TOP ACTIVATIONS
MAX = -1.000

Tom went to his bed and hid under the covers .
Tom went to his bed and hid under the covers
. Tom went to his bed and hid under
Tom went to his bed and hid under the
talking , table ?" The table did not say anything either
you talking , table ?" The table did not say anything
, table ?" The table did not say anything either .
table ?" The table did not say anything either . Tom
either . Tom was scared . Tom went to
anything either . Tom was scared . Tom went
not say anything either . Tom was scared .
say anything either . Tom was scared . Tom
Tom was scared . Tom went to his bed
. Tom was scared . Tom went to his
was scared . Tom went to his bed and
scared . Tom went to his bed and hid
did not say anything either . Tom was scared .
table did not say anything either . Tom was scared .
?" The table did not say anything either . Tom was
The table did not say anything either . Tom was scared

MIN ACTIVATIONS
MIN = -1.000

Tom went to his bed and hid under the covers .
Tom went to his bed and hid under the covers
. Tom went to his bed and hid under
Tom went to his bed and hid under the
talking , table ?" The table did not say anything either
you talking , table ?" The table did not say anything
, table ?" The table did not say anything either .
table ?" The table did not say anything either . Tom
either . Tom was scared . Tom went to
anything either . Tom was scared . Tom went
not say anything either . Tom was scared .
say anything either . Tom was scared . Tom
Tom was scared . Tom went to his bed
. Tom was scared . Tom went to his
was scared . Tom went to his bed and
scared . Tom went to his bed and hid
did not say anything either . Tom was scared .
table did not say anything either . Tom was scared .
?" The table did not say anything either . Tom was
The table did not say anything either . Tom was scared

INTERVAL -1.000 - -1.000
CONTAINS 0.000%

TokenTom
Token ID13787
Feature activation-1.00e+00

Pos logit contributions
 and+3.793
,+3.743
 the+3.571
.+3.571
 a+3.353
Neg logit contributions
lor-5.109
umm-4.994
arians-4.899
bek-4.864
 former-4.831
Token went
Token ID1816
Feature activation-1.00e+00

Pos logit contributions
 and+3.016
,+3.008
 the+2.887
.+2.877
 a+2.667
Neg logit contributions
lor-5.701
umm-5.554
arians-5.536
 former-5.424
bek-5.422
Token to
Token ID284
Feature activation-1.00e+00

Pos logit contributions
 and+1.897
,+1.862
 the+1.695
.+1.685
 a+1.486
Neg logit contributions
lor-6.857
umm-6.725
arians-6.671
rol-6.622
 former-6.609
Token his
Token ID465
Feature activation-1.00e+00

Pos logit contributions
 and+2.421
,+2.379
.+2.188
 the+2.075
 a+1.907
Neg logit contributions
lor-6.291
umm-6.209
arians-6.152
 former-6.147
ocol-6.106
Token bed
Token ID3996
Feature activation-1.00e+00

Pos logit contributions
 and+3.913
,+3.873
 the+3.718
.+3.705
 a+3.490
Neg logit contributions
lor-4.834
umm-4.816
 former-4.723
arians-4.721
bek-4.586
Token and
Token ID290
Feature activation-1.00e+00

Pos logit contributions
 and+1.202
,+1.175
 the+1.102
.+0.994
 a+0.868
Neg logit contributions
lor-7.530
umm-7.394
arians-7.294
 former-7.289
rol-7.173
Token hid
Token ID24519
Feature activation-1.00e+00

Pos logit contributions
 and+3.673
,+3.642
.+3.481
 the+3.418
 a+3.205
Neg logit contributions
lor-5.079
umm-4.905
arians-4.883
 former-4.883
bek-4.841
Token under
Token ID739
Feature activation-1.00e+00

Pos logit contributions
 and+3.087
,+3.063
 the+2.823
.+2.810
 a+2.646
Neg logit contributions
lor-5.605
umm-5.559
arians-5.462
ocol-5.453
 former-5.388
Token the
Token ID262
Feature activation-1.00e+00

Pos logit contributions
 and+1.535
,+1.490
.+1.283
 the+1.171
 a+0.964
Neg logit contributions
lor-7.193
umm-7.128
ocol-7.026
 former-7.003
arians-6.979
Token covers
Token ID8698
Feature activation-1.00e+00

Pos logit contributions
 and+4.553
,+4.535
 the+4.373
.+4.330
 a+4.174
Neg logit contributions
lor-4.191
umm-4.148
arians-3.968
ocol-3.956
 former-3.947
Token.
Token ID13
Feature activation-1.00e+00

Pos logit contributions
 and+0.805
,+0.772
 the+0.612
.+0.530
 a+0.430
Neg logit contributions
lor-7.961
umm-7.861
arians-7.701
rol-7.682
ocol-7.637
Token
Token ID198
Feature activation-1.00e+00

Pos logit contributions
 and+1.407
,+1.362
 the+1.163
.+1.162
 a+0.958
Neg logit contributions
lor-7.425
umm-7.252
arians-7.161
 former-7.132
rol-7.118
TokenTom
Token ID13787
Feature activation-1.00e+00

Pos logit contributions
 and+3.793
,+3.743
 the+3.571
.+3.571
 a+3.353
Neg logit contributions
lor-5.109
umm-4.994
arians-4.899
bek-4.864
 former-4.831
Token went
Token ID1816
Feature activation-1.00e+00

Pos logit contributions
 and+3.016
,+3.008
 the+2.887
.+2.877
 a+2.667
Neg logit contributions
lor-5.701
umm-5.554
arians-5.536
 former-5.424
bek-5.422
Token to
Token ID284
Feature activation-1.00e+00

Pos logit contributions
 and+1.897
,+1.862
 the+1.695
.+1.685
 a+1.486
Neg logit contributions
lor-6.857
umm-6.725
arians-6.671
rol-6.622
 former-6.609
Token his
Token ID465
Feature activation-1.00e+00

Pos logit contributions
 and+2.421
,+2.379
.+2.188
 the+2.075
 a+1.907
Neg logit contributions
lor-6.291
umm-6.209
arians-6.152
 former-6.147
ocol-6.106
Token bed
Token ID3996
Feature activation-1.00e+00

Pos logit contributions
 and+3.913
,+3.873
 the+3.718
.+3.705
 a+3.490
Neg logit contributions
lor-4.834
umm-4.816
 former-4.723
arians-4.721
bek-4.586
Token and
Token ID290
Feature activation-1.00e+00

Pos logit contributions
 and+1.202
,+1.175
 the+1.102
.+0.994
 a+0.868
Neg logit contributions
lor-7.530
umm-7.394
arians-7.294
 former-7.289
rol-7.173
Token hid
Token ID24519
Feature activation-1.00e+00

Pos logit contributions
 and+3.673
,+3.642
.+3.481
 the+3.418
 a+3.205
Neg logit contributions
lor-5.079
umm-4.905
arians-4.883
 former-4.883
bek-4.841
Token under
Token ID739
Feature activation-1.00e+00

Pos logit contributions
 and+3.087
,+3.063
 the+2.823
.+2.810
 a+2.646
Neg logit contributions
lor-5.605
umm-5.559
arians-5.462
ocol-5.453
 former-5.388
Token the
Token ID262
Feature activation-1.00e+00

Pos logit contributions
 and+1.535
,+1.490
.+1.283
 the+1.171
 a+0.964
Neg logit contributions
lor-7.193
umm-7.128
ocol-7.026
 former-7.003
arians-6.979
Token covers
Token ID8698
Feature activation-1.00e+00

Pos logit contributions
 and+4.553
,+4.535
 the+4.373
.+4.330
 a+4.174
Neg logit contributions
lor-4.191
umm-4.148
arians-3.968
ocol-3.956
 former-3.947
Token.
Token ID13
Feature activation-1.00e+00

Pos logit contributions
 and+0.489
,+0.453
 the+0.380
.+0.260
 a+0.205
Neg logit contributions
umm-8.076
lor-8.012
arians-7.877
ocol-7.862
rol-7.818
Token
Token ID198
Feature activation-1.00e+00

Pos logit contributions
 and+3.077
,+3.030
 the+2.838
.+2.837
 a+2.615
Neg logit contributions
lor-5.751
umm-5.696
arians-5.556
 former-5.522
bek-5.482
Token
Token ID198
Feature activation-1.00e+00

Pos logit contributions
 and+1.407
,+1.362
 the+1.163
.+1.162
 a+0.958
Neg logit contributions
lor-7.425
umm-7.252
arians-7.161
 former-7.132
rol-7.118
TokenTom
Token ID13787
Feature activation-1.00e+00

Pos logit contributions
 and+3.793
,+3.743
 the+3.571
.+3.571
 a+3.353
Neg logit contributions
lor-5.109
umm-4.994
arians-4.899
bek-4.864
 former-4.831
Token went
Token ID1816
Feature activation-1.00e+00

Pos logit contributions
 and+3.016
,+3.008
 the+2.887
.+2.877
 a+2.667
Neg logit contributions
lor-5.701
umm-5.554
arians-5.536
 former-5.424
bek-5.422
Token to
Token ID284
Feature activation-1.00e+00

Pos logit contributions
 and+1.897
,+1.862
 the+1.695
.+1.685
 a+1.486
Neg logit contributions
lor-6.857
umm-6.725
arians-6.671
rol-6.622
 former-6.609
Token his
Token ID465
Feature activation-1.00e+00

Pos logit contributions
 and+2.421
,+2.379
.+2.188
 the+2.075
 a+1.907
Neg logit contributions
lor-6.291
umm-6.209
arians-6.152
 former-6.147
ocol-6.106
Token bed
Token ID3996
Feature activation-1.00e+00

Pos logit contributions
 and+3.913
,+3.873
 the+3.718
.+3.705
 a+3.490
Neg logit contributions
lor-4.834
umm-4.816
 former-4.723
arians-4.721
bek-4.586
Token and
Token ID290
Feature activation-1.00e+00

Pos logit contributions
 and+1.202
,+1.175
 the+1.102
.+0.994
 a+0.868
Neg logit contributions
lor-7.530
umm-7.394
arians-7.294
 former-7.289
rol-7.173
Token hid
Token ID24519
Feature activation-1.00e+00

Pos logit contributions
 and+3.673
,+3.642
.+3.481
 the+3.418
 a+3.205
Neg logit contributions
lor-5.079
umm-4.905
arians-4.883
 former-4.883
bek-4.841
Token under
Token ID739
Feature activation-1.00e+00

Pos logit contributions
 and+3.087
,+3.063
 the+2.823
.+2.810
 a+2.646
Neg logit contributions
lor-5.605
umm-5.559
arians-5.462
ocol-5.453
 former-5.388
Token
Token ID198
Feature activation-1.00e+00

Pos logit contributions
 and+3.077
,+3.030
 the+2.838
.+2.837
 a+2.615
Neg logit contributions
lor-5.751
umm-5.696
arians-5.556
 former-5.522
bek-5.482
Token
Token ID198
Feature activation-1.00e+00

Pos logit contributions
 and+1.407
,+1.362
 the+1.163
.+1.162
 a+0.958
Neg logit contributions
lor-7.425
umm-7.252
arians-7.161
 former-7.132
rol-7.118
TokenTom
Token ID13787
Feature activation-1.00e+00

Pos logit contributions
 and+3.793
,+3.743
 the+3.571
.+3.571
 a+3.353
Neg logit contributions
lor-5.109
umm-4.994
arians-4.899
bek-4.864
 former-4.831
Token went
Token ID1816
Feature activation-1.00e+00

Pos logit contributions
 and+3.016
,+3.008
 the+2.887
.+2.877
 a+2.667
Neg logit contributions
lor-5.701
umm-5.554
arians-5.536
 former-5.424
bek-5.422
Token to
Token ID284
Feature activation-1.00e+00

Pos logit contributions
 and+1.897
,+1.862
 the+1.695
.+1.685
 a+1.486
Neg logit contributions
lor-6.857
umm-6.725
arians-6.671
rol-6.622
 former-6.609
Token his
Token ID465
Feature activation-1.00e+00

Pos logit contributions
 and+2.421
,+2.379
.+2.188
 the+2.075
 a+1.907
Neg logit contributions
lor-6.291
umm-6.209
arians-6.152
 former-6.147
ocol-6.106
Token bed
Token ID3996
Feature activation-1.00e+00

Pos logit contributions
 and+3.913
,+3.873
 the+3.718
.+3.705
 a+3.490
Neg logit contributions
lor-4.834
umm-4.816
 former-4.723
arians-4.721
bek-4.586
Token and
Token ID290
Feature activation-1.00e+00

Pos logit contributions
 and+1.202
,+1.175
 the+1.102
.+0.994
 a+0.868
Neg logit contributions
lor-7.530
umm-7.394
arians-7.294
 former-7.289
rol-7.173
Token hid
Token ID24519
Feature activation-1.00e+00

Pos logit contributions
 and+3.673
,+3.642
.+3.481
 the+3.418
 a+3.205
Neg logit contributions
lor-5.079
umm-4.905
arians-4.883
 former-4.883
bek-4.841
Token under
Token ID739
Feature activation-1.00e+00

Pos logit contributions
 and+3.087
,+3.063
 the+2.823
.+2.810
 a+2.646
Neg logit contributions
lor-5.605
umm-5.559
arians-5.462
ocol-5.453
 former-5.388
Token the
Token ID262
Feature activation-1.00e+00

Pos logit contributions
 and+1.535
,+1.490
.+1.283
 the+1.171
 a+0.964
Neg logit contributions
lor-7.193
umm-7.128
ocol-7.026
 former-7.003
arians-6.979
Token talking
Token ID3375
Feature activation-1.00e+00

Pos logit contributions
 and+3.829
,+3.751
 the+3.632
.+3.587
 a+3.396
Neg logit contributions
lor-4.929
umm-4.802
arians-4.752
 former-4.727
rol-4.659
Token,
Token ID11
Feature activation-1.00e+00

Pos logit contributions
 and+2.866
,+2.841
 the+2.709
.+2.650
 a+2.470
Neg logit contributions
lor-5.876
umm-5.771
arians-5.686
 former-5.659
rol-5.595
Token table
Token ID3084
Feature activation-1.00e+00

Pos logit contributions
 and+3.800
,+3.783
.+3.646
 the+3.611
 a+3.406
Neg logit contributions
lor-4.892
umm-4.862
arians-4.766
 former-4.745
ocol-4.659
Token?"
Token ID1701
Feature activation-1.00e+00

Pos logit contributions
 and+2.232
,+2.187
 the+2.104
.+2.024
 a+1.870
Neg logit contributions
lor-6.480
umm-6.419
arians-6.281
 former-6.237
ocol-6.176
Token The
Token ID383
Feature activation-1.00e+00

Pos logit contributions
 and+3.193
,+3.135
.+2.971
 the+2.937
 a+2.746
Neg logit contributions
lor-5.541
umm-5.451
arians-5.367
 former-5.345
ocol-5.305
Token table
Token ID3084
Feature activation-1.00e+00

Pos logit contributions
 and+4.303
,+4.266
.+4.087
 the+4.085
 a+3.857
Neg logit contributions
lor-4.456
umm-4.453
arians-4.320
 former-4.289
ocol-4.251
Token did
Token ID750
Feature activation-1.00e+00

Pos logit contributions
 and+3.856
,+3.814
 the+3.699
.+3.660
 a+3.469
Neg logit contributions
lor-4.885
umm-4.796
arians-4.665
 former-4.617
rol-4.600
Token not
Token ID407
Feature activation-1.00e+00

Pos logit contributions
 and+2.404
,+2.342
 the+2.194
.+2.169
 a+1.956
Neg logit contributions
lor-6.311
umm-6.157
 former-6.122
arians-6.107
vation-6.030
Token say
Token ID910
Feature activation-1.00e+00

Pos logit contributions
 and+3.985
,+3.941
 the+3.798
.+3.755
 a+3.556
Neg logit contributions
umm-4.696
lor-4.684
arians-4.572
 former-4.546
ocol-4.534
Token anything
Token ID1997
Feature activation-1.00e+00

Pos logit contributions
 and+4.240
,+4.100
.+3.956
 the+3.952
 a+3.727
Neg logit contributions
lor-4.611
umm-4.447
arians-4.346
ocol-4.309
osity-4.283
Token either
Token ID2035
Feature activation-1.00e+00

Pos logit contributions
 and+1.887
,+1.833
 the+1.715
.+1.636
 a+1.521
Neg logit contributions
lor-6.792
umm-6.693
arians-6.629
 former-6.556
osity-6.517
Token you
Token ID345
Feature activation-1.00e+00

Pos logit contributions
 and+3.315
,+3.285
.+3.142
 the+3.140
 a+2.952
Neg logit contributions
lor-5.376
umm-5.298
arians-5.276
 former-5.143
rol-5.130
Token talking
Token ID3375
Feature activation-1.00e+00

Pos logit contributions
 and+3.829
,+3.751
 the+3.632
.+3.587
 a+3.396
Neg logit contributions
lor-4.929
umm-4.802
arians-4.752
 former-4.727
rol-4.659
Token,
Token ID11
Feature activation-1.00e+00

Pos logit contributions
 and+2.866
,+2.841
 the+2.709
.+2.650
 a+2.470
Neg logit contributions
lor-5.876
umm-5.771
arians-5.686
 former-5.659
rol-5.595
Token table
Token ID3084
Feature activation-1.00e+00

Pos logit contributions
 and+3.800
,+3.783
.+3.646
 the+3.611
 a+3.406
Neg logit contributions
lor-4.892
umm-4.862
arians-4.766
 former-4.745
ocol-4.659
Token?"
Token ID1701
Feature activation-1.00e+00

Pos logit contributions
 and+2.232
,+2.187
 the+2.104
.+2.024
 a+1.870
Neg logit contributions
lor-6.480
umm-6.419
arians-6.281
 former-6.237
ocol-6.176
Token The
Token ID383
Feature activation-1.00e+00

Pos logit contributions
 and+3.193
,+3.135
.+2.971
 the+2.937
 a+2.746
Neg logit contributions
lor-5.541
umm-5.451
arians-5.367
 former-5.345
ocol-5.305
Token table
Token ID3084
Feature activation-1.00e+00

Pos logit contributions
 and+4.303
,+4.266
.+4.087
 the+4.085
 a+3.857
Neg logit contributions
lor-4.456
umm-4.453
arians-4.320
 former-4.289
ocol-4.251
Token did
Token ID750
Feature activation-1.00e+00

Pos logit contributions
 and+3.856
,+3.814
 the+3.699
.+3.660
 a+3.469
Neg logit contributions
lor-4.885
umm-4.796
arians-4.665
 former-4.617
rol-4.600
Token not
Token ID407
Feature activation-1.00e+00

Pos logit contributions
 and+2.404
,+2.342
 the+2.194
.+2.169
 a+1.956
Neg logit contributions
lor-6.311
umm-6.157
 former-6.122
arians-6.107
vation-6.030
Token say
Token ID910
Feature activation-1.00e+00

Pos logit contributions
 and+3.985
,+3.941
 the+3.798
.+3.755
 a+3.556
Neg logit contributions
umm-4.696
lor-4.684
arians-4.572
 former-4.546
ocol-4.534
Token anything
Token ID1997
Feature activation-1.00e+00

Pos logit contributions
 and+4.240
,+4.100
.+3.956
 the+3.952
 a+3.727
Neg logit contributions
lor-4.611
umm-4.447
arians-4.346
ocol-4.309
osity-4.283
Token,
Token ID11
Feature activation-1.00e+00

Pos logit contributions
 and+2.866
,+2.841
 the+2.709
.+2.650
 a+2.470
Neg logit contributions
lor-5.876
umm-5.771
arians-5.686
 former-5.659
rol-5.595
Token table
Token ID3084
Feature activation-1.00e+00

Pos logit contributions
 and+3.800
,+3.783
.+3.646
 the+3.611
 a+3.406
Neg logit contributions
lor-4.892
umm-4.862
arians-4.766
 former-4.745
ocol-4.659
Token?"
Token ID1701
Feature activation-1.00e+00

Pos logit contributions
 and+2.232
,+2.187
 the+2.104
.+2.024
 a+1.870
Neg logit contributions
lor-6.480
umm-6.419
arians-6.281
 former-6.237
ocol-6.176
Token The
Token ID383
Feature activation-1.00e+00

Pos logit contributions
 and+3.193
,+3.135
.+2.971
 the+2.937
 a+2.746
Neg logit contributions
lor-5.541
umm-5.451
arians-5.367
 former-5.345
ocol-5.305
Token table
Token ID3084
Feature activation-1.00e+00

Pos logit contributions
 and+4.303
,+4.266
.+4.087
 the+4.085
 a+3.857
Neg logit contributions
lor-4.456
umm-4.453
arians-4.320
 former-4.289
ocol-4.251
Token did
Token ID750
Feature activation-1.00e+00

Pos logit contributions
 and+3.856
,+3.814
 the+3.699
.+3.660
 a+3.469
Neg logit contributions
lor-4.885
umm-4.796
arians-4.665
 former-4.617
rol-4.600
Token not
Token ID407
Feature activation-1.00e+00

Pos logit contributions
 and+2.404
,+2.342
 the+2.194
.+2.169
 a+1.956
Neg logit contributions
lor-6.311
umm-6.157
 former-6.122
arians-6.107
vation-6.030
Token say
Token ID910
Feature activation-1.00e+00

Pos logit contributions
 and+3.985
,+3.941
 the+3.798
.+3.755
 a+3.556
Neg logit contributions
umm-4.696
lor-4.684
arians-4.572
 former-4.546
ocol-4.534
Token anything
Token ID1997
Feature activation-1.00e+00

Pos logit contributions
 and+4.240
,+4.100
.+3.956
 the+3.952
 a+3.727
Neg logit contributions
lor-4.611
umm-4.447
arians-4.346
ocol-4.309
osity-4.283
Token either
Token ID2035
Feature activation-1.00e+00

Pos logit contributions
 and+1.887
,+1.833
 the+1.715
.+1.636
 a+1.521
Neg logit contributions
lor-6.792
umm-6.693
arians-6.629
 former-6.556
osity-6.517
Token.
Token ID13
Feature activation-1.00e+00

Pos logit contributions
 and+0.908
,+0.845
 the+0.754
.+0.661
 a+0.551
Neg logit contributions
lor-7.796
umm-7.712
arians-7.585
bek-7.520
rol-7.508
Token table
Token ID3084
Feature activation-1.00e+00

Pos logit contributions
 and+3.800
,+3.783
.+3.646
 the+3.611
 a+3.406
Neg logit contributions
lor-4.892
umm-4.862
arians-4.766
 former-4.745
ocol-4.659
Token?"
Token ID1701
Feature activation-1.00e+00

Pos logit contributions
 and+2.232
,+2.187
 the+2.104
.+2.024
 a+1.870
Neg logit contributions
lor-6.480
umm-6.419
arians-6.281
 former-6.237
ocol-6.176
Token The
Token ID383
Feature activation-1.00e+00

Pos logit contributions
 and+3.193
,+3.135
.+2.971
 the+2.937
 a+2.746
Neg logit contributions
lor-5.541
umm-5.451
arians-5.367
 former-5.345
ocol-5.305
Token table
Token ID3084
Feature activation-1.00e+00

Pos logit contributions
 and+4.303
,+4.266
.+4.087
 the+4.085
 a+3.857
Neg logit contributions
lor-4.456
umm-4.453
arians-4.320
 former-4.289
ocol-4.251
Token did
Token ID750
Feature activation-1.00e+00

Pos logit contributions
 and+3.856
,+3.814
 the+3.699
.+3.660
 a+3.469
Neg logit contributions
lor-4.885
umm-4.796
arians-4.665
 former-4.617
rol-4.600
Token not
Token ID407
Feature activation-1.00e+00

Pos logit contributions
 and+2.404
,+2.342
 the+2.194
.+2.169
 a+1.956
Neg logit contributions
lor-6.311
umm-6.157
 former-6.122
arians-6.107
vation-6.030
Token say
Token ID910
Feature activation-1.00e+00

Pos logit contributions
 and+3.985
,+3.941
 the+3.798
.+3.755
 a+3.556
Neg logit contributions
umm-4.696
lor-4.684
arians-4.572
 former-4.546
ocol-4.534
Token anything
Token ID1997
Feature activation-1.00e+00

Pos logit contributions
 and+4.240
,+4.100
.+3.956
 the+3.952
 a+3.727
Neg logit contributions
lor-4.611
umm-4.447
arians-4.346
ocol-4.309
osity-4.283
Token either
Token ID2035
Feature activation-1.00e+00

Pos logit contributions
 and+1.887
,+1.833
 the+1.715
.+1.636
 a+1.521
Neg logit contributions
lor-6.792
umm-6.693
arians-6.629
 former-6.556
osity-6.517
Token.
Token ID13
Feature activation-1.00e+00

Pos logit contributions
 and+0.908
,+0.845
 the+0.754
.+0.661
 a+0.551
Neg logit contributions
lor-7.796
umm-7.712
arians-7.585
bek-7.520
rol-7.508
Token Tom
Token ID4186
Feature activation-1.00e+00

Pos logit contributions
 and+2.998
,+2.958
.+2.773
 the+2.765
 a+2.545
Neg logit contributions
lor-5.835
umm-5.736
arians-5.627
 former-5.598
bek-5.542
Token either
Token ID2035
Feature activation-1.00e+00

Pos logit contributions
 and+1.887
,+1.833
 the+1.715
.+1.636
 a+1.521
Neg logit contributions
lor-6.792
umm-6.693
arians-6.629
 former-6.556
osity-6.517
Token.
Token ID13
Feature activation-1.00e+00

Pos logit contributions
 and+0.908
,+0.845
 the+0.754
.+0.661
 a+0.551
Neg logit contributions
lor-7.796
umm-7.712
arians-7.585
bek-7.520
rol-7.508
Token Tom
Token ID4186
Feature activation-1.00e+00

Pos logit contributions
 and+2.998
,+2.958
.+2.773
 the+2.765
 a+2.545
Neg logit contributions
lor-5.835
umm-5.736
arians-5.627
 former-5.598
bek-5.542
Token was
Token ID373
Feature activation-1.00e+00

Pos logit contributions
 and+3.051
,+3.050
 the+2.920
.+2.910
 a+2.699
Neg logit contributions
lor-5.644
umm-5.518
arians-5.485
 former-5.403
bek-5.367
Token scared
Token ID12008
Feature activation-1.00e+00

Pos logit contributions
 and+3.745
,+3.721
.+3.537
 the+3.501
 a+3.237
Neg logit contributions
lor-4.966
umm-4.875
 former-4.831
arians-4.811
rol-4.768
Token.
Token ID13
Feature activation-1.00e+00

Pos logit contributions
 and+0.489
,+0.453
 the+0.380
.+0.260
 a+0.205
Neg logit contributions
umm-8.076
lor-8.012
arians-7.877
ocol-7.862
rol-7.818
Token
Token ID198
Feature activation-1.00e+00

Pos logit contributions
 and+3.077
,+3.030
 the+2.838
.+2.837
 a+2.615
Neg logit contributions
lor-5.751
umm-5.696
arians-5.556
 former-5.522
bek-5.482
Token
Token ID198
Feature activation-1.00e+00

Pos logit contributions
 and+1.407
,+1.362
 the+1.163
.+1.162
 a+0.958
Neg logit contributions
lor-7.425
umm-7.252
arians-7.161
 former-7.132
rol-7.118
TokenTom
Token ID13787
Feature activation-1.00e+00

Pos logit contributions
 and+3.793
,+3.743
 the+3.571
.+3.571
 a+3.353
Neg logit contributions
lor-5.109
umm-4.994
arians-4.899
bek-4.864
 former-4.831
Token went
Token ID1816
Feature activation-1.00e+00

Pos logit contributions
 and+3.016
,+3.008
 the+2.887
.+2.877
 a+2.667
Neg logit contributions
lor-5.701
umm-5.554
arians-5.536
 former-5.424
bek-5.422
Token to
Token ID284
Feature activation-1.00e+00

Pos logit contributions
 and+1.897
,+1.862
 the+1.695
.+1.685
 a+1.486
Neg logit contributions
lor-6.857
umm-6.725
arians-6.671
rol-6.622
 former-6.609
Token anything
Token ID1997
Feature activation-1.00e+00

Pos logit contributions
 and+4.240
,+4.100
.+3.956
 the+3.952
 a+3.727
Neg logit contributions
lor-4.611
umm-4.447
arians-4.346
ocol-4.309
osity-4.283
Token either
Token ID2035
Feature activation-1.00e+00

Pos logit contributions
 and+1.887
,+1.833
 the+1.715
.+1.636
 a+1.521
Neg logit contributions
lor-6.792
umm-6.693
arians-6.629
 former-6.556
osity-6.517
Token.
Token ID13
Feature activation-1.00e+00

Pos logit contributions
 and+0.908
,+0.845
 the+0.754
.+0.661
 a+0.551
Neg logit contributions
lor-7.796
umm-7.712
arians-7.585
bek-7.520
rol-7.508
Token Tom
Token ID4186
Feature activation-1.00e+00

Pos logit contributions
 and+2.998
,+2.958
.+2.773
 the+2.765
 a+2.545
Neg logit contributions
lor-5.835
umm-5.736
arians-5.627
 former-5.598
bek-5.542
Token was
Token ID373
Feature activation-1.00e+00

Pos logit contributions
 and+3.051
,+3.050
 the+2.920
.+2.910
 a+2.699
Neg logit contributions
lor-5.644
umm-5.518
arians-5.485
 former-5.403
bek-5.367
Token scared
Token ID12008
Feature activation-1.00e+00

Pos logit contributions
 and+3.745
,+3.721
.+3.537
 the+3.501
 a+3.237
Neg logit contributions
lor-4.966
umm-4.875
 former-4.831
arians-4.811
rol-4.768
Token.
Token ID13
Feature activation-1.00e+00

Pos logit contributions
 and+0.489
,+0.453
 the+0.380
.+0.260
 a+0.205
Neg logit contributions
umm-8.076
lor-8.012
arians-7.877
ocol-7.862
rol-7.818
Token
Token ID198
Feature activation-1.00e+00

Pos logit contributions
 and+3.077
,+3.030
 the+2.838
.+2.837
 a+2.615
Neg logit contributions
lor-5.751
umm-5.696
arians-5.556
 former-5.522
bek-5.482
Token
Token ID198
Feature activation-1.00e+00

Pos logit contributions
 and+1.407
,+1.362
 the+1.163
.+1.162
 a+0.958
Neg logit contributions
lor-7.425
umm-7.252
arians-7.161
 former-7.132
rol-7.118
TokenTom
Token ID13787
Feature activation-1.00e+00

Pos logit contributions
 and+3.793
,+3.743
 the+3.571
.+3.571
 a+3.353
Neg logit contributions
lor-5.109
umm-4.994
arians-4.899
bek-4.864
 former-4.831
Token went
Token ID1816
Feature activation-1.00e+00

Pos logit contributions
 and+3.016
,+3.008
 the+2.887
.+2.877
 a+2.667
Neg logit contributions
lor-5.701
umm-5.554
arians-5.536
 former-5.424
bek-5.422
Token not
Token ID407
Feature activation-1.00e+00

Pos logit contributions
 and+2.404
,+2.342
 the+2.194
.+2.169
 a+1.956
Neg logit contributions
lor-6.311
umm-6.157
 former-6.122
arians-6.107
vation-6.030
Token say
Token ID910
Feature activation-1.00e+00

Pos logit contributions
 and+3.985
,+3.941
 the+3.798
.+3.755
 a+3.556
Neg logit contributions
umm-4.696
lor-4.684
arians-4.572
 former-4.546
ocol-4.534
Token anything
Token ID1997
Feature activation-1.00e+00

Pos logit contributions
 and+4.240
,+4.100
.+3.956
 the+3.952
 a+3.727
Neg logit contributions
lor-4.611
umm-4.447
arians-4.346
ocol-4.309
osity-4.283
Token either
Token ID2035
Feature activation-1.00e+00

Pos logit contributions
 and+1.887
,+1.833
 the+1.715
.+1.636
 a+1.521
Neg logit contributions
lor-6.792
umm-6.693
arians-6.629
 former-6.556
osity-6.517
Token.
Token ID13
Feature activation-1.00e+00

Pos logit contributions
 and+0.908
,+0.845
 the+0.754
.+0.661
 a+0.551
Neg logit contributions
lor-7.796
umm-7.712
arians-7.585
bek-7.520
rol-7.508
Token Tom
Token ID4186
Feature activation-1.00e+00

Pos logit contributions
 and+2.998
,+2.958
.+2.773
 the+2.765
 a+2.545
Neg logit contributions
lor-5.835
umm-5.736
arians-5.627
 former-5.598
bek-5.542
Token was
Token ID373
Feature activation-1.00e+00

Pos logit contributions
 and+3.051
,+3.050
 the+2.920
.+2.910
 a+2.699
Neg logit contributions
lor-5.644
umm-5.518
arians-5.485
 former-5.403
bek-5.367
Token scared
Token ID12008
Feature activation-1.00e+00

Pos logit contributions
 and+3.745
,+3.721
.+3.537
 the+3.501
 a+3.237
Neg logit contributions
lor-4.966
umm-4.875
 former-4.831
arians-4.811
rol-4.768
Token.
Token ID13
Feature activation-1.00e+00

Pos logit contributions
 and+0.489
,+0.453
 the+0.380
.+0.260
 a+0.205
Neg logit contributions
umm-8.076
lor-8.012
arians-7.877
ocol-7.862
rol-7.818
Token
Token ID198
Feature activation-1.00e+00

Pos logit contributions
 and+3.077
,+3.030
 the+2.838
.+2.837
 a+2.615
Neg logit contributions
lor-5.751
umm-5.696
arians-5.556
 former-5.522
bek-5.482
Token
Token ID198
Feature activation-1.00e+00

Pos logit contributions
 and+1.407
,+1.362
 the+1.163
.+1.162
 a+0.958
Neg logit contributions
lor-7.425
umm-7.252
arians-7.161
 former-7.132
rol-7.118
Token say
Token ID910
Feature activation-1.00e+00

Pos logit contributions
 and+3.985
,+3.941
 the+3.798
.+3.755
 a+3.556
Neg logit contributions
umm-4.696
lor-4.684
arians-4.572
 former-4.546
ocol-4.534
Token anything
Token ID1997
Feature activation-1.00e+00

Pos logit contributions
 and+4.240
,+4.100
.+3.956
 the+3.952
 a+3.727
Neg logit contributions
lor-4.611
umm-4.447
arians-4.346
ocol-4.309
osity-4.283
Token either
Token ID2035
Feature activation-1.00e+00

Pos logit contributions
 and+1.887
,+1.833
 the+1.715
.+1.636
 a+1.521
Neg logit contributions
lor-6.792
umm-6.693
arians-6.629
 former-6.556
osity-6.517
Token.
Token ID13
Feature activation-1.00e+00

Pos logit contributions
 and+0.908
,+0.845
 the+0.754
.+0.661
 a+0.551
Neg logit contributions
lor-7.796
umm-7.712
arians-7.585
bek-7.520
rol-7.508
Token Tom
Token ID4186
Feature activation-1.00e+00

Pos logit contributions
 and+2.998
,+2.958
.+2.773
 the+2.765
 a+2.545
Neg logit contributions
lor-5.835
umm-5.736
arians-5.627
 former-5.598
bek-5.542
Token was
Token ID373
Feature activation-1.00e+00

Pos logit contributions
 and+3.051
,+3.050
 the+2.920
.+2.910
 a+2.699
Neg logit contributions
lor-5.644
umm-5.518
arians-5.485
 former-5.403
bek-5.367
Token scared
Token ID12008
Feature activation-1.00e+00

Pos logit contributions
 and+3.745
,+3.721
.+3.537
 the+3.501
 a+3.237
Neg logit contributions
lor-4.966
umm-4.875
 former-4.831
arians-4.811
rol-4.768
Token.
Token ID13
Feature activation-1.00e+00

Pos logit contributions
 and+0.489
,+0.453
 the+0.380
.+0.260
 a+0.205
Neg logit contributions
umm-8.076
lor-8.012
arians-7.877
ocol-7.862
rol-7.818
Token
Token ID198
Feature activation-1.00e+00

Pos logit contributions
 and+3.077
,+3.030
 the+2.838
.+2.837
 a+2.615
Neg logit contributions
lor-5.751
umm-5.696
arians-5.556
 former-5.522
bek-5.482
Token
Token ID198
Feature activation-1.00e+00

Pos logit contributions
 and+1.407
,+1.362
 the+1.163
.+1.162
 a+0.958
Neg logit contributions
lor-7.425
umm-7.252
arians-7.161
 former-7.132
rol-7.118
TokenTom
Token ID13787
Feature activation-1.00e+00

Pos logit contributions
 and+3.793
,+3.743
 the+3.571
.+3.571
 a+3.353
Neg logit contributions
lor-5.109
umm-4.994
arians-4.899
bek-4.864
 former-4.831
Token Tom
Token ID4186
Feature activation-1.00e+00

Pos logit contributions
 and+2.998
,+2.958
.+2.773
 the+2.765
 a+2.545
Neg logit contributions
lor-5.835
umm-5.736
arians-5.627
 former-5.598
bek-5.542
Token was
Token ID373
Feature activation-1.00e+00

Pos logit contributions
 and+3.051
,+3.050
 the+2.920
.+2.910
 a+2.699
Neg logit contributions
lor-5.644
umm-5.518
arians-5.485
 former-5.403
bek-5.367
Token scared
Token ID12008
Feature activation-1.00e+00

Pos logit contributions
 and+3.745
,+3.721
.+3.537
 the+3.501
 a+3.237
Neg logit contributions
lor-4.966
umm-4.875
 former-4.831
arians-4.811
rol-4.768
Token.
Token ID13
Feature activation-1.00e+00

Pos logit contributions
 and+0.489
,+0.453
 the+0.380
.+0.260
 a+0.205
Neg logit contributions
umm-8.076
lor-8.012
arians-7.877
ocol-7.862
rol-7.818
Token
Token ID198
Feature activation-1.00e+00

Pos logit contributions
 and+3.077
,+3.030
 the+2.838
.+2.837
 a+2.615
Neg logit contributions
lor-5.751
umm-5.696
arians-5.556
 former-5.522
bek-5.482
Token
Token ID198
Feature activation-1.00e+00

Pos logit contributions
 and+1.407
,+1.362
 the+1.163
.+1.162
 a+0.958
Neg logit contributions
lor-7.425
umm-7.252
arians-7.161
 former-7.132
rol-7.118
TokenTom
Token ID13787
Feature activation-1.00e+00

Pos logit contributions
 and+3.793
,+3.743
 the+3.571
.+3.571
 a+3.353
Neg logit contributions
lor-5.109
umm-4.994
arians-4.899
bek-4.864
 former-4.831
Token went
Token ID1816
Feature activation-1.00e+00

Pos logit contributions
 and+3.016
,+3.008
 the+2.887
.+2.877
 a+2.667
Neg logit contributions
lor-5.701
umm-5.554
arians-5.536
 former-5.424
bek-5.422
Token to
Token ID284
Feature activation-1.00e+00

Pos logit contributions
 and+1.897
,+1.862
 the+1.695
.+1.685
 a+1.486
Neg logit contributions
lor-6.857
umm-6.725
arians-6.671
rol-6.622
 former-6.609
Token his
Token ID465
Feature activation-1.00e+00

Pos logit contributions
 and+2.421
,+2.379
.+2.188
 the+2.075
 a+1.907
Neg logit contributions
lor-6.291
umm-6.209
arians-6.152
 former-6.147
ocol-6.106
Token bed
Token ID3996
Feature activation-1.00e+00

Pos logit contributions
 and+3.913
,+3.873
 the+3.718
.+3.705
 a+3.490
Neg logit contributions
lor-4.834
umm-4.816
 former-4.723
arians-4.721
bek-4.586
Token.
Token ID13
Feature activation-1.00e+00

Pos logit contributions
 and+0.908
,+0.845
 the+0.754
.+0.661
 a+0.551
Neg logit contributions
lor-7.796
umm-7.712
arians-7.585
bek-7.520
rol-7.508
Token Tom
Token ID4186
Feature activation-1.00e+00

Pos logit contributions
 and+2.998
,+2.958
.+2.773
 the+2.765
 a+2.545
Neg logit contributions
lor-5.835
umm-5.736
arians-5.627
 former-5.598
bek-5.542
Token was
Token ID373
Feature activation-1.00e+00

Pos logit contributions
 and+3.051
,+3.050
 the+2.920
.+2.910
 a+2.699
Neg logit contributions
lor-5.644
umm-5.518
arians-5.485
 former-5.403
bek-5.367
Token scared
Token ID12008
Feature activation-1.00e+00

Pos logit contributions
 and+3.745
,+3.721
.+3.537
 the+3.501
 a+3.237
Neg logit contributions
lor-4.966
umm-4.875
 former-4.831
arians-4.811
rol-4.768
Token.
Token ID13
Feature activation-1.00e+00

Pos logit contributions
 and+0.489
,+0.453
 the+0.380
.+0.260
 a+0.205
Neg logit contributions
umm-8.076
lor-8.012
arians-7.877
ocol-7.862
rol-7.818
Token
Token ID198
Feature activation-1.00e+00

Pos logit contributions
 and+3.077
,+3.030
 the+2.838
.+2.837
 a+2.615
Neg logit contributions
lor-5.751
umm-5.696
arians-5.556
 former-5.522
bek-5.482
Token
Token ID198
Feature activation-1.00e+00

Pos logit contributions
 and+1.407
,+1.362
 the+1.163
.+1.162
 a+0.958
Neg logit contributions
lor-7.425
umm-7.252
arians-7.161
 former-7.132
rol-7.118
TokenTom
Token ID13787
Feature activation-1.00e+00

Pos logit contributions
 and+3.793
,+3.743
 the+3.571
.+3.571
 a+3.353
Neg logit contributions
lor-5.109
umm-4.994
arians-4.899
bek-4.864
 former-4.831
Token went
Token ID1816
Feature activation-1.00e+00

Pos logit contributions
 and+3.016
,+3.008
 the+2.887
.+2.877
 a+2.667
Neg logit contributions
lor-5.701
umm-5.554
arians-5.536
 former-5.424
bek-5.422
Token to
Token ID284
Feature activation-1.00e+00

Pos logit contributions
 and+1.897
,+1.862
 the+1.695
.+1.685
 a+1.486
Neg logit contributions
lor-6.857
umm-6.725
arians-6.671
rol-6.622
 former-6.609
Token his
Token ID465
Feature activation-1.00e+00

Pos logit contributions
 and+2.421
,+2.379
.+2.188
 the+2.075
 a+1.907
Neg logit contributions
lor-6.291
umm-6.209
arians-6.152
 former-6.147
ocol-6.106
Token was
Token ID373
Feature activation-1.00e+00

Pos logit contributions
 and+3.051
,+3.050
 the+2.920
.+2.910
 a+2.699
Neg logit contributions
lor-5.644
umm-5.518
arians-5.485
 former-5.403
bek-5.367
Token scared
Token ID12008
Feature activation-1.00e+00

Pos logit contributions
 and+3.745
,+3.721
.+3.537
 the+3.501
 a+3.237
Neg logit contributions
lor-4.966
umm-4.875
 former-4.831
arians-4.811
rol-4.768
Token.
Token ID13
Feature activation-1.00e+00

Pos logit contributions
 and+0.489
,+0.453
 the+0.380
.+0.260
 a+0.205
Neg logit contributions
umm-8.076
lor-8.012
arians-7.877
ocol-7.862
rol-7.818
Token
Token ID198
Feature activation-1.00e+00

Pos logit contributions
 and+3.077
,+3.030
 the+2.838
.+2.837
 a+2.615
Neg logit contributions
lor-5.751
umm-5.696
arians-5.556
 former-5.522
bek-5.482
Token
Token ID198
Feature activation-1.00e+00

Pos logit contributions
 and+1.407
,+1.362
 the+1.163
.+1.162
 a+0.958
Neg logit contributions
lor-7.425
umm-7.252
arians-7.161
 former-7.132
rol-7.118
TokenTom
Token ID13787
Feature activation-1.00e+00

Pos logit contributions
 and+3.793
,+3.743
 the+3.571
.+3.571
 a+3.353
Neg logit contributions
lor-5.109
umm-4.994
arians-4.899
bek-4.864
 former-4.831
Token went
Token ID1816
Feature activation-1.00e+00

Pos logit contributions
 and+3.016
,+3.008
 the+2.887
.+2.877
 a+2.667
Neg logit contributions
lor-5.701
umm-5.554
arians-5.536
 former-5.424
bek-5.422
Token to
Token ID284
Feature activation-1.00e+00

Pos logit contributions
 and+1.897
,+1.862
 the+1.695
.+1.685
 a+1.486
Neg logit contributions
lor-6.857
umm-6.725
arians-6.671
rol-6.622
 former-6.609
Token his
Token ID465
Feature activation-1.00e+00

Pos logit contributions
 and+2.421
,+2.379
.+2.188
 the+2.075
 a+1.907
Neg logit contributions
lor-6.291
umm-6.209
arians-6.152
 former-6.147
ocol-6.106
Token bed
Token ID3996
Feature activation-1.00e+00

Pos logit contributions
 and+3.913
,+3.873
 the+3.718
.+3.705
 a+3.490
Neg logit contributions
lor-4.834
umm-4.816
 former-4.723
arians-4.721
bek-4.586
Token and
Token ID290
Feature activation-1.00e+00

Pos logit contributions
 and+1.202
,+1.175
 the+1.102
.+0.994
 a+0.868
Neg logit contributions
lor-7.530
umm-7.394
arians-7.294
 former-7.289
rol-7.173
Token scared
Token ID12008
Feature activation-1.00e+00

Pos logit contributions
 and+3.745
,+3.721
.+3.537
 the+3.501
 a+3.237
Neg logit contributions
lor-4.966
umm-4.875
 former-4.831
arians-4.811
rol-4.768
Token.
Token ID13
Feature activation-1.00e+00

Pos logit contributions
 and+0.489
,+0.453
 the+0.380
.+0.260
 a+0.205
Neg logit contributions
umm-8.076
lor-8.012
arians-7.877
ocol-7.862
rol-7.818
Token
Token ID198
Feature activation-1.00e+00

Pos logit contributions
 and+3.077
,+3.030
 the+2.838
.+2.837
 a+2.615
Neg logit contributions
lor-5.751
umm-5.696
arians-5.556
 former-5.522
bek-5.482
Token
Token ID198
Feature activation-1.00e+00

Pos logit contributions
 and+1.407
,+1.362
 the+1.163
.+1.162
 a+0.958
Neg logit contributions
lor-7.425
umm-7.252
arians-7.161
 former-7.132
rol-7.118
TokenTom
Token ID13787
Feature activation-1.00e+00

Pos logit contributions
 and+3.793
,+3.743
 the+3.571
.+3.571
 a+3.353
Neg logit contributions
lor-5.109
umm-4.994
arians-4.899
bek-4.864
 former-4.831
Token went
Token ID1816
Feature activation-1.00e+00

Pos logit contributions
 and+3.016
,+3.008
 the+2.887
.+2.877
 a+2.667
Neg logit contributions
lor-5.701
umm-5.554
arians-5.536
 former-5.424
bek-5.422
Token to
Token ID284
Feature activation-1.00e+00

Pos logit contributions
 and+1.897
,+1.862
 the+1.695
.+1.685
 a+1.486
Neg logit contributions
lor-6.857
umm-6.725
arians-6.671
rol-6.622
 former-6.609
Token his
Token ID465
Feature activation-1.00e+00

Pos logit contributions
 and+2.421
,+2.379
.+2.188
 the+2.075
 a+1.907
Neg logit contributions
lor-6.291
umm-6.209
arians-6.152
 former-6.147
ocol-6.106
Token bed
Token ID3996
Feature activation-1.00e+00

Pos logit contributions
 and+3.913
,+3.873
 the+3.718
.+3.705
 a+3.490
Neg logit contributions
lor-4.834
umm-4.816
 former-4.723
arians-4.721
bek-4.586
Token and
Token ID290
Feature activation-1.00e+00

Pos logit contributions
 and+1.202
,+1.175
 the+1.102
.+0.994
 a+0.868
Neg logit contributions
lor-7.530
umm-7.394
arians-7.294
 former-7.289
rol-7.173
Token hid
Token ID24519
Feature activation-1.00e+00

Pos logit contributions
 and+3.673
,+3.642
.+3.481
 the+3.418
 a+3.205
Neg logit contributions
lor-5.079
umm-4.905
arians-4.883
 former-4.883
bek-4.841
Token did
Token ID750
Feature activation-1.00e+00

Pos logit contributions
 and+3.856
,+3.814
 the+3.699
.+3.660
 a+3.469
Neg logit contributions
lor-4.885
umm-4.796
arians-4.665
 former-4.617
rol-4.600
Token not
Token ID407
Feature activation-1.00e+00

Pos logit contributions
 and+2.404
,+2.342
 the+2.194
.+2.169
 a+1.956
Neg logit contributions
lor-6.311
umm-6.157
 former-6.122
arians-6.107
vation-6.030
Token say
Token ID910
Feature activation-1.00e+00

Pos logit contributions
 and+3.985
,+3.941
 the+3.798
.+3.755
 a+3.556
Neg logit contributions
umm-4.696
lor-4.684
arians-4.572
 former-4.546
ocol-4.534
Token anything
Token ID1997
Feature activation-1.00e+00

Pos logit contributions
 and+4.240
,+4.100
.+3.956
 the+3.952
 a+3.727
Neg logit contributions
lor-4.611
umm-4.447
arians-4.346
ocol-4.309
osity-4.283
Token either
Token ID2035
Feature activation-1.00e+00

Pos logit contributions
 and+1.887
,+1.833
 the+1.715
.+1.636
 a+1.521
Neg logit contributions
lor-6.792
umm-6.693
arians-6.629
 former-6.556
osity-6.517
Token.
Token ID13
Feature activation-1.00e+00

Pos logit contributions
 and+0.908
,+0.845
 the+0.754
.+0.661
 a+0.551
Neg logit contributions
lor-7.796
umm-7.712
arians-7.585
bek-7.520
rol-7.508
Token Tom
Token ID4186
Feature activation-1.00e+00

Pos logit contributions
 and+2.998
,+2.958
.+2.773
 the+2.765
 a+2.545
Neg logit contributions
lor-5.835
umm-5.736
arians-5.627
 former-5.598
bek-5.542
Token was
Token ID373
Feature activation-1.00e+00

Pos logit contributions
 and+3.051
,+3.050
 the+2.920
.+2.910
 a+2.699
Neg logit contributions
lor-5.644
umm-5.518
arians-5.485
 former-5.403
bek-5.367
Token scared
Token ID12008
Feature activation-1.00e+00

Pos logit contributions
 and+3.745
,+3.721
.+3.537
 the+3.501
 a+3.237
Neg logit contributions
lor-4.966
umm-4.875
 former-4.831
arians-4.811
rol-4.768
Token.
Token ID13
Feature activation-1.00e+00

Pos logit contributions
 and+0.489
,+0.453
 the+0.380
.+0.260
 a+0.205
Neg logit contributions
umm-8.076
lor-8.012
arians-7.877
ocol-7.862
rol-7.818
Token
Token ID198
Feature activation-1.00e+00

Pos logit contributions
 and+3.077
,+3.030
 the+2.838
.+2.837
 a+2.615
Neg logit contributions
lor-5.751
umm-5.696
arians-5.556
 former-5.522
bek-5.482
Token table
Token ID3084
Feature activation-1.00e+00

Pos logit contributions
 and+4.303
,+4.266
.+4.087
 the+4.085
 a+3.857
Neg logit contributions
lor-4.456
umm-4.453
arians-4.320
 former-4.289
ocol-4.251
Token did
Token ID750
Feature activation-1.00e+00

Pos logit contributions
 and+3.856
,+3.814
 the+3.699
.+3.660
 a+3.469
Neg logit contributions
lor-4.885
umm-4.796
arians-4.665
 former-4.617
rol-4.600
Token not
Token ID407
Feature activation-1.00e+00

Pos logit contributions
 and+2.404
,+2.342
 the+2.194
.+2.169
 a+1.956
Neg logit contributions
lor-6.311
umm-6.157
 former-6.122
arians-6.107
vation-6.030
Token say
Token ID910
Feature activation-1.00e+00

Pos logit contributions
 and+3.985
,+3.941
 the+3.798
.+3.755
 a+3.556
Neg logit contributions
umm-4.696
lor-4.684
arians-4.572
 former-4.546
ocol-4.534
Token anything
Token ID1997
Feature activation-1.00e+00

Pos logit contributions
 and+4.240
,+4.100
.+3.956
 the+3.952
 a+3.727
Neg logit contributions
lor-4.611
umm-4.447
arians-4.346
ocol-4.309
osity-4.283
Token either
Token ID2035
Feature activation-1.00e+00

Pos logit contributions
 and+1.887
,+1.833
 the+1.715
.+1.636
 a+1.521
Neg logit contributions
lor-6.792
umm-6.693
arians-6.629
 former-6.556
osity-6.517
Token.
Token ID13
Feature activation-1.00e+00

Pos logit contributions
 and+0.908
,+0.845
 the+0.754
.+0.661
 a+0.551
Neg logit contributions
lor-7.796
umm-7.712
arians-7.585
bek-7.520
rol-7.508
Token Tom
Token ID4186
Feature activation-1.00e+00

Pos logit contributions
 and+2.998
,+2.958
.+2.773
 the+2.765
 a+2.545
Neg logit contributions
lor-5.835
umm-5.736
arians-5.627
 former-5.598
bek-5.542
Token was
Token ID373
Feature activation-1.00e+00

Pos logit contributions
 and+3.051
,+3.050
 the+2.920
.+2.910
 a+2.699
Neg logit contributions
lor-5.644
umm-5.518
arians-5.485
 former-5.403
bek-5.367
Token scared
Token ID12008
Feature activation-1.00e+00

Pos logit contributions
 and+3.745
,+3.721
.+3.537
 the+3.501
 a+3.237
Neg logit contributions
lor-4.966
umm-4.875
 former-4.831
arians-4.811
rol-4.768
Token.
Token ID13
Feature activation-1.00e+00

Pos logit contributions
 and+0.489
,+0.453
 the+0.380
.+0.260
 a+0.205
Neg logit contributions
umm-8.076
lor-8.012
arians-7.877
ocol-7.862
rol-7.818
Token?"
Token ID1701
Feature activation-1.00e+00

Pos logit contributions
 and+2.232
,+2.187
 the+2.104
.+2.024
 a+1.870
Neg logit contributions
lor-6.480
umm-6.419
arians-6.281
 former-6.237
ocol-6.176
Token The
Token ID383
Feature activation-1.00e+00

Pos logit contributions
 and+3.193
,+3.135
.+2.971
 the+2.937
 a+2.746
Neg logit contributions
lor-5.541
umm-5.451
arians-5.367
 former-5.345
ocol-5.305
Token table
Token ID3084
Feature activation-1.00e+00

Pos logit contributions
 and+4.303
,+4.266
.+4.087
 the+4.085
 a+3.857
Neg logit contributions
lor-4.456
umm-4.453
arians-4.320
 former-4.289
ocol-4.251
Token did
Token ID750
Feature activation-1.00e+00

Pos logit contributions
 and+3.856
,+3.814
 the+3.699
.+3.660
 a+3.469
Neg logit contributions
lor-4.885
umm-4.796
arians-4.665
 former-4.617
rol-4.600
Token not
Token ID407
Feature activation-1.00e+00

Pos logit contributions
 and+2.404
,+2.342
 the+2.194
.+2.169
 a+1.956
Neg logit contributions
lor-6.311
umm-6.157
 former-6.122
arians-6.107
vation-6.030
Token say
Token ID910
Feature activation-1.00e+00

Pos logit contributions
 and+3.985
,+3.941
 the+3.798
.+3.755
 a+3.556
Neg logit contributions
umm-4.696
lor-4.684
arians-4.572
 former-4.546
ocol-4.534
Token anything
Token ID1997
Feature activation-1.00e+00

Pos logit contributions
 and+4.240
,+4.100
.+3.956
 the+3.952
 a+3.727
Neg logit contributions
lor-4.611
umm-4.447
arians-4.346
ocol-4.309
osity-4.283
Token either
Token ID2035
Feature activation-1.00e+00

Pos logit contributions
 and+1.887
,+1.833
 the+1.715
.+1.636
 a+1.521
Neg logit contributions
lor-6.792
umm-6.693
arians-6.629
 former-6.556
osity-6.517
Token.
Token ID13
Feature activation-1.00e+00

Pos logit contributions
 and+0.908
,+0.845
 the+0.754
.+0.661
 a+0.551
Neg logit contributions
lor-7.796
umm-7.712
arians-7.585
bek-7.520
rol-7.508
Token Tom
Token ID4186
Feature activation-1.00e+00

Pos logit contributions
 and+2.998
,+2.958
.+2.773
 the+2.765
 a+2.545
Neg logit contributions
lor-5.835
umm-5.736
arians-5.627
 former-5.598
bek-5.542
Token was
Token ID373
Feature activation-1.00e+00

Pos logit contributions
 and+3.051
,+3.050
 the+2.920
.+2.910
 a+2.699
Neg logit contributions
lor-5.644
umm-5.518
arians-5.485
 former-5.403
bek-5.367
Token The
Token ID383
Feature activation-1.00e+00

Pos logit contributions
 and+3.193
,+3.135
.+2.971
 the+2.937
 a+2.746
Neg logit contributions
lor-5.541
umm-5.451
arians-5.367
 former-5.345
ocol-5.305
Token table
Token ID3084
Feature activation-1.00e+00

Pos logit contributions
 and+4.303
,+4.266
.+4.087
 the+4.085
 a+3.857
Neg logit contributions
lor-4.456
umm-4.453
arians-4.320
 former-4.289
ocol-4.251
Token did
Token ID750
Feature activation-1.00e+00

Pos logit contributions
 and+3.856
,+3.814
 the+3.699
.+3.660
 a+3.469
Neg logit contributions
lor-4.885
umm-4.796
arians-4.665
 former-4.617
rol-4.600
Token not
Token ID407
Feature activation-1.00e+00

Pos logit contributions
 and+2.404
,+2.342
 the+2.194
.+2.169
 a+1.956
Neg logit contributions
lor-6.311
umm-6.157
 former-6.122
arians-6.107
vation-6.030
Token say
Token ID910
Feature activation-1.00e+00

Pos logit contributions
 and+3.985
,+3.941
 the+3.798
.+3.755
 a+3.556
Neg logit contributions
umm-4.696
lor-4.684
arians-4.572
 former-4.546
ocol-4.534
Token anything
Token ID1997
Feature activation-1.00e+00

Pos logit contributions
 and+4.240
,+4.100
.+3.956
 the+3.952
 a+3.727
Neg logit contributions
lor-4.611
umm-4.447
arians-4.346
ocol-4.309
osity-4.283
Token either
Token ID2035
Feature activation-1.00e+00

Pos logit contributions
 and+1.887
,+1.833
 the+1.715
.+1.636
 a+1.521
Neg logit contributions
lor-6.792
umm-6.693
arians-6.629
 former-6.556
osity-6.517
Token.
Token ID13
Feature activation-1.00e+00

Pos logit contributions
 and+0.908
,+0.845
 the+0.754
.+0.661
 a+0.551
Neg logit contributions
lor-7.796
umm-7.712
arians-7.585
bek-7.520
rol-7.508
Token Tom
Token ID4186
Feature activation-1.00e+00

Pos logit contributions
 and+2.998
,+2.958
.+2.773
 the+2.765
 a+2.545
Neg logit contributions
lor-5.835
umm-5.736
arians-5.627
 former-5.598
bek-5.542
Token was
Token ID373
Feature activation-1.00e+00

Pos logit contributions
 and+3.051
,+3.050
 the+2.920
.+2.910
 a+2.699
Neg logit contributions
lor-5.644
umm-5.518
arians-5.485
 former-5.403
bek-5.367
Token scared
Token ID12008
Feature activation-1.00e+00

Pos logit contributions
 and+3.745
,+3.721
.+3.537
 the+3.501
 a+3.237
Neg logit contributions
lor-4.966
umm-4.875
 former-4.831
arians-4.811
rol-4.768
TokenTom
Token ID13787
Feature activation-1.00e+00

Pos logit contributions
 and+3.793
,+3.743
 the+3.571
.+3.571
 a+3.353
Neg logit contributions
lor-5.109
umm-4.994
arians-4.899
bek-4.864
 former-4.831
Token went
Token ID1816
Feature activation-1.00e+00

Pos logit contributions
 and+3.016
,+3.008
 the+2.887
.+2.877
 a+2.667
Neg logit contributions
lor-5.701
umm-5.554
arians-5.536
 former-5.424
bek-5.422
Token to
Token ID284
Feature activation-1.00e+00

Pos logit contributions
 and+1.897
,+1.862
 the+1.695
.+1.685
 a+1.486
Neg logit contributions
lor-6.857
umm-6.725
arians-6.671
rol-6.622
 former-6.609
Token his
Token ID465
Feature activation-1.00e+00

Pos logit contributions
 and+2.421
,+2.379
.+2.188
 the+2.075
 a+1.907
Neg logit contributions
lor-6.291
umm-6.209
arians-6.152
 former-6.147
ocol-6.106
Token bed
Token ID3996
Feature activation-1.00e+00

Pos logit contributions
 and+3.913
,+3.873
 the+3.718
.+3.705
 a+3.490
Neg logit contributions
lor-4.834
umm-4.816
 former-4.723
arians-4.721
bek-4.586
Token and
Token ID290
Feature activation-1.00e+00

Pos logit contributions
 and+1.202
,+1.175
 the+1.102
.+0.994
 a+0.868
Neg logit contributions
lor-7.530
umm-7.394
arians-7.294
 former-7.289
rol-7.173
Token hid
Token ID24519
Feature activation-1.00e+00

Pos logit contributions
 and+3.673
,+3.642
.+3.481
 the+3.418
 a+3.205
Neg logit contributions
lor-5.079
umm-4.905
arians-4.883
 former-4.883
bek-4.841
Token under
Token ID739
Feature activation-1.00e+00

Pos logit contributions
 and+3.087
,+3.063
 the+2.823
.+2.810
 a+2.646
Neg logit contributions
lor-5.605
umm-5.559
arians-5.462
ocol-5.453
 former-5.388
Token the
Token ID262
Feature activation-1.00e+00

Pos logit contributions
 and+1.535
,+1.490
.+1.283
 the+1.171
 a+0.964
Neg logit contributions
lor-7.193
umm-7.128
ocol-7.026
 former-7.003
arians-6.979
Token covers
Token ID8698
Feature activation-1.00e+00

Pos logit contributions
 and+4.553
,+4.535
 the+4.373
.+4.330
 a+4.174
Neg logit contributions
lor-4.191
umm-4.148
arians-3.968
ocol-3.956
 former-3.947
Token.
Token ID13
Feature activation-1.00e+00

Pos logit contributions
 and+0.805
,+0.772
 the+0.612
.+0.530
 a+0.430
Neg logit contributions
lor-7.961
umm-7.861
arians-7.701
rol-7.682
ocol-7.637
Token
Token ID198
Feature activation-1.00e+00

Pos logit contributions
 and+1.407
,+1.362
 the+1.163
.+1.162
 a+0.958
Neg logit contributions
lor-7.425
umm-7.252
arians-7.161
 former-7.132
rol-7.118
TokenTom
Token ID13787
Feature activation-1.00e+00

Pos logit contributions
 and+3.793
,+3.743
 the+3.571
.+3.571
 a+3.353
Neg logit contributions
lor-5.109
umm-4.994
arians-4.899
bek-4.864
 former-4.831
Token went
Token ID1816
Feature activation-1.00e+00

Pos logit contributions
 and+3.016
,+3.008
 the+2.887
.+2.877
 a+2.667
Neg logit contributions
lor-5.701
umm-5.554
arians-5.536
 former-5.424
bek-5.422
Token to
Token ID284
Feature activation-1.00e+00

Pos logit contributions
 and+1.897
,+1.862
 the+1.695
.+1.685
 a+1.486
Neg logit contributions
lor-6.857
umm-6.725
arians-6.671
rol-6.622
 former-6.609
Token his
Token ID465
Feature activation-1.00e+00

Pos logit contributions
 and+2.421
,+2.379
.+2.188
 the+2.075
 a+1.907
Neg logit contributions
lor-6.291
umm-6.209
arians-6.152
 former-6.147
ocol-6.106
Token bed
Token ID3996
Feature activation-1.00e+00

Pos logit contributions
 and+3.913
,+3.873
 the+3.718
.+3.705
 a+3.490
Neg logit contributions
lor-4.834
umm-4.816
 former-4.723
arians-4.721
bek-4.586
Token and
Token ID290
Feature activation-1.00e+00

Pos logit contributions
 and+1.202
,+1.175
 the+1.102
.+0.994
 a+0.868
Neg logit contributions
lor-7.530
umm-7.394
arians-7.294
 former-7.289
rol-7.173
Token hid
Token ID24519
Feature activation-1.00e+00

Pos logit contributions
 and+3.673
,+3.642
.+3.481
 the+3.418
 a+3.205
Neg logit contributions
lor-5.079
umm-4.905
arians-4.883
 former-4.883
bek-4.841
Token under
Token ID739
Feature activation-1.00e+00

Pos logit contributions
 and+3.087
,+3.063
 the+2.823
.+2.810
 a+2.646
Neg logit contributions
lor-5.605
umm-5.559
arians-5.462
ocol-5.453
 former-5.388
Token the
Token ID262
Feature activation-1.00e+00

Pos logit contributions
 and+1.535
,+1.490
.+1.283
 the+1.171
 a+0.964
Neg logit contributions
lor-7.193
umm-7.128
ocol-7.026
 former-7.003
arians-6.979
Token covers
Token ID8698
Feature activation-1.00e+00

Pos logit contributions
 and+4.553
,+4.535
 the+4.373
.+4.330
 a+4.174
Neg logit contributions
lor-4.191
umm-4.148
arians-3.968
ocol-3.956
 former-3.947
Token.
Token ID13
Feature activation-1.00e+00

Pos logit contributions
 and+0.489
,+0.453
 the+0.380
.+0.260
 a+0.205
Neg logit contributions
umm-8.076
lor-8.012
arians-7.877
ocol-7.862
rol-7.818
Token
Token ID198
Feature activation-1.00e+00

Pos logit contributions
 and+3.077
,+3.030
 the+2.838
.+2.837
 a+2.615
Neg logit contributions
lor-5.751
umm-5.696
arians-5.556
 former-5.522
bek-5.482
Token
Token ID198
Feature activation-1.00e+00

Pos logit contributions
 and+1.407
,+1.362
 the+1.163
.+1.162
 a+0.958
Neg logit contributions
lor-7.425
umm-7.252
arians-7.161
 former-7.132
rol-7.118
TokenTom
Token ID13787
Feature activation-1.00e+00

Pos logit contributions
 and+3.793
,+3.743
 the+3.571
.+3.571
 a+3.353
Neg logit contributions
lor-5.109
umm-4.994
arians-4.899
bek-4.864
 former-4.831
Token went
Token ID1816
Feature activation-1.00e+00

Pos logit contributions
 and+3.016
,+3.008
 the+2.887
.+2.877
 a+2.667
Neg logit contributions
lor-5.701
umm-5.554
arians-5.536
 former-5.424
bek-5.422
Token to
Token ID284
Feature activation-1.00e+00

Pos logit contributions
 and+1.897
,+1.862
 the+1.695
.+1.685
 a+1.486
Neg logit contributions
lor-6.857
umm-6.725
arians-6.671
rol-6.622
 former-6.609
Token his
Token ID465
Feature activation-1.00e+00

Pos logit contributions
 and+2.421
,+2.379
.+2.188
 the+2.075
 a+1.907
Neg logit contributions
lor-6.291
umm-6.209
arians-6.152
 former-6.147
ocol-6.106
Token bed
Token ID3996
Feature activation-1.00e+00

Pos logit contributions
 and+3.913
,+3.873
 the+3.718
.+3.705
 a+3.490
Neg logit contributions
lor-4.834
umm-4.816
 former-4.723
arians-4.721
bek-4.586
Token and
Token ID290
Feature activation-1.00e+00

Pos logit contributions
 and+1.202
,+1.175
 the+1.102
.+0.994
 a+0.868
Neg logit contributions
lor-7.530
umm-7.394
arians-7.294
 former-7.289
rol-7.173
Token hid
Token ID24519
Feature activation-1.00e+00

Pos logit contributions
 and+3.673
,+3.642
.+3.481
 the+3.418
 a+3.205
Neg logit contributions
lor-5.079
umm-4.905
arians-4.883
 former-4.883
bek-4.841
Token under
Token ID739
Feature activation-1.00e+00

Pos logit contributions
 and+3.087
,+3.063
 the+2.823
.+2.810
 a+2.646
Neg logit contributions
lor-5.605
umm-5.559
arians-5.462
ocol-5.453
 former-5.388
Token
Token ID198
Feature activation-1.00e+00

Pos logit contributions
 and+3.077
,+3.030
 the+2.838
.+2.837
 a+2.615
Neg logit contributions
lor-5.751
umm-5.696
arians-5.556
 former-5.522
bek-5.482
Token
Token ID198
Feature activation-1.00e+00

Pos logit contributions
 and+1.407
,+1.362
 the+1.163
.+1.162
 a+0.958
Neg logit contributions
lor-7.425
umm-7.252
arians-7.161
 former-7.132
rol-7.118
TokenTom
Token ID13787
Feature activation-1.00e+00

Pos logit contributions
 and+3.793
,+3.743
 the+3.571
.+3.571
 a+3.353
Neg logit contributions
lor-5.109
umm-4.994
arians-4.899
bek-4.864
 former-4.831
Token went
Token ID1816
Feature activation-1.00e+00

Pos logit contributions
 and+3.016
,+3.008
 the+2.887
.+2.877
 a+2.667
Neg logit contributions
lor-5.701
umm-5.554
arians-5.536
 former-5.424
bek-5.422
Token to
Token ID284
Feature activation-1.00e+00

Pos logit contributions
 and+1.897
,+1.862
 the+1.695
.+1.685
 a+1.486
Neg logit contributions
lor-6.857
umm-6.725
arians-6.671
rol-6.622
 former-6.609
Token his
Token ID465
Feature activation-1.00e+00

Pos logit contributions
 and+2.421
,+2.379
.+2.188
 the+2.075
 a+1.907
Neg logit contributions
lor-6.291
umm-6.209
arians-6.152
 former-6.147
ocol-6.106
Token bed
Token ID3996
Feature activation-1.00e+00

Pos logit contributions
 and+3.913
,+3.873
 the+3.718
.+3.705
 a+3.490
Neg logit contributions
lor-4.834
umm-4.816
 former-4.723
arians-4.721
bek-4.586
Token and
Token ID290
Feature activation-1.00e+00

Pos logit contributions
 and+1.202
,+1.175
 the+1.102
.+0.994
 a+0.868
Neg logit contributions
lor-7.530
umm-7.394
arians-7.294
 former-7.289
rol-7.173
Token hid
Token ID24519
Feature activation-1.00e+00

Pos logit contributions
 and+3.673
,+3.642
.+3.481
 the+3.418
 a+3.205
Neg logit contributions
lor-5.079
umm-4.905
arians-4.883
 former-4.883
bek-4.841
Token under
Token ID739
Feature activation-1.00e+00

Pos logit contributions
 and+3.087
,+3.063
 the+2.823
.+2.810
 a+2.646
Neg logit contributions
lor-5.605
umm-5.559
arians-5.462
ocol-5.453
 former-5.388
Token the
Token ID262
Feature activation-1.00e+00

Pos logit contributions
 and+1.535
,+1.490
.+1.283
 the+1.171
 a+0.964
Neg logit contributions
lor-7.193
umm-7.128
ocol-7.026
 former-7.003
arians-6.979
Token talking
Token ID3375
Feature activation-1.00e+00

Pos logit contributions
 and+3.829
,+3.751
 the+3.632
.+3.587
 a+3.396
Neg logit contributions
lor-4.929
umm-4.802
arians-4.752
 former-4.727
rol-4.659
Token,
Token ID11
Feature activation-1.00e+00

Pos logit contributions
 and+2.866
,+2.841
 the+2.709
.+2.650
 a+2.470
Neg logit contributions
lor-5.876
umm-5.771
arians-5.686
 former-5.659
rol-5.595
Token table
Token ID3084
Feature activation-1.00e+00

Pos logit contributions
 and+3.800
,+3.783
.+3.646
 the+3.611
 a+3.406
Neg logit contributions
lor-4.892
umm-4.862
arians-4.766
 former-4.745
ocol-4.659
Token?"
Token ID1701
Feature activation-1.00e+00

Pos logit contributions
 and+2.232
,+2.187
 the+2.104
.+2.024
 a+1.870
Neg logit contributions
lor-6.480
umm-6.419
arians-6.281
 former-6.237
ocol-6.176
Token The
Token ID383
Feature activation-1.00e+00

Pos logit contributions
 and+3.193
,+3.135
.+2.971
 the+2.937
 a+2.746
Neg logit contributions
lor-5.541
umm-5.451
arians-5.367
 former-5.345
ocol-5.305
Token table
Token ID3084
Feature activation-1.00e+00

Pos logit contributions
 and+4.303
,+4.266
.+4.087
 the+4.085
 a+3.857
Neg logit contributions
lor-4.456
umm-4.453
arians-4.320
 former-4.289
ocol-4.251
Token did
Token ID750
Feature activation-1.00e+00

Pos logit contributions
 and+3.856
,+3.814
 the+3.699
.+3.660
 a+3.469
Neg logit contributions
lor-4.885
umm-4.796
arians-4.665
 former-4.617
rol-4.600
Token not
Token ID407
Feature activation-1.00e+00

Pos logit contributions
 and+2.404
,+2.342
 the+2.194
.+2.169
 a+1.956
Neg logit contributions
lor-6.311
umm-6.157
 former-6.122
arians-6.107
vation-6.030
Token say
Token ID910
Feature activation-1.00e+00

Pos logit contributions
 and+3.985
,+3.941
 the+3.798
.+3.755
 a+3.556
Neg logit contributions
umm-4.696
lor-4.684
arians-4.572
 former-4.546
ocol-4.534
Token anything
Token ID1997
Feature activation-1.00e+00

Pos logit contributions
 and+4.240
,+4.100
.+3.956
 the+3.952
 a+3.727
Neg logit contributions
lor-4.611
umm-4.447
arians-4.346
ocol-4.309
osity-4.283
Token either
Token ID2035
Feature activation-1.00e+00

Pos logit contributions
 and+1.887
,+1.833
 the+1.715
.+1.636
 a+1.521
Neg logit contributions
lor-6.792
umm-6.693
arians-6.629
 former-6.556
osity-6.517
Token you
Token ID345
Feature activation-1.00e+00

Pos logit contributions
 and+3.315
,+3.285
.+3.142
 the+3.140
 a+2.952
Neg logit contributions
lor-5.376
umm-5.298
arians-5.276
 former-5.143
rol-5.130
Token talking
Token ID3375
Feature activation-1.00e+00

Pos logit contributions
 and+3.829
,+3.751
 the+3.632
.+3.587
 a+3.396
Neg logit contributions
lor-4.929
umm-4.802
arians-4.752
 former-4.727
rol-4.659
Token,
Token ID11
Feature activation-1.00e+00

Pos logit contributions
 and+2.866
,+2.841
 the+2.709
.+2.650
 a+2.470
Neg logit contributions
lor-5.876
umm-5.771
arians-5.686
 former-5.659
rol-5.595
Token table
Token ID3084
Feature activation-1.00e+00

Pos logit contributions
 and+3.800
,+3.783
.+3.646
 the+3.611
 a+3.406
Neg logit contributions
lor-4.892
umm-4.862
arians-4.766
 former-4.745
ocol-4.659
Token?"
Token ID1701
Feature activation-1.00e+00

Pos logit contributions
 and+2.232
,+2.187
 the+2.104
.+2.024
 a+1.870
Neg logit contributions
lor-6.480
umm-6.419
arians-6.281
 former-6.237
ocol-6.176
Token The
Token ID383
Feature activation-1.00e+00

Pos logit contributions
 and+3.193
,+3.135
.+2.971
 the+2.937
 a+2.746
Neg logit contributions
lor-5.541
umm-5.451
arians-5.367
 former-5.345
ocol-5.305
Token table
Token ID3084
Feature activation-1.00e+00

Pos logit contributions
 and+4.303
,+4.266
.+4.087
 the+4.085
 a+3.857
Neg logit contributions
lor-4.456
umm-4.453
arians-4.320
 former-4.289
ocol-4.251
Token did
Token ID750
Feature activation-1.00e+00

Pos logit contributions
 and+3.856
,+3.814
 the+3.699
.+3.660
 a+3.469
Neg logit contributions
lor-4.885
umm-4.796
arians-4.665
 former-4.617
rol-4.600
Token not
Token ID407
Feature activation-1.00e+00

Pos logit contributions
 and+2.404
,+2.342
 the+2.194
.+2.169
 a+1.956
Neg logit contributions
lor-6.311
umm-6.157
 former-6.122
arians-6.107
vation-6.030
Token say
Token ID910
Feature activation-1.00e+00

Pos logit contributions
 and+3.985
,+3.941
 the+3.798
.+3.755
 a+3.556
Neg logit contributions
umm-4.696
lor-4.684
arians-4.572
 former-4.546
ocol-4.534
Token anything
Token ID1997
Feature activation-1.00e+00

Pos logit contributions
 and+4.240
,+4.100
.+3.956
 the+3.952
 a+3.727
Neg logit contributions
lor-4.611
umm-4.447
arians-4.346
ocol-4.309
osity-4.283
Token,
Token ID11
Feature activation-1.00e+00

Pos logit contributions
 and+2.866
,+2.841
 the+2.709
.+2.650
 a+2.470
Neg logit contributions
lor-5.876
umm-5.771
arians-5.686
 former-5.659
rol-5.595
Token table
Token ID3084
Feature activation-1.00e+00

Pos logit contributions
 and+3.800
,+3.783
.+3.646
 the+3.611
 a+3.406
Neg logit contributions
lor-4.892
umm-4.862
arians-4.766
 former-4.745
ocol-4.659
Token?"
Token ID1701
Feature activation-1.00e+00

Pos logit contributions
 and+2.232
,+2.187
 the+2.104
.+2.024
 a+1.870
Neg logit contributions
lor-6.480
umm-6.419
arians-6.281
 former-6.237
ocol-6.176
Token The
Token ID383
Feature activation-1.00e+00

Pos logit contributions
 and+3.193
,+3.135
.+2.971
 the+2.937
 a+2.746
Neg logit contributions
lor-5.541
umm-5.451
arians-5.367
 former-5.345
ocol-5.305
Token table
Token ID3084
Feature activation-1.00e+00

Pos logit contributions
 and+4.303
,+4.266
.+4.087
 the+4.085
 a+3.857
Neg logit contributions
lor-4.456
umm-4.453
arians-4.320
 former-4.289
ocol-4.251
Token did
Token ID750
Feature activation-1.00e+00

Pos logit contributions
 and+3.856
,+3.814
 the+3.699
.+3.660
 a+3.469
Neg logit contributions
lor-4.885
umm-4.796
arians-4.665
 former-4.617
rol-4.600
Token not
Token ID407
Feature activation-1.00e+00

Pos logit contributions
 and+2.404
,+2.342
 the+2.194
.+2.169
 a+1.956
Neg logit contributions
lor-6.311
umm-6.157
 former-6.122
arians-6.107
vation-6.030
Token say
Token ID910
Feature activation-1.00e+00

Pos logit contributions
 and+3.985
,+3.941
 the+3.798
.+3.755
 a+3.556
Neg logit contributions
umm-4.696
lor-4.684
arians-4.572
 former-4.546
ocol-4.534
Token anything
Token ID1997
Feature activation-1.00e+00

Pos logit contributions
 and+4.240
,+4.100
.+3.956
 the+3.952
 a+3.727
Neg logit contributions
lor-4.611
umm-4.447
arians-4.346
ocol-4.309
osity-4.283
Token either
Token ID2035
Feature activation-1.00e+00

Pos logit contributions
 and+1.887
,+1.833
 the+1.715
.+1.636
 a+1.521
Neg logit contributions
lor-6.792
umm-6.693
arians-6.629
 former-6.556
osity-6.517
Token.
Token ID13
Feature activation-1.00e+00

Pos logit contributions
 and+0.908
,+0.845
 the+0.754
.+0.661
 a+0.551
Neg logit contributions
lor-7.796
umm-7.712
arians-7.585
bek-7.520
rol-7.508
Token table
Token ID3084
Feature activation-1.00e+00

Pos logit contributions
 and+3.800
,+3.783
.+3.646
 the+3.611
 a+3.406
Neg logit contributions
lor-4.892
umm-4.862
arians-4.766
 former-4.745
ocol-4.659
Token?"
Token ID1701
Feature activation-1.00e+00

Pos logit contributions
 and+2.232
,+2.187
 the+2.104
.+2.024
 a+1.870
Neg logit contributions
lor-6.480
umm-6.419
arians-6.281
 former-6.237
ocol-6.176
Token The
Token ID383
Feature activation-1.00e+00

Pos logit contributions
 and+3.193
,+3.135
.+2.971
 the+2.937
 a+2.746
Neg logit contributions
lor-5.541
umm-5.451
arians-5.367
 former-5.345
ocol-5.305
Token table
Token ID3084
Feature activation-1.00e+00

Pos logit contributions
 and+4.303
,+4.266
.+4.087
 the+4.085
 a+3.857
Neg logit contributions
lor-4.456
umm-4.453
arians-4.320
 former-4.289
ocol-4.251
Token did
Token ID750
Feature activation-1.00e+00

Pos logit contributions
 and+3.856
,+3.814
 the+3.699
.+3.660
 a+3.469
Neg logit contributions
lor-4.885
umm-4.796
arians-4.665
 former-4.617
rol-4.600
Token not
Token ID407
Feature activation-1.00e+00

Pos logit contributions
 and+2.404
,+2.342
 the+2.194
.+2.169
 a+1.956
Neg logit contributions
lor-6.311
umm-6.157
 former-6.122
arians-6.107
vation-6.030
Token say
Token ID910
Feature activation-1.00e+00

Pos logit contributions
 and+3.985
,+3.941
 the+3.798
.+3.755
 a+3.556
Neg logit contributions
umm-4.696
lor-4.684
arians-4.572
 former-4.546
ocol-4.534
Token anything
Token ID1997
Feature activation-1.00e+00

Pos logit contributions
 and+4.240
,+4.100
.+3.956
 the+3.952
 a+3.727
Neg logit contributions
lor-4.611
umm-4.447
arians-4.346
ocol-4.309
osity-4.283
Token either
Token ID2035
Feature activation-1.00e+00

Pos logit contributions
 and+1.887
,+1.833
 the+1.715
.+1.636
 a+1.521
Neg logit contributions
lor-6.792
umm-6.693
arians-6.629
 former-6.556
osity-6.517
Token.
Token ID13
Feature activation-1.00e+00

Pos logit contributions
 and+0.908
,+0.845
 the+0.754
.+0.661
 a+0.551
Neg logit contributions
lor-7.796
umm-7.712
arians-7.585
bek-7.520
rol-7.508
Token Tom
Token ID4186
Feature activation-1.00e+00

Pos logit contributions
 and+2.998
,+2.958
.+2.773
 the+2.765
 a+2.545
Neg logit contributions
lor-5.835
umm-5.736
arians-5.627
 former-5.598
bek-5.542
Token either
Token ID2035
Feature activation-1.00e+00

Pos logit contributions
 and+1.887
,+1.833
 the+1.715
.+1.636
 a+1.521
Neg logit contributions
lor-6.792
umm-6.693
arians-6.629
 former-6.556
osity-6.517
Token.
Token ID13
Feature activation-1.00e+00

Pos logit contributions
 and+0.908
,+0.845
 the+0.754
.+0.661
 a+0.551
Neg logit contributions
lor-7.796
umm-7.712
arians-7.585
bek-7.520
rol-7.508
Token Tom
Token ID4186
Feature activation-1.00e+00

Pos logit contributions
 and+2.998
,+2.958
.+2.773
 the+2.765
 a+2.545
Neg logit contributions
lor-5.835
umm-5.736
arians-5.627
 former-5.598
bek-5.542
Token was
Token ID373
Feature activation-1.00e+00

Pos logit contributions
 and+3.051
,+3.050
 the+2.920
.+2.910
 a+2.699
Neg logit contributions
lor-5.644
umm-5.518
arians-5.485
 former-5.403
bek-5.367
Token scared
Token ID12008
Feature activation-1.00e+00

Pos logit contributions
 and+3.745
,+3.721
.+3.537
 the+3.501
 a+3.237
Neg logit contributions
lor-4.966
umm-4.875
 former-4.831
arians-4.811
rol-4.768
Token.
Token ID13
Feature activation-1.00e+00

Pos logit contributions
 and+0.489
,+0.453
 the+0.380
.+0.260
 a+0.205
Neg logit contributions
umm-8.076
lor-8.012
arians-7.877
ocol-7.862
rol-7.818
Token
Token ID198
Feature activation-1.00e+00

Pos logit contributions
 and+3.077
,+3.030
 the+2.838
.+2.837
 a+2.615
Neg logit contributions
lor-5.751
umm-5.696
arians-5.556
 former-5.522
bek-5.482
Token
Token ID198
Feature activation-1.00e+00

Pos logit contributions
 and+1.407
,+1.362
 the+1.163
.+1.162
 a+0.958
Neg logit contributions
lor-7.425
umm-7.252
arians-7.161
 former-7.132
rol-7.118
TokenTom
Token ID13787
Feature activation-1.00e+00

Pos logit contributions
 and+3.793
,+3.743
 the+3.571
.+3.571
 a+3.353
Neg logit contributions
lor-5.109
umm-4.994
arians-4.899
bek-4.864
 former-4.831
Token went
Token ID1816
Feature activation-1.00e+00

Pos logit contributions
 and+3.016
,+3.008
 the+2.887
.+2.877
 a+2.667
Neg logit contributions
lor-5.701
umm-5.554
arians-5.536
 former-5.424
bek-5.422
Token to
Token ID284
Feature activation-1.00e+00

Pos logit contributions
 and+1.897
,+1.862
 the+1.695
.+1.685
 a+1.486
Neg logit contributions
lor-6.857
umm-6.725
arians-6.671
rol-6.622
 former-6.609
Token anything
Token ID1997
Feature activation-1.00e+00

Pos logit contributions
 and+4.240
,+4.100
.+3.956
 the+3.952
 a+3.727
Neg logit contributions
lor-4.611
umm-4.447
arians-4.346
ocol-4.309
osity-4.283
Token either
Token ID2035
Feature activation-1.00e+00

Pos logit contributions
 and+1.887
,+1.833
 the+1.715
.+1.636
 a+1.521
Neg logit contributions
lor-6.792
umm-6.693
arians-6.629
 former-6.556
osity-6.517
Token.
Token ID13
Feature activation-1.00e+00

Pos logit contributions
 and+0.908
,+0.845
 the+0.754
.+0.661
 a+0.551
Neg logit contributions
lor-7.796
umm-7.712
arians-7.585
bek-7.520
rol-7.508
Token Tom
Token ID4186
Feature activation-1.00e+00

Pos logit contributions
 and+2.998
,+2.958
.+2.773
 the+2.765
 a+2.545
Neg logit contributions
lor-5.835
umm-5.736
arians-5.627
 former-5.598
bek-5.542
Token was
Token ID373
Feature activation-1.00e+00

Pos logit contributions
 and+3.051
,+3.050
 the+2.920
.+2.910
 a+2.699
Neg logit contributions
lor-5.644
umm-5.518
arians-5.485
 former-5.403
bek-5.367
Token scared
Token ID12008
Feature activation-1.00e+00

Pos logit contributions
 and+3.745
,+3.721
.+3.537
 the+3.501
 a+3.237
Neg logit contributions
lor-4.966
umm-4.875
 former-4.831
arians-4.811
rol-4.768
Token.
Token ID13
Feature activation-1.00e+00

Pos logit contributions
 and+0.489
,+0.453
 the+0.380
.+0.260
 a+0.205
Neg logit contributions
umm-8.076
lor-8.012
arians-7.877
ocol-7.862
rol-7.818
Token
Token ID198
Feature activation-1.00e+00

Pos logit contributions
 and+3.077
,+3.030
 the+2.838
.+2.837
 a+2.615
Neg logit contributions
lor-5.751
umm-5.696
arians-5.556
 former-5.522
bek-5.482
Token
Token ID198
Feature activation-1.00e+00

Pos logit contributions
 and+1.407
,+1.362
 the+1.163
.+1.162
 a+0.958
Neg logit contributions
lor-7.425
umm-7.252
arians-7.161
 former-7.132
rol-7.118
TokenTom
Token ID13787
Feature activation-1.00e+00

Pos logit contributions
 and+3.793
,+3.743
 the+3.571
.+3.571
 a+3.353
Neg logit contributions
lor-5.109
umm-4.994
arians-4.899
bek-4.864
 former-4.831
Token went
Token ID1816
Feature activation-1.00e+00

Pos logit contributions
 and+3.016
,+3.008
 the+2.887
.+2.877
 a+2.667
Neg logit contributions
lor-5.701
umm-5.554
arians-5.536
 former-5.424
bek-5.422
Token not
Token ID407
Feature activation-1.00e+00

Pos logit contributions
 and+2.404
,+2.342
 the+2.194
.+2.169
 a+1.956
Neg logit contributions
lor-6.311
umm-6.157
 former-6.122
arians-6.107
vation-6.030
Token say
Token ID910
Feature activation-1.00e+00

Pos logit contributions
 and+3.985
,+3.941
 the+3.798
.+3.755
 a+3.556
Neg logit contributions
umm-4.696
lor-4.684
arians-4.572
 former-4.546
ocol-4.534
Token anything
Token ID1997
Feature activation-1.00e+00

Pos logit contributions
 and+4.240
,+4.100
.+3.956
 the+3.952
 a+3.727
Neg logit contributions
lor-4.611
umm-4.447
arians-4.346
ocol-4.309
osity-4.283
Token either
Token ID2035
Feature activation-1.00e+00

Pos logit contributions
 and+1.887
,+1.833
 the+1.715
.+1.636
 a+1.521
Neg logit contributions
lor-6.792
umm-6.693
arians-6.629
 former-6.556
osity-6.517
Token.
Token ID13
Feature activation-1.00e+00

Pos logit contributions
 and+0.908
,+0.845
 the+0.754
.+0.661
 a+0.551
Neg logit contributions
lor-7.796
umm-7.712
arians-7.585
bek-7.520
rol-7.508
Token Tom
Token ID4186
Feature activation-1.00e+00

Pos logit contributions
 and+2.998
,+2.958
.+2.773
 the+2.765
 a+2.545
Neg logit contributions
lor-5.835
umm-5.736
arians-5.627
 former-5.598
bek-5.542
Token was
Token ID373
Feature activation-1.00e+00

Pos logit contributions
 and+3.051
,+3.050
 the+2.920
.+2.910
 a+2.699
Neg logit contributions
lor-5.644
umm-5.518
arians-5.485
 former-5.403
bek-5.367
Token scared
Token ID12008
Feature activation-1.00e+00

Pos logit contributions
 and+3.745
,+3.721
.+3.537
 the+3.501
 a+3.237
Neg logit contributions
lor-4.966
umm-4.875
 former-4.831
arians-4.811
rol-4.768
Token.
Token ID13
Feature activation-1.00e+00

Pos logit contributions
 and+0.489
,+0.453
 the+0.380
.+0.260
 a+0.205
Neg logit contributions
umm-8.076
lor-8.012
arians-7.877
ocol-7.862
rol-7.818
Token
Token ID198
Feature activation-1.00e+00

Pos logit contributions
 and+3.077
,+3.030
 the+2.838
.+2.837
 a+2.615
Neg logit contributions
lor-5.751
umm-5.696
arians-5.556
 former-5.522
bek-5.482
Token
Token ID198
Feature activation-1.00e+00

Pos logit contributions
 and+1.407
,+1.362
 the+1.163
.+1.162
 a+0.958
Neg logit contributions
lor-7.425
umm-7.252
arians-7.161
 former-7.132
rol-7.118
Token say
Token ID910
Feature activation-1.00e+00

Pos logit contributions
 and+3.985
,+3.941
 the+3.798
.+3.755
 a+3.556
Neg logit contributions
umm-4.696
lor-4.684
arians-4.572
 former-4.546
ocol-4.534
Token anything
Token ID1997
Feature activation-1.00e+00

Pos logit contributions
 and+4.240
,+4.100
.+3.956
 the+3.952
 a+3.727
Neg logit contributions
lor-4.611
umm-4.447
arians-4.346
ocol-4.309
osity-4.283
Token either
Token ID2035
Feature activation-1.00e+00

Pos logit contributions
 and+1.887
,+1.833
 the+1.715
.+1.636
 a+1.521
Neg logit contributions
lor-6.792
umm-6.693
arians-6.629
 former-6.556
osity-6.517
Token.
Token ID13
Feature activation-1.00e+00

Pos logit contributions
 and+0.908
,+0.845
 the+0.754
.+0.661
 a+0.551
Neg logit contributions
lor-7.796
umm-7.712
arians-7.585
bek-7.520
rol-7.508
Token Tom
Token ID4186
Feature activation-1.00e+00

Pos logit contributions
 and+2.998
,+2.958
.+2.773
 the+2.765
 a+2.545
Neg logit contributions
lor-5.835
umm-5.736
arians-5.627
 former-5.598
bek-5.542
Token was
Token ID373
Feature activation-1.00e+00

Pos logit contributions
 and+3.051
,+3.050
 the+2.920
.+2.910
 a+2.699
Neg logit contributions
lor-5.644
umm-5.518
arians-5.485
 former-5.403
bek-5.367
Token scared
Token ID12008
Feature activation-1.00e+00

Pos logit contributions
 and+3.745
,+3.721
.+3.537
 the+3.501
 a+3.237
Neg logit contributions
lor-4.966
umm-4.875
 former-4.831
arians-4.811
rol-4.768
Token.
Token ID13
Feature activation-1.00e+00

Pos logit contributions
 and+0.489
,+0.453
 the+0.380
.+0.260
 a+0.205
Neg logit contributions
umm-8.076
lor-8.012
arians-7.877
ocol-7.862
rol-7.818
Token
Token ID198
Feature activation-1.00e+00

Pos logit contributions
 and+3.077
,+3.030
 the+2.838
.+2.837
 a+2.615
Neg logit contributions
lor-5.751
umm-5.696
arians-5.556
 former-5.522
bek-5.482
Token
Token ID198
Feature activation-1.00e+00

Pos logit contributions
 and+1.407
,+1.362
 the+1.163
.+1.162
 a+0.958
Neg logit contributions
lor-7.425
umm-7.252
arians-7.161
 former-7.132
rol-7.118
TokenTom
Token ID13787
Feature activation-1.00e+00

Pos logit contributions
 and+3.793
,+3.743
 the+3.571
.+3.571
 a+3.353
Neg logit contributions
lor-5.109
umm-4.994
arians-4.899
bek-4.864
 former-4.831
Token Tom
Token ID4186
Feature activation-1.00e+00

Pos logit contributions
 and+2.998
,+2.958
.+2.773
 the+2.765
 a+2.545
Neg logit contributions
lor-5.835
umm-5.736
arians-5.627
 former-5.598
bek-5.542
Token was
Token ID373
Feature activation-1.00e+00

Pos logit contributions
 and+3.051
,+3.050
 the+2.920
.+2.910
 a+2.699
Neg logit contributions
lor-5.644
umm-5.518
arians-5.485
 former-5.403
bek-5.367
Token scared
Token ID12008
Feature activation-1.00e+00

Pos logit contributions
 and+3.745
,+3.721
.+3.537
 the+3.501
 a+3.237
Neg logit contributions
lor-4.966
umm-4.875
 former-4.831
arians-4.811
rol-4.768
Token.
Token ID13
Feature activation-1.00e+00

Pos logit contributions
 and+0.489
,+0.453
 the+0.380
.+0.260
 a+0.205
Neg logit contributions
umm-8.076
lor-8.012
arians-7.877
ocol-7.862
rol-7.818
Token
Token ID198
Feature activation-1.00e+00

Pos logit contributions
 and+3.077
,+3.030
 the+2.838
.+2.837
 a+2.615
Neg logit contributions
lor-5.751
umm-5.696
arians-5.556
 former-5.522
bek-5.482
Token
Token ID198
Feature activation-1.00e+00

Pos logit contributions
 and+1.407
,+1.362
 the+1.163
.+1.162
 a+0.958
Neg logit contributions
lor-7.425
umm-7.252
arians-7.161
 former-7.132
rol-7.118
TokenTom
Token ID13787
Feature activation-1.00e+00

Pos logit contributions
 and+3.793
,+3.743
 the+3.571
.+3.571
 a+3.353
Neg logit contributions
lor-5.109
umm-4.994
arians-4.899
bek-4.864
 former-4.831
Token went
Token ID1816
Feature activation-1.00e+00

Pos logit contributions
 and+3.016
,+3.008
 the+2.887
.+2.877
 a+2.667
Neg logit contributions
lor-5.701
umm-5.554
arians-5.536
 former-5.424
bek-5.422
Token to
Token ID284
Feature activation-1.00e+00

Pos logit contributions
 and+1.897
,+1.862
 the+1.695
.+1.685
 a+1.486
Neg logit contributions
lor-6.857
umm-6.725
arians-6.671
rol-6.622
 former-6.609
Token his
Token ID465
Feature activation-1.00e+00

Pos logit contributions
 and+2.421
,+2.379
.+2.188
 the+2.075
 a+1.907
Neg logit contributions
lor-6.291
umm-6.209
arians-6.152
 former-6.147
ocol-6.106
Token bed
Token ID3996
Feature activation-1.00e+00

Pos logit contributions
 and+3.913
,+3.873
 the+3.718
.+3.705
 a+3.490
Neg logit contributions
lor-4.834
umm-4.816
 former-4.723
arians-4.721
bek-4.586
Token.
Token ID13
Feature activation-1.00e+00

Pos logit contributions
 and+0.908
,+0.845
 the+0.754
.+0.661
 a+0.551
Neg logit contributions
lor-7.796
umm-7.712
arians-7.585
bek-7.520
rol-7.508
Token Tom
Token ID4186
Feature activation-1.00e+00

Pos logit contributions
 and+2.998
,+2.958
.+2.773
 the+2.765
 a+2.545
Neg logit contributions
lor-5.835
umm-5.736
arians-5.627
 former-5.598
bek-5.542
Token was
Token ID373
Feature activation-1.00e+00

Pos logit contributions
 and+3.051
,+3.050
 the+2.920
.+2.910
 a+2.699
Neg logit contributions
lor-5.644
umm-5.518
arians-5.485
 former-5.403
bek-5.367
Token scared
Token ID12008
Feature activation-1.00e+00

Pos logit contributions
 and+3.745
,+3.721
.+3.537
 the+3.501
 a+3.237
Neg logit contributions
lor-4.966
umm-4.875
 former-4.831
arians-4.811
rol-4.768
Token.
Token ID13
Feature activation-1.00e+00

Pos logit contributions
 and+0.489
,+0.453
 the+0.380
.+0.260
 a+0.205
Neg logit contributions
umm-8.076
lor-8.012
arians-7.877
ocol-7.862
rol-7.818
Token
Token ID198
Feature activation-1.00e+00

Pos logit contributions
 and+3.077
,+3.030
 the+2.838
.+2.837
 a+2.615
Neg logit contributions
lor-5.751
umm-5.696
arians-5.556
 former-5.522
bek-5.482
Token
Token ID198
Feature activation-1.00e+00

Pos logit contributions
 and+1.407
,+1.362
 the+1.163
.+1.162
 a+0.958
Neg logit contributions
lor-7.425
umm-7.252
arians-7.161
 former-7.132
rol-7.118
TokenTom
Token ID13787
Feature activation-1.00e+00

Pos logit contributions
 and+3.793
,+3.743
 the+3.571
.+3.571
 a+3.353
Neg logit contributions
lor-5.109
umm-4.994
arians-4.899
bek-4.864
 former-4.831
Token went
Token ID1816
Feature activation-1.00e+00

Pos logit contributions
 and+3.016
,+3.008
 the+2.887
.+2.877
 a+2.667
Neg logit contributions
lor-5.701
umm-5.554
arians-5.536
 former-5.424
bek-5.422
Token to
Token ID284
Feature activation-1.00e+00

Pos logit contributions
 and+1.897
,+1.862
 the+1.695
.+1.685
 a+1.486
Neg logit contributions
lor-6.857
umm-6.725
arians-6.671
rol-6.622
 former-6.609
Token his
Token ID465
Feature activation-1.00e+00

Pos logit contributions
 and+2.421
,+2.379
.+2.188
 the+2.075
 a+1.907
Neg logit contributions
lor-6.291
umm-6.209
arians-6.152
 former-6.147
ocol-6.106
Token was
Token ID373
Feature activation-1.00e+00

Pos logit contributions
 and+3.051
,+3.050
 the+2.920
.+2.910
 a+2.699
Neg logit contributions
lor-5.644
umm-5.518
arians-5.485
 former-5.403
bek-5.367
Token scared
Token ID12008
Feature activation-1.00e+00

Pos logit contributions
 and+3.745
,+3.721
.+3.537
 the+3.501
 a+3.237
Neg logit contributions
lor-4.966
umm-4.875
 former-4.831
arians-4.811
rol-4.768
Token.
Token ID13
Feature activation-1.00e+00

Pos logit contributions
 and+0.489
,+0.453
 the+0.380
.+0.260
 a+0.205
Neg logit contributions
umm-8.076
lor-8.012
arians-7.877
ocol-7.862
rol-7.818
Token
Token ID198
Feature activation-1.00e+00

Pos logit contributions
 and+3.077
,+3.030
 the+2.838
.+2.837
 a+2.615
Neg logit contributions
lor-5.751
umm-5.696
arians-5.556
 former-5.522
bek-5.482
Token
Token ID198
Feature activation-1.00e+00

Pos logit contributions
 and+1.407
,+1.362
 the+1.163
.+1.162
 a+0.958
Neg logit contributions
lor-7.425
umm-7.252
arians-7.161
 former-7.132
rol-7.118
TokenTom
Token ID13787
Feature activation-1.00e+00

Pos logit contributions
 and+3.793
,+3.743
 the+3.571
.+3.571
 a+3.353
Neg logit contributions
lor-5.109
umm-4.994
arians-4.899
bek-4.864
 former-4.831
Token went
Token ID1816
Feature activation-1.00e+00

Pos logit contributions
 and+3.016
,+3.008
 the+2.887
.+2.877
 a+2.667
Neg logit contributions
lor-5.701
umm-5.554
arians-5.536
 former-5.424
bek-5.422
Token to
Token ID284
Feature activation-1.00e+00

Pos logit contributions
 and+1.897
,+1.862
 the+1.695
.+1.685
 a+1.486
Neg logit contributions
lor-6.857
umm-6.725
arians-6.671
rol-6.622
 former-6.609
Token his
Token ID465
Feature activation-1.00e+00

Pos logit contributions
 and+2.421
,+2.379
.+2.188
 the+2.075
 a+1.907
Neg logit contributions
lor-6.291
umm-6.209
arians-6.152
 former-6.147
ocol-6.106
Token bed
Token ID3996
Feature activation-1.00e+00

Pos logit contributions
 and+3.913
,+3.873
 the+3.718
.+3.705
 a+3.490
Neg logit contributions
lor-4.834
umm-4.816
 former-4.723
arians-4.721
bek-4.586
Token and
Token ID290
Feature activation-1.00e+00

Pos logit contributions
 and+1.202
,+1.175
 the+1.102
.+0.994
 a+0.868
Neg logit contributions
lor-7.530
umm-7.394
arians-7.294
 former-7.289
rol-7.173
Token scared
Token ID12008
Feature activation-1.00e+00

Pos logit contributions
 and+3.745
,+3.721
.+3.537
 the+3.501
 a+3.237
Neg logit contributions
lor-4.966
umm-4.875
 former-4.831
arians-4.811
rol-4.768
Token.
Token ID13
Feature activation-1.00e+00

Pos logit contributions
 and+0.489
,+0.453
 the+0.380
.+0.260
 a+0.205
Neg logit contributions
umm-8.076
lor-8.012
arians-7.877
ocol-7.862
rol-7.818
Token
Token ID198
Feature activation-1.00e+00

Pos logit contributions
 and+3.077
,+3.030
 the+2.838
.+2.837
 a+2.615
Neg logit contributions
lor-5.751
umm-5.696
arians-5.556
 former-5.522
bek-5.482
Token
Token ID198
Feature activation-1.00e+00

Pos logit contributions
 and+1.407
,+1.362
 the+1.163
.+1.162
 a+0.958
Neg logit contributions
lor-7.425
umm-7.252
arians-7.161
 former-7.132
rol-7.118
TokenTom
Token ID13787
Feature activation-1.00e+00

Pos logit contributions
 and+3.793
,+3.743
 the+3.571
.+3.571
 a+3.353
Neg logit contributions
lor-5.109
umm-4.994
arians-4.899
bek-4.864
 former-4.831
Token went
Token ID1816
Feature activation-1.00e+00

Pos logit contributions
 and+3.016
,+3.008
 the+2.887
.+2.877
 a+2.667
Neg logit contributions
lor-5.701
umm-5.554
arians-5.536
 former-5.424
bek-5.422
Token to
Token ID284
Feature activation-1.00e+00

Pos logit contributions
 and+1.897
,+1.862
 the+1.695
.+1.685
 a+1.486
Neg logit contributions
lor-6.857
umm-6.725
arians-6.671
rol-6.622
 former-6.609
Token his
Token ID465
Feature activation-1.00e+00

Pos logit contributions
 and+2.421
,+2.379
.+2.188
 the+2.075
 a+1.907
Neg logit contributions
lor-6.291
umm-6.209
arians-6.152
 former-6.147
ocol-6.106
Token bed
Token ID3996
Feature activation-1.00e+00

Pos logit contributions
 and+3.913
,+3.873
 the+3.718
.+3.705
 a+3.490
Neg logit contributions
lor-4.834
umm-4.816
 former-4.723
arians-4.721
bek-4.586
Token and
Token ID290
Feature activation-1.00e+00

Pos logit contributions
 and+1.202
,+1.175
 the+1.102
.+0.994
 a+0.868
Neg logit contributions
lor-7.530
umm-7.394
arians-7.294
 former-7.289
rol-7.173
Token hid
Token ID24519
Feature activation-1.00e+00

Pos logit contributions
 and+3.673
,+3.642
.+3.481
 the+3.418
 a+3.205
Neg logit contributions
lor-5.079
umm-4.905
arians-4.883
 former-4.883
bek-4.841
Token did
Token ID750
Feature activation-1.00e+00

Pos logit contributions
 and+3.856
,+3.814
 the+3.699
.+3.660
 a+3.469
Neg logit contributions
lor-4.885
umm-4.796
arians-4.665
 former-4.617
rol-4.600
Token not
Token ID407
Feature activation-1.00e+00

Pos logit contributions
 and+2.404
,+2.342
 the+2.194
.+2.169
 a+1.956
Neg logit contributions
lor-6.311
umm-6.157
 former-6.122
arians-6.107
vation-6.030
Token say
Token ID910
Feature activation-1.00e+00

Pos logit contributions
 and+3.985
,+3.941
 the+3.798
.+3.755
 a+3.556
Neg logit contributions
umm-4.696
lor-4.684
arians-4.572
 former-4.546
ocol-4.534
Token anything
Token ID1997
Feature activation-1.00e+00

Pos logit contributions
 and+4.240
,+4.100
.+3.956
 the+3.952
 a+3.727
Neg logit contributions
lor-4.611
umm-4.447
arians-4.346
ocol-4.309
osity-4.283
Token either
Token ID2035
Feature activation-1.00e+00

Pos logit contributions
 and+1.887
,+1.833
 the+1.715
.+1.636
 a+1.521
Neg logit contributions
lor-6.792
umm-6.693
arians-6.629
 former-6.556
osity-6.517
Token.
Token ID13
Feature activation-1.00e+00

Pos logit contributions
 and+0.908
,+0.845
 the+0.754
.+0.661
 a+0.551
Neg logit contributions
lor-7.796
umm-7.712
arians-7.585
bek-7.520
rol-7.508
Token Tom
Token ID4186
Feature activation-1.00e+00

Pos logit contributions
 and+2.998
,+2.958
.+2.773
 the+2.765
 a+2.545
Neg logit contributions
lor-5.835
umm-5.736
arians-5.627
 former-5.598
bek-5.542
Token was
Token ID373
Feature activation-1.00e+00

Pos logit contributions
 and+3.051
,+3.050
 the+2.920
.+2.910
 a+2.699
Neg logit contributions
lor-5.644
umm-5.518
arians-5.485
 former-5.403
bek-5.367
Token scared
Token ID12008
Feature activation-1.00e+00

Pos logit contributions
 and+3.745
,+3.721
.+3.537
 the+3.501
 a+3.237
Neg logit contributions
lor-4.966
umm-4.875
 former-4.831
arians-4.811
rol-4.768
Token.
Token ID13
Feature activation-1.00e+00

Pos logit contributions
 and+0.489
,+0.453
 the+0.380
.+0.260
 a+0.205
Neg logit contributions
umm-8.076
lor-8.012
arians-7.877
ocol-7.862
rol-7.818
Token
Token ID198
Feature activation-1.00e+00

Pos logit contributions
 and+3.077
,+3.030
 the+2.838
.+2.837
 a+2.615
Neg logit contributions
lor-5.751
umm-5.696
arians-5.556
 former-5.522
bek-5.482
Token table
Token ID3084
Feature activation-1.00e+00

Pos logit contributions
 and+4.303
,+4.266
.+4.087
 the+4.085
 a+3.857
Neg logit contributions
lor-4.456
umm-4.453
arians-4.320
 former-4.289
ocol-4.251
Token did
Token ID750
Feature activation-1.00e+00

Pos logit contributions
 and+3.856
,+3.814
 the+3.699
.+3.660
 a+3.469
Neg logit contributions
lor-4.885
umm-4.796
arians-4.665
 former-4.617
rol-4.600
Token not
Token ID407
Feature activation-1.00e+00

Pos logit contributions
 and+2.404
,+2.342
 the+2.194
.+2.169
 a+1.956
Neg logit contributions
lor-6.311
umm-6.157
 former-6.122
arians-6.107
vation-6.030
Token say
Token ID910
Feature activation-1.00e+00

Pos logit contributions
 and+3.985
,+3.941
 the+3.798
.+3.755
 a+3.556
Neg logit contributions
umm-4.696
lor-4.684
arians-4.572
 former-4.546
ocol-4.534
Token anything
Token ID1997
Feature activation-1.00e+00

Pos logit contributions
 and+4.240
,+4.100
.+3.956
 the+3.952
 a+3.727
Neg logit contributions
lor-4.611
umm-4.447
arians-4.346
ocol-4.309
osity-4.283
Token either
Token ID2035
Feature activation-1.00e+00

Pos logit contributions
 and+1.887
,+1.833
 the+1.715
.+1.636
 a+1.521
Neg logit contributions
lor-6.792
umm-6.693
arians-6.629
 former-6.556
osity-6.517
Token.
Token ID13
Feature activation-1.00e+00

Pos logit contributions
 and+0.908
,+0.845
 the+0.754
.+0.661
 a+0.551
Neg logit contributions
lor-7.796
umm-7.712
arians-7.585
bek-7.520
rol-7.508
Token Tom
Token ID4186
Feature activation-1.00e+00

Pos logit contributions
 and+2.998
,+2.958
.+2.773
 the+2.765
 a+2.545
Neg logit contributions
lor-5.835
umm-5.736
arians-5.627
 former-5.598
bek-5.542
Token was
Token ID373
Feature activation-1.00e+00

Pos logit contributions
 and+3.051
,+3.050
 the+2.920
.+2.910
 a+2.699
Neg logit contributions
lor-5.644
umm-5.518
arians-5.485
 former-5.403
bek-5.367
Token scared
Token ID12008
Feature activation-1.00e+00

Pos logit contributions
 and+3.745
,+3.721
.+3.537
 the+3.501
 a+3.237
Neg logit contributions
lor-4.966
umm-4.875
 former-4.831
arians-4.811
rol-4.768
Token.
Token ID13
Feature activation-1.00e+00

Pos logit contributions
 and+0.489
,+0.453
 the+0.380
.+0.260
 a+0.205
Neg logit contributions
umm-8.076
lor-8.012
arians-7.877
ocol-7.862
rol-7.818
Token?"
Token ID1701
Feature activation-1.00e+00

Pos logit contributions
 and+2.232
,+2.187
 the+2.104
.+2.024
 a+1.870
Neg logit contributions
lor-6.480
umm-6.419
arians-6.281
 former-6.237
ocol-6.176
Token The
Token ID383
Feature activation-1.00e+00

Pos logit contributions
 and+3.193
,+3.135
.+2.971
 the+2.937
 a+2.746
Neg logit contributions
lor-5.541
umm-5.451
arians-5.367
 former-5.345
ocol-5.305
Token table
Token ID3084
Feature activation-1.00e+00

Pos logit contributions
 and+4.303
,+4.266
.+4.087
 the+4.085
 a+3.857
Neg logit contributions
lor-4.456
umm-4.453
arians-4.320
 former-4.289
ocol-4.251
Token did
Token ID750
Feature activation-1.00e+00

Pos logit contributions
 and+3.856
,+3.814
 the+3.699
.+3.660
 a+3.469
Neg logit contributions
lor-4.885
umm-4.796
arians-4.665
 former-4.617
rol-4.600
Token not
Token ID407
Feature activation-1.00e+00

Pos logit contributions
 and+2.404
,+2.342
 the+2.194
.+2.169
 a+1.956
Neg logit contributions
lor-6.311
umm-6.157
 former-6.122
arians-6.107
vation-6.030
Token say
Token ID910
Feature activation-1.00e+00

Pos logit contributions
 and+3.985
,+3.941
 the+3.798
.+3.755
 a+3.556
Neg logit contributions
umm-4.696
lor-4.684
arians-4.572
 former-4.546
ocol-4.534
Token anything
Token ID1997
Feature activation-1.00e+00

Pos logit contributions
 and+4.240
,+4.100
.+3.956
 the+3.952
 a+3.727
Neg logit contributions
lor-4.611
umm-4.447
arians-4.346
ocol-4.309
osity-4.283
Token either
Token ID2035
Feature activation-1.00e+00

Pos logit contributions
 and+1.887
,+1.833
 the+1.715
.+1.636
 a+1.521
Neg logit contributions
lor-6.792
umm-6.693
arians-6.629
 former-6.556
osity-6.517
Token.
Token ID13
Feature activation-1.00e+00

Pos logit contributions
 and+0.908
,+0.845
 the+0.754
.+0.661
 a+0.551
Neg logit contributions
lor-7.796
umm-7.712
arians-7.585
bek-7.520
rol-7.508
Token Tom
Token ID4186
Feature activation-1.00e+00

Pos logit contributions
 and+2.998
,+2.958
.+2.773
 the+2.765
 a+2.545
Neg logit contributions
lor-5.835
umm-5.736
arians-5.627
 former-5.598
bek-5.542
Token was
Token ID373
Feature activation-1.00e+00

Pos logit contributions
 and+3.051
,+3.050
 the+2.920
.+2.910
 a+2.699
Neg logit contributions
lor-5.644
umm-5.518
arians-5.485
 former-5.403
bek-5.367
Token The
Token ID383
Feature activation-1.00e+00

Pos logit contributions
 and+3.193
,+3.135
.+2.971
 the+2.937
 a+2.746
Neg logit contributions
lor-5.541
umm-5.451
arians-5.367
 former-5.345
ocol-5.305
Token table
Token ID3084
Feature activation-1.00e+00

Pos logit contributions
 and+4.303
,+4.266
.+4.087
 the+4.085
 a+3.857
Neg logit contributions
lor-4.456
umm-4.453
arians-4.320
 former-4.289
ocol-4.251
Token did
Token ID750
Feature activation-1.00e+00

Pos logit contributions
 and+3.856
,+3.814
 the+3.699
.+3.660
 a+3.469
Neg logit contributions
lor-4.885
umm-4.796
arians-4.665
 former-4.617
rol-4.600
Token not
Token ID407
Feature activation-1.00e+00

Pos logit contributions
 and+2.404
,+2.342
 the+2.194
.+2.169
 a+1.956
Neg logit contributions
lor-6.311
umm-6.157
 former-6.122
arians-6.107
vation-6.030
Token say
Token ID910
Feature activation-1.00e+00

Pos logit contributions
 and+3.985
,+3.941
 the+3.798
.+3.755
 a+3.556
Neg logit contributions
umm-4.696
lor-4.684
arians-4.572
 former-4.546
ocol-4.534
Token anything
Token ID1997
Feature activation-1.00e+00

Pos logit contributions
 and+4.240
,+4.100
.+3.956
 the+3.952
 a+3.727
Neg logit contributions
lor-4.611
umm-4.447
arians-4.346
ocol-4.309
osity-4.283
Token either
Token ID2035
Feature activation-1.00e+00

Pos logit contributions
 and+1.887
,+1.833
 the+1.715
.+1.636
 a+1.521
Neg logit contributions
lor-6.792
umm-6.693
arians-6.629
 former-6.556
osity-6.517
Token.
Token ID13
Feature activation-1.00e+00

Pos logit contributions
 and+0.908
,+0.845
 the+0.754
.+0.661
 a+0.551
Neg logit contributions
lor-7.796
umm-7.712
arians-7.585
bek-7.520
rol-7.508
Token Tom
Token ID4186
Feature activation-1.00e+00

Pos logit contributions
 and+2.998
,+2.958
.+2.773
 the+2.765
 a+2.545
Neg logit contributions
lor-5.835
umm-5.736
arians-5.627
 former-5.598
bek-5.542
Token was
Token ID373
Feature activation-1.00e+00

Pos logit contributions
 and+3.051
,+3.050
 the+2.920
.+2.910
 a+2.699
Neg logit contributions
lor-5.644
umm-5.518
arians-5.485
 former-5.403
bek-5.367
Token scared
Token ID12008
Feature activation-1.00e+00

Pos logit contributions
 and+3.745
,+3.721
.+3.537
 the+3.501
 a+3.237
Neg logit contributions
lor-4.966
umm-4.875
 former-4.831
arians-4.811
rol-4.768