TOP ACTIVATIONS
MAX = 0.915

bug as it slowly sc ur ried away . <|endoftext|> Once
of the tree and sc ur ried along the ground .
a tower . She sc ur ried outside to the backyard
ground , and quickly sc ur ried away . Jim laughed
the mouse , who sc ur ried away to safety .
. The ant quickly sc ur ried away , and Lily
pocket and the mouse sc ur ried away . The old
crab ! The crab sc ur ried away quickly . Tim
The squirrel sc ur ried up a tree and
closer , the rat sc ur ried away !
thanked the parent before sc ur rying away .
her ! So she sc ur ried away , leaving the
was too quick and sc ur ried away . Suddenly ,
that , the mouse sc ur ried away as fast as
happy and he quickly sc ur ried inside the tiny hole
The mouse brave ly sc ur ried onto the bridge ,
The animals sc ur ried off , leaving the
of them . He sc ur ried around looking for the
. The baby birds sc ur ried away quickly !
got home , she unf ur led the carpet and started

MIN ACTIVATIONS
MIN = -0.590

magical ! It made a big , beautiful bubble . It
The lady loaded everything into big bags and then loaded the
? It looks like a big cotton ball !"
He had made such a big mess that he had to
help you ". With a big smile , the old man
until he came across a big house in the woods .
enough , there was a big , shiny screen . The
She quickly pulled out a big t eddy bear holding a
monster ! It was a big , scary monster . The
hope it will be a big and bright sun ," Max
! <|endoftext|> John had a big backyard . He liked to
â„¢ t know very many big words yet . One day
! That was the great big fish I promised to show
Sean . They had used big blocks of snow to make
all kinds of things ; big and small , round and
I 'm dreaming of a big , tall volcano and I
It was a big beautiful spring . It made
was able to catch a big , pretty bubble . He
now ." They shared a big smile and ran home together
he was chewing like a big boy .

INTERVAL 0.539 - 0.915
CONTAINS 0.226%

He also has a sle igh and re ind eer who
the tunnel was never - ending . It was pitch black
branch . The bird ch ir ped happily and flew away
happy that her dad was able to help fix the pigeon
the printer began to wh ir r and print the mint

INTERVAL 0.162 - 0.539
CONTAINS 18.310%

let me show you how to polish it . It likes
grabbed the muff in with its claws . Lily was scared
mirror so she could see how pretty she looked with the
are , my little superhero ." <|endoftext|> Once upon a time
Tell us more . We like the statues . They are

INTERVAL -0.214 - 0.162
CONTAINS 64.974%

poison had damaged his body . He did not get better
swing went even higher . Sam was so
a cre ak . Ben went inside and there was a
made him happy . They liked Rex . "
can buy things with it . Like candy or ice cream

INTERVAL -0.590 - -0.214
CONTAINS 16.491%

was different from the other fish . It had a long
will make ants come ." L ily was sorry
small hole near a big farm . He was always so
her new toy that the old lady showed Clara a special
she could manage it . The brave little girl
Token bug
Token ID5434
Feature activation-8.21e-02

Pos logit contributions
 big+0.203
 small+0.186
 little+0.174
 boy+0.173
 new+0.170
Neg logit contributions
owing-0.390
ur-0.376
ared-0.368
ares-0.361
beh-0.361
Token as
Token ID355
Feature activation+4.38e-01

Pos logit contributions
 big+0.211
 little+0.194
 small+0.190
 other+0.178
 new+0.172
Neg logit contributions
owing-0.236
ur-0.230
ors-0.225
ared-0.223
beh-0.223
Token it
Token ID340
Feature activation+1.13e-01

Pos logit contributions
owing+1.267
ur+1.238
ors+1.184
ares+1.182
rying+1.172
Neg logit contributions
 big-1.066
 little-0.987
 small-0.959
 boy-0.900
 other-0.883
Token slowly
Token ID6364
Feature activation+9.33e-02

Pos logit contributions
owing+0.339
ur+0.334
owed+0.320
ares+0.316
rying+0.316
Neg logit contributions
 big-0.262
 little-0.243
 small-0.236
 boy-0.220
 other-0.216
Token sc
Token ID629
Feature activation-8.09e-02

Pos logit contributions
owing+0.293
ur+0.286
beh+0.281
ors+0.280
ares+0.279
Neg logit contributions
 big-0.214
 little-0.197
 small-0.191
 other-0.173
 boy-0.171
Tokenur
Token ID333
Feature activation+9.05e-01

Pos logit contributions
 big+0.338
 little+0.322
 small+0.320
 new+0.310
 other+0.307
Neg logit contributions
ors-0.054
fully-0.048
ility-0.047
owing-0.044
rying-0.042
Tokenried
Token ID2228
Feature activation+7.33e-01

Pos logit contributions
ares+0.790
owing+0.782
ur+0.752
ors+0.724
istent+0.720
Neg logit contributions
 big-4.007
 little-3.856
 small-3.838
 other-3.684
 boy-3.675
Token away
Token ID1497
Feature activation+3.49e-01

Pos logit contributions
owing+1.889
ur+1.774
owed+1.736
ors+1.732
beh+1.731
Neg logit contributions
 big-2.271
 little-2.092
 small-2.071
 other-1.931
 boy-1.883
Token.
Token ID13
Feature activation+6.09e-02

Pos logit contributions
owing+1.197
ors+1.171
ares+1.164
ur+1.163
beh+1.152
Neg logit contributions
 big-0.752
 little-0.686
 small-0.667
 other-0.586
 new-0.576
Token<|endoftext|>
Token ID50256
Feature activation-1.75e-01

Pos logit contributions
ur+0.216
owing+0.212
ares+0.205
owed+0.205
ors+0.201
Neg logit contributions
 big-0.098
 little-0.086
 small-0.083
 other-0.078
 boy-0.077
TokenOnce
Token ID7454
Feature activation-4.70e-02

Pos logit contributions
 big+0.291
 little+0.271
 small+0.259
 boy+0.225
 other+0.223
Neg logit contributions
owing-0.594
ur-0.577
ors-0.559
ares-0.558
owed-0.556
Token of
Token ID286
Feature activation+1.69e-01

Pos logit contributions
 big+0.210
 little+0.188
 small+0.183
 other+0.164
 boy+0.162
Neg logit contributions
owing-0.354
ur-0.348
beh-0.343
ares-0.340
ors-0.339
Token the
Token ID262
Feature activation-1.35e-01

Pos logit contributions
ur+0.450
owing+0.425
rying+0.414
ared+0.413
ales+0.408
Neg logit contributions
 big-0.287
 little-0.274
 boy-0.269
 family-0.247
 small-0.246
Token tree
Token ID5509
Feature activation-3.24e-01

Pos logit contributions
 big+0.183
 little+0.182
 boy+0.166
 small+0.164
 family+0.146
Neg logit contributions
owing-0.448
ur-0.446
ared-0.422
ors-0.410
rying-0.408
Token and
Token ID290
Feature activation-4.87e-02

Pos logit contributions
 big+0.640
 little+0.577
 small+0.562
 other+0.501
 boy+0.497
Neg logit contributions
owing-1.106
ur-1.089
ares-1.070
ors-1.060
beh-1.058
Token sc
Token ID629
Feature activation-8.39e-02

Pos logit contributions
 big+0.104
 little+0.095
 small+0.092
 boy+0.084
 other+0.083
Neg logit contributions
owing-0.160
ur-0.156
ares-0.151
ors-0.150
rying-0.149
Tokenur
Token ID333
Feature activation+9.04e-01

Pos logit contributions
 big+0.358
 little+0.338
 small+0.332
 other+0.322
 new+0.317
Neg logit contributions
ors-0.061
ility-0.053
rying-0.048
beh-0.047
ares-0.045
Tokenried
Token ID2228
Feature activation+7.32e-01

Pos logit contributions
ares+0.846
owing+0.836
ors+0.791
ur+0.790
istent+0.729
Neg logit contributions
 big-3.969
 little-3.797
 small-3.770
 other-3.652
 boy-3.641
Token along
Token ID1863
Feature activation+3.33e-01

Pos logit contributions
owing+2.050
beh+1.951
ares+1.948
owed+1.895
ors+1.894
Neg logit contributions
 big-2.138
 little-1.938
 small-1.917
 other-1.803
 new-1.734
Token the
Token ID262
Feature activation-1.35e-01

Pos logit contributions
owing+1.161
ares+1.132
ur+1.126
ors+1.107
beh+1.105
Neg logit contributions
 big-0.687
 little-0.621
 small-0.608
 other-0.541
 new-0.518
Token ground
Token ID2323
Feature activation-2.18e-01

Pos logit contributions
 big+0.205
 little+0.194
 boy+0.184
 small+0.183
 family+0.157
Neg logit contributions
owing-0.448
ur-0.434
rying-0.429
iously-0.425
ared-0.415
Token.
Token ID13
Feature activation+6.01e-02

Pos logit contributions
 big+0.436
 small+0.385
 little+0.384
 other+0.342
 new+0.326
Neg logit contributions
ares-0.746
owing-0.745
ur-0.738
beh-0.737
ors-0.729
Token a
Token ID257
Feature activation-2.14e-01

Pos logit contributions
owing+0.442
ur+0.432
ors+0.420
ares+0.419
rying+0.417
Neg logit contributions
 big-0.189
 little-0.174
 small-0.163
 boy-0.151
 other-0.144
Token tower
Token ID10580
Feature activation-1.41e-01

Pos logit contributions
 little+0.230
 big+0.228
 small+0.206
 boy+0.197
 other+0.195
Neg logit contributions
ur-0.723
rying-0.707
owing-0.706
ares-0.692
ors-0.684
Token.
Token ID13
Feature activation+5.77e-02

Pos logit contributions
 big+0.311
 small+0.264
 little+0.262
 boy+0.239
 park+0.238
Neg logit contributions
owing-0.470
ur-0.466
ared-0.455
ares-0.455
beh-0.451
Token She
Token ID1375
Feature activation+1.70e-01

Pos logit contributions
owing+0.166
ur+0.160
ares+0.155
rying+0.154
ors+0.154
Neg logit contributions
 big-0.148
 little-0.138
 small-0.134
 boy-0.124
 other-0.124
Token sc
Token ID629
Feature activation-8.44e-02

Pos logit contributions
ur+0.470
owing+0.456
owed+0.449
ors+0.448
rying+0.441
Neg logit contributions
 big-0.398
 little-0.370
 small-0.359
 new-0.339
 other-0.334
Tokenur
Token ID333
Feature activation+9.04e-01

Pos logit contributions
 big+0.320
 little+0.300
 small+0.295
 other+0.283
 boy+0.280
Neg logit contributions
rying-0.095
ility-0.092
owing-0.092
ors-0.091
beh-0.086
Tokenried
Token ID2228
Feature activation+7.31e-01

Pos logit contributions
owing+0.814
ur+0.761
ares+0.726
ors+0.677
beh+0.624
Neg logit contributions
 big-4.058
 little-3.907
 small-3.852
 boy-3.745
 other-3.695
Token outside
Token ID2354
Feature activation+1.94e-01

Pos logit contributions
owing+2.067
ur+1.972
ares+1.926
beh+1.926
owed+1.891
Neg logit contributions
 big-2.003
 little-1.844
 small-1.813
 other-1.676
 boy-1.663
Token to
Token ID284
Feature activation+2.23e-01

Pos logit contributions
owing+0.686
ur+0.673
ares+0.654
ors+0.653
beh+0.652
Neg logit contributions
 big-0.371
 little-0.335
 small-0.323
 other-0.289
 boy-0.288
Token the
Token ID262
Feature activation-1.35e-01

Pos logit contributions
ur+0.657
owing+0.655
rying+0.636
ares+0.611
ors+0.606
Neg logit contributions
 big-0.464
 little-0.432
 small-0.418
 boy-0.394
 other-0.368
Token backyard
Token ID24296
Feature activation-3.25e-01

Pos logit contributions
 big+0.233
 little+0.232
 small+0.219
 boy+0.204
 lot+0.200
Neg logit contributions
owing-0.359
rying-0.330
ur-0.327
 correctly-0.314
ors-0.314
Token ground
Token ID2323
Feature activation-2.20e-01

Pos logit contributions
 big+0.228
 small+0.202
 little+0.202
 boy+0.182
 new+0.174
Neg logit contributions
owing-0.471
ur-0.461
ared-0.442
iously-0.435
rying-0.430
Token,
Token ID11
Feature activation+4.01e-02

Pos logit contributions
 big+0.452
 little+0.408
 small+0.400
 other+0.346
 new+0.339
Neg logit contributions
beh-0.736
ares-0.733
owing-0.733
ur-0.728
ors-0.718
Token and
Token ID290
Feature activation-5.33e-02

Pos logit contributions
owing+0.135
ur+0.132
ares+0.128
ors+0.127
beh+0.127
Neg logit contributions
 big-0.083
 little-0.075
 small-0.073
 other-0.065
 boy-0.065
Token quickly
Token ID2952
Feature activation+1.68e-01

Pos logit contributions
 big+0.131
 little+0.121
 small+0.118
 other+0.109
 boy+0.108
Neg logit contributions
owing-0.160
ur-0.154
ors-0.151
ares-0.151
beh-0.148
Token sc
Token ID629
Feature activation-8.46e-02

Pos logit contributions
owing+0.518
ur+0.496
ares+0.492
ors+0.488
beh+0.484
Neg logit contributions
 big-0.402
 little-0.370
 small-0.359
 other-0.326
 boy-0.317
Tokenur
Token ID333
Feature activation+9.03e-01

Pos logit contributions
 big+0.359
 little+0.340
 small+0.336
 new+0.322
 other+0.321
Neg logit contributions
ors-0.062
ility-0.051
rying-0.050
owing-0.046
beh-0.046
Tokenried
Token ID2228
Feature activation+7.31e-01

Pos logit contributions
ares+0.941
ors+0.916
owing+0.872
ur+0.821
istent+0.778
Neg logit contributions
 big-3.865
 little-3.755
 small-3.687
 other-3.522
 boy-3.521
Token away
Token ID1497
Feature activation+3.48e-01

Pos logit contributions
owing+1.946
owed+1.817
ares+1.815
ors+1.801
beh+1.796
Neg logit contributions
 big-2.190
 little-2.007
 small-1.980
 other-1.859
 new-1.799
Token.
Token ID13
Feature activation+5.36e-02

Pos logit contributions
owing+1.116
ares+1.104
ors+1.099
ur+1.081
beh+1.071
Neg logit contributions
 big-0.808
 little-0.737
 small-0.720
 other-0.642
 new-0.635
Token Jim
Token ID5395
Feature activation+3.18e-01

Pos logit contributions
owing+0.189
ur+0.186
ares+0.179
ared+0.178
ors+0.178
Neg logit contributions
 big-0.098
 little-0.088
 small-0.085
 boy-0.077
 other-0.076
Token laughed
Token ID13818
Feature activation+1.57e-01

Pos logit contributions
owing+1.113
ur+1.096
owed+1.045
ared+1.041
ors+1.039
Neg logit contributions
 big-0.588
 little-0.521
 small-0.511
 boy-0.463
 other-0.460
Token the
Token ID262
Feature activation-1.37e-01

Pos logit contributions
owing+1.063
ur+1.048
ares+1.009
ors+1.007
beh+0.996
Neg logit contributions
 big-0.461
 little-0.409
 small-0.392
 boy-0.353
 other-0.343
Token mouse
Token ID10211
Feature activation-1.87e-01

Pos logit contributions
 big+0.200
 small+0.172
 park+0.168
 little+0.165
 other+0.156
Neg logit contributions
owing-0.461
ur-0.413
ring-0.410
owed-0.406
rying-0.400
Token,
Token ID11
Feature activation+4.19e-02

Pos logit contributions
 big+0.448
 little+0.413
 small+0.402
 other+0.365
 boy+0.358
Neg logit contributions
owing-0.567
ur-0.551
ares-0.543
ors-0.539
beh-0.534
Token who
Token ID508
Feature activation+9.47e-02

Pos logit contributions
owing+0.133
ur+0.130
ors+0.124
ares+0.124
rying+0.124
Neg logit contributions
 big-0.092
 little-0.085
 small-0.082
 boy-0.076
 other-0.075
Token sc
Token ID629
Feature activation-8.35e-02

Pos logit contributions
owing+0.318
ur+0.314
owed+0.300
ors+0.298
rying+0.296
Neg logit contributions
 big-0.184
 little-0.167
 small-0.161
 other-0.145
 boy-0.144
Tokenur
Token ID333
Feature activation+9.03e-01

Pos logit contributions
 big+0.340
 little+0.321
 small+0.318
 other+0.305
 new+0.297
Neg logit contributions
rying-0.069
ors-0.067
owing-0.057
ility-0.057
ares-0.055
Tokenried
Token ID2228
Feature activation+7.32e-01

Pos logit contributions
ares+0.928
ors+0.896
ur+0.863
owing+0.846
istent+0.785
Neg logit contributions
 big-3.779
 little-3.667
 small-3.612
 boy-3.502
 other-3.468
Token away
Token ID1497
Feature activation+3.47e-01

Pos logit contributions
owing+1.871
ur+1.771
ares+1.748
ors+1.724
beh+1.718
Neg logit contributions
 big-2.192
 little-2.034
 small-1.997
 other-1.866
 boy-1.845
Token to
Token ID284
Feature activation+2.21e-01

Pos logit contributions
owing+1.097
ur+1.066
ares+1.063
ors+1.057
beh+1.047
Neg logit contributions
 big-0.822
 little-0.755
 small-0.733
 other-0.656
 boy-0.647
Token safety
Token ID3747
Feature activation+1.73e-02

Pos logit contributions
owing+0.680
ur+0.670
rying+0.635
beh+0.628
ares+0.626
Neg logit contributions
 big-0.483
 little-0.444
 small-0.435
 boy-0.411
 other-0.388
Token.
Token ID13
Feature activation+5.85e-02

Pos logit contributions
owing+0.056
ur+0.056
ares+0.055
beh+0.054
ors+0.054
Neg logit contributions
 big-0.038
 little-0.035
 small-0.033
 other-0.031
 boy-0.030
Token.
Token ID13
Feature activation+6.01e-02

Pos logit contributions
 big+0.284
 little+0.256
 small+0.248
 other+0.220
 park+0.216
Neg logit contributions
beh-0.448
owing-0.445
ares-0.441
ur-0.435
ors-0.430
Token The
Token ID383
Feature activation-1.43e-02

Pos logit contributions
owing+0.204
ur+0.192
beh+0.190
rying+0.190
ares+0.189
Neg logit contributions
 big-0.127
 little-0.119
 small-0.114
 boy-0.101
 other-0.100
Token ant
Token ID1885
Feature activation-8.22e-02

Pos logit contributions
 big+0.031
 small+0.027
 park+0.027
 little+0.027
 boy+0.026
Neg logit contributions
owing-0.036
ared-0.034
ur-0.034
rying-0.033
iously-0.033
Token quickly
Token ID2952
Feature activation+1.73e-01

Pos logit contributions
 big+0.163
 little+0.143
 small+0.141
 boy+0.131
 other+0.128
Neg logit contributions
owing-0.268
ur-0.267
owed-0.259
ared-0.251
ors-0.249
Token sc
Token ID629
Feature activation-8.14e-02

Pos logit contributions
owing+0.532
ur+0.519
ares+0.499
ors+0.498
rying+0.493
Neg logit contributions
 big-0.402
 little-0.369
 small-0.360
 boy-0.331
 other-0.330
Tokenur
Token ID333
Feature activation+9.03e-01

Pos logit contributions
 big+0.344
 little+0.327
 small+0.324
 new+0.310
 other+0.306
Neg logit contributions
ors-0.056
rying-0.049
ility-0.045
beh-0.042
owing-0.039
Tokenried
Token ID2228
Feature activation+7.30e-01

Pos logit contributions
ares+0.901
owing+0.874
ors+0.838
ur+0.798
istent+0.768
Neg logit contributions
 big-3.832
 little-3.732
 small-3.682
 boy-3.548
 other-3.530
Token away
Token ID1497
Feature activation+3.49e-01

Pos logit contributions
owing+1.911
beh+1.770
ares+1.768
ur+1.760
ors+1.750
Neg logit contributions
 big-2.207
 little-2.043
 small-2.013
 other-1.860
 boy-1.837
Token,
Token ID11
Feature activation+4.71e-02

Pos logit contributions
owing+1.182
ares+1.160
ors+1.157
beh+1.152
ur+1.144
Neg logit contributions
 big-0.760
 little-0.698
 small-0.672
 new-0.581
 other-0.580
Token and
Token ID290
Feature activation-4.80e-02

Pos logit contributions
owing+0.143
ur+0.139
ors+0.135
ares+0.135
beh+0.133
Neg logit contributions
 big-0.114
 little-0.105
 small-0.103
 boy-0.094
 other-0.093
Token Lily
Token ID20037
Feature activation-2.12e-02

Pos logit contributions
 big+0.099
 little+0.090
 small+0.087
 boy+0.079
 other+0.079
Neg logit contributions
owing-0.158
ur-0.156
ors-0.149
ares-0.149
rying-0.148
Token pocket
Token ID10000
Feature activation-5.43e-02

Pos logit contributions
owing+0.050
ur+0.050
owed+0.045
iously+0.044
ared+0.043
Neg logit contributions
 big-0.041
 boy-0.039
 little-0.039
 other-0.038
 small-0.038
Token and
Token ID290
Feature activation-4.87e-02

Pos logit contributions
 big+0.102
 little+0.092
 small+0.089
 other+0.079
 boy+0.076
Neg logit contributions
owing-0.192
ur-0.190
ares-0.188
beh-0.187
ors-0.183
Token the
Token ID262
Feature activation-1.38e-01

Pos logit contributions
 big+0.108
 little+0.099
 small+0.097
 other+0.089
 boy+0.088
Neg logit contributions
owing-0.151
ur-0.149
ors-0.142
owed-0.142
rying-0.141
Token mouse
Token ID10211
Feature activation-1.85e-01

Pos logit contributions
 big+0.173
 lot+0.153
 small+0.131
 park+0.129
Me+0.128
Neg logit contributions
owing-0.444
ur-0.411
rying-0.401
ility-0.400
iously-0.393
Token sc
Token ID629
Feature activation-8.15e-02

Pos logit contributions
 big+0.378
 little+0.344
 small+0.335
 boy+0.309
 other+0.301
Neg logit contributions
owing-0.610
ur-0.598
owed-0.572
ors-0.571
rying-0.567
Tokenur
Token ID333
Feature activation+9.03e-01

Pos logit contributions
 big+0.367
 little+0.350
 small+0.344
 new+0.329
 other+0.326
Neg logit contributions
ors-0.045
rying-0.042
owing-0.037
ility-0.036
beh-0.032
Tokenried
Token ID2228
Feature activation+7.30e-01

Pos logit contributions
ares+0.825
owing+0.816
ors+0.803
ur+0.765
istent+0.696
Neg logit contributions
 big-3.952
 little-3.829
 small-3.760
 boy-3.640
 other-3.606
Token away
Token ID1497
Feature activation+3.48e-01

Pos logit contributions
owing+1.985
beh+1.838
ur+1.837
ares+1.833
owed+1.830
Neg logit contributions
 big-2.159
 little-1.981
 small-1.948
 other-1.834
 boy-1.770
Token.
Token ID13
Feature activation+6.14e-02

Pos logit contributions
owing+1.169
ares+1.155
ors+1.139
ur+1.138
beh+1.134
Neg logit contributions
 big-0.766
 little-0.693
 small-0.676
 other-0.601
 new-0.590
Token The
Token ID383
Feature activation-1.97e-02

Pos logit contributions
owing+0.207
ur+0.201
ares+0.195
ors+0.194
rying+0.194
Neg logit contributions
 big-0.127
 little-0.117
 small-0.112
 boy-0.102
 other-0.101
Token old
Token ID1468
Feature activation-3.29e-01

Pos logit contributions
 big+0.023
 lot+0.022
Me+0.022
 park+0.019
 other+0.018
Neg logit contributions
owing-0.056
ility-0.052
rying-0.050
ur-0.049
ring-0.048
Token crab
Token ID32202
Feature activation-2.42e-02

Pos logit contributions
 big+0.307
 small+0.292
 little+0.290
 park+0.265
 other+0.264
Neg logit contributions
owing-0.345
ares-0.329
ared-0.328
ur-0.321
rying-0.316
Token!
Token ID0
Feature activation+2.89e-01

Pos logit contributions
 big+0.054
 little+0.049
 small+0.047
 other+0.042
 boy+0.041
Neg logit contributions
ur-0.079
owing-0.079
beh-0.076
ares-0.076
owed-0.075
Token The
Token ID383
Feature activation-1.63e-02

Pos logit contributions
ur+0.808
owing+0.807
ors+0.784
ares+0.770
ared+0.763
Neg logit contributions
 big-0.694
 little-0.634
 small-0.626
 other-0.587
 boy-0.582
Token crab
Token ID32202
Feature activation-2.43e-02

Pos logit contributions
 big+0.037
 small+0.035
 little+0.035
 park+0.032
 new+0.032
Neg logit contributions
owing-0.039
ares-0.039
ared-0.038
ur-0.037
oot-0.036
Token sc
Token ID629
Feature activation-8.17e-02

Pos logit contributions
 big+0.049
 little+0.045
 small+0.044
 boy+0.040
 park+0.040
Neg logit contributions
owing-0.079
ur-0.077
ors-0.075
ared-0.074
ares-0.074
Tokenur
Token ID333
Feature activation+9.03e-01

Pos logit contributions
 big+0.325
 little+0.307
 small+0.302
 other+0.292
 new+0.284
Neg logit contributions
ility-0.076
rying-0.073
owing-0.072
ors-0.069
istent-0.063
Tokenried
Token ID2228
Feature activation+7.29e-01

Pos logit contributions
owing+0.917
ur+0.908
ares+0.832
ors+0.789
istent+0.759
Neg logit contributions
 big-3.836
 little-3.741
 small-3.658
 boy-3.567
 other-3.530
Token away
Token ID1497
Feature activation+3.49e-01

Pos logit contributions
owing+1.878
ur+1.752
owed+1.740
beh+1.732
ares+1.707
Neg logit contributions
 big-2.243
 little-2.070
 small-2.040
 other-1.899
 boy-1.882
Token quickly
Token ID2952
Feature activation+1.74e-01

Pos logit contributions
owing+1.241
beh+1.227
ares+1.210
ur+1.209
ors+1.203
Neg logit contributions
 big-0.714
 little-0.648
 small-0.621
 other-0.527
 boy-0.525
Token.
Token ID13
Feature activation+6.12e-02

Pos logit contributions
beh+0.637
ur+0.634
owing+0.632
ares+0.618
owed+0.616
Neg logit contributions
 big-0.315
 little-0.287
 small-0.262
 other-0.231
 park-0.221
Token Tim
Token ID5045
Feature activation+1.91e-01

Pos logit contributions
owing+0.153
ur+0.151
ors+0.145
ares+0.144
ared+0.141
Neg logit contributions
 big-0.173
 little-0.161
 small-0.158
 other-0.148
 boy-0.147
Token
Token ID198
Feature activation-2.23e-01

Pos logit contributions
owing+0.906
ur+0.886
ares+0.854
ors+0.853
rying+0.846
Neg logit contributions
 big-0.580
 little-0.529
 small-0.514
 boy-0.468
 other-0.466
Token
Token ID198
Feature activation-2.23e-01

Pos logit contributions
 big+0.328
 little+0.304
 small+0.281
 boy+0.275
 other+0.249
Neg logit contributions
ur-0.827
owing-0.826
ors-0.794
oot-0.789
ares-0.783
TokenThe
Token ID464
Feature activation-1.95e-01

Pos logit contributions
 big+0.460
 little+0.427
 small+0.406
 boy+0.383
 other+0.370
Neg logit contributions
owing-0.712
ur-0.707
ors-0.679
beh-0.673
ares-0.671
Token squirrel
Token ID33039
Feature activation-2.02e-01

Pos logit contributions
 big+0.347
 small+0.324
 little+0.312
 lot+0.310
 room+0.304
Neg logit contributions
beh-0.512
ur-0.510
oot-0.510
owing-0.507
ared-0.472
Token sc
Token ID629
Feature activation-8.47e-02

Pos logit contributions
 big+0.383
 little+0.339
 small+0.331
 boy+0.301
 other+0.300
Neg logit contributions
owing-0.698
ur-0.696
owed-0.665
ared-0.661
ares-0.656
Tokenur
Token ID333
Feature activation+9.02e-01

Pos logit contributions
 big+0.362
 little+0.340
 small+0.339
 other+0.328
 new+0.321
Neg logit contributions
rying-0.050
ility-0.047
ors-0.045
owing-0.041
ares-0.035
Tokenried
Token ID2228
Feature activation+7.29e-01

Pos logit contributions
owing+0.866
ares+0.858
ors+0.798
ur+0.786
istent+0.735
Neg logit contributions
 big-3.864
 little-3.743
 small-3.699
 boy-3.572
 other-3.564
Token up
Token ID510
Feature activation+2.10e-01

Pos logit contributions
owing+1.901
owed+1.754
beh+1.747
ares+1.746
ors+1.734
Neg logit contributions
 big-2.212
 little-2.053
 small-2.015
 other-1.867
 boy-1.862
Token a
Token ID257
Feature activation-2.12e-01

Pos logit contributions
owing+0.624
ur+0.597
ors+0.593
ares+0.592
beh+0.583
Neg logit contributions
 big-0.530
 little-0.485
 small-0.476
 boy-0.435
 other-0.433
Token tree
Token ID5509
Feature activation-3.23e-01

Pos logit contributions
 big+0.263
 other+0.226
 boy+0.223
 park+0.215
 small+0.210
Neg logit contributions
ur-0.687
owing-0.678
rying-0.660
ge-0.643
oot-0.636
Token and
Token ID290
Feature activation-5.03e-02

Pos logit contributions
 big+0.581
 little+0.513
 small+0.500
 other+0.422
 boy+0.421
Neg logit contributions
ares-1.150
owing-1.141
beh-1.139
ors-1.133
ur-1.131
Token closer
Token ID5699
Feature activation+2.81e-01

Pos logit contributions
ors+0.019
owing+0.018
ares+0.018
istent+0.017
owed+0.017
Neg logit contributions
 big-0.018
 small-0.017
 little-0.016
 other-0.015
 new-0.015
Token,
Token ID11
Feature activation+4.39e-02

Pos logit contributions
beh+0.993
owing+0.980
ares+0.967
ur+0.954
ors+0.947
Neg logit contributions
 big-0.577
 little-0.520
 small-0.509
 new-0.444
 other-0.432
Token the
Token ID262
Feature activation-1.38e-01

Pos logit contributions
owing+0.132
ur+0.129
ares+0.124
ors+0.123
owed+0.122
Neg logit contributions
 big-0.102
 little-0.094
 small-0.091
 boy-0.084
 other-0.084
Token rat
Token ID4227
Feature activation-1.56e-01

Pos logit contributions
 big+0.274
 little+0.250
 new+0.247
 small+0.246
 park+0.236
Neg logit contributions
owing-0.326
iously-0.299
ared-0.293
used-0.288
ur-0.281
Token sc
Token ID629
Feature activation-8.59e-02

Pos logit contributions
 big+0.333
 little+0.302
 small+0.293
 boy+0.272
 other+0.269
Neg logit contributions
owing-0.494
ur-0.488
owed-0.465
ared-0.461
rying-0.459
Tokenur
Token ID333
Feature activation+9.02e-01

Pos logit contributions
 big+0.373
 little+0.353
 small+0.351
 other+0.331
 new+0.330
Neg logit contributions
ors-0.054
rying-0.044
beh-0.042
ility-0.041
owing-0.036
Tokenried
Token ID2228
Feature activation+7.30e-01

Pos logit contributions
ares+0.825
owing+0.817
ors+0.800
ur+0.785
oot+0.698
Neg logit contributions
 big-3.947
 little-3.783
 small-3.761
 boy-3.614
 other-3.595
Token away
Token ID1497
Feature activation+3.46e-01

Pos logit contributions
owing+1.885
ors+1.780
beh+1.771
ares+1.753
ur+1.750
Neg logit contributions
 big-2.208
 little-2.048
 small-2.019
 other-1.870
 boy-1.845
Token!
Token ID0
Feature activation+2.86e-01

Pos logit contributions
owing+1.112
ors+1.088
ur+1.077
ares+1.076
beh+1.075
Neg logit contributions
 big-0.813
 little-0.747
 small-0.726
 other-0.636
 new-0.633
Token
Token ID198
Feature activation-2.22e-01

Pos logit contributions
ur+0.848
owing+0.831
ares+0.816
owed+0.793
ared+0.787
Neg logit contributions
 big-0.619
 little-0.559
 small-0.545
 other-0.519
 boy-0.511
Token
Token ID198
Feature activation-2.22e-01

Pos logit contributions
 big+0.327
 little+0.304
 boy+0.284
 small+0.280
 other+0.258
Neg logit contributions
ur-0.799
owing-0.777
ares-0.762
owed-0.756
ors-0.740
Token thanked
Token ID26280
Feature activation+5.93e-02

Pos logit contributions
 big+0.113
 little+0.104
 small+0.101
 boy+0.094
 other+0.094
Neg logit contributions
owing-0.148
ur-0.148
owed-0.139
ors-0.138
beh-0.138
Token the
Token ID262
Feature activation-1.36e-01

Pos logit contributions
owing+0.216
ur+0.212
ors+0.205
ares+0.205
rying+0.203
Neg logit contributions
 big-0.104
 little-0.093
 small-0.089
 boy-0.080
 other-0.079
Token parent
Token ID2560
Feature activation-1.38e-01

Pos logit contributions
 big+0.253
 park+0.247
 grass+0.215
 small+0.213
 little+0.205
Neg logit contributions
owing-0.349
ur-0.337
ring-0.322
rying-0.309
ors-0.308
Token before
Token ID878
Feature activation+3.98e-01

Pos logit contributions
 big+0.355
 little+0.336
 small+0.323
 other+0.306
 boy+0.302
Neg logit contributions
owing-0.385
beh-0.381
ors-0.379
ur-0.377
ares-0.372
Token sc
Token ID629
Feature activation-8.20e-02

Pos logit contributions
owing+1.016
ur+0.973
rying+0.930
ares+0.918
ors+0.912
Neg logit contributions
 big-1.077
 little-1.010
 small-0.984
 boy-0.941
 other-0.921
Tokenur
Token ID333
Feature activation+9.02e-01

Pos logit contributions
 big+0.293
 little+0.278
 small+0.273
 other+0.267
 new+0.261
Neg logit contributions
ors-0.113
istent-0.101
beh-0.101
rying-0.099
fully-0.098
Tokenrying
Token ID14992
Feature activation+8.30e-01

Pos logit contributions
owing+1.145
ors+1.118
ur+1.118
ares+1.112
istent+1.032
Neg logit contributions
 big-3.595
 little-3.482
 small-3.441
 boy-3.327
 other-3.311
Token away
Token ID1497
Feature activation+3.48e-01

Pos logit contributions
owing+2.048
ur+1.981
ares+1.884
rying+1.873
owed+1.861
Neg logit contributions
 big-2.616
 little-2.406
 small-2.372
 other-2.230
 boy-2.209
Token.
Token ID13
Feature activation+5.86e-02

Pos logit contributions
owing+1.196
ur+1.158
ares+1.143
ors+1.143
beh+1.133
Neg logit contributions
 big-0.744
 little-0.676
 small-0.650
 other-0.588
 boy-0.577
Token
Token ID220
Feature activation-7.76e-02

Pos logit contributions
ur+0.179
owing+0.178
ors+0.171
ares+0.169
owed+0.167
Neg logit contributions
 big-0.133
 little-0.121
 small-0.118
 other-0.110
 boy-0.108
Token
Token ID198
Feature activation-2.24e-01

Pos logit contributions
 big+0.090
 little+0.075
 small+0.071
 other+0.057
 boy+0.057
Neg logit contributions
owing-0.329
ur-0.322
ares-0.314
ors-0.314
rying-0.313
Token her
Token ID607
Feature activation+1.33e-01

Pos logit contributions
owing+0.366
ur+0.359
ors+0.347
ares+0.345
rying+0.343
Neg logit contributions
 big-0.204
 little-0.185
 small-0.178
 boy-0.164
 other-0.158
Token!
Token ID0
Feature activation+2.85e-01

Pos logit contributions
owing+0.462
ur+0.442
owed+0.436
ors+0.424
ares+0.422
Neg logit contributions
 big-0.233
 little-0.208
 small-0.205
 boy-0.195
 other-0.183
Token So
Token ID1406
Feature activation+1.20e-01

Pos logit contributions
owing+0.988
ur+0.982
ors+0.951
ared+0.943
ares+0.942
Neg logit contributions
 big-0.509
 little-0.448
 small-0.433
 other-0.387
 boy-0.370
Token she
Token ID673
Feature activation+1.53e-01

Pos logit contributions
owing+0.341
ur+0.335
ors+0.322
ared+0.315
owed+0.315
Neg logit contributions
 big-0.279
 little-0.255
 small-0.250
 boy-0.231
 other-0.230
Token sc
Token ID629
Feature activation-8.53e-02

Pos logit contributions
ur+0.459
owing+0.450
ared+0.430
owed+0.429
beh+0.428
Neg logit contributions
 big-0.349
 little-0.314
 small-0.312
 other-0.286
 new-0.284
Tokenur
Token ID333
Feature activation+9.02e-01

Pos logit contributions
 big+0.356
 little+0.339
 small+0.333
 other+0.326
 boy+0.314
Neg logit contributions
rying-0.081
ors-0.077
owing-0.073
ility-0.065
ares-0.060
Tokenried
Token ID2228
Feature activation+7.29e-01

Pos logit contributions
owing+0.820
ur+0.752
ares+0.699
ors+0.683
oot+0.596
Neg logit contributions
 big-4.043
 little-3.896
 small-3.838
 boy-3.739
 other-3.709
Token away
Token ID1497
Feature activation+3.46e-01

Pos logit contributions
owing+1.955
ares+1.831
beh+1.825
owed+1.813
ur+1.803
Neg logit contributions
 big-2.191
 little-2.004
 small-1.986
 other-1.855
 boy-1.816
Token,
Token ID11
Feature activation+4.55e-02

Pos logit contributions
owing+1.157
ares+1.126
ur+1.126
beh+1.122
ors+1.117
Neg logit contributions
 big-0.767
 little-0.699
 small-0.681
 other-0.597
 boy-0.585
Token leaving
Token ID4305
Feature activation+3.26e-01

Pos logit contributions
owing+0.137
ur+0.134
ares+0.128
ors+0.128
rying+0.127
Neg logit contributions
 big-0.109
 little-0.100
 small-0.098
 boy-0.090
 other-0.090
Token the
Token ID262
Feature activation-1.40e-01

Pos logit contributions
owing+1.125
ur+1.094
ors+1.051
owed+1.044
rying+1.040
Neg logit contributions
 big-0.578
 little-0.522
 small-0.500
 boy-0.473
 other-0.430
Token was
Token ID373
Feature activation-3.04e-01

Pos logit contributions
 big+0.153
 little+0.136
 small+0.132
 boy+0.118
 other+0.116
Neg logit contributions
owing-0.308
ur-0.302
ors-0.291
owed-0.290
ared-0.290
Token too
Token ID1165
Feature activation+1.57e-01

Pos logit contributions
 big+0.718
 little+0.665
 small+0.641
 boy+0.609
 other+0.596
Neg logit contributions
owing-0.911
ur-0.894
ares-0.850
rying-0.846
beh-0.843
Token quick
Token ID2068
Feature activation-6.60e-02

Pos logit contributions
owing+0.613
ur+0.601
ared+0.596
ares+0.583
rying+0.576
Neg logit contributions
 big-0.167
 park-0.159
 little-0.149
 boy-0.149
 other-0.146
Token and
Token ID290
Feature activation-5.06e-02

Pos logit contributions
 big+0.129
 little+0.117
 small+0.109
 other+0.101
 new+0.100
Neg logit contributions
ur-0.231
owing-0.228
ares-0.227
beh-0.227
owed-0.224
Token sc
Token ID629
Feature activation-8.34e-02

Pos logit contributions
 big+0.119
 little+0.109
 small+0.106
 boy+0.098
 other+0.097
Neg logit contributions
owing-0.156
ur-0.152
ares-0.146
ors-0.146
rying-0.144
Tokenur
Token ID333
Feature activation+9.01e-01

Pos logit contributions
 big+0.351
 small+0.329
 little+0.326
 new+0.314
 other+0.311
Neg logit contributions
ors-0.059
ility-0.055
rying-0.053
owing-0.048
fully-0.047
Tokenried
Token ID2228
Feature activation+7.28e-01

Pos logit contributions
ares+0.941
owing+0.901
ur+0.883
ors+0.846
istent+0.834
Neg logit contributions
 big-3.822
 small-3.640
 little-3.638
 other-3.495
 boy-3.483
Token away
Token ID1497
Feature activation+3.48e-01

Pos logit contributions
owing+1.924
ares+1.800
owed+1.788
ur+1.781
beh+1.770
Neg logit contributions
 big-2.221
 little-2.030
 small-2.026
 other-1.888
 new-1.822
Token.
Token ID13
Feature activation+5.91e-02

Pos logit contributions
owing+1.233
ares+1.221
ors+1.214
beh+1.204
ur+1.182
Neg logit contributions
 big-0.723
 little-0.649
 small-0.636
 other-0.554
 new-0.546
Token Suddenly
Token ID24975
Feature activation+7.10e-02

Pos logit contributions
owing+0.141
ur+0.138
ares+0.130
ors+0.130
ared+0.128
Neg logit contributions
 big-0.177
 little-0.166
 small-0.162
 boy-0.153
 other-0.152
Token,
Token ID11
Feature activation+4.49e-02

Pos logit contributions
owing+0.232
ur+0.225
ares+0.219
ors+0.218
beh+0.217
Neg logit contributions
 big-0.153
 little-0.140
 small-0.136
 other-0.123
 boy-0.123
Token that
Token ID326
Feature activation+1.62e-01

Pos logit contributions
ur+0.322
owing+0.322
ares+0.299
ared+0.299
owed+0.299
Neg logit contributions
 big-0.223
 little-0.209
 small-0.200
 boy-0.195
 other-0.186
Token,
Token ID11
Feature activation+4.01e-02

Pos logit contributions
owing+0.503
ur+0.489
ares+0.468
ors+0.468
owed+0.464
Neg logit contributions
 big-0.365
 little-0.337
 small-0.324
 other-0.299
 boy-0.299
Token the
Token ID262
Feature activation-1.42e-01

Pos logit contributions
owing+0.139
ur+0.136
ors+0.130
ares+0.130
rying+0.130
Neg logit contributions
 big-0.075
 little-0.068
 small-0.066
 boy-0.059
 other-0.058
Token mouse
Token ID10211
Feature activation-1.86e-01

Pos logit contributions
 big+0.194
 park+0.184
 little+0.167
 boy+0.155
 small+0.154
Neg logit contributions
owing-0.392
istent-0.344
owed-0.342
asing-0.335
ishly-0.335
Token sc
Token ID629
Feature activation-8.28e-02

Pos logit contributions
 big+0.397
 little+0.362
 small+0.352
 boy+0.322
 other+0.320
Neg logit contributions
owing-0.600
ur-0.589
ors-0.563
ares-0.563
owed-0.558
Tokenur
Token ID333
Feature activation+9.01e-01

Pos logit contributions
 big+0.343
 little+0.325
 small+0.321
 other+0.306
 new+0.299
Neg logit contributions
rying-0.079
owing-0.076
ors-0.073
ility-0.069
ares-0.065
Tokenried
Token ID2228
Feature activation+7.29e-01

Pos logit contributions
owing+0.786
ur+0.764
ares+0.758
ors+0.755
oot+0.639
Neg logit contributions
 big-3.944
 little-3.831
 small-3.770
 boy-3.664
 other-3.611
Token away
Token ID1497
Feature activation+3.47e-01

Pos logit contributions
owing+1.763
ur+1.645
ares+1.619
ors+1.616
beh+1.605
Neg logit contributions
 big-2.300
 little-2.137
 small-2.103
 other-1.986
 boy-1.945
Token as
Token ID355
Feature activation+4.37e-01

Pos logit contributions
owing+1.042
ur+1.008
ors+1.006
ares+1.004
beh+0.983
Neg logit contributions
 big-0.868
 little-0.800
 small-0.782
 other-0.709
 boy-0.700
Token fast
Token ID3049
Feature activation-1.40e-01

Pos logit contributions
owing+1.490
ur+1.470
rying+1.402
ors+1.393
owed+1.386
Neg logit contributions
 big-0.812
 little-0.738
 small-0.703
 boy-0.654
 other-0.630
Token as
Token ID355
Feature activation+4.37e-01

Pos logit contributions
 big+0.456
 little+0.440
 small+0.420
 other+0.395
 boy+0.390
Neg logit contributions
owing-0.326
owed-0.299
ares-0.298
beh-0.298
rying-0.295
Token happy
Token ID3772
Feature activation-2.76e-01

Pos logit contributions
owing+0.305
ur+0.304
rying+0.279
owed+0.279
ares+0.279
Neg logit contributions
 big-0.176
 little-0.167
 other-0.156
 boy-0.156
 park-0.154
Token and
Token ID290
Feature activation-5.08e-02

Pos logit contributions
 big+0.534
 little+0.486
 small+0.445
 boy+0.422
 new+0.404
Neg logit contributions
ares-0.982
owing-0.964
beh-0.962
ur-0.955
owed-0.935
Token he
Token ID339
Feature activation+1.12e-01

Pos logit contributions
 big+0.115
 little+0.105
 small+0.102
 boy+0.094
 other+0.094
Neg logit contributions
owing-0.158
ur-0.156
rying-0.148
ors-0.148
ares-0.147
Token quickly
Token ID2952
Feature activation+1.68e-01

Pos logit contributions
ur+0.317
owing+0.299
owed+0.289
beh+0.286
ors+0.286
Neg logit contributions
 big-0.275
 small-0.250
 little-0.247
 boy-0.234
 other-0.233
Token sc
Token ID629
Feature activation-8.60e-02

Pos logit contributions
owing+0.523
ur+0.506
ares+0.492
ors+0.490
rying+0.484
Neg logit contributions
 big-0.391
 little-0.360
 small-0.350
 other-0.320
 boy-0.319
Tokenur
Token ID333
Feature activation+9.01e-01

Pos logit contributions
 big+0.370
 little+0.349
 small+0.344
 other+0.334
 new+0.328
Neg logit contributions
ors-0.062
ility-0.056
rying-0.054
owing-0.047
ares-0.047
Tokenried
Token ID2228
Feature activation+7.29e-01

Pos logit contributions
ares+0.858
owing+0.841
ors+0.828
ur+0.789
istent+0.748
Neg logit contributions
 big-3.922
 little-3.777
 small-3.719
 boy-3.635
 other-3.619
Token inside
Token ID2641
Feature activation+2.43e-01

Pos logit contributions
owing+2.121
owed+2.006
ares+2.005
beh+1.991
ors+1.963
Neg logit contributions
 big-2.053
 little-1.850
 small-1.826
 other-1.717
 new-1.657
Token the
Token ID262
Feature activation-1.36e-01

Pos logit contributions
owing+0.811
ur+0.798
beh+0.790
ares+0.783
ors+0.782
Neg logit contributions
 big-0.525
 little-0.482
 small-0.463
 other-0.418
 new-0.411
Token tiny
Token ID7009
Feature activation-3.43e-01

Pos logit contributions
 big+0.238
 little+0.224
 small+0.209
 boy+0.205
 other+0.204
Neg logit contributions
owing-0.395
ur-0.377
rying-0.377
ors-0.366
ares-0.361
Token hole
Token ID7604
Feature activation-2.57e-01

Pos logit contributions
 big+0.520
 little+0.433
 small+0.423
 other+0.404
 boy+0.372
Neg logit contributions
owing-1.244
ur-1.209
ors-1.193
rying-1.178
ared-1.164
Token The
Token ID383
Feature activation-2.25e-02

Pos logit contributions
owing+0.199
ur+0.194
ares+0.187
ors+0.187
rying+0.186
Neg logit contributions
 big-0.117
 little-0.106
 small-0.103
 boy-0.093
 other-0.093
Token mouse
Token ID10211
Feature activation-1.88e-01

Pos logit contributions
 big+0.036
 park+0.031
 small+0.030
 little+0.029
 lot+0.029
Neg logit contributions
rying-0.061
owing-0.060
ur-0.060
ility-0.055
ares-0.055
Token brave
Token ID14802
Feature activation-1.90e-01

Pos logit contributions
 big+0.365
 little+0.320
 small+0.317
 boy+0.285
 other+0.284
Neg logit contributions
owing-0.636
ur-0.634
owed-0.609
ared-0.599
ors-0.597
Tokenly
Token ID306
Feature activation+5.41e-01

Pos logit contributions
 big+0.731
 little+0.719
 small+0.689
 boy+0.671
 other+0.655
Neg logit contributions
owing-0.294
ur-0.276
ares-0.266
beh-0.265
rying-0.264
Token sc
Token ID629
Feature activation-8.48e-02

Pos logit contributions
owing+1.659
ur+1.643
owed+1.557
ors+1.551
ared+1.548
Neg logit contributions
 big-1.215
 little-1.085
 small-1.076
 other-0.995
 boy-0.985
Tokenur
Token ID333
Feature activation+9.01e-01

Pos logit contributions
 big+0.363
 little+0.344
 small+0.341
 other+0.331
 new+0.325
Neg logit contributions
rying-0.053
ors-0.051
ility-0.048
owing-0.043
beh-0.042
Tokenried
Token ID2228
Feature activation+7.27e-01

Pos logit contributions
owing+0.779
ares+0.751
ur+0.711
ors+0.705
beh+0.605
Neg logit contributions
 big-3.979
 little-3.858
 small-3.802
 boy-3.671
 other-3.661
Token onto
Token ID4291
Feature activation+4.70e-01

Pos logit contributions
owing+1.884
ares+1.751
ur+1.744
beh+1.740
owed+1.737
Neg logit contributions
 big-2.189
 little-2.031
 small-2.001
 other-1.862
 boy-1.843
Token the
Token ID262
Feature activation-1.38e-01

Pos logit contributions
ur+1.602
owing+1.585
ors+1.520
ares+1.505
rying+1.496
Neg logit contributions
 big-0.811
 little-0.738
 small-0.701
 boy-0.683
 other-0.613
Token bridge
Token ID7696
Feature activation-1.75e-01

Pos logit contributions
 big+0.240
 little+0.221
 small+0.213
 boy+0.208
 park+0.197
Neg logit contributions
rying-0.421
owing-0.415
ors-0.390
ur-0.388
ales-0.376
Token,
Token ID11
Feature activation+4.36e-02

Pos logit contributions
 big+0.336
 little+0.300
 small+0.293
 other+0.260
 boy+0.254
Neg logit contributions
owing-0.603
beh-0.601
ares-0.600
ur-0.597
ors-0.583
Token
Token ID198
Feature activation-2.22e-01

Pos logit contributions
ur+0.216
owing+0.215
ors+0.208
ares+0.205
ared+0.203
Neg logit contributions
 big-0.103
 little-0.091
 small-0.088
 other-0.077
 boy-0.076
Token
Token ID198
Feature activation-2.21e-01

Pos logit contributions
 big+0.333
 little+0.304
 small+0.284
 boy+0.276
 other+0.249
Neg logit contributions
ur-0.816
owing-0.804
ors-0.782
ares-0.776
oot-0.776
TokenThe
Token ID464
Feature activation-1.94e-01

Pos logit contributions
 big+0.458
 little+0.409
 small+0.399
 boy+0.383
 new+0.366
Neg logit contributions
ur-0.701
owing-0.684
beh-0.681
ors-0.675
ares-0.672
Token animals
Token ID4695
Feature activation-2.70e-01

Pos logit contributions
 big+0.337
 small+0.305
 little+0.281
 lot+0.278
 pretty+0.263
Neg logit contributions
ur-0.504
owing-0.503
rying-0.481
ors-0.480
ility-0.469
Token sc
Token ID629
Feature activation-8.29e-02

Pos logit contributions
 big+0.582
 little+0.531
 small+0.517
 boy+0.470
 other+0.468
Neg logit contributions
owing-0.877
ur-0.856
ares-0.823
ors-0.821
rying-0.816
Tokenur
Token ID333
Feature activation+9.01e-01

Pos logit contributions
 big+0.335
 little+0.317
 small+0.312
 other+0.305
 boy+0.295
Neg logit contributions
owing-0.077
rying-0.077
ility-0.074
ors-0.074
ares-0.069
Tokenried
Token ID2228
Feature activation+7.27e-01

Pos logit contributions
owing+0.756
ur+0.719
ares+0.673
ors+0.649
oot+0.551
Neg logit contributions
 big-4.019
 little-3.911
 small-3.833
 boy-3.734
 other-3.712
Token off
Token ID572
Feature activation+4.76e-01

Pos logit contributions
owing+1.684
ur+1.606
ares+1.550
ors+1.543
owed+1.525
Neg logit contributions
 big-2.301
 little-2.156
 small-2.116
 other-1.992
 boy-1.990
Token,
Token ID11
Feature activation+4.55e-02

Pos logit contributions
owing+1.500
beh+1.427
ur+1.425
ares+1.420
ors+1.417
Neg logit contributions
 big-1.156
 little-1.043
 small-1.028
 other-0.937
 new-0.907
Token leaving
Token ID4305
Feature activation+3.26e-01

Pos logit contributions
owing+0.130
ur+0.126
rying+0.121
ares+0.119
ors+0.119
Neg logit contributions
 big-0.114
 little-0.105
 small-0.102
 other-0.095
 boy-0.095
Token the
Token ID262
Feature activation-1.35e-01

Pos logit contributions
owing+1.118
ur+1.087
rying+1.040
ors+1.039
owed+1.025
Neg logit contributions
 big-0.575
 little-0.516
 small-0.502
 boy-0.456
 park-0.434
Token of
Token ID286
Feature activation+1.63e-01

Pos logit contributions
 big+0.307
 little+0.281
 small+0.277
 boy+0.251
 other+0.248
Neg logit contributions
owing-0.461
ur-0.446
ares-0.429
rying-0.423
ors-0.422
Token them
Token ID606
Feature activation+2.47e-01

Pos logit contributions
owing+0.561
ur+0.549
ors+0.529
ares+0.525
rying+0.524
Neg logit contributions
 big-0.300
 little-0.272
 small-0.262
 boy-0.244
 other-0.227
Token.
Token ID13
Feature activation+5.76e-02

Pos logit contributions
owing+0.820
ur+0.811
ares+0.795
beh+0.788
ors+0.785
Neg logit contributions
 big-0.524
 little-0.476
 small-0.458
 other-0.421
 boy-0.405
Token He
Token ID679
Feature activation+5.20e-02

Pos logit contributions
owing+0.178
ur+0.175
ares+0.168
ors+0.168
beh+0.165
Neg logit contributions
 big-0.133
 little-0.122
 small-0.119
 boy-0.109
 other-0.108
Token sc
Token ID629
Feature activation-8.78e-02

Pos logit contributions
ur+0.173
owing+0.169
owed+0.163
ors+0.161
ared+0.161
Neg logit contributions
 big-0.099
 little-0.090
 small-0.089
 boy-0.079
 other-0.077
Tokenur
Token ID333
Feature activation+9.01e-01

Pos logit contributions
 big+0.374
 little+0.358
 small+0.349
 other+0.338
 boy+0.331
Neg logit contributions
rying-0.073
ors-0.070
owing-0.070
ility-0.062
ares-0.060
Tokenried
Token ID2228
Feature activation+7.30e-01

Pos logit contributions
owing+0.773
ur+0.724
ors+0.717
ares+0.717
oot+0.609
Neg logit contributions
 big-4.026
 little-3.910
 small-3.826
 boy-3.759
 other-3.688
Token around
Token ID1088
Feature activation+3.32e-01

Pos logit contributions
owing+1.897
ur+1.788
ares+1.756
beh+1.749
owed+1.732
Neg logit contributions
 big-2.157
 little-2.004
 small-1.963
 other-1.842
 boy-1.818
Token looking
Token ID2045
Feature activation+3.51e-02

Pos logit contributions
owing+1.173
ur+1.151
ors+1.105
ares+1.102
rying+1.100
Neg logit contributions
 big-0.612
 little-0.550
 small-0.530
 boy-0.479
 other-0.474
Token for
Token ID329
Feature activation+3.33e-01

Pos logit contributions
owing+0.088
ur+0.084
beh+0.082
ares+0.082
ors+0.082
Neg logit contributions
 big-0.107
 little-0.100
 small-0.098
 other-0.091
 new-0.091
Token the
Token ID262
Feature activation-1.44e-01

Pos logit contributions
owing+1.062
ur+1.049
rying+0.981
ors+0.981
owed+0.975
Neg logit contributions
 big-0.645
 little-0.580
 small-0.571
 boy-0.561
 park-0.514
Token.
Token ID13
Feature activation+5.52e-02

Pos logit contributions
owing+1.210
ur+1.183
ors+1.166
ares+1.160
beh+1.151
Neg logit contributions
 big-0.817
 little-0.731
 small-0.717
 other-0.644
 boy-0.634
Token The
Token ID383
Feature activation-2.09e-02

Pos logit contributions
owing+0.187
ur+0.182
ors+0.176
ares+0.176
rying+0.175
Neg logit contributions
 big-0.112
 little-0.102
 small-0.099
 boy-0.089
 other-0.089
Token baby
Token ID5156
Feature activation-2.37e-01

Pos logit contributions
 big+0.031
 small+0.027
 little+0.026
 boy+0.024
 new+0.022
Neg logit contributions
owing-0.065
iously-0.063
ring-0.060
ur-0.059
rying-0.059
Token birds
Token ID10087
Feature activation-2.15e-01

Pos logit contributions
 big+0.358
 small+0.297
 little+0.290
 new+0.253
 park+0.249
Neg logit contributions
owing-0.903
ur-0.869
owed-0.852
ors-0.828
rying-0.824
Token sc
Token ID629
Feature activation-8.35e-02

Pos logit contributions
 big+0.467
 little+0.430
 small+0.414
 other+0.379
 boy+0.373
Neg logit contributions
owing-0.690
ur-0.676
ors-0.660
ares-0.660
beh-0.657
Tokenur
Token ID333
Feature activation+9.01e-01

Pos logit contributions
 big+0.355
 little+0.337
 small+0.332
 other+0.319
 new+0.313
Neg logit contributions
ors-0.051
ility-0.050
rying-0.048
ares-0.047
owing-0.044
Tokenried
Token ID2228
Feature activation+7.29e-01

Pos logit contributions
ares+0.846
owing+0.796
ors+0.787
ur+0.784
beh+0.694
Neg logit contributions
 big-3.884
 little-3.799
 small-3.708
 boy-3.613
 other-3.561
Token away
Token ID1497
Feature activation+3.47e-01

Pos logit contributions
owing+1.877
ur+1.769
ares+1.757
ors+1.750
beh+1.743
Neg logit contributions
 big-2.168
 little-2.009
 small-1.975
 other-1.831
 boy-1.814
Token quickly
Token ID2952
Feature activation+1.69e-01

Pos logit contributions
owing+1.125
ors+1.100
ur+1.099
ares+1.097
beh+1.083
Neg logit contributions
 big-0.781
 little-0.714
 small-0.695
 other-0.612
 new-0.603
Token!
Token ID0
Feature activation+2.82e-01

Pos logit contributions
owing+0.571
ur+0.568
beh+0.566
ares+0.565
ors+0.561
Neg logit contributions
 big-0.344
 little-0.313
 small-0.298
 other-0.262
 park-0.253
Token
Token ID198
Feature activation-2.26e-01

Pos logit contributions
owing+0.992
ur+0.984
ares+0.947
ared+0.935
owed+0.931
Neg logit contributions
 big-0.500
 little-0.443
 small-0.430
 boy-0.384
 other-0.381
Token got
Token ID1392
Feature activation+8.48e-03

Pos logit contributions
 big+0.885
 small+0.804
 little+0.785
 new+0.713
 boy+0.709
Neg logit contributions
owing-1.238
ur-1.228
ared-1.162
owed-1.155
ors-1.152
Token home
Token ID1363
Feature activation+8.62e-02

Pos logit contributions
owing+0.026
ur+0.025
ors+0.025
ares+0.025
owed+0.024
Neg logit contributions
 big-0.021
 little-0.019
 small-0.018
 boy-0.017
 other-0.017
Token,
Token ID11
Feature activation+4.56e-02

Pos logit contributions
owing+0.282
ur+0.278
ares+0.270
ors+0.269
beh+0.268
Neg logit contributions
 big-0.187
 little-0.171
 small-0.165
 boy-0.150
 other-0.149
Token she
Token ID673
Feature activation+1.53e-01

Pos logit contributions
owing+0.114
ur+0.109
owed+0.105
rying+0.103
beh+0.101
Neg logit contributions
 big-0.121
 little-0.110
 small-0.109
 park-0.101
 other-0.101
Token unf
Token ID3684
Feature activation+1.95e-01

Pos logit contributions
ur+0.467
owing+0.460
owed+0.447
rying+0.436
ared+0.435
Neg logit contributions
 big-0.321
 small-0.289
 little-0.287
 other-0.265
 boy-0.263
Tokenur
Token ID333
Feature activation+9.01e-01

Pos logit contributions
ors+0.251
rying+0.232
owing+0.227
ility+0.210
beh+0.202
Neg logit contributions
 big-0.658
 little-0.658
 small-0.617
 park-0.606
 boy-0.603
Tokenled
Token ID992
Feature activation+5.10e-01

Pos logit contributions
owing+0.760
ur+0.720
ares+0.627
ors+0.616
beh+0.564
Neg logit contributions
 big-4.110
 little-3.965
 small-3.903
 boy-3.779
 other-3.746
Token the
Token ID262
Feature activation-1.34e-01

Pos logit contributions
owing+1.551
ur+1.524
ares+1.493
beh+1.482
ors+1.468
Neg logit contributions
 big-1.278
 little-1.176
 small-1.149
 boy-1.040
 other-1.038
Token carpet
Token ID20710
Feature activation-1.20e-01

Pos logit contributions
 big+0.237
 small+0.198
 little+0.195
 other+0.179
 boy+0.171
Neg logit contributions
rying-0.401
ors-0.398
ur-0.396
owing-0.393
ares-0.372
Token and
Token ID290
Feature activation-5.05e-02

Pos logit contributions
 big+0.249
 little+0.227
 small+0.219
 other+0.197
 boy+0.195
Neg logit contributions
owing-0.401
ur-0.398
ares-0.390
beh-0.388
ors-0.383
Token started
Token ID2067
Feature activation+2.62e-02

Pos logit contributions
 big+0.109
 little+0.100
 small+0.097
 boy+0.088
 other+0.088
Neg logit contributions
owing-0.160
ur-0.157
ors-0.151
rying-0.150
owed-0.150
Token magical
Token ID10883
Feature activation-2.63e-01

Pos logit contributions
 big+0.095
 little+0.089
 small+0.087
 other+0.082
 boy+0.082
Neg logit contributions
owing-0.064
ur-0.063
ares-0.060
rying-0.059
ared-0.058
Token!
Token ID0
Feature activation+2.35e-01

Pos logit contributions
 big+0.537
 little+0.485
 small+0.475
 boy+0.429
 other+0.429
Neg logit contributions
owing-0.866
ur-0.845
ors-0.816
rying-0.808
ares-0.808
Token It
Token ID632
Feature activation+6.48e-02

Pos logit contributions
owing+0.771
ur+0.745
ors+0.723
ares+0.722
rying+0.721
Neg logit contributions
 big-0.501
 little-0.462
 small-0.445
 boy-0.409
 other-0.405
Token made
Token ID925
Feature activation-9.94e-02

Pos logit contributions
owing+0.247
ur+0.243
ares+0.235
ors+0.235
rying+0.233
Neg logit contributions
 big-0.100
 little-0.088
 small-0.084
 boy-0.074
 other-0.073
Token a
Token ID257
Feature activation-2.49e-01

Pos logit contributions
 big+0.222
 little+0.204
 small+0.198
 other+0.180
 boy+0.179
Neg logit contributions
owing-0.318
ur-0.309
ares-0.298
ors-0.297
rying-0.296
Token big
Token ID1263
Feature activation-5.88e-01

Pos logit contributions
 big+0.272
 little+0.236
 small+0.232
 other+0.231
 boy+0.227
Neg logit contributions
owing-0.877
ur-0.874
rying-0.836
ares-0.830
istent-0.811
Token,
Token ID11
Feature activation+1.53e-02

Pos logit contributions
 big+1.167
 little+1.057
 small+1.041
 other+0.979
 boy+0.944
Neg logit contributions
owing-1.899
ur-1.826
rying-1.770
ares-1.762
ors-1.759
Token beautiful
Token ID4950
Feature activation-3.86e-01

Pos logit contributions
owing+0.057
ur+0.057
rying+0.055
ares+0.054
owed+0.054
Neg logit contributions
 big-0.017
 little-0.015
 small-0.014
 other-0.014
 boy-0.013
Token bubble
Token ID14310
Feature activation-1.44e-01

Pos logit contributions
 big+0.631
 small+0.560
 little+0.545
 other+0.533
 boy+0.492
Neg logit contributions
owing-1.310
ur-1.273
ors-1.232
rying-1.230
owed-1.220
Token.
Token ID13
Feature activation+2.87e-02

Pos logit contributions
 big+0.338
 little+0.310
 small+0.301
 other+0.276
 boy+0.275
Neg logit contributions
owing-0.441
ur-0.431
ares-0.414
ors-0.412
beh-0.411
Token It
Token ID632
Feature activation+7.85e-02

Pos logit contributions
owing+0.093
ur+0.091
ares+0.087
ors+0.087
rying+0.087
Neg logit contributions
 big-0.062
 little-0.057
 small-0.055
 boy-0.050
 other-0.050
Token The
Token ID383
Feature activation-5.00e-02

Pos logit contributions
owing+0.871
ur+0.835
rying+0.815
ors+0.811
ares+0.808
Neg logit contributions
 big-0.605
 little-0.563
 small-0.541
 boy-0.503
 other-0.494
Token lady
Token ID10846
Feature activation-2.93e-01

Pos logit contributions
 big+0.067
 small+0.057
 little+0.053
 new+0.045
 other+0.045
Neg logit contributions
owing-0.171
ur-0.170
rying-0.164
ors-0.160
ares-0.159
Token loaded
Token ID9639
Feature activation+1.70e-01

Pos logit contributions
 big+0.529
 little+0.476
 small+0.457
 boy+0.410
 other+0.406
Neg logit contributions
owing-1.049
ur-1.027
ares-0.996
ors-0.994
beh-0.987
Token everything
Token ID2279
Feature activation-7.67e-02

Pos logit contributions
owing+0.577
ur+0.565
ares+0.544
ors+0.544
rying+0.540
Neg logit contributions
 big-0.336
 little-0.305
 small-0.295
 boy-0.267
 other-0.266
Token into
Token ID656
Feature activation+4.18e-01

Pos logit contributions
 big+0.210
 little+0.190
 small+0.190
 new+0.171
 other+0.171
Neg logit contributions
owing-0.209
ares-0.206
ur-0.204
beh-0.199
ors-0.199
Token big
Token ID1263
Feature activation-5.83e-01

Pos logit contributions
ur+1.364
owing+1.357
rying+1.299
ors+1.289
beh+1.282
Neg logit contributions
 big-0.701
 little-0.626
 boy-0.603
 small-0.595
 park-0.539
Token bags
Token ID11668
Feature activation-1.41e-01

Pos logit contributions
 big+1.111
 little+1.000
 small+0.968
 other+0.869
 boy+0.867
Neg logit contributions
owing-2.046
ur-2.010
ares-1.944
ors-1.929
beh-1.925
Token and
Token ID290
Feature activation-7.38e-02

Pos logit contributions
 big+0.270
 little+0.237
 small+0.230
 other+0.202
 boy+0.194
Neg logit contributions
ur-0.500
beh-0.500
owing-0.499
ares-0.490
ors-0.476
Token then
Token ID788
Feature activation+1.69e-01

Pos logit contributions
 big+0.158
 little+0.145
 small+0.140
 boy+0.128
 other+0.128
Neg logit contributions
owing-0.236
ur-0.232
ors-0.222
rying-0.221
ares-0.221
Token loaded
Token ID9639
Feature activation+1.77e-01

Pos logit contributions
owing+0.549
ur+0.530
ares+0.520
ors+0.515
ared+0.510
Neg logit contributions
 big-0.377
 little-0.343
 small-0.333
 boy-0.305
 other-0.304
Token the
Token ID262
Feature activation-1.59e-01

Pos logit contributions
owing+0.552
ur+0.538
ares+0.518
ors+0.515
beh+0.513
Neg logit contributions
 big-0.411
 little-0.377
 small-0.367
 other-0.337
 boy-0.336
Token?
Token ID30
Feature activation+1.69e-01

Pos logit contributions
owing+0.218
ur+0.214
beh+0.213
ares+0.208
ors+0.207
Neg logit contributions
 big-0.220
 little-0.203
 small-0.196
 other-0.180
 new-0.175
Token It
Token ID632
Feature activation+7.81e-02

Pos logit contributions
owing+0.485
ur+0.460
ors+0.452
rying+0.451
beh+0.448
Neg logit contributions
 big-0.429
 little-0.403
 small-0.389
 boy-0.365
 other-0.357
Token looks
Token ID3073
Feature activation-6.69e-02

Pos logit contributions
owing+0.264
ur+0.259
owed+0.252
ors+0.251
ares+0.248
Neg logit contributions
 big-0.143
 little-0.131
 small-0.126
 boy-0.115
 other-0.113
Token like
Token ID588
Feature activation+2.51e-01

Pos logit contributions
 big+0.133
 little+0.121
 small+0.117
 boy+0.106
 other+0.105
Neg logit contributions
owing-0.228
ur-0.223
ares-0.215
ors-0.215
rying-0.213
Token a
Token ID257
Feature activation-2.42e-01

Pos logit contributions
owing+0.871
ur+0.869
ors+0.828
beh+0.828
rying+0.820
Neg logit contributions
 big-0.395
 little-0.360
 small-0.344
 boy-0.324
 other-0.302
Token big
Token ID1263
Feature activation-5.83e-01

Pos logit contributions
 big+0.322
 little+0.294
 small+0.289
 other+0.262
 boy+0.252
Neg logit contributions
owing-0.784
ur-0.775
rying-0.749
ares-0.746
ors-0.728
Token cotton
Token ID15985
Feature activation-2.61e-02

Pos logit contributions
 big+1.031
 little+0.917
 small+0.910
 other+0.827
 boy+0.777
Neg logit contributions
owing-2.009
ur-1.947
ors-1.881
rying-1.878
ares-1.877
Token ball
Token ID2613
Feature activation-3.39e-01

Pos logit contributions
 big+0.045
 little+0.040
 small+0.040
 other+0.035
 boy+0.034
Neg logit contributions
owing-0.092
ur-0.091
ors-0.089
ares-0.088
rying-0.086
Token!"
Token ID2474
Feature activation+2.58e-01

Pos logit contributions
 big+0.866
 little+0.772
 small+0.752
 boy+0.706
 other+0.705
Neg logit contributions
owing-1.012
ur-0.966
beh-0.961
ared-0.940
ares-0.940
Token
Token ID198
Feature activation-2.42e-01

Pos logit contributions
owing+0.992
ur+0.968
ares+0.939
ors+0.938
rying+0.937
Neg logit contributions
 big-0.411
 little-0.366
 small-0.349
 boy-0.308
 other-0.305
Token
Token ID198
Feature activation-2.40e-01

Pos logit contributions
 big+0.364
 little+0.319
 small+0.302
 boy+0.274
 other+0.268
Neg logit contributions
ur-0.896
owing-0.892
ares-0.861
ors-0.861
oot-0.856
Token He
Token ID679
Feature activation+3.28e-02

Pos logit contributions
owing+0.070
ur+0.068
ors+0.066
rying+0.066
ares+0.066
Neg logit contributions
 big-0.042
 little-0.038
 small-0.037
 boy-0.034
 other-0.033
Token had
Token ID550
Feature activation-2.21e-01

Pos logit contributions
owing+0.106
ur+0.105
ares+0.101
ors+0.100
owed+0.100
Neg logit contributions
 big-0.068
 little-0.061
 small-0.060
 boy-0.055
 other-0.054
Token made
Token ID925
Feature activation-8.23e-02

Pos logit contributions
 big+0.525
 little+0.486
 small+0.472
 boy+0.441
 other+0.434
Neg logit contributions
owing-0.661
ur-0.647
ares-0.618
ors-0.617
beh-0.615
Token such
Token ID884
Feature activation+3.93e-01

Pos logit contributions
 big+0.124
 little+0.110
 small+0.106
 boy+0.097
 other+0.091
Neg logit contributions
owing-0.308
ur-0.303
ares-0.292
ors-0.292
beh-0.290
Token a
Token ID257
Feature activation-2.45e-01

Pos logit contributions
owing+1.375
ur+1.369
beh+1.321
ared+1.291
ares+1.283
Neg logit contributions
 big-0.551
 little-0.464
 small-0.459
 boy-0.455
 park-0.437
Token big
Token ID1263
Feature activation-5.82e-01

Pos logit contributions
 big+0.284
 little+0.254
 small+0.251
 other+0.247
 boy+0.239
Neg logit contributions
owing-0.818
ur-0.798
rying-0.783
ares-0.747
beh-0.740
Token mess
Token ID2085
Feature activation-1.22e-01

Pos logit contributions
 big+1.081
 little+0.978
 small+0.958
 other+0.886
 boy+0.837
Neg logit contributions
owing-1.977
ur-1.883
rying-1.837
ors-1.820
ares-1.813
Token that
Token ID326
Feature activation+1.41e-01

Pos logit contributions
 big+0.241
 little+0.215
 small+0.204
 other+0.183
 boy+0.180
Neg logit contributions
ur-0.433
owing-0.426
beh-0.424
ared-0.422
ares-0.416
Token he
Token ID339
Feature activation+9.16e-02

Pos logit contributions
owing+0.440
ur+0.432
ors+0.416
beh+0.412
ares+0.410
Neg logit contributions
 big-0.292
 little-0.270
 small-0.262
 boy-0.236
 other-0.234
Token had
Token ID550
Feature activation-2.09e-01

Pos logit contributions
owing+0.315
ur+0.310
ors+0.300
rying+0.298
beh+0.298
Neg logit contributions
 big-0.170
 little-0.152
 small-0.150
 boy-0.133
 other-0.132
Token to
Token ID284
Feature activation+2.02e-01

Pos logit contributions
 big+0.533
 little+0.493
 small+0.481
 other+0.446
 boy+0.440
Neg logit contributions
owing-0.601
ur-0.584
ares-0.565
ors-0.561
rying-0.554
Token help
Token ID1037
Feature activation+3.25e-02

Pos logit contributions
 big+0.060
 little+0.055
 small+0.053
 other+0.048
 boy+0.047
Neg logit contributions
owing-0.088
ur-0.085
ares-0.084
ors-0.083
ared-0.083
Token you
Token ID345
Feature activation+2.07e-01

Pos logit contributions
owing+0.093
ur+0.091
ares+0.089
ared+0.088
owed+0.087
Neg logit contributions
 big-0.087
 little-0.082
 small-0.078
 other-0.075
 boy-0.071
Token".
Token ID1911
Feature activation+3.55e-01

Pos logit contributions
owing+0.629
ur+0.621
ares+0.605
ared+0.601
ors+0.599
Neg logit contributions
 big-0.504
 little-0.466
 small-0.448
 other-0.411
 new-0.393
Token With
Token ID2080
Feature activation+1.68e-01

Pos logit contributions
owing+1.346
ur+1.314
ares+1.276
ors+1.275
rying+1.270
Neg logit contributions
 big-0.570
 little-0.508
 small-0.485
 boy-0.430
 other-0.426
Token a
Token ID257
Feature activation-2.37e-01

Pos logit contributions
owing+0.531
ur+0.529
ors+0.500
ares+0.498
ared+0.494
Neg logit contributions
 big-0.353
 little-0.326
 small-0.313
 boy-0.296
 other-0.285
Token big
Token ID1263
Feature activation-5.82e-01

Pos logit contributions
 big+0.356
 park+0.355
 other+0.334
 boy+0.333
 little+0.332
Neg logit contributions
ur-0.750
owing-0.747
ares-0.697
owed-0.686
istent-0.681
Token smile
Token ID8212
Feature activation-8.14e-03

Pos logit contributions
 big+1.367
 little+1.258
 small+1.234
 other+1.180
 boy+1.153
Neg logit contributions
owing-1.705
ur-1.664
ares-1.584
ared-1.550
owed-1.545
Token,
Token ID11
Feature activation+1.78e-02

Pos logit contributions
 big+0.016
 little+0.015
 small+0.014
 boy+0.013
 other+0.012
Neg logit contributions
owing-0.028
beh-0.028
ur-0.027
ares-0.027
ors-0.027
Token the
Token ID262
Feature activation-1.65e-01

Pos logit contributions
owing+0.054
ur+0.053
ares+0.051
ors+0.051
rying+0.050
Neg logit contributions
 big-0.041
 little-0.038
 small-0.037
 boy-0.034
 other-0.034
Token old
Token ID1468
Feature activation-3.53e-01

Pos logit contributions
 big+0.198
 small+0.163
 little+0.152
 other+0.143
 park+0.136
Neg logit contributions
owing-0.583
ur-0.562
rying-0.537
owed-0.530
iously-0.522
Token man
Token ID582
Feature activation-4.13e-01

Pos logit contributions
 big+0.405
 little+0.320
 small+0.318
 other+0.272
 new+0.233
Neg logit contributions
owing-1.435
ur-1.398
ors-1.358
oot-1.345
owed-1.342
Token until
Token ID1566
Feature activation+2.46e-01

Pos logit contributions
 big+0.605
 little+0.547
 small+0.525
 boy+0.475
 other+0.472
Neg logit contributions
owing-0.928
beh-0.893
ur-0.888
ares-0.882
ors-0.873
Token he
Token ID339
Feature activation+1.07e-01

Pos logit contributions
owing+0.809
ur+0.780
ares+0.761
ors+0.757
rying+0.754
Neg logit contributions
 big-0.542
 little-0.495
 small-0.477
 boy-0.438
 other-0.438
Token came
Token ID1625
Feature activation+7.24e-02

Pos logit contributions
owing+0.374
ur+0.370
owed+0.354
ared+0.352
ares+0.352
Neg logit contributions
 big-0.192
 little-0.173
 small-0.169
 boy-0.150
 other-0.149
Token across
Token ID1973
Feature activation+1.80e-01

Pos logit contributions
owing+0.207
ors+0.203
ur+0.201
ares+0.200
beh+0.197
Neg logit contributions
 big-0.190
 little-0.174
 small-0.171
 other-0.156
 boy-0.153
Token a
Token ID257
Feature activation-2.42e-01

Pos logit contributions
owing+0.684
ur+0.671
ares+0.650
ors+0.649
rying+0.644
Neg logit contributions
 big-0.287
 little-0.253
 small-0.243
 boy-0.213
 other-0.212
Token big
Token ID1263
Feature activation-5.82e-01

Pos logit contributions
 other+0.203
 big+0.203
 little+0.171
 small+0.165
 boy+0.150
Neg logit contributions
ur-0.865
owing-0.859
rying-0.834
istent-0.782
oot-0.782
Token house
Token ID2156
Feature activation-3.04e-01

Pos logit contributions
 big+0.981
 little+0.892
 small+0.869
 other+0.864
 boy+0.753
Neg logit contributions
owing-1.965
ur-1.916
ors-1.834
rying-1.832
ared-1.789
Token in
Token ID287
Feature activation+1.47e-01

Pos logit contributions
 big+0.639
 little+0.570
 small+0.547
 boy+0.506
 park+0.501
Neg logit contributions
ur-1.016
ares-1.004
owing-0.998
beh-0.995
ors-0.979
Token the
Token ID262
Feature activation-1.51e-01

Pos logit contributions
owing+0.474
ur+0.467
rying+0.455
ors+0.450
ared+0.444
Neg logit contributions
 big-0.250
 little-0.233
 small-0.221
 other-0.207
 boy-0.204
Token woods
Token ID16479
Feature activation-3.08e-01

Pos logit contributions
 big+0.211
 little+0.196
 small+0.190
 boy+0.165
 new+0.158
Neg logit contributions
owing-0.470
ur-0.459
rying-0.448
rol-0.442
ors-0.439
Token.
Token ID13
Feature activation+4.43e-02

Pos logit contributions
 big+0.653
 little+0.591
 small+0.576
 other+0.520
 boy+0.519
Neg logit contributions
ur-1.007
owing-1.007
ares-0.989
beh-0.977
ors-0.970
Token enough
Token ID1576
Feature activation+4.41e-01

Pos logit contributions
owing+0.824
ur+0.823
beh+0.793
ors+0.785
ares+0.784
Neg logit contributions
 big-0.517
 little-0.463
 small-0.452
 other-0.430
 boy-0.398
Token,
Token ID11
Feature activation+7.96e-03

Pos logit contributions
owing+1.344
ur+1.310
ares+1.268
ors+1.259
beh+1.254
Neg logit contributions
 big-1.054
 little-0.970
 small-0.941
 other-0.869
 boy-0.867
Token there
Token ID612
Feature activation+2.22e-02

Pos logit contributions
owing+0.024
ur+0.024
ares+0.023
ors+0.023
rying+0.023
Neg logit contributions
 big-0.019
 little-0.017
 small-0.017
 boy-0.015
 other-0.015
Token was
Token ID373
Feature activation-3.38e-01

Pos logit contributions
owing+0.088
ur+0.087
ors+0.084
ares+0.084
owed+0.084
Neg logit contributions
 big-0.030
 little-0.026
 small-0.025
 boy-0.021
 other-0.021
Token a
Token ID257
Feature activation-2.42e-01

Pos logit contributions
 big+0.533
 little+0.473
 small+0.454
 boy+0.413
 other+0.397
Neg logit contributions
owing-1.253
ur-1.241
beh-1.182
ares-1.181
ors-1.180
Token big
Token ID1263
Feature activation-5.82e-01

Pos logit contributions
 other+0.194
 big+0.191
 small+0.146
 park+0.141
 little+0.137
Neg logit contributions
ur-0.827
owing-0.822
rying-0.786
istent-0.755
 able-0.743
Token,
Token ID11
Feature activation+1.98e-02

Pos logit contributions
 big+1.078
 little+0.967
 small+0.961
 other+0.936
 new+0.832
Neg logit contributions
owing-1.896
ur-1.822
rying-1.741
ors-1.732
ares-1.718
Token shiny
Token ID22441
Feature activation-3.48e-01

Pos logit contributions
owing+0.069
ur+0.068
rying+0.065
ares+0.063
beh+0.063
Neg logit contributions
 big-0.020
 other-0.020
 little-0.019
 small-0.017
 boy-0.016
Token screen
Token ID3159
Feature activation-1.11e-01

Pos logit contributions
 big+0.586
 little+0.516
 small+0.513
 other+0.467
 boy+0.436
Neg logit contributions
owing-1.236
ur-1.204
ors-1.177
rying-1.161
ares-1.161
Token.
Token ID13
Feature activation+3.92e-02

Pos logit contributions
 big+0.251
 little+0.227
 small+0.219
 boy+0.202
 other+0.197
Neg logit contributions
owing-0.356
ur-0.349
beh-0.341
ares-0.339
rying-0.335
Token The
Token ID383
Feature activation-3.78e-02

Pos logit contributions
owing+0.118
ur+0.116
ares+0.111
ors+0.111
beh+0.109
Neg logit contributions
 big-0.092
 little-0.084
 small-0.082
 other-0.075
 boy-0.075
Token She
Token ID1375
Feature activation+1.45e-01

Pos logit contributions
owing+0.876
ur+0.849
ares+0.823
ors+0.822
rying+0.819
Neg logit contributions
 big-0.525
 little-0.481
 small-0.463
 boy-0.422
 other-0.418
Token quickly
Token ID2952
Feature activation+1.46e-01

Pos logit contributions
owing+0.477
ur+0.471
ors+0.451
ares+0.449
rying+0.446
Neg logit contributions
 big-0.295
 little-0.268
 small-0.261
 boy-0.239
 other-0.237
Token pulled
Token ID5954
Feature activation+1.92e-01

Pos logit contributions
owing+0.457
ur+0.439
ares+0.432
ors+0.428
beh+0.424
Neg logit contributions
 big-0.336
 little-0.309
 small-0.299
 other-0.271
 boy-0.268
Token out
Token ID503
Feature activation+2.88e-01

Pos logit contributions
owing+0.597
ur+0.576
beh+0.564
owed+0.555
ares+0.555
Neg logit contributions
 big-0.474
 little-0.432
 small-0.423
 other-0.388
 boy-0.374
Token a
Token ID257
Feature activation-2.42e-01

Pos logit contributions
owing+1.025
ur+1.007
ares+0.971
ors+0.969
rying+0.961
Neg logit contributions
 big-0.514
 little-0.461
 small-0.445
 boy-0.404
 other-0.397
Token big
Token ID1263
Feature activation-5.81e-01

Pos logit contributions
 big+0.286
 little+0.257
 other+0.243
 boy+0.242
 small+0.240
Neg logit contributions
owing-0.882
ur-0.869
ares-0.833
rying-0.826
owed-0.811
Token t
Token ID256
Feature activation-2.15e-01

Pos logit contributions
 big+1.095
 little+0.994
 small+0.962
 other+0.905
 boy+0.879
Neg logit contributions
owing-1.974
ur-1.932
ares-1.857
ors-1.844
rying-1.831
Tokeneddy
Token ID21874
Feature activation+2.54e-01

Pos logit contributions
 big+0.599
 little+0.564
 small+0.529
 boy+0.522
 other+0.478
Neg logit contributions
owing-0.531
ur-0.522
beh-0.517
ares-0.513
rying-0.506
Token bear
Token ID6842
Feature activation-2.45e-01

Pos logit contributions
owing+1.014
ur+0.992
ors+0.967
ares+0.956
rying+0.956
Neg logit contributions
 big-0.349
 little-0.295
 small-0.290
 other-0.244
 boy-0.236
Token holding
Token ID4769
Feature activation+1.15e-01

Pos logit contributions
 big+0.538
 little+0.489
 small+0.458
 park+0.412
 boy+0.407
Neg logit contributions
beh-0.772
ares-0.755
owing-0.745
ors-0.735
ared-0.724
Token a
Token ID257
Feature activation-2.30e-01

Pos logit contributions
owing+0.420
ur+0.410
ares+0.398
ors+0.397
rying+0.395
Neg logit contributions
 big-0.204
 little-0.183
 small-0.176
 other-0.156
 boy-0.154
Token monster
Token ID9234
Feature activation-1.11e-01

Pos logit contributions
 other+0.201
 big+0.200
 little+0.166
 small+0.163
 two+0.152
Neg logit contributions
ur-0.761
owing-0.754
rying-0.733
ares-0.687
istent-0.686
Token!
Token ID0
Feature activation+2.63e-01

Pos logit contributions
 big+0.266
 little+0.246
 small+0.234
 boy+0.221
 other+0.213
Neg logit contributions
owing-0.339
ur-0.330
ares-0.323
beh-0.322
ared-0.321
Token It
Token ID632
Feature activation+7.83e-02

Pos logit contributions
owing+0.857
ur+0.827
ors+0.800
rying+0.800
ares+0.798
Neg logit contributions
 big-0.571
 little-0.526
 small-0.509
 boy-0.466
 other-0.462
Token was
Token ID373
Feature activation-3.31e-01

Pos logit contributions
ur+0.289
owing+0.288
owed+0.279
ors+0.277
ares+0.275
Neg logit contributions
 big-0.116
 little-0.103
 small-0.098
 other-0.086
 boy-0.085
Token a
Token ID257
Feature activation-2.39e-01

Pos logit contributions
 big+0.664
 little+0.607
 small+0.585
 boy+0.540
 other+0.532
Neg logit contributions
owing-1.107
ur-1.088
ares-1.044
ors-1.041
rying-1.034
Token big
Token ID1263
Feature activation-5.81e-01

Pos logit contributions
 big+0.320
 other+0.290
 little+0.286
 small+0.284
 park+0.269
Neg logit contributions
ur-0.747
owing-0.739
rying-0.695
ares-0.683
ors-0.672
Token,
Token ID11
Feature activation+2.36e-02

Pos logit contributions
 big+1.107
 little+0.993
 small+0.983
 other+0.931
 new+0.857
Neg logit contributions
owing-1.900
ur-1.826
ors-1.758
ares-1.756
rying-1.753
Token scary
Token ID14343
Feature activation-1.72e-01

Pos logit contributions
owing+0.087
ur+0.085
rying+0.082
ares+0.082
ors+0.082
Neg logit contributions
 big-0.028
 little-0.026
 other-0.024
 small-0.023
 boy-0.021
Token monster
Token ID9234
Feature activation-1.25e-01

Pos logit contributions
 big+0.319
 small+0.283
 little+0.281
 other+0.267
 new+0.241
Neg logit contributions
owing-0.573
ur-0.552
ors-0.543
rying-0.530
ares-0.526
Token.
Token ID13
Feature activation+3.98e-02

Pos logit contributions
 big+0.294
 little+0.274
 small+0.260
 boy+0.245
 other+0.238
Neg logit contributions
owing-0.381
ur-0.372
ares-0.367
beh-0.363
ared-0.358
Token The
Token ID383
Feature activation-3.93e-02

Pos logit contributions
owing+0.126
ur+0.123
ors+0.118
ares+0.118
rying+0.118
Neg logit contributions
 big-0.089
 little-0.082
 small-0.080
 boy-0.073
 other-0.073
Token hope
Token ID2911
Feature activation+7.04e-02

Pos logit contributions
 big+0.369
 little+0.342
 small+0.331
 boy+0.305
 other+0.305
Neg logit contributions
owing-0.444
ur-0.431
ors-0.422
ares-0.414
rying-0.414
Token it
Token ID340
Feature activation+8.46e-02

Pos logit contributions
owing+0.214
ur+0.205
ares+0.201
ared+0.199
beh+0.198
Neg logit contributions
 big-0.175
 little-0.163
 small-0.156
 other-0.146
 boy-0.144
Token will
Token ID481
Feature activation-3.11e-02

Pos logit contributions
owing+0.300
ur+0.294
ares+0.284
owed+0.283
ors+0.282
Neg logit contributions
 big-0.154
 little-0.138
 small-0.133
 other-0.119
 boy-0.119
Token be
Token ID307
Feature activation-2.18e-01

Pos logit contributions
 big+0.057
 little+0.051
 small+0.049
 other+0.044
 boy+0.044
Neg logit contributions
owing-0.112
ur-0.109
ares-0.106
ors-0.106
rying-0.105
Token a
Token ID257
Feature activation-2.39e-01

Pos logit contributions
 big+0.395
 little+0.353
 small+0.341
 other+0.300
 boy+0.297
Neg logit contributions
owing-0.796
ur-0.778
ares-0.757
ors-0.754
rying-0.747
Token big
Token ID1263
Feature activation-5.81e-01

Pos logit contributions
 big+0.296
 small+0.252
 little+0.239
 other+0.237
 park+0.220
Neg logit contributions
ur-0.788
owing-0.770
rying-0.747
ares-0.723
ility-0.718
Token and
Token ID290
Feature activation-7.23e-02

Pos logit contributions
 big+1.051
 small+0.928
 little+0.917
 other+0.861
 new+0.794
Neg logit contributions
owing-1.953
ur-1.904
rying-1.823
ares-1.817
ors-1.797
Token bright
Token ID6016
Feature activation-3.60e-01

Pos logit contributions
 big+0.088
 little+0.084
 park+0.074
 small+0.074
 other+0.074
Neg logit contributions
ur-0.257
owing-0.250
beh-0.245
rying-0.240
owed-0.238
Token sun
Token ID4252
Feature activation-4.01e-01

Pos logit contributions
 big+0.604
 small+0.526
 little+0.523
 other+0.483
 boy+0.450
Neg logit contributions
owing-1.277
ur-1.236
ares-1.201
ors-1.200
rying-1.192
Token,"
Token ID553
Feature activation+2.01e-01

Pos logit contributions
 big+1.034
 little+0.954
 small+0.917
 boy+0.881
 other+0.838
Neg logit contributions
ur-1.136
owing-1.119
ares-1.097
beh-1.092
ors-1.068
Token Max
Token ID5436
Feature activation+7.36e-02

Pos logit contributions
owing+0.622
ur+0.615
ares+0.587
ors+0.586
beh+0.580
Neg logit contributions
 big-0.450
 little-0.409
 small-0.399
 other-0.361
 boy-0.360
Token!
Token ID0
Feature activation+2.72e-01

Pos logit contributions
owing+1.049
ur+1.027
ors+0.968
rying+0.968
ared+0.960
Neg logit contributions
 big-0.961
 little-0.904
 small-0.878
 boy-0.816
 other-0.806
Token<|endoftext|>
Token ID50256
Feature activation-1.93e-01

Pos logit contributions
owing+0.871
ur+0.835
rying+0.815
ors+0.811
ares+0.808
Neg logit contributions
 big-0.605
 little-0.563
 small-0.541
 boy-0.503
 other-0.494
TokenJohn
Token ID7554
Feature activation+1.70e-01

Pos logit contributions
 big+0.334
 little+0.301
 small+0.292
 other+0.259
 boy+0.257
Neg logit contributions
owing-0.678
ur-0.670
ares-0.644
ors-0.638
owed-0.638
Token had
Token ID550
Feature activation-2.14e-01

Pos logit contributions
owing+0.556
ur+0.542
ors+0.521
ares+0.519
ared+0.517
Neg logit contributions
 big-0.360
 little-0.326
 small-0.319
 other-0.289
 boy-0.289
Token a
Token ID257
Feature activation-2.43e-01

Pos logit contributions
 big+0.340
 little+0.307
 small+0.294
 boy+0.276
 other+0.261
Neg logit contributions
owing-0.785
ur-0.773
ares-0.747
ors-0.745
ared-0.743
Token big
Token ID1263
Feature activation-5.81e-01

Pos logit contributions
 big+0.187
 little+0.181
 other+0.181
 small+0.173
 boy+0.147
Neg logit contributions
owing-0.845
ur-0.844
ares-0.785
ared-0.775
rying-0.758
Token backyard
Token ID24296
Feature activation-3.43e-01

Pos logit contributions
 big+1.156
 little+1.067
 small+1.051
 other+0.992
 boy+0.907
Neg logit contributions
owing-1.830
ur-1.756
ared-1.644
ares-1.644
ors-1.637
Token.
Token ID13
Feature activation+3.34e-02

Pos logit contributions
 big+0.800
 little+0.731
 small+0.711
 boy+0.654
 other+0.643
Neg logit contributions
owing-1.056
ur-1.036
ares-1.008
ors-1.002
beh-0.995
Token He
Token ID679
Feature activation+3.77e-02

Pos logit contributions
owing+0.110
ur+0.107
rying+0.103
ors+0.103
beh+0.103
Neg logit contributions
 big-0.072
 little-0.066
 small-0.064
 boy-0.059
 other-0.057
Token liked
Token ID8288
Feature activation-2.06e-01

Pos logit contributions
owing+0.134
ur+0.134
owed+0.131
ors+0.129
ared+0.127
Neg logit contributions
 big-0.058
 little-0.051
 small-0.050
 other-0.045
 boy-0.045
Token to
Token ID284
Feature activation+2.03e-01

Pos logit contributions
 big+0.584
 little+0.548
 small+0.535
 boy+0.504
 other+0.502
Neg logit contributions
owing-0.516
ur-0.502
ors-0.478
ares-0.473
rying-0.472
Tokenâ„¢
Token ID8151
Feature activation+2.58e-01

Pos logit contributions
owing+0.990
ur+0.966
ors+0.924
ares+0.924
ared+0.914
Neg logit contributions
 big-0.788
 little-0.722
 small-0.707
 other-0.652
 boy-0.651
Tokent
Token ID83
Feature activation+4.19e-01

Pos logit contributions
owing+0.635
ur+0.629
rying+0.602
ors+0.597
beh+0.594
Neg logit contributions
 big-0.737
 little-0.690
 small-0.666
 boy-0.638
 other-0.635
Token know
Token ID760
Feature activation+1.52e-01

Pos logit contributions
owing+1.273
ur+1.248
ares+1.208
ors+1.208
rying+1.191
Neg logit contributions
 big-0.995
 little-0.927
 small-0.889
 other-0.821
 boy-0.817
Token very
Token ID845
Feature activation-2.11e-01

Pos logit contributions
owing+0.435
ur+0.423
ares+0.412
ared+0.405
beh+0.405
Neg logit contributions
 big-0.395
 little-0.369
 small-0.357
 other-0.335
 boy-0.324
Token many
Token ID867
Feature activation-2.30e-01

Pos logit contributions
 big+0.304
 little+0.266
 small+0.254
 boy+0.243
 other+0.227
Neg logit contributions
owing-0.790
ur-0.788
beh-0.754
ares-0.750
rying-0.749
Token big
Token ID1263
Feature activation-5.81e-01

Pos logit contributions
 big+0.380
 little+0.334
 small+0.328
 boy+0.319
 park+0.281
Neg logit contributions
owing-0.800
ur-0.782
ors-0.759
beh-0.756
rying-0.745
Token words
Token ID2456
Feature activation-1.04e-01

Pos logit contributions
 big+1.140
 little+1.033
 small+1.008
 boy+0.910
 other+0.908
Neg logit contributions
owing-1.948
ur-1.889
ors-1.836
rying-1.808
ares-1.806
Token yet
Token ID1865
Feature activation+3.78e-01

Pos logit contributions
 big+0.217
 little+0.190
 small+0.186
 other+0.171
 new+0.162
Neg logit contributions
owing-0.350
ur-0.347
beh-0.344
rying-0.337
ares-0.337
Token.
Token ID13
Feature activation+3.08e-02

Pos logit contributions
owing+1.188
ur+1.163
ares+1.120
ors+1.114
rying+1.109
Neg logit contributions
 big-0.858
 little-0.785
 small-0.765
 other-0.702
 boy-0.695
Token One
Token ID1881
Feature activation+3.06e-02

Pos logit contributions
owing+0.099
ur+0.096
ares+0.093
ors+0.093
rying+0.092
Neg logit contributions
 big-0.067
 little-0.062
 small-0.060
 boy-0.055
 other-0.055
Token day
Token ID1110
Feature activation-3.28e-01

Pos logit contributions
owing+0.115
ur+0.112
owed+0.107
ared+0.105
beh+0.105
Neg logit contributions
 big-0.040
 small-0.033
 little-0.033
 other-0.029
 boy-0.027
Token!
Token ID0
Feature activation+2.66e-01

Pos logit contributions
ur+0.001
owing+0.001
ares+0.001
beh+0.001
owed+0.001
Neg logit contributions
 big-0.001
 little-0.000
 small-0.000
 other-0.000
 boy-0.000
Token That
Token ID1320
Feature activation+2.52e-01

Pos logit contributions
owing+0.912
ur+0.891
ares+0.861
ors+0.860
rying+0.854
Neg logit contributions
 big-0.519
 little-0.471
 small-0.455
 boy-0.411
 other-0.409
Token was
Token ID373
Feature activation-3.24e-01

Pos logit contributions
owing+0.836
ur+0.798
ors+0.794
ared+0.789
beh+0.784
Neg logit contributions
 big-0.430
 little-0.387
 small-0.383
 new-0.320
 other-0.310
Token the
Token ID262
Feature activation-1.65e-01

Pos logit contributions
 big+0.694
 little+0.633
 small+0.615
 other+0.559
 boy+0.556
Neg logit contributions
owing-1.064
ur-1.035
ares-1.003
ors-1.002
rying-0.991
Token great
Token ID1049
Feature activation-3.00e-01

Pos logit contributions
 big+0.240
 small+0.214
 little+0.212
 boy+0.176
 other+0.169
Neg logit contributions
owing-0.550
ur-0.523
rying-0.515
beh-0.506
ares-0.498
Token big
Token ID1263
Feature activation-5.81e-01

Pos logit contributions
 big+0.542
 little+0.481
 small+0.479
 other+0.425
 boy+0.401
Neg logit contributions
owing-1.033
ur-0.997
rying-0.961
beh-0.957
ares-0.955
Token fish
Token ID5916
Feature activation-2.50e-01

Pos logit contributions
 big+0.982
 little+0.862
 small+0.854
 other+0.760
 new+0.700
Neg logit contributions
owing-2.061
ur-1.976
ors-1.919
rying-1.913
ared-1.904
Token I
Token ID314
Feature activation+1.77e-01

Pos logit contributions
 big+0.633
 little+0.590
 small+0.565
 other+0.534
 boy+0.534
Neg logit contributions
owing-0.712
ur-0.701
ares-0.696
ors-0.675
beh-0.671
Token promised
Token ID8072
Feature activation+1.91e-01

Pos logit contributions
owing+0.574
ur+0.557
ors+0.545
ares+0.543
rying+0.535
Neg logit contributions
 big-0.380
 little-0.346
 small-0.333
 boy-0.307
 other-0.307
Token to
Token ID284
Feature activation+2.04e-01

Pos logit contributions
owing+0.580
ares+0.560
ur+0.560
rying+0.543
ors+0.540
Neg logit contributions
 big-0.471
 little-0.433
 small-0.415
 other-0.398
 new-0.383
Token show
Token ID905
Feature activation-1.07e-01

Pos logit contributions
owing+0.676
ur+0.661
ares+0.638
ors+0.637
rying+0.631
Neg logit contributions
 big-0.426
 little-0.388
 small-0.375
 other-0.341
 boy-0.341
Token Sean
Token ID11465
Feature activation+3.24e-01

Pos logit contributions
 big+0.166
 little+0.153
 small+0.150
 other+0.138
 boy+0.137
Neg logit contributions
owing-0.202
ur-0.199
ors-0.188
ares-0.188
beh-0.187
Token.
Token ID13
Feature activation+2.76e-02

Pos logit contributions
owing+1.073
ur+1.055
ares+1.009
ors+1.008
owed+1.002
Neg logit contributions
 big-0.657
 little-0.597
 small-0.582
 boy-0.527
 other-0.521
Token They
Token ID1119
Feature activation-7.80e-03

Pos logit contributions
owing+0.088
ur+0.085
ors+0.082
ares+0.082
rying+0.081
Neg logit contributions
 big-0.061
 little-0.057
 small-0.055
 boy-0.051
 other-0.050
Token had
Token ID550
Feature activation-2.22e-01

Pos logit contributions
 big+0.017
 little+0.016
 small+0.015
 boy+0.014
 other+0.014
Neg logit contributions
owing-0.025
ur-0.024
ares-0.023
ors-0.023
rying-0.023
Token used
Token ID973
Feature activation+4.04e-02

Pos logit contributions
 big+0.368
 little+0.346
 small+0.324
 boy+0.321
 park+0.284
Neg logit contributions
owing-0.750
ur-0.748
beh-0.725
ared-0.712
rying-0.703
Token big
Token ID1263
Feature activation-5.81e-01

Pos logit contributions
owing+0.141
ur+0.139
ors+0.134
ares+0.133
beh+0.132
Neg logit contributions
 big-0.074
 little-0.067
 small-0.064
 boy-0.059
 other-0.058
Token blocks
Token ID7021
Feature activation-1.31e-01

Pos logit contributions
 big+1.250
 little+1.161
 small+1.113
 boy+1.043
 other+1.022
Neg logit contributions
owing-1.804
ur-1.714
ors-1.695
ared-1.657
ares-1.648
Token of
Token ID286
Feature activation+1.44e-01

Pos logit contributions
 big+0.294
 small+0.250
 little+0.249
 other+0.227
 new+0.218
Neg logit contributions
owing-0.429
beh-0.428
ur-0.422
ares-0.415
rying-0.412
Token snow
Token ID6729
Feature activation-3.05e-01

Pos logit contributions
owing+0.440
ur+0.437
ors+0.431
ares+0.418
rying+0.412
Neg logit contributions
 big-0.273
 little-0.254
 boy-0.241
 small-0.240
 park-0.219
Token to
Token ID284
Feature activation+2.05e-01

Pos logit contributions
 big+0.784
 little+0.703
 small+0.687
 boy+0.650
 other+0.639
Neg logit contributions
ur-0.864
ares-0.849
owing-0.846
beh-0.844
ared-0.809
Token make
Token ID787
Feature activation-1.50e-02

Pos logit contributions
owing+0.625
ur+0.611
ors+0.591
owed+0.585
rying+0.583
Neg logit contributions
 big-0.435
 little-0.413
 small-0.394
 boy-0.377
 other-0.355
Token all
Token ID477
Feature activation+1.54e-02

Pos logit contributions
owing+0.290
ur+0.287
beh+0.270
rying+0.268
owed+0.266
Neg logit contributions
 big-0.164
 little-0.154
 small-0.145
 boy-0.145
 park-0.129
Token kinds
Token ID6982
Feature activation+1.11e-01

Pos logit contributions
owing+0.045
ur+0.044
ors+0.042
beh+0.042
rying+0.042
Neg logit contributions
 big-0.035
 little-0.033
 small-0.031
 boy-0.030
 other-0.029
Token of
Token ID286
Feature activation+1.55e-01

Pos logit contributions
owing+0.315
ur+0.306
ares+0.296
ors+0.294
rying+0.293
Neg logit contributions
 big-0.287
 little-0.266
 small-0.259
 other-0.240
 boy-0.238
Token things
Token ID1243
Feature activation-2.12e-01

Pos logit contributions
owing+0.530
ur+0.528
beh+0.502
owed+0.495
ors+0.495
Neg logit contributions
 big-0.253
 little-0.222
 small-0.217
 boy-0.214
 park-0.184
Token;
Token ID26
Feature activation+4.51e-01

Pos logit contributions
 big+0.477
 little+0.417
 small+0.410
 new+0.376
 other+0.373
Neg logit contributions
owing-0.691
ares-0.676
ur-0.675
ared-0.669
beh-0.661
Token big
Token ID1263
Feature activation-5.80e-01

Pos logit contributions
owing+1.380
ur+1.359
ors+1.298
rying+1.287
beh+1.285
Neg logit contributions
 big-0.983
 little-0.901
 small-0.877
 boy-0.815
 other-0.798
Token and
Token ID290
Feature activation-7.06e-02

Pos logit contributions
 big+1.083
 little+0.982
 small+0.961
 other+0.871
 boy+0.867
Neg logit contributions
owing-1.926
ur-1.884
ors-1.834
rying-1.795
ares-1.779
Token small
Token ID1402
Feature activation-5.03e-01

Pos logit contributions
 big+0.084
 little+0.079
 small+0.068
 boy+0.065
 park+0.065
Neg logit contributions
ur-0.251
owing-0.247
beh-0.246
rying-0.239
owed-0.235
Token,
Token ID11
Feature activation+2.70e-02

Pos logit contributions
 big+0.988
 little+0.890
 small+0.869
 other+0.783
 boy+0.782
Neg logit contributions
owing-1.697
ur-1.658
ors-1.596
ares-1.584
rying-1.581
Token round
Token ID2835
Feature activation-1.41e-01

Pos logit contributions
owing+0.095
ur+0.094
ors+0.091
rying+0.090
beh+0.089
Neg logit contributions
 big-0.042
 little-0.038
 small-0.036
 other-0.033
 boy-0.032
Token and
Token ID290
Feature activation-6.42e-02

Pos logit contributions
 big+0.264
 little+0.237
 small+0.231
 boy+0.206
 other+0.206
Neg logit contributions
owing-0.491
ur-0.481
ors-0.465
ares-0.463
rying-0.460
TokenI
Token ID40
Feature activation-1.41e-01

Pos logit contributions
 big+0.004
 little+0.004
 small+0.004
 new+0.003
 other+0.003
Neg logit contributions
ur-0.005
owing-0.005
beh-0.005
ares-0.005
ared-0.005
Token'm
Token ID1101
Feature activation+3.66e-03

Pos logit contributions
 big+0.356
 little+0.331
 small+0.321
 boy+0.298
 other+0.296
Neg logit contributions
owing-0.410
ur-0.398
ors-0.388
ares-0.383
rying-0.380
Token dreaming
Token ID28368
Feature activation+1.57e-01

Pos logit contributions
owing+0.011
ur+0.010
ors+0.010
ared+0.010
ares+0.010
Neg logit contributions
 big-0.009
 little-0.009
 small-0.009
 other-0.008
 boy-0.008
Token of
Token ID286
Feature activation+1.43e-01

Pos logit contributions
owing+0.440
ur+0.422
beh+0.416
rying+0.412
ors+0.409
Neg logit contributions
 big-0.428
 little-0.402
 small-0.386
 other-0.356
 new-0.349
Token a
Token ID257
Feature activation-2.38e-01

Pos logit contributions
owing+0.445
ur+0.438
ors+0.422
beh+0.416
ares+0.416
Neg logit contributions
 big-0.296
 little-0.272
 small-0.263
 boy-0.251
 other-0.236
Token big
Token ID1263
Feature activation-5.79e-01

Pos logit contributions
 big+0.255
 small+0.228
 little+0.215
 other+0.201
 boy+0.199
Neg logit contributions
ur-0.857
owing-0.831
rying-0.803
ors-0.791
ares-0.791
Token,
Token ID11
Feature activation+2.29e-02

Pos logit contributions
 big+0.951
 small+0.848
 little+0.846
 other+0.772
 boy+0.717
Neg logit contributions
owing-2.029
ur-1.982
ors-1.930
rying-1.909
ares-1.877
Token tall
Token ID7331
Feature activation-3.31e-01

Pos logit contributions
ur+0.084
owing+0.083
ares+0.080
ors+0.079
rying+0.078
Neg logit contributions
 big-0.024
 other-0.020
 little-0.020
 small-0.020
 park-0.019
Token volcano
Token ID32410
Feature activation-1.14e-01

Pos logit contributions
 big+0.523
 little+0.454
 small+0.453
 other+0.400
 boy+0.376
Neg logit contributions
owing-1.197
ur-1.171
ors-1.153
rying-1.134
ares-1.119
Token and
Token ID290
Feature activation-6.09e-02

Pos logit contributions
 big+0.305
 little+0.281
 small+0.273
 boy+0.258
 other+0.249
Neg logit contributions
owing-0.318
ur-0.311
ares-0.304
beh-0.302
ared-0.294
Token I
Token ID314
Feature activation+1.80e-01

Pos logit contributions
 big+0.123
 little+0.116
 small+0.109
 boy+0.106
 other+0.103
Neg logit contributions
ur-0.183
owing-0.180
ors-0.172
rying-0.171
beh-0.171
Token
Token ID198
Feature activation-2.47e-01

Pos logit contributions
owing+0.106
ur+0.103
rying+0.100
ors+0.100
ares+0.099
Neg logit contributions
 big-0.061
 little-0.056
 small-0.054
 boy-0.049
 other-0.049
Token
Token ID198
Feature activation-2.47e-01

Pos logit contributions
 big+0.380
 little+0.339
 small+0.316
 boy+0.298
 other+0.280
Neg logit contributions
ur-0.916
owing-0.898
ares-0.877
ors-0.866
oot-0.863
TokenIt
Token ID1026
Feature activation-1.21e-01

Pos logit contributions
 big+0.535
 little+0.486
 small+0.469
 boy+0.435
 other+0.430
Neg logit contributions
ur-0.780
owing-0.776
ares-0.743
beh-0.742
ors-0.734
Token was
Token ID373
Feature activation-3.36e-01

Pos logit contributions
 big+0.167
 little+0.144
 small+0.137
 other+0.119
 boy+0.117
Neg logit contributions
owing-0.476
ur-0.474
owed-0.459
ares-0.456
ors-0.455
Token a
Token ID257
Feature activation-2.44e-01

Pos logit contributions
 big+0.609
 little+0.551
 small+0.529
 boy+0.493
 other+0.479
Neg logit contributions
owing-1.173
ur-1.159
ares-1.110
rying-1.100
ors-1.098
Token big
Token ID1263
Feature activation-5.79e-01

Pos logit contributions
 big+0.283
 other+0.255
 little+0.239
 small+0.237
 two+0.201
Neg logit contributions
ur-0.792
owing-0.776
rying-0.735
oot-0.695
ares-0.694
Token beautiful
Token ID4950
Feature activation-3.80e-01

Pos logit contributions
 big+1.109
 little+0.988
 small+0.980
 other+0.939
 new+0.841
Neg logit contributions
owing-1.891
ur-1.828
rying-1.749
ares-1.731
ors-1.718
Token spring
Token ID6076
Feature activation-2.35e-01

Pos logit contributions
 big+0.590
 small+0.511
 other+0.497
 little+0.482
 boy+0.404
Neg logit contributions
owing-1.320
ur-1.279
rying-1.230
ors-1.211
oot-1.210
Token.
Token ID13
Feature activation+3.26e-02

Pos logit contributions
 big+0.471
 little+0.427
 small+0.414
 boy+0.374
 other+0.373
Neg logit contributions
owing-0.796
ur-0.779
ares-0.751
ors-0.750
rying-0.744
Token It
Token ID632
Feature activation+8.74e-02

Pos logit contributions
owing+0.101
ur+0.097
rying+0.095
ors+0.094
beh+0.094
Neg logit contributions
 big-0.076
 little-0.071
 small-0.068
 boy-0.063
 other-0.062
Token made
Token ID925
Feature activation-7.85e-02

Pos logit contributions
ur+0.305
owing+0.297
owed+0.295
rying+0.285
beh+0.284
Neg logit contributions
 big-0.141
 little-0.127
 small-0.121
 boy-0.111
 other-0.110
Token was
Token ID373
Feature activation-3.34e-01

Pos logit contributions
owing+0.281
ur+0.281
ares+0.267
owed+0.266
ors+0.266
Neg logit contributions
 big-0.163
 little-0.147
 small-0.145
 other-0.129
 boy-0.129
Token able
Token ID1498
Feature activation+7.10e-01

Pos logit contributions
 big+0.985
 little+0.917
 small+0.898
 other+0.837
 boy+0.820
Neg logit contributions
owing-0.835
ur-0.810
ors-0.794
ares-0.784
ared-0.768
Token to
Token ID284
Feature activation+1.93e-01

Pos logit contributions
owing+1.833
ur+1.781
ares+1.699
ors+1.697
rying+1.675
Neg logit contributions
 big-2.004
 little-1.871
 small-1.831
 boy-1.710
 other-1.708
Token catch
Token ID4929
Feature activation+7.91e-03

Pos logit contributions
owing+0.592
ur+0.578
ors+0.550
rying+0.549
ares+0.548
Neg logit contributions
 big-0.433
 little-0.399
 small-0.393
 boy-0.366
 other-0.352
Token a
Token ID257
Feature activation-2.38e-01

Pos logit contributions
owing+0.027
ur+0.027
ares+0.026
ors+0.026
rying+0.026
Neg logit contributions
 big-0.015
 little-0.014
 small-0.013
 boy-0.012
 other-0.012
Token big
Token ID1263
Feature activation-5.79e-01

Pos logit contributions
 big+0.285
 little+0.252
 small+0.251
 park+0.227
 boy+0.226
Neg logit contributions
ur-0.842
owing-0.837
ares-0.803
rying-0.799
oot-0.783
Token,
Token ID11
Feature activation+2.25e-02

Pos logit contributions
 big+0.965
 little+0.858
 small+0.854
 other+0.779
 boy+0.748
Neg logit contributions
owing-2.032
ur-2.006
ors-1.905
rying-1.902
ares-1.901
Token pretty
Token ID2495
Feature activation-4.01e-01

Pos logit contributions
ur+0.081
owing+0.081
rying+0.078
ares+0.076
beh+0.075
Neg logit contributions
 big-0.027
 little-0.025
 small-0.023
 other-0.022
 boy-0.022
Token bubble
Token ID14310
Feature activation-1.34e-01

Pos logit contributions
 big+0.626
 small+0.549
 little+0.540
 other+0.489
 boy+0.474
Neg logit contributions
owing-1.426
ur-1.421
ors-1.374
rying-1.350
ares-1.342
Token.
Token ID13
Feature activation+3.70e-02

Pos logit contributions
 big+0.321
 little+0.295
 small+0.284
 other+0.263
 boy+0.261
Neg logit contributions
owing-0.411
ur-0.398
beh-0.387
ares-0.387
ared-0.385
Token He
Token ID679
Feature activation+3.62e-02

Pos logit contributions
owing+0.122
ur+0.120
ares+0.116
ors+0.115
beh+0.114
Neg logit contributions
 big-0.077
 little-0.070
 small-0.068
 boy-0.062
 other-0.062
Token now
Token ID783
Feature activation+1.98e-01

Pos logit contributions
 big+0.390
 small+0.353
 little+0.340
 boy+0.318
 blue+0.312
Neg logit contributions
ur-0.567
beh-0.550
oot-0.541
owing-0.532
ares-0.529
Token."
Token ID526
Feature activation+1.72e-01

Pos logit contributions
owing+0.601
ur+0.585
ares+0.565
ors+0.564
ared+0.557
Neg logit contributions
 big-0.477
 little-0.441
 small-0.426
 boy-0.393
 other-0.392
Token They
Token ID1119
Feature activation+9.19e-03

Pos logit contributions
owing+0.660
ur+0.644
ors+0.626
ares+0.625
rying+0.624
Neg logit contributions
 big-0.270
 little-0.242
 small-0.230
 boy-0.203
 other-0.201
Token shared
Token ID4888
Feature activation+1.65e-01

Pos logit contributions
owing+0.029
ur+0.028
ares+0.027
ors+0.027
owed+0.027
Neg logit contributions
 big-0.020
 little-0.019
 small-0.018
 boy-0.017
 other-0.017
Token a
Token ID257
Feature activation-2.38e-01

Pos logit contributions
owing+0.491
ur+0.475
ors+0.466
owed+0.464
ares+0.461
Neg logit contributions
 big-0.327
 little-0.308
 small-0.295
 boy-0.283
 park-0.262
Token big
Token ID1263
Feature activation-5.79e-01

Pos logit contributions
 other+0.286
 little+0.283
 big+0.277
 boy+0.269
 small+0.266
Neg logit contributions
ur-0.709
owing-0.696
owed-0.670
ares-0.669
oot-0.661
Token smile
Token ID8212
Feature activation+3.59e-04

Pos logit contributions
 big+1.315
 little+1.262
 small+1.237
 other+1.209
 boy+1.119
Neg logit contributions
owing-1.545
ur-1.493
owed-1.374
ares-1.368
oot-1.351
Token and
Token ID290
Feature activation-6.59e-02

Pos logit contributions
owing+0.001
ur+0.001
ares+0.001
beh+0.001
rying+0.001
Neg logit contributions
 big-0.001
 little-0.001
 small-0.001
 boy-0.001
 other-0.001
Token ran
Token ID4966
Feature activation+3.18e-02

Pos logit contributions
 big+0.155
 little+0.144
 small+0.141
 boy+0.129
 park+0.126
Neg logit contributions
owing-0.188
ur-0.188
owed-0.180
beh-0.177
ared-0.172
Token home
Token ID1363
Feature activation+7.69e-02

Pos logit contributions
owing+0.094
ares+0.090
owed+0.090
ur+0.089
ors+0.089
Neg logit contributions
 big-0.084
 little-0.076
 small-0.074
 other-0.069
 boy-0.067
Token together
Token ID1978
Feature activation+3.69e-01

Pos logit contributions
owing+0.239
ur+0.236
ares+0.236
ors+0.230
ared+0.227
Neg logit contributions
 big-0.178
 little-0.163
 small-0.159
 other-0.143
 boy-0.141
Token he
Token ID339
Feature activation+8.76e-02

Pos logit contributions
owing+0.014
ur+0.014
ares+0.013
ors+0.013
beh+0.013
Neg logit contributions
 big-0.011
 little-0.010
 small-0.009
 boy-0.009
 other-0.009
Token was
Token ID373
Feature activation-3.40e-01

Pos logit contributions
owing+0.285
ur+0.281
ares+0.267
ors+0.267
owed+0.267
Neg logit contributions
 big-0.182
 little-0.166
 small-0.162
 boy-0.147
 other-0.146
Token chewing
Token ID36615
Feature activation+2.21e-01

Pos logit contributions
 big+0.865
 little+0.800
 small+0.783
 other+0.720
 boy+0.715
Neg logit contributions
owing-0.975
ur-0.951
ares-0.920
ors-0.920
rying-0.902
Token like
Token ID588
Feature activation+2.59e-01

Pos logit contributions
owing+0.707
ur+0.691
ares+0.665
ors+0.664
rying+0.658
Neg logit contributions
 big-0.485
 little-0.444
 small-0.431
 boy-0.394
 other-0.393
Token a
Token ID257
Feature activation-2.37e-01

Pos logit contributions
owing+0.925
ur+0.918
ors+0.874
beh+0.870
ares+0.870
Neg logit contributions
 big-0.425
 little-0.377
 small-0.366
 boy-0.335
 other-0.319
Token big
Token ID1263
Feature activation-5.79e-01

Pos logit contributions
 big+0.384
 small+0.343
 little+0.341
 other+0.326
 boy+0.325
Neg logit contributions
owing-0.763
ur-0.750
ares-0.703
owed-0.691
ared-0.690
Token boy
Token ID2933
Feature activation-4.93e-01

Pos logit contributions
 big+1.093
 little+0.979
 small+0.970
 other+0.900
 boy+0.859
Neg logit contributions
owing-1.944
ur-1.892
ares-1.799
ors-1.798
rying-1.787
Token.
Token ID13
Feature activation+3.71e-02

Pos logit contributions
 big+1.080
 little+1.018
 small+0.953
 boy+0.897
 other+0.882
Neg logit contributions
owing-1.521
ur-1.520
ares-1.513
ors-1.504
beh-1.475
Token
Token ID220
Feature activation-9.59e-02

Pos logit contributions
owing+0.122
ur+0.120
ares+0.116
ors+0.115
rying+0.114
Neg logit contributions
 big-0.077
 little-0.070
 small-0.068
 other-0.061
 boy-0.061
Token
Token ID198
Feature activation-2.48e-01

Pos logit contributions
 big+0.117
 little+0.099
 small+0.094
 boy+0.078
 other+0.078
Neg logit contributions
owing-0.399
ur-0.392
ares-0.381
ors-0.381
rying-0.378
Token
Token ID198
Feature activation-2.47e-01

Pos logit contributions
 big+0.391
 little+0.342
 small+0.323
 boy+0.301
 other+0.281
Neg logit contributions
ur-0.909
owing-0.891
ares-0.866
ors-0.858
oot-0.855
Token He
Token ID679
Feature activation+5.10e-02

Pos logit contributions
owing+0.194
ur+0.191
ares+0.183
ors+0.183
rying+0.180
Neg logit contributions
 big-0.133
 little-0.121
 small-0.118
 other-0.107
 boy-0.107
Token also
Token ID635
Feature activation-1.87e-01

Pos logit contributions
ur+0.164
owing+0.163
ors+0.156
ares+0.154
owed+0.154
Neg logit contributions
 big-0.103
 little-0.096
 small-0.092
 boy-0.084
 other-0.083
Token has
Token ID468
Feature activation-1.41e-01

Pos logit contributions
 big+0.390
 little+0.361
 small+0.346
 boy+0.320
 other+0.315
Neg logit contributions
owing-0.601
ur-0.592
ares-0.566
rying-0.563
owed-0.563
Token a
Token ID257
Feature activation-2.15e-01

Pos logit contributions
 big+0.212
 little+0.197
 small+0.183
 boy+0.182
 park+0.159
Neg logit contributions
ur-0.497
owing-0.493
beh-0.475
ors-0.470
ared-0.464
Token sle
Token ID3133
Feature activation+1.16e-01

Pos logit contributions
 big+0.165
 little+0.158
 other+0.158
 boy+0.148
 small+0.140
Neg logit contributions
ur-0.782
owing-0.759
rying-0.715
ors-0.713
ares-0.706
Tokenigh
Token ID394
Feature activation+5.59e-01

Pos logit contributions
beh+0.218
ur+0.217
rying+0.209
ares+0.200
ors+0.190
Neg logit contributions
 big-0.367
 little-0.341
 small-0.335
 other-0.321
 boy-0.319
Token and
Token ID290
Feature activation-5.46e-02

Pos logit contributions
owing+1.826
ur+1.819
ares+1.789
beh+1.773
rying+1.739
Neg logit contributions
 big-1.213
 little-1.104
 small-1.057
 boy-0.946
 other-0.938
Token re
Token ID302
Feature activation-1.45e-01

Pos logit contributions
 big+0.092
 little+0.082
 small+0.079
 boy+0.077
 park+0.071
Neg logit contributions
ur-0.188
owing-0.183
ors-0.177
beh-0.174
owed-0.173
Tokenind
Token ID521
Feature activation+2.72e-01

Pos logit contributions
 big+0.385
 little+0.361
 small+0.355
 boy+0.331
 other+0.321
Neg logit contributions
ur-0.362
ares-0.361
owing-0.351
ancing-0.336
beh-0.335
Tokeneer
Token ID28153
Feature activation+2.83e-01

Pos logit contributions
owing+0.633
ur+0.629
ares+0.620
rying+0.592
beh+0.592
Neg logit contributions
 big-0.822
 little-0.774
 small-0.752
 boy-0.720
 other-0.720
Token who
Token ID508
Feature activation+8.91e-02

Pos logit contributions
owing+0.902
ur+0.888
ares+0.876
beh+0.858
rying+0.853
Neg logit contributions
 big-0.628
 little-0.575
 small-0.555
 other-0.509
 boy-0.502
Token the
Token ID262
Feature activation-1.55e-01

Pos logit contributions
owing+0.893
ur+0.884
ors+0.839
rying+0.838
beh+0.837
Neg logit contributions
 big-0.518
 little-0.470
 small-0.455
 boy-0.421
 other-0.410
Token tunnel
Token ID13275
Feature activation-1.96e-01

Pos logit contributions
 big+0.211
 small+0.184
 little+0.180
 other+0.145
 boy+0.142
Neg logit contributions
owing-0.546
ur-0.518
rying-0.515
beh-0.500
ares-0.498
Token was
Token ID373
Feature activation-3.12e-01

Pos logit contributions
 big+0.346
 little+0.307
 small+0.293
 boy+0.262
 other+0.261
Neg logit contributions
owing-0.718
ur-0.707
ares-0.688
beh-0.683
ors-0.676
Token never
Token ID1239
Feature activation+9.23e-02

Pos logit contributions
 big+0.731
 little+0.671
 small+0.655
 other+0.600
 boy+0.600
Neg logit contributions
owing-0.955
ur-0.931
ares-0.896
ors-0.895
beh-0.885
Token-
Token ID12
Feature activation+1.48e-01

Pos logit contributions
owing+0.277
ur+0.271
ors+0.262
ares+0.262
beh+0.258
Neg logit contributions
 big-0.224
 little-0.207
 small-0.201
 other-0.185
 boy-0.184
Tokenending
Token ID1571
Feature activation+6.73e-01

Pos logit contributions
owing+0.301
ur+0.289
ares+0.286
owed+0.272
istent+0.269
Neg logit contributions
 big-0.488
 little-0.460
 small-0.453
 other-0.427
 boy-0.424
Token.
Token ID13
Feature activation+3.50e-02

Pos logit contributions
owing+1.931
ur+1.887
ares+1.823
ared+1.793
beh+1.793
Neg logit contributions
 big-1.752
 little-1.612
 small-1.579
 other-1.467
 boy-1.446
Token It
Token ID632
Feature activation+8.82e-02

Pos logit contributions
owing+0.110
ur+0.108
ares+0.104
ors+0.103
rying+0.102
Neg logit contributions
 big-0.078
 little-0.071
 small-0.069
 boy-0.064
 other-0.063
Token was
Token ID373
Feature activation-3.28e-01

Pos logit contributions
ur+0.322
owing+0.317
owed+0.309
beh+0.306
rying+0.305
Neg logit contributions
 big-0.137
 little-0.118
 small-0.116
 other-0.103
 new-0.099
Token pitch
Token ID7078
Feature activation-1.44e-01

Pos logit contributions
 big+0.711
 little+0.657
 small+0.632
 boy+0.594
 other+0.585
Neg logit contributions
owing-1.034
ur-1.020
ares-0.968
rying-0.967
ors-0.964
Token black
Token ID2042
Feature activation-3.12e-01

Pos logit contributions
 big+0.354
 little+0.324
 small+0.317
 boy+0.290
 other+0.290
Neg logit contributions
owing-0.433
ur-0.421
ares-0.409
ors-0.404
beh-0.403
Token branch
Token ID8478
Feature activation-6.92e-02

Pos logit contributions
 big+0.389
 boy+0.363
 little+0.354
 small+0.347
 other+0.327
Neg logit contributions
owing-0.731
ur-0.721
rying-0.675
ors-0.667
oot-0.665
Token.
Token ID13
Feature activation+5.07e-02

Pos logit contributions
 big+0.139
 little+0.122
 small+0.119
 other+0.105
 park+0.104
Neg logit contributions
beh-0.236
owing-0.232
ares-0.232
ur-0.230
ors-0.228
Token The
Token ID383
Feature activation-3.32e-02

Pos logit contributions
owing+0.155
ur+0.152
ares+0.146
ors+0.146
rying+0.144
Neg logit contributions
 big-0.117
 little-0.108
 small-0.105
 boy-0.096
 other-0.096
Token bird
Token ID6512
Feature activation-3.26e-01

Pos logit contributions
 big+0.044
 small+0.038
 little+0.035
 lot+0.033
 boy+0.032
Neg logit contributions
owing-0.103
ur-0.098
oot-0.094
rying-0.093
ring-0.093
Token ch
Token ID442
Feature activation-2.20e-01

Pos logit contributions
 big+0.662
 little+0.597
 small+0.582
 boy+0.535
 other+0.533
Neg logit contributions
owing-1.084
ur-1.068
owed-1.024
ors-1.017
ared-1.011
Tokenir
Token ID343
Feature activation+5.67e-01

Pos logit contributions
 big+0.781
 little+0.751
 small+0.737
 other+0.678
 boy+0.671
Neg logit contributions
owing-0.361
rying-0.351
ors-0.335
beh-0.326
ur-0.324
Tokenped
Token ID9124
Feature activation+4.59e-01

Pos logit contributions
owing+1.016
ur+0.955
rying+0.917
ares+0.914
ors+0.903
Neg logit contributions
 big-2.048
 little-1.970
 small-1.910
 other-1.827
 boy-1.787
Token happily
Token ID18177
Feature activation+1.62e-01

Pos logit contributions
owing+1.494
ur+1.437
ors+1.420
ares+1.419
beh+1.417
Neg logit contributions
 big-1.038
 little-0.956
 small-0.926
 boy-0.820
 other-0.817
Token and
Token ID290
Feature activation-6.02e-02

Pos logit contributions
ors+0.555
beh+0.552
ares+0.551
owing+0.550
ur+0.546
Neg logit contributions
 big-0.317
 little-0.293
 small-0.277
 other-0.242
 boy-0.233
Token flew
Token ID13112
Feature activation+8.91e-02

Pos logit contributions
 big+0.138
 little+0.127
 small+0.124
 boy+0.114
 other+0.113
Neg logit contributions
owing-0.182
ur-0.181
ors-0.171
beh-0.171
owed-0.170
Token away
Token ID1497
Feature activation+3.43e-01

Pos logit contributions
owing+0.245
ors+0.233
ares+0.232
beh+0.231
istent+0.223
Neg logit contributions
 big-0.264
 little-0.239
 small-0.237
 other-0.217
 new-0.217
Token happy
Token ID3772
Feature activation-2.85e-01

Pos logit contributions
owing+0.305
ur+0.300
beh+0.284
owed+0.284
ares+0.284
Neg logit contributions
 big-0.133
 little-0.123
 boy-0.118
 other-0.114
 small-0.112
Token that
Token ID326
Feature activation+1.52e-01

Pos logit contributions
 big+0.593
 little+0.556
 small+0.504
 boy+0.475
 new+0.473
Neg logit contributions
ares-0.971
owing-0.958
beh-0.949
ur-0.937
ared-0.936
Token her
Token ID607
Feature activation+1.22e-01

Pos logit contributions
owing+0.432
ur+0.422
ors+0.402
ares+0.402
beh+0.398
Neg logit contributions
 big-0.388
 little-0.360
 small-0.351
 boy-0.326
 other-0.324
Token dad
Token ID9955
Feature activation-1.74e-01

Pos logit contributions
owing+0.424
ur+0.383
owed+0.383
ared+0.382
oot+0.378
Neg logit contributions
 big-0.172
 small-0.152
 little-0.144
 other-0.141
 boy-0.137
Token was
Token ID373
Feature activation-3.16e-01

Pos logit contributions
 big+0.300
 little+0.266
 small+0.258
 boy+0.228
 other+0.227
Neg logit contributions
owing-0.636
ur-0.623
ors-0.601
ares-0.600
rying-0.596
Token able
Token ID1498
Feature activation+7.27e-01

Pos logit contributions
 big+0.955
 little+0.886
 small+0.871
 other+0.810
 new+0.788
Neg logit contributions
owing-0.773
ur-0.759
ors-0.749
ares-0.738
ared-0.725
Token to
Token ID284
Feature activation+2.12e-01

Pos logit contributions
owing+1.969
ur+1.914
ares+1.877
ors+1.866
owed+1.821
Neg logit contributions
 big-2.020
 little-1.871
 small-1.833
 other-1.699
 boy-1.677
Token help
Token ID1037
Feature activation+4.39e-02

Pos logit contributions
owing+0.662
ur+0.646
ares+0.620
ors+0.619
rying+0.614
Neg logit contributions
 big-0.481
 little-0.442
 small-0.430
 boy-0.396
 other-0.393
Token fix
Token ID4259
Feature activation+1.45e-01

Pos logit contributions
owing+0.142
ur+0.141
ares+0.138
ared+0.136
beh+0.136
Neg logit contributions
 big-0.099
 little-0.092
 small-0.087
 other-0.083
 boy-0.078
Token the
Token ID262
Feature activation-1.50e-01

Pos logit contributions
owing+0.521
ur+0.506
ors+0.497
ares+0.492
rying+0.489
Neg logit contributions
 big-0.252
 little-0.226
 small-0.217
 boy-0.196
 other-0.188
Token pigeon
Token ID46387
Feature activation-4.58e-02

Pos logit contributions
 big+0.287
 small+0.256
 little+0.252
 lot+0.244
 other+0.229
Neg logit contributions
owing-0.403
ared-0.382
rying-0.364
ring-0.357
beh-0.354
Token the
Token ID262
Feature activation-1.45e-01

Pos logit contributions
 big+0.133
 little+0.122
 small+0.119
 boy+0.108
 other+0.108
Neg logit contributions
owing-0.186
ur-0.180
ares-0.175
beh-0.173
ors-0.173
Token printer
Token ID20632
Feature activation-8.02e-02

Pos logit contributions
 big+0.255
 small+0.226
 little+0.211
 other+0.203
 park+0.200
Neg logit contributions
owing-0.407
ring-0.395
ors-0.382
owed-0.380
rying-0.375
Token began
Token ID2540
Feature activation+1.20e-01

Pos logit contributions
 big+0.170
 little+0.156
 small+0.151
 boy+0.138
 other+0.137
Neg logit contributions
owing-0.260
ur-0.254
ares-0.245
ors-0.245
rying-0.242
Token to
Token ID284
Feature activation+2.20e-01

Pos logit contributions
owing+0.336
ur+0.326
ares+0.319
ors+0.315
beh+0.312
Neg logit contributions
 big-0.323
 little-0.297
 small-0.293
 other-0.264
 new-0.263
Token wh
Token ID348
Feature activation-2.53e-02

Pos logit contributions
owing+0.654
ur+0.636
rying+0.620
ares+0.614
owed+0.607
Neg logit contributions
 big-0.482
 little-0.449
 small-0.432
 boy-0.418
 other-0.412
Tokenir
Token ID343
Feature activation+5.64e-01

Pos logit contributions
 big+0.079
 small+0.073
 little+0.072
 other+0.068
 park+0.068
Neg logit contributions
ur-0.054
owing-0.053
beh-0.049
ors-0.049
owed-0.048
Tokenr
Token ID81
Feature activation+5.70e-01

Pos logit contributions
owing+1.134
ur+1.118
rying+1.071
ares+1.056
beh+1.017
Neg logit contributions
 big-1.883
 little-1.808
 small-1.728
 other-1.641
 new-1.577
Token and
Token ID290
Feature activation-5.78e-02

Pos logit contributions
owing+1.860
ur+1.841
beh+1.774
ares+1.765
rying+1.756
Neg logit contributions
 big-1.287
 little-1.177
 small-1.139
 other-1.003
 new-0.974
Token print
Token ID3601
Feature activation-2.65e-02

Pos logit contributions
 big+0.135
 little+0.123
 small+0.121
 other+0.111
 boy+0.110
Neg logit contributions
owing-0.181
ur-0.175
ares-0.170
ors-0.170
ared-0.168
Token the
Token ID262
Feature activation-1.45e-01

Pos logit contributions
 big+0.057
 little+0.052
 small+0.051
 boy+0.046
 other+0.046
Neg logit contributions
owing-0.086
ur-0.084
ares-0.081
ors-0.081
rying-0.080
Token mint
Token ID21043
Feature activation-9.56e-02

Pos logit contributions
 big+0.245
 small+0.214
 little+0.208
 park+0.190
 boy+0.187
Neg logit contributions
owing-0.452
ors-0.430
rying-0.428
ring-0.424
ur-0.424
Token let
Token ID1309
Feature activation+9.09e-02

Pos logit contributions
owing+0.130
ur+0.123
ors+0.122
ares+0.120
rying+0.120
Neg logit contributions
 big-0.106
 little-0.099
 small-0.095
 boy-0.088
 other-0.087
Token me
Token ID502
Feature activation-5.35e-02

Pos logit contributions
owing+0.302
ur+0.298
ors+0.289
ares+0.288
beh+0.283
Neg logit contributions
 big-0.183
 little-0.165
 small-0.163
 boy-0.146
 other-0.142
Token show
Token ID905
Feature activation-9.50e-02

Pos logit contributions
 big+0.116
 little+0.106
 small+0.101
 other+0.091
 boy+0.089
Neg logit contributions
owing-0.175
ur-0.170
ors-0.168
beh-0.167
ared-0.167
Token you
Token ID345
Feature activation+2.25e-01

Pos logit contributions
 big+0.217
 little+0.202
 other+0.190
 small+0.190
 boy+0.174
Neg logit contributions
owing-0.319
rying-0.300
ur-0.295
beh-0.290
ared-0.290
Token how
Token ID703
Feature activation+3.77e-01

Pos logit contributions
owing+0.685
ur+0.665
ares+0.643
beh+0.639
ared+0.638
Neg logit contributions
 big-0.563
 little-0.530
 small-0.509
 other-0.482
 new-0.459
Token to
Token ID284
Feature activation+2.25e-01

Pos logit contributions
owing+1.039
ur+1.012
ares+0.967
ors+0.966
rying+0.955
Neg logit contributions
 big-0.997
 little-0.927
 small-0.906
 boy-0.843
 other-0.841
Token polish
Token ID25245
Feature activation+6.91e-02

Pos logit contributions
owing+0.669
ur+0.663
ors+0.627
owed+0.623
rying+0.619
Neg logit contributions
 big-0.503
 little-0.465
 small-0.456
 boy-0.440
 other-0.410
Token it
Token ID340
Feature activation+1.10e-01

Pos logit contributions
owing+0.216
ur+0.211
ares+0.201
beh+0.200
ared+0.200
Neg logit contributions
 big-0.163
 little-0.149
 small-0.146
 other-0.136
 boy-0.132
Token.
Token ID13
Feature activation+6.18e-02

Pos logit contributions
owing+0.340
ur+0.329
beh+0.317
ared+0.315
ares+0.311
Neg logit contributions
 big-0.274
 little-0.251
 small-0.246
 other-0.229
 boy-0.219
Token It
Token ID632
Feature activation+1.07e-01

Pos logit contributions
owing+0.182
ur+0.171
rying+0.171
ors+0.167
ared+0.167
Neg logit contributions
 big-0.155
 little-0.145
 small-0.141
 boy-0.131
 other-0.130
Token likes
Token ID7832
Feature activation-1.44e-01

Pos logit contributions
owing+0.382
ur+0.377
ares+0.366
ors+0.364
beh+0.360
Neg logit contributions
 big-0.187
 little-0.170
 small-0.162
 boy-0.145
 other-0.143
Token grabbed
Token ID13176
Feature activation+1.18e-01

Pos logit contributions
 big+0.116
 little+0.108
 small+0.104
 other+0.097
 boy+0.096
Neg logit contributions
owing-0.141
ur-0.141
ors-0.133
rying-0.133
owed-0.133
Token the
Token ID262
Feature activation-1.35e-01

Pos logit contributions
owing+0.415
ur+0.413
ares+0.399
ors+0.395
beh+0.391
Neg logit contributions
 big-0.209
 little-0.188
 small-0.180
 boy-0.164
 other-0.160
Token muff
Token ID27563
Feature activation-6.97e-02

Pos logit contributions
 big+0.292
 park+0.261
 little+0.261
 small+0.259
 boy+0.242
Neg logit contributions
owing-0.362
ur-0.336
ared-0.333
ares-0.332
ring-0.327
Tokenin
Token ID259
Feature activation+2.04e-01

Pos logit contributions
 big+0.175
 small+0.157
 little+0.154
 other+0.150
 boy+0.142
Neg logit contributions
ur-0.197
owing-0.194
istent-0.191
ors-0.188
ancing-0.183
Token with
Token ID351
Feature activation+1.12e-01

Pos logit contributions
owing+0.669
ur+0.659
ares+0.648
ors+0.643
beh+0.638
Neg logit contributions
 big-0.444
 little-0.398
 small-0.389
 other-0.354
 boy-0.348
Token its
Token ID663
Feature activation+2.16e-01

Pos logit contributions
ur+0.284
owing+0.284
ares+0.272
ors+0.266
ared+0.264
Neg logit contributions
 big-0.302
 little-0.285
 small-0.277
 boy-0.269
 other-0.259
Token claws
Token ID28421
Feature activation+2.47e-01

Pos logit contributions
owing+0.655
ur+0.641
ared+0.623
ares+0.609
owed+0.609
Neg logit contributions
 big-0.441
 little-0.415
 boy-0.407
 park-0.399
 small-0.397
Token.
Token ID13
Feature activation+6.78e-02

Pos logit contributions
beh+0.858
ur+0.856
owing+0.847
ors+0.831
ares+0.821
Neg logit contributions
 big-0.495
 little-0.446
 small-0.434
 other-0.371
 new-0.355
Token Lily
Token ID20037
Feature activation-1.84e-02

Pos logit contributions
owing+0.226
ur+0.221
ares+0.213
ors+0.213
rying+0.211
Neg logit contributions
 big-0.141
 little-0.128
 small-0.124
 boy-0.113
 other-0.113
Token was
Token ID373
Feature activation-2.99e-01

Pos logit contributions
 big+0.033
 small+0.029
 little+0.029
 new+0.026
 boy+0.026
Neg logit contributions
owing-0.063
ur-0.063
owed-0.062
ared-0.060
ors-0.060
Token scared
Token ID12008
Feature activation-5.36e-02

Pos logit contributions
 big+0.566
 little+0.517
 small+0.494
 boy+0.461
 other+0.451
Neg logit contributions
owing-1.039
ur-1.014
ares-0.973
beh-0.966
rying-0.966
Token mirror
Token ID10162
Feature activation-5.13e-02

Pos logit contributions
 big+0.278
 little+0.246
 small+0.232
 boy+0.198
 blue+0.195
Neg logit contributions
beh-0.490
ares-0.486
ors-0.482
owing-0.481
rying-0.478
Token so
Token ID523
Feature activation+9.68e-02

Pos logit contributions
 big+0.111
 little+0.099
 small+0.092
 boy+0.083
 new+0.082
Neg logit contributions
ares-0.169
beh-0.167
ur-0.166
ors-0.166
owing-0.165
Token she
Token ID673
Feature activation+1.53e-01

Pos logit contributions
owing+0.284
ur+0.277
ors+0.265
ares+0.264
owed+0.262
Neg logit contributions
 big-0.236
 little-0.218
 small-0.213
 boy-0.198
 other-0.197
Token could
Token ID714
Feature activation+1.30e-01

Pos logit contributions
owing+0.451
ur+0.442
ors+0.423
ares+0.422
rying+0.418
Neg logit contributions
 big-0.373
 little-0.344
 small-0.337
 other-0.310
 boy-0.310
Token see
Token ID766
Feature activation+4.40e-02

Pos logit contributions
owing+0.426
ur+0.410
ares+0.405
ors+0.404
beh+0.403
Neg logit contributions
 big-0.289
 little-0.261
 small-0.251
 other-0.228
 boy-0.219
Token how
Token ID703
Feature activation+3.78e-01

Pos logit contributions
owing+0.134
ur+0.131
ors+0.126
ares+0.126
rying+0.124
Neg logit contributions
 big-0.101
 little-0.093
 small-0.090
 boy-0.084
 other-0.082
Token pretty
Token ID2495
Feature activation-3.78e-01

Pos logit contributions
owing+1.477
ur+1.461
beh+1.412
ors+1.402
owed+1.397
Neg logit contributions
 big-0.478
 little-0.420
 small-0.392
 boy-0.371
 park-0.354
Token she
Token ID673
Feature activation+1.54e-01

Pos logit contributions
 big+0.850
 little+0.776
 small+0.751
 other+0.700
 boy+0.687
Neg logit contributions
owing-1.221
ur-1.199
ares-1.149
beh-1.140
ared-1.138
Token looked
Token ID3114
Feature activation-9.66e-02

Pos logit contributions
owing+0.547
ur+0.535
owed+0.526
ors+0.519
beh+0.513
Neg logit contributions
 big-0.263
 little-0.235
 small-0.230
 other-0.198
 boy-0.198
Token with
Token ID351
Feature activation+1.10e-01

Pos logit contributions
 big+0.224
 little+0.203
 small+0.196
 new+0.178
 other+0.174
Neg logit contributions
owing-0.314
ur-0.313
beh-0.307
ares-0.303
ared-0.302
Token the
Token ID262
Feature activation-1.39e-01

Pos logit contributions
owing+0.351
ur+0.345
ares+0.332
ors+0.331
beh+0.326
Neg logit contributions
 big-0.227
 little-0.208
 small-0.202
 boy-0.191
 other-0.183
Token are
Token ID389
Feature activation+3.42e-02

Pos logit contributions
owing+0.653
ur+0.621
owed+0.595
ared+0.591
beh+0.587
Neg logit contributions
 big-0.566
 little-0.524
 small-0.521
 boy-0.480
 other-0.476
Token,
Token ID11
Feature activation+4.89e-02

Pos logit contributions
owing+0.122
ur+0.120
rying+0.115
beh+0.114
owed+0.114
Neg logit contributions
 big-0.059
 little-0.054
 small-0.052
 boy-0.048
 other-0.046
Token my
Token ID616
Feature activation+1.19e-01

Pos logit contributions
owing+0.145
ur+0.145
ares+0.140
ors+0.139
rying+0.137
Neg logit contributions
 big-0.107
 small-0.095
 little-0.093
 other-0.086
 boy-0.085
Token little
Token ID1310
Feature activation-5.13e-01

Pos logit contributions
owing+0.438
ur+0.419
owed+0.413
rying+0.402
ors+0.390
Neg logit contributions
 big-0.161
 small-0.138
 other-0.132
 little-0.114
 boy-0.112
Token superhero
Token ID17343
Feature activation-8.70e-02

Pos logit contributions
 big+0.711
 little+0.590
 small+0.582
 other+0.497
 boy+0.463
Neg logit contributions
owing-2.034
ur-1.976
rying-1.941
ors-1.915
ares-1.903
Token."
Token ID526
Feature activation+1.94e-01

Pos logit contributions
 big+0.228
 little+0.211
 small+0.207
 boy+0.192
 other+0.192
Neg logit contributions
owing-0.241
ur-0.234
ares-0.224
ors-0.224
rying-0.221
Token<|endoftext|>
Token ID50256
Feature activation-1.77e-01

Pos logit contributions
owing+0.693
ur+0.685
ares+0.664
ors+0.662
owed+0.655
Neg logit contributions
 big-0.345
 little-0.305
 small-0.298
 boy-0.265
 other-0.264
TokenOnce
Token ID7454
Feature activation-4.90e-02

Pos logit contributions
 big+0.283
 little+0.263
 small+0.252
 boy+0.229
 other+0.214
Neg logit contributions
owing-0.606
ur-0.588
ors-0.573
ares-0.572
owed-0.566
Token upon
Token ID2402
Feature activation+1.53e-01

Pos logit contributions
 big+0.125
 little+0.116
 small+0.113
 boy+0.106
 other+0.105
Neg logit contributions
owing-0.135
ur-0.131
ares-0.127
ors-0.126
ared-0.124
Token a
Token ID257
Feature activation-2.08e-01

Pos logit contributions
owing+0.478
ur+0.462
owed+0.462
ares+0.444
beh+0.438
Neg logit contributions
 big-0.241
 small-0.219
 boy-0.216
 little-0.215
 other-0.195
Token time
Token ID640
Feature activation-2.83e-01

Pos logit contributions
 big+0.266
 small+0.228
 little+0.225
 boy+0.220
 other+0.219
Neg logit contributions
owing-0.808
ur-0.778
ared-0.765
ares-0.762
owed-0.756
Token Tell
Token ID14026
Feature activation+3.18e-01

Pos logit contributions
owing+0.088
ur+0.084
ors+0.082
ares+0.082
rying+0.081
Neg logit contributions
 big-0.094
 little-0.089
 small-0.087
 boy-0.082
 other-0.080
Token us
Token ID514
Feature activation+2.18e-01

Pos logit contributions
owing+0.973
ur+0.956
ors+0.919
ares+0.911
beh+0.902
Neg logit contributions
 big-0.715
 little-0.654
 small-0.642
 boy-0.601
 other-0.576
Token more
Token ID517
Feature activation-5.45e-02

Pos logit contributions
owing+0.716
ur+0.694
ares+0.680
ors+0.673
ared+0.669
Neg logit contributions
 big-0.471
 little-0.432
 small-0.416
 other-0.383
 boy-0.372
Token.
Token ID13
Feature activation+3.61e-02

Pos logit contributions
 big+0.104
 little+0.094
 small+0.091
 boy+0.084
 other+0.082
Neg logit contributions
owing-0.187
ur-0.183
ares-0.176
ors-0.176
beh-0.175
Token We
Token ID775
Feature activation+2.40e-01

Pos logit contributions
owing+0.097
ur+0.092
ors+0.090
rying+0.090
ares+0.089
Neg logit contributions
 big-0.098
 little-0.093
 small-0.090
 boy-0.085
 other-0.084
Token like
Token ID588
Feature activation+2.62e-01

Pos logit contributions
owing+0.757
ur+0.741
ares+0.709
ors+0.706
rying+0.701
Neg logit contributions
 big-0.534
 little-0.490
 small-0.478
 boy-0.437
 other-0.434
Token the
Token ID262
Feature activation-1.63e-01

Pos logit contributions
owing+0.755
ur+0.743
ors+0.714
beh+0.703
ares+0.701
Neg logit contributions
 big-0.615
 little-0.572
 small-0.554
 boy-0.526
 other-0.508
Token statues
Token ID25827
Feature activation+8.24e-02

Pos logit contributions
 big+0.237
 little+0.216
 small+0.214
 boy+0.179
 other+0.171
Neg logit contributions
owing-0.552
ur-0.526
rying-0.520
ors-0.508
beh-0.506
Token.
Token ID13
Feature activation+3.98e-02

Pos logit contributions
owing+0.262
ur+0.262
ares+0.250
beh+0.250
rying+0.249
Neg logit contributions
 big-0.189
 little-0.169
 small-0.166
 other-0.153
 boy-0.150
Token They
Token ID1119
Feature activation+3.72e-03

Pos logit contributions
owing+0.121
ur+0.115
ors+0.113
rying+0.113
ared+0.112
Neg logit contributions
 big-0.096
 little-0.089
 small-0.087
 boy-0.080
 other-0.079
Token are
Token ID389
Feature activation+1.12e-02

Pos logit contributions
owing+0.011
ur+0.011
ors+0.011
ares+0.011
owed+0.011
Neg logit contributions
 big-0.008
 little-0.008
 small-0.008
 boy-0.007
 other-0.007
Token poison
Token ID8764
Feature activation+3.97e-02

Pos logit contributions
 big+0.039
 little+0.036
 small+0.036
 boy+0.031
 pretty+0.031
Neg logit contributions
owing-0.051
ur-0.050
beh-0.047
rying-0.046
ares-0.046
Token had
Token ID550
Feature activation-1.87e-01

Pos logit contributions
owing+0.142
ur+0.139
ors+0.135
owed+0.135
ares+0.134
Neg logit contributions
 big-0.068
 little-0.060
 small-0.059
 other-0.051
 boy-0.051
Token damaged
Token ID9694
Feature activation+1.39e-01

Pos logit contributions
 big+0.428
 little+0.396
 small+0.385
 boy+0.363
 other+0.352
Neg logit contributions
owing-0.562
ur-0.557
ors-0.529
ares-0.528
ared-0.526
Token his
Token ID465
Feature activation+1.77e-02

Pos logit contributions
owing+0.471
ur+0.461
ors+0.445
ares+0.445
rying+0.440
Neg logit contributions
 big-0.276
 little-0.250
 small-0.242
 boy-0.219
 other-0.218
Token body
Token ID1767
Feature activation-1.47e-01

Pos logit contributions
owing+0.055
ur+0.050
owed+0.050
ared+0.049
ors+0.048
Neg logit contributions
 big-0.036
 small-0.032
 little-0.032
 boy-0.030
 park-0.030
Token.
Token ID13
Feature activation+6.12e-02

Pos logit contributions
 big+0.293
 little+0.264
 small+0.256
 other+0.230
 boy+0.224
Neg logit contributions
owing-0.504
ur-0.500
ares-0.486
beh-0.480
ors-0.478
Token He
Token ID679
Feature activation+5.66e-02

Pos logit contributions
owing+0.172
ur+0.169
ares+0.167
ors+0.162
ared+0.161
Neg logit contributions
 big-0.149
 little-0.138
 small-0.135
 other-0.126
 boy-0.125
Token did
Token ID750
Feature activation-7.51e-02

Pos logit contributions
ur+0.183
owing+0.182
ors+0.179
ared+0.177
owed+0.177
Neg logit contributions
 big-0.106
 little-0.096
 small-0.096
 new-0.086
 boy-0.083
Token not
Token ID407
Feature activation+5.56e-02

Pos logit contributions
 big+0.153
 little+0.134
 small+0.131
 other+0.119
 new+0.115
Neg logit contributions
owing-0.270
ur-0.261
rying-0.252
ors-0.251
beh-0.249
Token get
Token ID651
Feature activation+8.88e-02

Pos logit contributions
owing+0.162
ur+0.159
ors+0.158
ares+0.155
rying+0.153
Neg logit contributions
 big-0.143
 little-0.131
 small-0.126
 other-0.117
 boy-0.116
Token better
Token ID1365
Feature activation+4.21e-03

Pos logit contributions
owing+0.285
ur+0.274
ors+0.269
owed+0.267
ares+0.266
Neg logit contributions
 big-0.211
 little-0.191
 small-0.188
 other-0.172
 boy-0.165
Token swing
Token ID9628
Feature activation-1.63e-01

Pos logit contributions
 big+0.257
 small+0.225
 little+0.220
 boy+0.191
 new+0.183
Neg logit contributions
owing-0.562
ur-0.543
rying-0.534
ors-0.525
beh-0.523
Token went
Token ID1816
Feature activation-1.43e-01

Pos logit contributions
 big+0.359
 little+0.323
 small+0.314
 other+0.290
 boy+0.285
Neg logit contributions
owing-0.532
ur-0.519
ares-0.505
beh-0.501
rying-0.500
Token even
Token ID772
Feature activation+8.80e-02

Pos logit contributions
 big+0.385
 little+0.343
 small+0.342
 new+0.311
 other+0.311
Neg logit contributions
owing-0.422
ur-0.398
owed-0.394
ares-0.392
ared-0.389
Token higher
Token ID2440
Feature activation+2.48e-01

Pos logit contributions
owing+0.219
ur+0.213
ares+0.202
ors+0.201
rying+0.200
Neg logit contributions
 big-0.255
 little-0.239
 small-0.233
 boy-0.219
 other-0.218
Token.
Token ID13
Feature activation+3.24e-02

Pos logit contributions
owing+0.768
ur+0.760
ares+0.733
beh+0.726
owed+0.719
Neg logit contributions
 big-0.594
 little-0.543
 small-0.531
 other-0.489
 boy-0.483
Token
Token ID220
Feature activation-9.64e-02

Pos logit contributions
owing+0.105
ur+0.103
ares+0.099
ors+0.099
rying+0.097
Neg logit contributions
 big-0.070
 little-0.063
 small-0.062
 boy-0.056
 other-0.056
Token
Token ID198
Feature activation-2.47e-01

Pos logit contributions
 big+0.112
 little+0.093
 small+0.088
 other+0.071
 boy+0.070
Neg logit contributions
owing-0.409
ur-0.401
ares-0.390
ors-0.390
rying-0.389
Token
Token ID198
Feature activation-2.46e-01

Pos logit contributions
 big+0.377
 little+0.331
 small+0.312
 boy+0.289
 other+0.269
Neg logit contributions
ur-0.922
owing-0.910
ares-0.884
ors-0.872
oot-0.869
TokenSam
Token ID16305
Feature activation-5.82e-02

Pos logit contributions
 big+0.572
 little+0.522
 small+0.507
 boy+0.475
 other+0.464
Neg logit contributions
ur-0.737
owing-0.728
beh-0.700
ares-0.696
ors-0.686
Token was
Token ID373
Feature activation-3.24e-01

Pos logit contributions
 big+0.119
 little+0.106
 small+0.105
 boy+0.095
 other+0.094
Neg logit contributions
owing-0.193
ur-0.189
ors-0.182
owed-0.181
ared-0.181
Token so
Token ID523
Feature activation+7.63e-02

Pos logit contributions
 big+0.753
 little+0.696
 small+0.676
 boy+0.633
 other+0.624
Neg logit contributions
owing-0.983
ur-0.961
ares-0.913
rying-0.908
beh-0.907
Token a
Token ID257
Feature activation-2.10e-01

Pos logit contributions
ur+0.366
owing+0.362
ares+0.348
ared+0.347
ors+0.340
Neg logit contributions
 big-0.163
 little-0.157
 boy-0.151
 small-0.141
 park-0.137
Token cre
Token ID1126
Feature activation+2.28e-02

Pos logit contributions
 big+0.264
 other+0.259
 little+0.250
 boy+0.245
 park+0.243
Neg logit contributions
owing-0.717
ur-0.699
ares-0.680
owed-0.659
ared-0.657
Tokenak
Token ID461
Feature activation+1.69e-01

Pos logit contributions
ur+0.066
owing+0.065
ors+0.063
ares+0.062
owed+0.062
Neg logit contributions
 big-0.055
 small-0.050
 little-0.049
 boy-0.044
 other-0.044
Token.
Token ID13
Feature activation+6.23e-02

Pos logit contributions
owing+0.545
beh+0.536
ur+0.533
ors+0.523
ares+0.522
Neg logit contributions
 big-0.383
 little-0.347
 small-0.334
 boy-0.289
 other-0.289
Token Ben
Token ID3932
Feature activation+6.87e-02

Pos logit contributions
owing+0.183
ur+0.181
ares+0.174
ors+0.172
ared+0.170
Neg logit contributions
 big-0.150
 little-0.138
 small-0.134
 other-0.125
 boy-0.125
Token went
Token ID1816
Feature activation-1.22e-01

Pos logit contributions
ur+0.242
owing+0.240
owed+0.234
ared+0.228
ors+0.227
Neg logit contributions
 big-0.118
 little-0.101
 small-0.101
 other-0.094
 boy-0.092
Token inside
Token ID2641
Feature activation+2.46e-01

Pos logit contributions
 big+0.332
 little+0.299
 small+0.294
 new+0.268
 other+0.265
Neg logit contributions
owing-0.350
ors-0.343
ares-0.340
beh-0.339
ared-0.335
Token and
Token ID290
Feature activation-4.83e-02

Pos logit contributions
owing+0.848
ur+0.831
ares+0.804
ors+0.803
beh+0.797
Neg logit contributions
 big-0.482
 little-0.437
 small-0.422
 boy-0.379
 other-0.378
Token there
Token ID612
Feature activation+5.01e-02

Pos logit contributions
 big+0.097
 little+0.087
 small+0.085
 other+0.077
 boy+0.077
Neg logit contributions
owing-0.163
ur-0.161
ors-0.153
rying-0.153
owed-0.153
Token was
Token ID373
Feature activation-3.00e-01

Pos logit contributions
owing+0.200
ur+0.196
owed+0.190
ors+0.188
ared+0.187
Neg logit contributions
 big-0.067
 little-0.058
 small-0.055
 boy-0.047
 other-0.046
Token a
Token ID257
Feature activation-2.10e-01

Pos logit contributions
 big+0.494
 little+0.461
 small+0.431
 boy+0.421
 other+0.389
Neg logit contributions
ur-1.030
owing-1.023
owed-0.975
rying-0.955
ors-0.948
Token made
Token ID925
Feature activation-5.00e-02

Pos logit contributions
ur+0.062
owing+0.060
owed+0.060
ared+0.057
icked+0.056
Neg logit contributions
 big-0.048
 little-0.046
 small-0.044
 new-0.042
 boy-0.040
Token him
Token ID683
Feature activation+4.59e-01

Pos logit contributions
 big+0.111
 little+0.104
 small+0.101
 boy+0.095
 park+0.095
Neg logit contributions
owing-0.141
ur-0.140
ares-0.137
ors-0.134
owed-0.132
Token happy
Token ID3772
Feature activation-2.75e-01

Pos logit contributions
owing+1.479
ur+1.429
owed+1.370
ares+1.368
beh+1.364
Neg logit contributions
 big-0.900
 little-0.852
 small-0.816
 boy-0.763
 other-0.763
Token.
Token ID13
Feature activation+6.62e-02

Pos logit contributions
 big+0.641
 little+0.590
 small+0.574
 boy+0.528
 other+0.526
Neg logit contributions
owing-0.849
ur-0.829
ares-0.797
ors-0.796
rying-0.788
Token They
Token ID1119
Feature activation+2.26e-02

Pos logit contributions
ur+0.211
owing+0.207
ares+0.205
ors+0.199
ared+0.195
Neg logit contributions
 big-0.127
 little-0.119
 small-0.111
 boy-0.104
 other-0.103
Token liked
Token ID8288
Feature activation-1.87e-01

Pos logit contributions
ur+0.065
owing+0.062
owed+0.062
ared+0.059
beh+0.059
Neg logit contributions
 big-0.051
 little-0.047
 small-0.047
 new-0.043
 boy-0.043
Token Rex
Token ID17853
Feature activation+7.50e-02

Pos logit contributions
 big+0.505
 little+0.475
 small+0.463
 boy+0.434
 other+0.428
Neg logit contributions
owing-0.485
ur-0.477
ors-0.451
ares-0.446
beh-0.445
Token.
Token ID13
Feature activation+6.63e-02

Pos logit contributions
owing+0.240
ur+0.233
owed+0.223
ors+0.222
ares+0.221
Neg logit contributions
 big-0.161
 little-0.147
 small-0.143
 boy-0.131
 other-0.129
Token
Token ID198
Feature activation-2.15e-01

Pos logit contributions
owing+0.216
ur+0.216
ares+0.211
ors+0.206
owed+0.202
Neg logit contributions
 big-0.126
 little-0.118
 small-0.112
 other-0.102
 boy-0.101
Token
Token ID198
Feature activation-2.14e-01

Pos logit contributions
 big+0.344
 little+0.337
 boy+0.313
 small+0.302
 girl+0.287
Neg logit contributions
ur-0.721
owing-0.699
ors-0.692
ares-0.686
oot-0.683
Token"
Token ID1
Feature activation+1.98e-02

Pos logit contributions
 big+0.506
 little+0.488
 small+0.450
 boy+0.444
 new+0.432
Neg logit contributions
ur-0.586
owing-0.564
ors-0.560
ares-0.550
rying-0.546
Token can
Token ID460
Feature activation-4.40e-02

Pos logit contributions
owing+0.959
ur+0.942
ares+0.905
ors+0.905
ared+0.894
Neg logit contributions
 big-0.591
 little-0.538
 small-0.522
 boy-0.475
 other-0.473
Token buy
Token ID2822
Feature activation+2.16e-01

Pos logit contributions
 big+0.118
 little+0.109
 small+0.106
 other+0.099
 boy+0.097
Neg logit contributions
owing-0.124
ur-0.118
rying-0.115
ares-0.114
ors-0.113
Token things
Token ID1243
Feature activation-2.09e-01

Pos logit contributions
ur+0.660
owing+0.660
ors+0.645
ares+0.634
beh+0.626
Neg logit contributions
 big-0.443
 little-0.414
 small-0.395
 boy-0.379
 park-0.355
Token with
Token ID351
Feature activation+1.05e-01

Pos logit contributions
 big+0.512
 small+0.445
 little+0.436
 new+0.408
 other+0.404
Neg logit contributions
owing-0.692
rying-0.651
beh-0.643
ared-0.641
owed-0.639
Token it
Token ID340
Feature activation+1.09e-01

Pos logit contributions
owing+0.324
ur+0.319
ors+0.310
ares+0.305
ared+0.303
Neg logit contributions
 big-0.228
 little-0.209
 small-0.203
 boy-0.192
 other-0.183
Token.
Token ID13
Feature activation+5.51e-02

Pos logit contributions
owing+0.331
ur+0.322
beh+0.314
ares+0.311
rying+0.309
Neg logit contributions
 big-0.271
 little-0.248
 small-0.244
 other-0.226
 boy-0.216
Token Like
Token ID4525
Feature activation+1.99e-01

Pos logit contributions
owing+0.155
ur+0.144
rying+0.142
ared+0.142
owed+0.141
Neg logit contributions
 big-0.144
 little-0.136
 small-0.133
 boy-0.124
 other-0.124
Token candy
Token ID18550
Feature activation-5.95e-02

Pos logit contributions
owing+0.623
ur+0.608
ares+0.585
ors+0.584
rying+0.579
Neg logit contributions
 big-0.451
 little-0.414
 small-0.403
 boy-0.369
 other-0.369
Token or
Token ID393
Feature activation+3.02e-01

Pos logit contributions
 big+0.128
 little+0.114
 small+0.111
 other+0.101
 boy+0.101
Neg logit contributions
owing-0.203
ur-0.197
beh-0.193
ares-0.191
rying-0.191
Token ice
Token ID4771
Feature activation-1.62e-01

Pos logit contributions
owing+0.951
ur+0.948
ors+0.905
ares+0.904
beh+0.902
Neg logit contributions
 big-0.611
 little-0.558
 small-0.541
 boy-0.507
 other-0.481
Token cream
Token ID8566
Feature activation-2.45e-02

Pos logit contributions
 big+0.369
 little+0.333
 small+0.324
 boy+0.303
 other+0.296
Neg logit contributions
owing-0.515
ur-0.506
ares-0.489
beh-0.482
rying-0.479
Token was
Token ID373
Feature activation-3.16e-01

Pos logit contributions
ur+0.321
owed+0.313
ares+0.304
ors+0.303
ared+0.302
Neg logit contributions
 big-0.149
 little-0.144
 small-0.129
 park-0.124
 other-0.123
Token different
Token ID1180
Feature activation-3.13e-01

Pos logit contributions
 big+0.512
 little+0.477
 small+0.440
 boy+0.432
 other+0.404
Neg logit contributions
ur-1.124
owing-1.118
ares-1.071
rying-1.064
ors-1.055
Token from
Token ID422
Feature activation+3.24e-01

Pos logit contributions
 big+0.814
 little+0.758
 small+0.732
 boy+0.677
 other+0.675
Neg logit contributions
owing-0.903
ur-0.889
ares-0.854
beh-0.845
ors-0.843
Token the
Token ID262
Feature activation-1.50e-01

Pos logit contributions
owing+1.086
ur+1.070
ors+1.031
rying+1.027
ares+1.024
Neg logit contributions
 big-0.621
 little-0.568
 small-0.542
 boy-0.506
 other-0.487
Token other
Token ID584
Feature activation-4.70e-01

Pos logit contributions
 big+0.211
 little+0.189
 small+0.183
 boy+0.158
 new+0.148
Neg logit contributions
owing-0.519
rying-0.503
ur-0.499
ors-0.480
ares-0.477
Token fish
Token ID5916
Feature activation-2.36e-01

Pos logit contributions
 big+0.799
 little+0.696
 small+0.692
 boy+0.600
 other+0.584
Neg logit contributions
owing-1.693
ur-1.623
rying-1.593
ors-1.589
ared-1.568
Token.
Token ID13
Feature activation+5.35e-02

Pos logit contributions
 big+0.551
 little+0.504
 small+0.489
 other+0.453
 boy+0.440
Neg logit contributions
owing-0.722
ur-0.717
ares-0.703
beh-0.694
ors-0.684
Token It
Token ID632
Feature activation+9.72e-02

Pos logit contributions
owing+0.170
ur+0.168
ares+0.162
ors+0.160
ared+0.158
Neg logit contributions
 big-0.116
 little-0.106
 small-0.102
 boy-0.094
 other-0.094
Token had
Token ID550
Feature activation-2.01e-01

Pos logit contributions
ur+0.324
owed+0.308
owing+0.303
ared+0.300
beh+0.299
Neg logit contributions
 big-0.161
 little-0.150
 small-0.140
 other-0.132
 new-0.132
Token a
Token ID257
Feature activation-2.22e-01

Pos logit contributions
 big+0.309
 little+0.294
 boy+0.292
 small+0.271
 park+0.247
Neg logit contributions
ur-0.692
owing-0.661
ared-0.645
beh-0.643
ors-0.637
Token long
Token ID890
Feature activation-2.32e-01

Pos logit contributions
 little+0.208
 big+0.200
 other+0.200
 boy+0.198
 park+0.174
Neg logit contributions
ur-0.775
owing-0.755
ares-0.750
ared-0.723
rying-0.718
Token will
Token ID481
Feature activation-1.39e-02

Pos logit contributions
owing+0.359
ur+0.352
ors+0.341
ares+0.341
beh+0.337
Neg logit contributions
 big-0.191
 little-0.172
 small-0.167
 boy-0.150
 other-0.148
Token make
Token ID787
Feature activation-8.11e-03

Pos logit contributions
 big+0.029
 little+0.027
 small+0.026
 boy+0.024
 other+0.023
Neg logit contributions
owing-0.044
ur-0.044
ares-0.042
ors-0.042
rying-0.042
Token ants
Token ID27842
Feature activation-8.13e-02

Pos logit contributions
 big+0.022
 little+0.020
 small+0.020
 boy+0.019
 other+0.018
Neg logit contributions
owing-0.021
ur-0.020
ors-0.020
ares-0.020
beh-0.019
Token come
Token ID1282
Feature activation+1.36e-01

Pos logit contributions
 big+0.175
 little+0.158
 small+0.154
 other+0.138
 boy+0.135
Neg logit contributions
owing-0.268
ur-0.266
ared-0.257
ares-0.255
ors-0.255
Token."
Token ID526
Feature activation+1.86e-01

Pos logit contributions
owing+0.376
ur+0.366
ared+0.353
ors+0.349
ares+0.349
Neg logit contributions
 big-0.381
 little-0.350
 small-0.342
 other-0.310
 boy-0.309
Token
Token ID198
Feature activation-2.27e-01

Pos logit contributions
owing+0.706
ur+0.698
ares+0.679
ors+0.673
owed+0.664
Neg logit contributions
 big-0.276
 little-0.237
 small-0.230
 other-0.197
 boy-0.189
Token
Token ID198
Feature activation-2.27e-01

Pos logit contributions
 big+0.371
 little+0.335
 small+0.316
 boy+0.296
 other+0.285
Neg logit contributions
ur-0.738
owing-0.732
oot-0.720
ors-0.717
ares-0.717
TokenL
Token ID43
Feature activation-1.32e-01

Pos logit contributions
 big+0.473
 little+0.421
 small+0.400
 new+0.368
 other+0.367
Neg logit contributions
ur-0.686
owing-0.684
beh-0.668
rying-0.661
ares-0.654
Tokenily
Token ID813
Feature activation+2.02e-01

Pos logit contributions
 big+0.336
 little+0.325
 small+0.305
 boy+0.293
 other+0.289
Neg logit contributions
owing-0.375
ur-0.365
ors-0.348
beh-0.348
ared-0.342
Token was
Token ID373
Feature activation-3.06e-01

Pos logit contributions
owing+0.619
owed+0.607
ur+0.603
ared+0.591
ors+0.572
Neg logit contributions
 big-0.439
 small-0.390
 little-0.379
 other-0.363
 new-0.356
Token sorry
Token ID7926
Feature activation+1.74e-01

Pos logit contributions
 big+0.618
 little+0.575
 small+0.542
 boy+0.540
 other+0.510
Neg logit contributions
owing-0.982
ur-0.954
beh-0.917
ares-0.916
owed-0.908
Token small
Token ID1402
Feature activation-4.90e-01

Pos logit contributions
 two+0.098
 other+0.089
 boy+0.086
 big+0.073
 little+0.069
Neg logit contributions
owing-0.761
ur-0.740
rying-0.727
ors-0.722
 able-0.713
Token hole
Token ID7604
Feature activation-2.63e-01

Pos logit contributions
 big+0.662
 other+0.582
 little+0.563
 small+0.527
 new+0.519
Neg logit contributions
owing-1.699
ur-1.602
ors-1.579
ared-1.555
rying-1.553
Token near
Token ID1474
Feature activation+1.77e-01

Pos logit contributions
 big+0.599
 little+0.546
 small+0.533
 other+0.478
 boy+0.473
Neg logit contributions
owing-0.824
ur-0.823
beh-0.800
ares-0.800
ors-0.784
Token a
Token ID257
Feature activation-2.16e-01

Pos logit contributions
owing+0.511
ur+0.499
ors+0.496
beh+0.466
owed+0.464
Neg logit contributions
 big-0.358
 little-0.330
 boy-0.326
 small-0.320
 girl-0.298
Token big
Token ID1263
Feature activation-5.57e-01

Pos logit contributions
 two+0.153
 big+0.140
 other+0.136
 boy+0.136
 little+0.132
Neg logit contributions
ur-0.750
owing-0.731
ors-0.714
rying-0.709
ility-0.693
Token farm
Token ID5318
Feature activation-2.99e-01

Pos logit contributions
 big+0.715
 little+0.638
 small+0.619
 other+0.589
 boy+0.534
Neg logit contributions
owing-2.056
ur-2.014
ors-1.977
rying-1.913
ares-1.889
Token.
Token ID13
Feature activation+5.45e-02

Pos logit contributions
 big+0.665
 little+0.605
 small+0.589
 boy+0.535
 other+0.533
Neg logit contributions
owing-0.957
ur-0.940
ares-0.918
ors-0.902
beh-0.899
Token He
Token ID679
Feature activation+5.47e-02

Pos logit contributions
ur+0.151
owing+0.147
ors+0.138
ares+0.135
ared+0.135
Neg logit contributions
 big-0.132
 little-0.118
 small-0.116
 other-0.111
 boy-0.108
Token was
Token ID373
Feature activation-3.09e-01

Pos logit contributions
ur+0.170
owing+0.166
owed+0.163
ared+0.160
ors+0.157
Neg logit contributions
 big-0.111
 little-0.099
 small-0.097
 new-0.092
 other-0.087
Token always
Token ID1464
Feature activation-3.65e-02

Pos logit contributions
 big+0.562
 little+0.512
 small+0.484
 boy+0.463
 other+0.451
Neg logit contributions
owing-1.076
ur-1.064
rying-1.005
beh-1.004
ares-0.992
Token so
Token ID523
Feature activation+9.25e-02

Pos logit contributions
 big+0.079
 little+0.072
 small+0.069
 other+0.065
 boy+0.065
Neg logit contributions
owing-0.117
ur-0.113
rying-0.109
beh-0.108
ares-0.107
Token her
Token ID607
Feature activation+1.09e-01

Pos logit contributions
owing+0.259
ur+0.254
ors+0.243
ares+0.241
beh+0.240
Neg logit contributions
 big-0.183
 little-0.167
 small-0.163
 boy-0.156
 other-0.146
Token new
Token ID649
Feature activation-4.47e-01

Pos logit contributions
owing+0.396
ur+0.380
ors+0.370
owed+0.366
ared+0.363
Neg logit contributions
 big-0.150
 small-0.130
 little-0.130
 boy-0.123
 other-0.111
Token toy
Token ID13373
Feature activation-4.02e-01

Pos logit contributions
 big+0.679
 little+0.592
 small+0.587
 boy+0.524
 other+0.508
Neg logit contributions
owing-1.628
ur-1.587
ors-1.541
rying-1.510
ared-1.505
Token that
Token ID326
Feature activation+1.47e-01

Pos logit contributions
 big+0.858
 little+0.784
 small+0.743
 other+0.704
 boy+0.687
Neg logit contributions
owing-1.331
ur-1.300
ares-1.273
beh-1.266
rying-1.254
Token the
Token ID262
Feature activation-1.58e-01

Pos logit contributions
owing+0.414
ur+0.406
ors+0.386
beh+0.384
owed+0.383
Neg logit contributions
 big-0.358
 little-0.334
 small-0.324
 boy-0.300
 other-0.296
Token old
Token ID1468
Feature activation-3.43e-01

Pos logit contributions
 big+0.203
 small+0.174
 little+0.172
 boy+0.135
 other+0.133
Neg logit contributions
owing-0.553
ur-0.532
rying-0.527
beh-0.519
ors-0.509
Token lady
Token ID10846
Feature activation-2.92e-01

Pos logit contributions
 big+0.510
 little+0.432
 small+0.430
 other+0.358
 boy+0.334
Neg logit contributions
owing-1.265
ur-1.227
ors-1.207
owed-1.185
oot-1.177
Token showed
Token ID3751
Feature activation+2.79e-02

Pos logit contributions
 big+0.506
 little+0.456
 small+0.431
 boy+0.392
 other+0.384
Neg logit contributions
owing-1.063
ur-1.044
ares-1.028
ors-1.015
beh-1.010
Token Clara
Token ID27443
Feature activation+2.59e-01

Pos logit contributions
owing+0.082
ur+0.079
rying+0.077
ares+0.077
ors+0.076
Neg logit contributions
 big-0.071
 little-0.066
 small-0.064
 other-0.060
 boy-0.058
Token a
Token ID257
Feature activation-2.28e-01

Pos logit contributions
owing+0.806
ur+0.786
ares+0.765
ors+0.757
rying+0.751
Neg logit contributions
 big-0.598
 little-0.550
 small-0.534
 other-0.489
 boy-0.484
Token special
Token ID2041
Feature activation-3.03e-01

Pos logit contributions
 big+0.211
 boy+0.203
 other+0.201
 little+0.193
 small+0.183
Neg logit contributions
ur-0.814
owing-0.795
ares-0.758
owed-0.750
oot-0.744
Token she
Token ID673
Feature activation+1.52e-01

Pos logit contributions
 big+0.086
 little+0.081
 small+0.077
 other+0.071
 boy+0.069
Neg logit contributions
owing-0.117
ur-0.113
beh-0.112
rying-0.111
ares-0.111
Token could
Token ID714
Feature activation+1.26e-01

Pos logit contributions
owing+0.441
ur+0.432
owed+0.415
ors+0.408
ared+0.406
Neg logit contributions
 big-0.370
 little-0.341
 small-0.335
 other-0.313
 park-0.306
Token manage
Token ID6687
Feature activation+2.99e-01

Pos logit contributions
owing+0.411
ur+0.401
ares+0.389
ors+0.387
beh+0.387
Neg logit contributions
 big-0.280
 little-0.254
 small-0.246
 other-0.223
 boy-0.219
Token it
Token ID340
Feature activation+1.09e-01

Pos logit contributions
owing+1.071
ur+1.049
ares+1.022
owed+1.014
beh+1.013
Neg logit contributions
 big-0.594
 little-0.521
 small-0.518
 other-0.459
 new-0.446
Token.
Token ID13
Feature activation+5.70e-02

Pos logit contributions
owing+0.356
ur+0.349
ares+0.345
beh+0.344
ared+0.336
Neg logit contributions
 big-0.246
 little-0.219
 small-0.216
 other-0.196
 new-0.191
Token
Token ID198
Feature activation-2.24e-01

Pos logit contributions
owing+0.182
ur+0.179
ors+0.173
ares+0.172
ared+0.170
Neg logit contributions
 big-0.124
 little-0.111
 small-0.109
 other-0.099
 boy-0.099
Token
Token ID198
Feature activation-2.24e-01

Pos logit contributions
 big+0.337
 little+0.300
 small+0.289
 boy+0.263
 other+0.251
Neg logit contributions
owing-0.819
ur-0.808
ares-0.786
ors-0.785
owed-0.775
TokenThe
Token ID464
Feature activation-1.97e-01

Pos logit contributions
 big+0.488
 little+0.435
 small+0.429
 boy+0.413
 new+0.397
Neg logit contributions
owing-0.652
ur-0.645
ors-0.628
beh-0.628
ares-0.625
Token brave
Token ID14802
Feature activation-1.90e-01

Pos logit contributions
 big+0.127
 small+0.076
 park+0.073
 other+0.048
 lot+0.046
Neg logit contributions
owing-0.761
rying-0.757
ur-0.734
fully-0.731
owed-0.715
Token little
Token ID1310
Feature activation-5.17e-01

Pos logit contributions
 big+0.157
 small+0.106
 other+0.088
 little+0.085
 park+0.079
Neg logit contributions
owing-0.836
ur-0.828
rying-0.803
ares-0.794
owed-0.793
Token girl
Token ID2576
Feature activation-4.06e-01

Pos logit contributions
 big+0.503
 small+0.360
 little+0.350
 other+0.294
 park+0.257
Neg logit contributions
owing-2.197
ur-2.144
rying-2.118
owed-2.077
ared-2.074