributions
igsaw-0.135
aj-0.120
ummy-0.117
 batch-0.114
 gym-0.112
Token went
Token ID1816
Feature activation+4.00e+00

Pos logit contributions
 never+0.110
 unable+0.104
pped+0.104
 decided+0.100
Please+0.099
Neg logit contributions
igsaw-0.267
aj-0.263
 batch-0.237
udd-0.233
ari-0.232
Token into
Token ID656
Feature activation-1.88e+00

Pos logit contributions
 decided+0.085
 tried+0.079
 never+0.078
 managed+0.076
 dropped+0.075
Neg logit contributions
igsaw-0.137
aj-0.124
ummy-0.116
 batch-0.109
ay-0.108
Token the
Token ID262
Feature activation-9.81e+00

Pos logit contributions
igsaw+0.065
aj+0.061
 batch+0.055
ummy+0.054
udd+0.054
Neg logit contributions
 decided-0.040
 tried-0.038
 never-0.038
 came-0.037
 stumbled-0.035
Token east
Token ID7627
Feature activation-4.08e+00

Pos logit contributions
igsaw+0.268
aj+0.256
 batch+0.219
udd+0.210
ummy+0.208
Neg logit contributions
 decided-0.298
 never-0.280
 tried-0.279
 came-0.272
 got-0.267
Token store
Token ID3650
Feature activation+1.02e+00

Pos logit contributions
igsaw+0.155
aj+0.149
 batch+0.134
 coll+0.130
udd+0.130
Neg logit contributions
 decided-0.078
 came-0.074
 never-0.074
 tried-0.072
 got-0.069
Token,
Token ID11
Feature activation-4.46e-01

Pos logit contributions
 decided+0.023
 tried+0.022
 never+0.022
 came+0.021
 dropped+0.021
Neg logit contributions
igsaw-0.033
aj-0.031
 batch-0.028
ummy-0.028
udd-0.027
Token he
Token ID339
Feature activation+7.63e+00

Pos logit contributions
igsaw+0.017
aj+0.016
ummy+0.015
 batch+0.015
 types+0.015
Neg logit contributions
 decided-0.006
 tried-0.006
 never-0.005
pped-0.005
 came-0.005
Token saw
Token ID2497
Feature activation-1.50e+00

Pos logit contributions
 decided+0.089
pped+0.087
 never+0.085
 tried+0.083
 dropped+0.074
Neg logit contributions
aj-0.289
igsaw-0.274
udd-0.263
 batch-0.256
 types-0.248
Token everywhere
Token ID8347
Feature activation+5.87e+00

Pos logit contributions
igsaw+0.119
aj+0.113
 batch+0.101
ummy+0.100
udd+0.099
Neg logit contributions
 decided-0.069
 tried-0.065
 never-0.064
 came-0.063
 stumbled-0.061
Token she
Token ID673
Feature activation+7.38e+00

Pos logit contributions
 decided+0.116
 tried+0.107
 stumbled+0.103
 never+0.101
 managed+0.098
Neg logit contributions
igsaw-0.206
aj-0.188
ummy-0.178
 batch-0.175
udd-0.170
Token went
Token ID1816
Feature activation+3.29e+00

Pos logit contributions
 decided+0.078
 never+0.077
pped+0.076
 tried+0.071
 almost+0.070
Neg logit contributions
igsaw-0.292
aj-0.279
 coll-0.267
udd-0.262
ay-0.261
Token.
Token ID13
Feature activation-9.24e-01

Pos logit contributions
 decided+0.072
 tried+0.070
 managed+0.068
 dropped+0.067
 never+0.067
Neg logit contributions
igsaw-0.106
aj-0.096
 coll-0.091
ummy-0.089
udd-0.088
Token The
Token ID383
Feature activation-8.76e+00

Pos logit contributions
igsaw+0.034
aj+0.033
 coll+0.030
 batch+0.030
udd+0.029
Neg logit contributions
 never-0.017
 decided-0.017
 tried-0.016
 came-0.016
 could-0.016
Token old
Token ID1468
Feature activation-9.78e+00

Pos logit contributions
igsaw+0.262
aj+0.249
udd+0.215
 batch+0.214
ummy+0.211
Neg logit contributions
 decided-0.237
 tried-0.227
 never-0.226
 came-0.218
 dropped-0.212
Token lady
Token ID10846
Feature activation+7.06e-01

Pos logit contributions
igsaw+0.256
aj+0.238
 batch+0.209
ummy+0.202
 coll+0.198
Neg logit contributions
 decided-0.290
 tried-0.278
 never-0.278
 came-0.270
 stumbled-0.265
Token was
Token ID373
Feature activation+2.85e+00

Pos logit contributions
 decided+0.010
 tried+0.009
 never+0.009
 stumbled+0.009
 came+0.009
Neg logit contributions
igsaw-0.027
aj-0.027
 batch-0.024
udd-0.024
 coll-0.023
Token happy
Token ID3772
Feature activation-3.82e+00

Pos logit contributions
 decided+0.060
 tried+0.058
 came+0.055
 stumbled+0.054
 never+0.054
Neg logit contributions
igsaw-0.093
aj-0.090
 batch-0.081
udd-0.079
ummy-0.078
Token to
Token ID284
Feature activation+4.27e+00

Pos logit contributions
igsaw+0.116
aj+0.108
ummy+0.105
 batch+0.103
udd+0.100
Neg logit contributions
 decided-0.082
pped-0.080
 dropped-0.078
 tried-0.077
 stumbled-0.076
Token have
Token ID423
Feature activation+5.61e+00

Pos logit contributions
 decided+0.080
 wouldn+0.079
pped+0.075
 stumbled+0.075
 tried+0.073
Neg logit contributions
igsaw-0.142
aj-0.120
 coll-0.118
 former-0.117
ummy-0.116
Token tree
Token ID5509
Feature activation-2.54e-01

Pos logit contributions
igsaw+0.292
aj+0.268
 batch+0.235
ummy+0.231
udd+0.226
Neg logit contributions
 decided-0.328
 tried-0.316
 never-0.313
 came-0.307
 stumbled-0.299
Token.
Token ID13
Feature activation-7.79e-01

Pos logit contributions
igsaw+0.009
aj+0.009
 batch+0.008
ummy+0.008
udd+0.008
Neg logit contributions
 decided-0.005
 tried-0.005
 never-0.004
 came-0.004
 dropped-0.004
Token He
Token ID679
Feature activation+7.50e+00

Pos logit contributions
igsaw+0.023
aj+0.022
udd+0.020
 batch+0.019
 coll+0.019
Neg logit contributions
 decided-0.021
 tried-0.020
 came-0.020
 never-0.019
 got-0.019
Token had
Token ID550
Feature activation+5.95e+00

Pos logit contributions
pped+0.112
 decided+0.102
 never+0.100
 managed+0.098
 wouldn+0.097
Neg logit contributions
igsaw-0.245
aj-0.242
 batch-0.235
 types-0.219
ummy-0.219
Token a
Token ID257
Feature activation-6.73e+00

Pos logit contributions
 decided+0.114
 wouldn+0.104
 tried+0.103
 came+0.100
 stumbled+0.097
Neg logit contributions
igsaw-0.193
aj-0.186
 batch-0.173
 coll-0.169
ummy-0.161
Token huge
Token ID3236
Feature activation-1.08e+01

Pos logit contributions
igsaw+0.181
aj+0.167
 batch+0.148
ummy+0.142
 coll+0.140
Neg logit contributions
 decided-0.195
 tried-0.185
 never-0.185
 came-0.180
 stumbled-0.176
Token bag
Token ID6131
Feature activation-9.95e-01

Pos logit contributions
igsaw+0.311
aj+0.290
 batch+0.257
ummy+0.251
udd+0.247
Neg logit contributions
 decided-0.290
 tried-0.276
 never-0.276
 came-0.268
 stumbled-0.261
Token over
Token ID625
Feature activation-1.69e+00

Pos logit contributions
igsaw+0.028
aj+0.026
ummy+0.024
 batch+0.023
ay+0.023
Neg logit contributions
 decided-0.025
 tried-0.024
 never-0.023
 stumbled-0.022
 wouldn-0.022
Token his
Token ID465
Feature activation-5.95e+00

Pos logit contributions
igsaw+0.051
aj+0.046
 batch+0.044
ummy+0.044
 types+0.043
Neg logit contributions
 decided-0.037
 wouldn-0.035
 never-0.035
 tried-0.035
 managed-0.034
Token shoulder
Token ID8163
Feature activation-1.04e+00

Pos logit contributions
igsaw+0.194
aj+0.178
 batch+0.162
udd+0.157
ushes+0.151
Neg logit contributions
 decided-0.143
 never-0.143
 tried-0.136
 dropped-0.130
 came-0.128
Token and
Token ID290
Feature activation+2.27e+00

Pos logit contributions
igsaw+0.037
aj+0.036
 batch+0.032
ummy+0.032
udd+0.031
Neg logit contributions
 decided-0.020
 tried-0.019
 never-0.018
 came-0.018
 stumbled-0.017