TOP ACTIVATIONS
MAX = 3.989

! Sign up for our Email News letters here . <|endoftext|>
ex pelling Cuba from the O AS in 1962 reversed course
of Mana s O ST set the bar for
Margaret At wood and Michael O nda at je . It
1999 The NIH and the O HR P require all people
<|endoftext|> The People v . O . J . Simpson :
ard took the reins of O CL C as its new
Gu ib bert , with O rec as filling the top
lens , put it on OL AF , and took images
in ik ain en @ il media . fi Translation to
a diplomatic courtesy Cuba invited O AS Secretary General Jose Miguel
( June 2012 ), and O CL C ( June 2012
apologized to [ Love ]," O ly ny k said .
. Earlier this month , O la , a local taxi
they first met , and O ' Neill attempted to advise
half right ; none of O ' Brian 's work was
, on a mission designated O A - 7 , was
to certain issues , to O ' Neill 's open -
s largest capacity cartridge , O car ina of Time was
cos such as BT , O 2 and Virgin having blocked

MIN ACTIVATIONS
MIN = -4.694

before the program was finally declass ified in 2011 . That
2008 election . Christ ie is widely considered to
exit polls . Christ ie s showing
humiliating defeat to the euros cept ic UK IP party in
system has been declass ified , although it is
US , where 11 b idd ers have sent the price
leak isn 't a ' cons piracy theory ' like Donald
, drew just eight b idd ers when auction ed by
), Gu illa ume ( nom inated five times for Benson
mentioned in at least one declass ified document dating from late
- o vert ime goal clin ched New Jersey
and the Giant Peach ( init ially titled James and the
dinosaurs do while nesting ( scient ists think some species sat
arts in the post - conf lict capital and her drive
called these accusations a ' cons piracy theory .'
one of the more devastating sequ ences in movie history .
such services remains a min usc ule fraction of the school
awareness regarding incorporation " ( Ne h ring 86 ). B
. Rand Paul is " bas ically an isolation ist ,"
You will receive emails containing news content , updates and promotions

INTERVAL 1.818 - 3.989
CONTAINS 1.134%

, it s always men . Then I
About that time , the L SO came up on tower
as much as the U . S . did on passenger
. Because despite his best efforts , the life could never
medical school . Harvard professor E . H . Clarke used

INTERVAL -0.352 - 1.818
CONTAINS 68.228%

with the glacier , anyway ) and in effect
s legal cases are filed . Whatever recon figured Supreme
song ] One , two , three , four .
it will consider the role of ment hol and other flavors
is on the way to failing . If you want to

INTERVAL -2.523 - -0.352
CONTAINS 30.490%

the party explores and discovers the discrepancy . How
takes steps to open flights to US on sidelines of Trump
Zone Threat Sur prisingly , Wallace caught nine
he will be impe ached , she said .
I know I m not the only one .

INTERVAL -4.694 - -2.523
CONTAINS 0.148%

that will be app reci ated by all lovers
dinosaurs do while nesting ( scient ists think some species sat
- f inance , wh itt les ea - 375 7
mentioned in at least one declass ified document dating from late
all non farm sectors ( author s analysis of
Token!
Token ID0
Feature activation-2.12e-01

Pos logit contributions
edIn+6.568
ification+5.982
ifiers+5.889
ified+5.856
itect+5.821
Neg logit contributions
senal-4.916
berman-4.916
 Klux-4.819
mma-4.814
tails-4.797
Token Sign
Token ID5865
Feature activation-1.12e+00

Pos logit contributions
edIn+0.696
itect+0.610
ification+0.599
ified+0.594
icians+0.593
Neg logit contributions
berman-0.637
tti-0.607
HAEL-0.597
mma-0.592
tails-0.592
Token up
Token ID510
Feature activation-6.88e-01

Pos logit contributions
edIn+4.447
ified+3.993
ification+3.969
icians+3.916
itect+3.889
Neg logit contributions
berman-2.484
HAEL-2.429
tti-2.371
senal-2.364
tails-2.336
Token for
Token ID329
Feature activation-1.68e-01

Pos logit contributions
edIn+2.573
ification+2.326
ified+2.312
icians+2.312
itect+2.274
Neg logit contributions
berman-1.645
HAEL-1.640
tails-1.559
tti-1.550
 Gamble-1.495
Token our
Token ID674
Feature activation+7.85e-01

Pos logit contributions
edIn+0.590
ification+0.521
icians+0.521
ified+0.520
itect+0.513
Neg logit contributions
berman-0.469
HAEL-0.448
tti-0.448
tails-0.437
mma-0.430
Token Email
Token ID9570
Feature activation+3.99e+00

Pos logit contributions
berman+2.009
HAEL+1.935
tti+1.926
tails+1.870
 Heck+1.865
Neg logit contributions
edIn-2.904
itect-2.573
ification-2.550
ified-2.531
icians-2.524
Token News
Token ID3000
Feature activation-1.27e+00

Pos logit contributions
berman+5.409
 Heck+5.091
tti+4.735
mma+4.714
HO+4.619
Neg logit contributions
edIn-17.007
itect-16.967
icter-16.800
icians-16.573
ifiers-16.443
Tokenletters
Token ID15653
Feature activation-8.13e-02

Pos logit contributions
edIn+2.873
ification+2.333
icians+2.295
ified+2.265
itect+2.240
Neg logit contributions
berman-5.100
HAEL-4.982
tti-4.945
tails-4.849
mma-4.785
Token here
Token ID994
Feature activation-1.21e-01

Pos logit contributions
edIn+0.258
icians+0.224
itect+0.224
ification+0.222
ified+0.221
Neg logit contributions
berman-0.256
tti-0.245
HAEL-0.243
tails-0.239
 Heck-0.238
Token.
Token ID13
Feature activation-1.04e-01

Pos logit contributions
edIn+0.489
ification+0.440
icians+0.437
ified+0.437
itect+0.435
Neg logit contributions
berman-0.274
HAEL-0.257
tti-0.256
tails-0.249
 Heck-0.241
Token<|endoftext|>
Token ID50256
Feature activation-7.42e-01

Pos logit contributions
edIn+0.327
icians+0.282
itect+0.279
ified+0.278
ification+0.278
Neg logit contributions
berman-0.328
tti-0.322
HAEL-0.317
 Heck-0.311
tails-0.309
Token ex
Token ID409
Feature activation+6.27e-01

Pos logit contributions
edIn+0.272
icians+0.238
itect+0.237
ification+0.236
ified+0.235
Neg logit contributions
berman-0.197
tti-0.189
HAEL-0.188
tails-0.184
 Heck-0.181
Tokenpelling
Token ID35025
Feature activation+7.89e-01

Pos logit contributions
berman+2.581
tti+2.504
tails+2.470
HAEL+2.467
 Heck+2.433
Neg logit contributions
edIn-1.361
icians-1.065
ified-1.044
itect-1.033
ification-1.032
Token Cuba
Token ID14159
Feature activation-5.19e-01

Pos logit contributions
berman+2.083
tti+2.002
HAEL+1.973
 Heck+1.955
tails+1.943
Neg logit contributions
edIn-2.849
icians-2.493
itect-2.483
ification-2.451
ified-2.444
Token from
Token ID422
Feature activation-6.66e-01

Pos logit contributions
edIn+1.956
icians+1.726
ification+1.721
itect+1.715
ified+1.712
Neg logit contributions
berman-1.307
tti-1.253
HAEL-1.252
tails-1.214
 Heck-1.191
Token the
Token ID262
Feature activation-3.13e-01

Pos logit contributions
edIn+2.336
icians+2.045
ification+2.043
itect+2.030
ified+2.029
Neg logit contributions
berman-1.850
HAEL-1.779
tti-1.778
tails-1.727
 Heck-1.696
Token O
Token ID440
Feature activation+3.88e+00

Pos logit contributions
edIn+1.197
icians+1.058
ification+1.056
itect+1.051
ified+1.049
Neg logit contributions
berman-0.769
tti-0.736
HAEL-0.735
tails-0.713
 Heck-0.700
TokenAS
Token ID1921
Feature activation+5.36e-01

Pos logit contributions
DI+5.143
HO+4.839
berman+4.767
tti+4.384
HAEL+4.322
Neg logit contributions
edIn-17.806
icter-15.905
icians-15.506
itect-15.461
ification-15.018
Token in
Token ID287
Feature activation-3.64e-01

Pos logit contributions
berman+1.410
tti+1.366
HAEL+1.351
tails+1.314
 Gamble+1.309
Neg logit contributions
edIn-1.956
icians-1.710
itect-1.683
ification-1.676
ified-1.673
Token 1962
Token ID20033
Feature activation+1.21e+00

Pos logit contributions
edIn+1.142
icians+0.982
ification+0.981
itect+0.974
ified+0.974
Neg logit contributions
berman-1.148
HAEL-1.110
tti-1.109
tails-1.082
 Heck-1.066
Token reversed
Token ID17687
Feature activation+9.48e-02

Pos logit contributions
berman+3.099
tti+3.031
HAEL+2.924
 Heck+2.855
tails+2.850
Neg logit contributions
edIn-4.537
icians-3.835
itect-3.783
ified-3.719
ification-3.712
Token course
Token ID1781
Feature activation+4.69e-02

Pos logit contributions
berman+0.232
tti+0.221
HAEL+0.220
tails+0.214
 Heck+0.211
Neg logit contributions
edIn-0.364
icians-0.322
itect-0.321
ification-0.321
ified-0.319
Token of
Token ID286
Feature activation+3.73e-01

Pos logit contributions
berman+0.924
tti+0.879
HAEL+0.871
 Heck+0.828
tails+0.823
Neg logit contributions
edIn-1.979
icians-1.770
itect-1.759
ification-1.759
ified-1.747
Token Mana
Token ID17493
Feature activation+1.21e+00

Pos logit contributions
berman+0.819
HAEL+0.780
tti+0.779
tails+0.753
 Heck+0.735
Neg logit contributions
edIn-1.526
icians-1.362
ification-1.360
itect-1.354
ified-1.353
Token
Token ID447
Feature activation-8.04e-02

Pos logit contributions
berman+2.947
tti+2.851
HAEL+2.756
 Heck+2.728
tails+2.696
Neg logit contributions
edIn-4.607
icians-4.033
ification-4.009
itect-3.989
ified-3.966
Token
Token ID247
Feature activation+6.33e-01

Pos logit contributions
edIn+0.258
icians+0.223
ification+0.223
itect+0.221
ified+0.221
Neg logit contributions
berman-0.247
tti-0.239
HAEL-0.239
tails-0.233
 Heck-0.229
Tokens
Token ID82
Feature activation+1.73e-01

Pos logit contributions
berman+1.597
tti+1.550
HAEL+1.503
tails+1.497
mma+1.453
Neg logit contributions
edIn-2.373
ification-2.069
icians-2.061
itect-2.047
ified-2.043
Token O
Token ID440
Feature activation+3.82e+00

Pos logit contributions
berman+0.507
tti+0.488
HAEL+0.486
tails+0.474
 Heck+0.469
Neg logit contributions
edIn-0.581
icians-0.505
ification-0.503
itect-0.501
ified-0.499
TokenST
Token ID2257
Feature activation+7.37e-01

Pos logit contributions
berman+9.091
tti+8.577
DI+8.569
HO+8.120
train+8.032
Neg logit contributions
edIn-12.923
icter-11.696
icians-11.370
itect-11.229
ified-11.181
Token set
Token ID900
Feature activation-8.79e-01

Pos logit contributions
berman+1.826
tti+1.767
HAEL+1.742
tails+1.696
 Heck+1.675
Neg logit contributions
edIn-2.788
icians-2.441
ification-2.412
itect-2.409
ified-2.394
Token the
Token ID262
Feature activation-3.69e-01

Pos logit contributions
edIn+3.253
ification+2.887
icians+2.884
ified+2.870
itect+2.851
Neg logit contributions
berman-2.239
HAEL-2.161
tti-2.137
tails-2.084
mma-2.050
Token bar
Token ID2318
Feature activation+8.27e-01

Pos logit contributions
edIn+1.267
icians+1.104
ification+1.100
itect+1.096
ified+1.092
Neg logit contributions
berman-1.056
tti-1.015
HAEL-1.013
tails-0.988
 Heck-0.974
Token for
Token ID329
Feature activation+1.16e-02

Pos logit contributions
berman+1.919
tti+1.805
HAEL+1.805
 Heck+1.769
tails+1.743
Neg logit contributions
edIn-3.292
icians-2.892
itect-2.883
ification-2.875
ified-2.848
Token Margaret
Token ID19579
Feature activation-1.80e-01

Pos logit contributions
berman+1.022
tti+0.994
HAEL+0.987
 Heck+0.957
tails+0.951
Neg logit contributions
edIn-1.245
icians-1.073
itect-1.060
ification-1.055
ified-1.051
Token At
Token ID1629
Feature activation+1.22e+00

Pos logit contributions
edIn+0.718
icians+0.639
ification+0.638
itect+0.635
ified+0.634
Neg logit contributions
berman-0.416
HAEL-0.397
tti-0.396
tails-0.383
 Heck-0.374
Tokenwood
Token ID3822
Feature activation-3.28e-01

Pos logit contributions
berman+3.051
tti+2.947
HAEL+2.776
tails+2.742
 Heck+2.723
Neg logit contributions
edIn-4.683
itect-4.022
icians-4.009
ified-3.972
ification-3.969
Token and
Token ID290
Feature activation+7.99e-01

Pos logit contributions
edIn+1.270
icians+1.127
ification+1.125
itect+1.119
ified+1.118
Neg logit contributions
berman-0.789
HAEL-0.754
tti-0.753
tails-0.730
 Heck-0.715
Token Michael
Token ID3899
Feature activation+2.61e+00

Pos logit contributions
berman+1.993
tti+1.935
HAEL+1.930
 Heck+1.876
 Gamble+1.865
Neg logit contributions
edIn-3.015
icians-2.621
ification-2.616
itect-2.615
ified-2.597
Token O
Token ID440
Feature activation+3.76e+00

Pos logit contributions
 Gamble+5.770
berman+5.697
 Heck+5.672
tti+5.662
HAEL+5.386
Neg logit contributions
edIn-9.905
icians-8.525
itect-8.498
icter-8.365
ification-8.344
Tokennda
Token ID45658
Feature activation-9.26e-01

Pos logit contributions
berman+10.356
tti+10.006
train+9.342
 Gamble+9.259
mouth+9.047
Neg logit contributions
edIn-11.473
icter-10.029
itect-9.847
icians-9.745
acters-9.552
Tokenat
Token ID265
Feature activation-8.47e-01

Pos logit contributions
edIn+3.034
itect+2.634
ification+2.629
icians+2.608
ified+2.606
Neg logit contributions
berman-2.762
tti-2.696
HAEL-2.643
tails-2.565
mma-2.544
Tokenje
Token ID18015
Feature activation-1.17e+00

Pos logit contributions
edIn+2.067
ification+1.764
ified+1.735
icians+1.734
ifiers+1.707
Neg logit contributions
berman-3.198
tti-3.082
tails-3.063
HAEL-3.054
train-2.977
Token.
Token ID13
Feature activation-1.18e-01

Pos logit contributions
edIn+4.546
ification+4.074
icians+4.069
itect+4.061
ified+4.036
Neg logit contributions
berman-2.643
HAEL-2.565
tails-2.482
tti-2.473
mma-2.394
Token It
Token ID632
Feature activation+6.78e-01

Pos logit contributions
edIn+0.431
icians+0.379
ification+0.377
ified+0.375
itect+0.375
Neg logit contributions
berman-0.312
tti-0.301
HAEL-0.301
tails-0.292
 Heck-0.288
Token1999
Token ID18946
Feature activation-1.08e+00

Pos logit contributions
berman+0.551
tti+0.530
HAEL+0.529
tails+0.514
mma+0.504
Neg logit contributions
edIn-0.735
icians-0.644
ification-0.640
itect-0.640
ified-0.636
Token The
Token ID383
Feature activation+3.42e-01

Pos logit contributions
edIn+3.970
icians+3.568
ification+3.547
ified+3.531
itect+3.493
Neg logit contributions
berman-2.680
HAEL-2.586
tti-2.534
tails-2.494
mma-2.434
Token NIH
Token ID37483
Feature activation-1.03e+00

Pos logit contributions
berman+0.826
tti+0.795
HAEL+0.786
 Heck+0.763
tails+0.760
Neg logit contributions
edIn-1.328
icians-1.168
itect-1.166
ification-1.164
ified-1.156
Token and
Token ID290
Feature activation+8.44e-01

Pos logit contributions
edIn+3.492
ification+3.094
icians+3.091
ified+3.074
itect+3.069
Neg logit contributions
berman-2.865
HAEL-2.743
tti-2.727
tails-2.667
mma-2.611
Token the
Token ID262
Feature activation+1.00e+00

Pos logit contributions
berman+2.101
tti+2.040
HAEL+2.004
 Heck+1.972
tails+1.946
Neg logit contributions
edIn-3.193
itect-2.785
ification-2.778
icians-2.771
ified-2.751
Token O
Token ID440
Feature activation+3.67e+00

Pos logit contributions
berman+2.306
tti+2.242
HAEL+2.181
 Heck+2.174
 Gamble+2.127
Neg logit contributions
edIn-3.961
itect-3.468
ification-3.459
icians-3.436
ifiers-3.422
TokenHR
Token ID17184
Feature activation+6.77e-01

Pos logit contributions
tti+8.931
berman+8.595
DI+8.577
HO+8.315
 Heck+7.817
Neg logit contributions
edIn-12.626
icter-11.168
itect-10.990
acters-10.746
icians-10.709
TokenP
Token ID47
Feature activation+1.31e+00

Pos logit contributions
berman+1.953
tti+1.883
HAEL+1.883
tails+1.829
 Heck+1.796
Neg logit contributions
edIn-2.321
icians-1.999
itect-1.983
ification-1.981
ified-1.975
Token require
Token ID2421
Feature activation+1.45e+00

Pos logit contributions
berman+3.747
tti+3.638
HAEL+3.602
tails+3.514
 Heck+3.456
Neg logit contributions
edIn-4.493
icians-3.834
itect-3.795
ification-3.779
ified-3.776
Token all
Token ID477
Feature activation+1.63e+00

Pos logit contributions
berman+3.642
tti+3.582
HAEL+3.452
 Heck+3.449
 Gamble+3.411
Neg logit contributions
edIn-5.379
itect-4.727
icians-4.622
ification-4.576
ifiers-4.560
Token people
Token ID661
Feature activation-4.28e-01

Pos logit contributions
berman+4.020
tti+3.939
 Heck+3.806
HAEL+3.744
 Gamble+3.700
Neg logit contributions
edIn-5.971
itect-5.230
icians-5.132
ification-5.117
ifiers-5.054
Token<|endoftext|>
Token ID50256
Feature activation-9.41e-01

Pos logit contributions
edIn+1.217
icians+1.059
ification+1.057
itect+1.051
ified+1.050
Neg logit contributions
berman-1.043
HAEL-1.005
tti-1.005
tails-0.979
 Heck-0.963
TokenThe
Token ID464
Feature activation-7.12e-01

Pos logit contributions
edIn+3.508
ification+3.096
ified+3.079
icians+3.078
itect+3.060
Neg logit contributions
berman-2.375
tti-2.273
HAEL-2.273
 Heck-2.188
tails-2.186
Token People
Token ID4380
Feature activation-2.86e-01

Pos logit contributions
edIn+2.662
ification+2.356
icians+2.352
ified+2.343
itect+2.339
Neg logit contributions
berman-1.798
HAEL-1.729
tti-1.719
tails-1.673
mma-1.632
Token v
Token ID410
Feature activation+3.02e-01

Pos logit contributions
edIn+0.979
icians+0.852
ification+0.848
itect+0.846
ified+0.843
Neg logit contributions
berman-0.826
tti-0.796
HAEL-0.791
tails-0.770
 Heck-0.762
Token.
Token ID13
Feature activation+1.76e+00

Pos logit contributions
berman+0.633
tti+0.600
HAEL+0.596
tails+0.575
 Heck+0.570
Neg logit contributions
edIn-1.265
icians-1.127
itect-1.125
ification-1.125
ified-1.119
Token O
Token ID440
Feature activation+3.66e+00

Pos logit contributions
berman+3.733
 Heck+3.535
 Gamble+3.456
HAEL+3.389
tti+3.383
Neg logit contributions
edIn-7.265
itect-6.391
icians-6.360
ified-6.219
acters-6.200
Token.
Token ID13
Feature activation+2.09e+00

Pos logit contributions
berman+10.419
tti+9.751
DI+9.470
HO+9.398
 Heck+9.357
Neg logit contributions
edIn-11.395
icter-10.068
icians-10.063
itect-9.848
acters-9.322
TokenJ
Token ID41
Feature activation-2.98e-01

Pos logit contributions
berman+3.467
HAEL+3.176
 Gamble+3.170
 Heck+3.129
tti+3.126
Neg logit contributions
edIn-9.618
itect-8.582
ifiers-8.498
icians-8.449
ification-8.367
Token.
Token ID13
Feature activation+1.60e+00

Pos logit contributions
edIn+1.205
icians+1.079
ification+1.075
itect+1.072
ified+1.070
Neg logit contributions
berman-0.663
HAEL-0.632
tti-0.632
tails-0.607
mma-0.590
Token Simpson
Token ID20531
Feature activation-9.58e-01

Pos logit contributions
berman+4.691
 Gamble+4.464
 Heck+4.452
tti+4.404
HAEL+4.399
Neg logit contributions
edIn-5.317
icians-4.557
ifiers-4.501
itect-4.472
ification-4.454
Token:
Token ID25
Feature activation-3.39e-01

Pos logit contributions
edIn+3.466
ification+3.073
ified+3.059
icians+3.037
itect+3.014
Neg logit contributions
berman-2.516
HAEL-2.414
tti-2.396
tails-2.332
mma-2.257
Tokenard
Token ID446
Feature activation-2.92e-01

Pos logit contributions
edIn+1.168
ification+1.017
icians+1.014
itect+1.012
ified+1.011
Neg logit contributions
berman-1.147
HAEL-1.111
tti-1.101
tails-1.081
mma-1.060
Token took
Token ID1718
Feature activation+5.21e-01

Pos logit contributions
edIn+1.214
icians+1.084
ification+1.082
itect+1.078
ified+1.076
Neg logit contributions
berman-0.623
tti-0.593
HAEL-0.592
tails-0.571
 Heck-0.558
Token the
Token ID262
Feature activation+4.29e-01

Pos logit contributions
berman+1.138
tti+1.104
HAEL+1.079
 Heck+1.061
 Gamble+1.050
Neg logit contributions
edIn-2.114
icians-1.890
itect-1.880
ification-1.855
ified-1.847
Token reins
Token ID35627
Feature activation+4.19e-03

Pos logit contributions
berman+1.006
tti+0.972
HAEL+0.954
 Heck+0.935
 Gamble+0.928
Neg logit contributions
edIn-1.681
icians-1.490
itect-1.478
ification-1.469
ified-1.465
Token of
Token ID286
Feature activation+4.00e-01

Pos logit contributions
berman+0.009
tti+0.009
HAEL+0.009
tails+0.008
 Heck+0.008
Neg logit contributions
edIn-0.017
icians-0.015
ification-0.015
itect-0.015
ified-0.015
Token O
Token ID440
Feature activation+3.66e+00

Pos logit contributions
berman+0.999
tti+0.967
HAEL+0.954
 Heck+0.933
 Gamble+0.928
Neg logit contributions
edIn-1.500
icians-1.327
itect-1.305
ification-1.304
ified-1.299
TokenCL
Token ID5097
Feature activation+4.00e-01

Pos logit contributions
tti+10.132
berman+10.114
DI+9.794
train+9.576
HO+9.387
Neg logit contributions
edIn-10.814
icter-9.534
icians-9.305
itect-9.062
ification-8.858
TokenC
Token ID34
Feature activation+2.81e-01

Pos logit contributions
berman+0.878
HAEL+0.844
tti+0.843
tails+0.813
 Heck+0.799
Neg logit contributions
edIn-1.626
icians-1.447
ification-1.433
itect-1.428
ified-1.425
Token as
Token ID355
Feature activation-3.10e-01

Pos logit contributions
berman+0.626
HAEL+0.605
tti+0.602
tails+0.579
 Heck+0.571
Neg logit contributions
edIn-1.136
icians-1.014
ification-1.002
ified-0.998
itect-0.996
Token its
Token ID663
Feature activation+9.46e-03

Pos logit contributions
edIn+1.097
icians+0.960
ification+0.957
itect+0.953
ified+0.951
Neg logit contributions
berman-0.850
tti-0.817
HAEL-0.817
tails-0.794
 Heck-0.781
Token new
Token ID649
Feature activation-4.86e-01

Pos logit contributions
berman+0.025
tti+0.024
HAEL+0.024
tails+0.024
 Heck+0.023
Neg logit contributions
edIn-0.034
icians-0.030
ification-0.030
itect-0.030
ified-0.030
Token Gu
Token ID1962
Feature activation+3.08e-01

Pos logit contributions
berman+0.899
tti+0.887
HAEL+0.857
 Heck+0.851
 Gamble+0.838
Neg logit contributions
edIn-1.590
icians-1.415
ification-1.397
itect-1.396
ified-1.389
Tokenib
Token ID571
Feature activation-2.50e-01

Pos logit contributions
berman+0.966
tti+0.930
HAEL+0.902
tails+0.895
mma+0.883
Neg logit contributions
edIn-0.991
icians-0.838
itect-0.832
ification-0.831
ified-0.826
Tokenbert
Token ID4835
Feature activation-1.45e-03

Pos logit contributions
edIn+0.801
icians+0.691
ification+0.690
itect+0.686
ified+0.685
Neg logit contributions
berman-0.768
HAEL-0.742
tti-0.742
tails-0.724
 Heck-0.713
Token,
Token ID11
Feature activation-1.05e-02

Pos logit contributions
edIn+0.006
icians+0.005
ification+0.005
itect+0.005
ified+0.005
Neg logit contributions
berman-0.004
tti-0.003
HAEL-0.003
tails-0.003
 Heck-0.003
Token with
Token ID351
Feature activation-1.01e+00

Pos logit contributions
edIn+0.037
icians+0.032
itect+0.032
ification+0.032
ified+0.032
Neg logit contributions
berman-0.029
tti-0.028
HAEL-0.028
tails-0.027
 Heck-0.027
Token O
Token ID440
Feature activation+3.66e+00

Pos logit contributions
edIn+3.785
ification+3.367
icians+3.348
ified+3.337
itect+3.300
Neg logit contributions
berman-2.540
HAEL-2.408
tti-2.390
tails-2.339
mma-2.276
Tokenrec
Token ID8344
Feature activation-1.59e-01

Pos logit contributions
tti+9.672
berman+9.470
DI+9.359
HAEL+8.943
tails+8.900
Neg logit contributions
edIn-11.625
icter-10.046
itect-9.844
icians-9.738
ificant-9.700
Tokenas
Token ID292
Feature activation-8.11e-01

Pos logit contributions
edIn+0.612
icians+0.541
ification+0.536
itect+0.535
ified+0.534
Neg logit contributions
berman-0.393
tti-0.377
HAEL-0.375
tails-0.364
 Heck-0.358
Token filling
Token ID12591
Feature activation+1.03e+00

Pos logit contributions
edIn+3.018
icians+2.678
ification+2.675
itect+2.658
ified+2.656
Neg logit contributions
berman-2.064
HAEL-1.976
tti-1.949
tails-1.912
mma-1.863
Token the
Token ID262
Feature activation+3.36e-02

Pos logit contributions
berman+2.290
tti+2.193
 Heck+2.155
HAEL+2.148
tails+2.126
Neg logit contributions
edIn-4.058
itect-3.688
icians-3.665
ification-3.616
ified-3.594
Token top
Token ID1353
Feature activation-7.78e-01

Pos logit contributions
berman+0.092
HAEL+0.089
tti+0.089
tails+0.086
 Heck+0.085
Neg logit contributions
edIn-0.119
icians-0.105
ification-0.104
itect-0.104
ified-0.104
Token lens
Token ID10317
Feature activation+4.06e-01

Pos logit contributions
berman+2.075
tti+1.995
HAEL+1.970
 Heck+1.912
mma+1.895
Neg logit contributions
edIn-3.203
icians-2.830
ification-2.809
itect-2.807
ified-2.804
Token,
Token ID11
Feature activation-8.42e-01

Pos logit contributions
berman+0.924
tti+0.885
HAEL+0.879
tails+0.851
 Heck+0.841
Neg logit contributions
edIn-1.627
icians-1.447
ification-1.437
itect-1.431
ified-1.430
Token put
Token ID1234
Feature activation-2.12e-01

Pos logit contributions
edIn+2.894
ification+2.551
ified+2.537
icians+2.534
itect+2.512
Neg logit contributions
berman-2.364
HAEL-2.281
tti-2.252
tails-2.215
mma-2.151
Token it
Token ID340
Feature activation+4.56e-01

Pos logit contributions
edIn+0.769
icians+0.676
ification+0.675
ified+0.671
itect+0.671
Neg logit contributions
berman-0.562
HAEL-0.540
tti-0.539
tails-0.524
 Heck-0.514
Token on
Token ID319
Feature activation+6.71e-01

Pos logit contributions
berman+0.961
tti+0.918
HAEL+0.903
tails+0.885
 Heck+0.862
Neg logit contributions
edIn-1.907
icians-1.702
itect-1.689
ification-1.688
ified-1.676
Token OL
Token ID22258
Feature activation+3.65e+00

Pos logit contributions
berman+1.697
tti+1.648
HAEL+1.618
 Heck+1.580
tails+1.575
Neg logit contributions
edIn-2.506
icians-2.204
itect-2.191
ification-2.184
ified-2.176
TokenAF
Token ID8579
Feature activation+6.83e-02

Pos logit contributions
tti+8.720
berman+8.628
DI+8.531
HO+8.166
HAEL+8.126
Neg logit contributions
edIn-12.350
icians-10.877
itect-10.788
icipated-10.656
acters-10.397
Token,
Token ID11
Feature activation+4.44e-01

Pos logit contributions
berman+0.170
tti+0.163
HAEL+0.162
tails+0.158
 Heck+0.155
Neg logit contributions
edIn-0.260
icians-0.230
ification-0.229
itect-0.228
ified-0.228
Token and
Token ID290
Feature activation+9.21e-01

Pos logit contributions
berman+1.242
tti+1.215
HAEL+1.194
 Heck+1.166
tails+1.161
Neg logit contributions
edIn-1.537
icians-1.343
itect-1.329
ification-1.318
ified-1.304
Token took
Token ID1718
Feature activation+5.61e-01

Pos logit contributions
berman+2.583
tti+2.530
HAEL+2.473
 Heck+2.436
tails+2.405
Neg logit contributions
edIn-3.159
icians-2.763
itect-2.742
ification-2.707
ified-2.679
Token images
Token ID4263
Feature activation+4.91e-01

Pos logit contributions
berman+1.496
tti+1.441
HAEL+1.435
tails+1.394
 Heck+1.388
Neg logit contributions
edIn-2.018
icians-1.767
itect-1.757
ification-1.752
ified-1.743
Tokenin
Token ID259
Feature activation-1.04e+00

Pos logit contributions
edIn+3.951
ification+3.424
ified+3.390
itect+3.372
icians+3.367
Neg logit contributions
berman-4.379
HAEL-4.328
tti-4.211
tails-4.185
 Heck-4.160
Tokenik
Token ID1134
Feature activation-9.39e-01

Pos logit contributions
edIn+3.272
icians+2.857
ification+2.849
itect+2.845
ified+2.831
Neg logit contributions
berman-3.199
HAEL-3.117
tti-3.085
tails-3.029
 Gamble-2.987
Tokenain
Token ID391
Feature activation-1.06e+00

Pos logit contributions
edIn+3.339
ification+2.944
icians+2.941
itect+2.931
ified+2.927
Neg logit contributions
berman-2.524
tti-2.434
HAEL-2.429
tails-2.366
 Heck-2.334
Tokenen
Token ID268
Feature activation-6.89e-01

Pos logit contributions
edIn+3.367
ification+2.911
icians+2.908
itect+2.895
ified+2.895
Neg logit contributions
berman-3.268
HAEL-3.179
tti-3.147
tails-3.090
 Heck-3.054
Token @
Token ID2488
Feature activation+1.46e+00

Pos logit contributions
edIn+2.262
icians+1.959
ification+1.959
itect+1.948
ified+1.946
Neg logit contributions
berman-2.067
HAEL-1.993
tti-1.990
tails-1.942
 Heck-1.912
Token il
Token ID4229
Feature activation+3.63e+00

Pos logit contributions
berman+3.753
tti+3.688
HAEL+3.613
tails+3.571
HO+3.520
Neg logit contributions
edIn-5.222
icians-4.580
itect-4.514
ification-4.498
ifiers-4.492
Tokenmedia
Token ID11431
Feature activation+1.39e+00

Pos logit contributions
tti+10.606
berman+10.584
mma+9.969
tails+9.901
mouth+9.668
Neg logit contributions
edIn-10.609
icians-8.319
acters-8.283
ified-8.190
ifiers-8.162
Token.
Token ID13
Feature activation+7.85e-01

Pos logit contributions
berman+3.768
tti+3.692
HAEL+3.625
tails+3.513
train+3.436
Neg logit contributions
edIn-4.825
icians-4.187
itect-4.133
ification-4.113
ified-4.093
Tokenfi
Token ID12463
Feature activation+7.47e-01

Pos logit contributions
berman+2.322
tti+2.269
HAEL+2.209
tails+2.182
mma+2.148
Neg logit contributions
edIn-2.601
icians-2.240
ification-2.219
itect-2.213
ified-2.198
TokenTranslation
Token ID48313
Feature activation-9.86e-01

Pos logit contributions
berman+1.946
HAEL+1.887
tti+1.886
tails+1.810
 Heck+1.795
Neg logit contributions
edIn-2.721
icians-2.400
itect-2.371
ification-2.360
ified-2.356
Token to
Token ID284
Feature activation-1.02e+00

Pos logit contributions
edIn+3.783
ification+3.381
icians+3.365
ified+3.361
itect+3.338
Neg logit contributions
berman-2.374
tti-2.262
HAEL-2.261
tails-2.210
mma-2.148
Token a
Token ID257
Feature activation-1.70e-01

Pos logit contributions
edIn+2.684
ification+2.357
icians+2.355
ified+2.338
itect+2.331
Neg logit contributions
berman-2.092
HAEL-2.010
tti-2.001
tails-1.952
mma-1.907
Token diplomatic
Token ID13093
Feature activation-2.38e-01

Pos logit contributions
edIn+0.596
icians+0.515
itect+0.513
ification+0.509
ified+0.506
Neg logit contributions
berman-0.479
tti-0.462
HAEL-0.457
tails-0.448
 Heck-0.446
Token courtesy
Token ID12537
Feature activation+3.23e-01

Pos logit contributions
edIn+0.883
icians+0.777
ification+0.772
itect+0.771
ified+0.767
Neg logit contributions
berman-0.616
tti-0.591
HAEL-0.588
tails-0.572
 Heck-0.565
Token Cuba
Token ID14159
Feature activation-6.05e-01

Pos logit contributions
berman+0.743
tti+0.715
HAEL+0.713
tails+0.683
 Heck+0.681
Neg logit contributions
edIn-1.283
icians-1.132
itect-1.131
ification-1.125
ified-1.121
Token invited
Token ID9392
Feature activation+2.40e-01

Pos logit contributions
edIn+2.043
icians+1.779
ification+1.775
itect+1.764
ified+1.762
Neg logit contributions
berman-1.758
HAEL-1.694
tti-1.692
tails-1.649
 Heck-1.622
Token O
Token ID440
Feature activation+3.63e+00

Pos logit contributions
berman+0.630
tti+0.607
HAEL+0.604
tails+0.588
 Heck+0.582
Neg logit contributions
edIn-0.875
icians-0.767
itect-0.765
ification-0.764
ified-0.759
TokenAS
Token ID1921
Feature activation+3.98e-01

Pos logit contributions
berman+4.781
DI+4.557
HO+4.390
tti+4.301
HAEL+4.251
Neg logit contributions
edIn-16.733
icter-15.240
icians-14.598
itect-14.593
ification-14.385
Token Secretary
Token ID4986
Feature activation+2.14e-01

Pos logit contributions
berman+1.097
tti+1.062
HAEL+1.054
tails+1.023
 Heck+1.019
Neg logit contributions
edIn-1.398
icians-1.198
itect-1.197
ification-1.196
ified-1.196
Token General
Token ID3611
Feature activation+9.83e-01

Pos logit contributions
berman+0.444
tti+0.424
HAEL+0.422
tails+0.406
 Heck+0.401
Neg logit contributions
edIn-0.905
icians-0.808
ification-0.805
itect-0.803
ified-0.800
Token Jose
Token ID5264
Feature activation+7.12e-01

Pos logit contributions
berman+2.237
tti+2.177
HAEL+2.156
 Heck+2.113
tails+2.084
Neg logit contributions
edIn-3.929
icians-3.426
itect-3.423
ification-3.388
ified-3.362
Token Miguel
Token ID29825
Feature activation+1.54e+00

Pos logit contributions
berman+1.613
tti+1.561
HAEL+1.498
 Heck+1.479
 Gamble+1.474
Neg logit contributions
edIn-2.877
icians-2.532
itect-2.517
ification-2.512
ified-2.494
Token (
Token ID357
Feature activation+1.94e-01

Pos logit contributions
berman+0.833
tti+0.805
HAEL+0.796
tails+0.774
 Heck+0.760
Neg logit contributions
edIn-1.495
icians-1.330
ification-1.324
itect-1.318
ified-1.315
TokenJune
Token ID15749
Feature activation-6.64e-01

Pos logit contributions
berman+0.582
tti+0.563
HAEL+0.561
tails+0.551
mma+0.538
Neg logit contributions
edIn-0.636
icians-0.550
itect-0.545
ification-0.544
ified-0.540
Token 2012
Token ID2321
Feature activation+6.00e-01

Pos logit contributions
edIn+1.857
icians+1.566
ification+1.565
itect+1.553
ified+1.552
Neg logit contributions
berman-2.312
HAEL-2.244
tti-2.241
tails-2.193
 Heck-2.162
Token),
Token ID828
Feature activation+3.40e-02

Pos logit contributions
berman+1.646
tti+1.586
HAEL+1.573
tails+1.535
mma+1.521
Neg logit contributions
edIn-2.124
icians-1.840
ification-1.824
itect-1.814
ified-1.811
Token and
Token ID290
Feature activation+1.30e+00

Pos logit contributions
berman+0.082
tti+0.079
HAEL+0.078
tails+0.076
 Heck+0.075
Neg logit contributions
edIn-0.132
icians-0.116
ification-0.116
itect-0.115
ified-0.115
Token O
Token ID440
Feature activation+3.61e+00

Pos logit contributions
berman+3.032
tti+2.961
 Heck+2.907
HAEL+2.874
 Gamble+2.869
Neg logit contributions
edIn-4.955
icians-4.383
ification-4.331
itect-4.328
ified-4.288
TokenCL
Token ID5097
Feature activation-4.05e-01

Pos logit contributions
berman+9.626
tti+9.571
DI+9.475
train+9.161
HO+9.098
Neg logit contributions
edIn-10.630
icter-9.382
icians-9.260
itect-9.134
ified-8.965
TokenC
Token ID34
Feature activation-3.52e-01

Pos logit contributions
edIn+1.822
icians+1.645
ification+1.643
itect+1.636
ified+1.635
Neg logit contributions
berman-0.724
tti-0.681
HAEL-0.680
tails-0.651
 Heck-0.632
Token (
Token ID357
Feature activation+5.26e-01

Pos logit contributions
edIn+1.405
icians+1.249
ification+1.247
itect+1.242
ified+1.240
Neg logit contributions
berman-0.810
tti-0.772
HAEL-0.772
tails-0.747
 Heck-0.731
TokenJune
Token ID15749
Feature activation-5.91e-01

Pos logit contributions
berman+1.530
tti+1.479
HAEL+1.465
tails+1.451
train+1.420
Neg logit contributions
edIn-1.767
icians-1.537
itect-1.519
ification-1.509
ified-1.497
Token 2012
Token ID2321
Feature activation+6.85e-01

Pos logit contributions
edIn+1.679
icians+1.417
ification+1.412
itect+1.403
ified+1.400
Neg logit contributions
berman-2.039
tti-1.977
HAEL-1.975
tails-1.933
 Heck-1.907
Token apologized
Token ID22893
Feature activation-1.43e-01

Pos logit contributions
edIn+0.758
icians+0.659
ification+0.657
itect+0.654
ified+0.653
Neg logit contributions
berman-0.640
tti-0.617
HAEL-0.616
tails-0.600
 Heck-0.590
Token to
Token ID284
Feature activation+2.96e-01

Pos logit contributions
edIn+0.562
ification+0.506
ified+0.504
icians+0.503
itect+0.500
Neg logit contributions
berman-0.334
HAEL-0.318
tti-0.316
tails-0.310
mma-0.298
Token [
Token ID685
Feature activation+2.16e+00

Pos logit contributions
berman+0.751
HAEL+0.723
tti+0.720
tails+0.695
 Heck+0.692
Neg logit contributions
edIn-1.111
icians-0.978
ification-0.972
itect-0.972
ified-0.966
TokenLove
Token ID18565
Feature activation+9.58e-01

Pos logit contributions
berman+4.415
train+4.259
HO+4.223
mouth+4.209
HAEL+4.198
Neg logit contributions
edIn-8.666
icter-7.755
itect-7.729
icians-7.670
osate-7.541
Token],"
Token ID17241
Feature activation-7.24e-02

Pos logit contributions
berman+2.931
tti+2.865
HAEL+2.836
 Heck+2.734
tails+2.727
Neg logit contributions
edIn-3.092
icians-2.616
itect-2.607
ification-2.574
ified-2.541
Token O
Token ID440
Feature activation+3.58e+00

Pos logit contributions
edIn+0.300
icians+0.268
ification+0.265
itect+0.265
ified+0.263
Neg logit contributions
berman-0.157
HAEL-0.150
tti-0.149
 Heck-0.144
tails-0.143
Tokenly
Token ID306
Feature activation+1.44e+00

Pos logit contributions
berman+10.555
tti+10.285
train+9.992
tails+9.663
HO+9.562
Neg logit contributions
edIn-10.476
icter-9.622
osate-8.910
itect-8.682
icians-8.671
Tokenny
Token ID3281
Feature activation-2.92e-01

Pos logit contributions
berman+4.648
tti+4.528
HAEL+4.347
mma+4.346
tails+4.345
Neg logit contributions
edIn-4.455
icians-3.693
itect-3.675
icter-3.637
ification-3.591
Tokenk
Token ID74
Feature activation-4.94e-01

Pos logit contributions
edIn+1.023
ification+0.919
icians+0.914
ified+0.914
itect+0.905
Neg logit contributions
berman-0.777
HAEL-0.773
tti-0.739
tails-0.736
 Gamble-0.728
Token said
Token ID531
Feature activation+4.94e-01

Pos logit contributions
edIn+1.676
icians+1.460
ification+1.460
ified+1.453
itect+1.449
Neg logit contributions
berman-1.423
HAEL-1.374
tti-1.372
tails-1.339
 Heck-1.311
Token.
Token ID13
Feature activation+3.99e-01

Pos logit contributions
berman+1.000
tti+0.949
HAEL+0.937
 Heck+0.897
tails+0.894
Neg logit contributions
edIn-2.114
icians-1.890
itect-1.884
ification-1.873
ified-1.859
Token.
Token ID13
Feature activation+8.64e-02

Pos logit contributions
edIn+1.148
ification+1.027
icians+1.026
ified+1.021
itect+1.019
Neg logit contributions
berman-0.681
HAEL-0.646
tti-0.640
tails-0.624
mma-0.609
Token Earlier
Token ID20635
Feature activation+5.43e-02

Pos logit contributions
berman+0.219
tti+0.212
HAEL+0.211
tails+0.205
 Heck+0.203
Neg logit contributions
edIn-0.324
icians-0.285
ification-0.284
itect-0.283
ified-0.283
Token this
Token ID428
Feature activation+1.69e-01

Pos logit contributions
berman+0.131
tti+0.125
HAEL+0.125
tails+0.121
 Heck+0.119
Neg logit contributions
edIn-0.211
icians-0.187
ification-0.186
itect-0.186
ified-0.185
Token month
Token ID1227
Feature activation+3.81e-01

Pos logit contributions
berman+0.414
tti+0.399
HAEL+0.398
tails+0.385
 Heck+0.380
Neg logit contributions
edIn-0.646
icians-0.571
ification-0.568
itect-0.567
ified-0.565
Token,
Token ID11
Feature activation-1.15e-01

Pos logit contributions
berman+0.726
tti+0.696
HAEL+0.689
tails+0.661
 Heck+0.650
Neg logit contributions
edIn-1.665
icians-1.490
ification-1.488
itect-1.484
ified-1.480
Token O
Token ID440
Feature activation+3.58e+00

Pos logit contributions
edIn+0.424
icians+0.374
ification+0.373
itect+0.371
ified+0.371
Neg logit contributions
berman-0.297
HAEL-0.285
tti-0.284
tails-0.276
 Heck-0.271
Tokenla
Token ID5031
Feature activation+1.75e+00

Pos logit contributions
DI+9.739
berman+9.726
tti+9.638
HO+9.240
train+9.165
Neg logit contributions
edIn-10.785
icter-9.270
icians-9.195
acters-9.050
itect-9.038
Token,
Token ID11
Feature activation+8.32e-01

Pos logit contributions
berman+4.204
tti+4.151
HAEL+4.046
 Gamble+3.982
 Heck+3.940
Neg logit contributions
edIn-6.460
icians-5.628
ification-5.616
itect-5.561
ified-5.540
Token a
Token ID257
Feature activation+5.72e-01

Pos logit contributions
berman+2.137
tti+2.088
HAEL+2.072
 Heck+2.017
tails+2.004
Neg logit contributions
edIn-3.045
icians-2.656
ification-2.637
itect-2.635
ified-2.615
Token local
Token ID1957
Feature activation+5.12e-02

Pos logit contributions
berman+1.390
tti+1.351
HAEL+1.328
 Heck+1.295
tails+1.291
Neg logit contributions
edIn-2.197
icians-1.922
itect-1.915
ification-1.912
ified-1.896
Token taxi
Token ID17536
Feature activation+8.87e-01

Pos logit contributions
berman+0.124
tti+0.119
HAEL+0.119
tails+0.115
 Heck+0.113
Neg logit contributions
edIn-0.198
icians-0.175
ification-0.175
itect-0.174
ified-0.174
Token they
Token ID484
Feature activation+1.91e-01

Pos logit contributions
berman+2.876
tti+2.777
HAEL+2.775
 Heck+2.721
 Gamble+2.654
Neg logit contributions
edIn-4.039
itect-3.561
ification-3.505
icians-3.504
ified-3.463
Token first
Token ID717
Feature activation-4.34e-01

Pos logit contributions
berman+0.570
tti+0.552
HAEL+0.542
tails+0.532
 Heck+0.528
Neg logit contributions
edIn-0.642
icians-0.545
itect-0.543
ification-0.542
ified-0.537
Token met
Token ID1138
Feature activation+8.63e-01

Pos logit contributions
edIn+1.448
icians+1.259
ification+1.257
itect+1.249
ified+1.249
Neg logit contributions
berman-1.276
HAEL-1.231
tti-1.229
tails-1.199
 Heck-1.179
Token,
Token ID11
Feature activation-3.38e-01

Pos logit contributions
berman+1.764
tti+1.681
HAEL+1.672
 Heck+1.607
tails+1.606
Neg logit contributions
edIn-3.638
itect-3.269
icians-3.249
ification-3.237
ified-3.205
Token and
Token ID290
Feature activation-4.69e-01

Pos logit contributions
edIn+1.242
icians+1.097
ification+1.095
ified+1.089
itect+1.084
Neg logit contributions
berman-0.874
HAEL-0.838
tti-0.838
tails-0.817
mma-0.796
Token O
Token ID440
Feature activation+3.54e+00

Pos logit contributions
edIn+1.731
icians+1.531
ification+1.528
ified+1.521
itect+1.511
Neg logit contributions
berman-1.204
HAEL-1.156
tti-1.153
tails-1.127
mma-1.101
Token'
Token ID6
Feature activation+1.94e+00

Pos logit contributions
berman+9.205
tti+8.899
HAEL+8.431
HO+8.419
DI+8.228
Neg logit contributions
edIn-12.008
icter-10.614
icians-10.087
itect-10.023
acters-9.927
TokenNeill
Token ID26538
Feature activation-5.03e-01

Pos logit contributions
berman+2.944
HAEL+2.831
tti+2.642
HO+2.565
 Gamble+2.442
Neg logit contributions
edIn-9.097
icter-8.285
itect-8.099
icians-8.082
icipated-8.020
Token attempted
Token ID7482
Feature activation+1.67e+00

Pos logit contributions
edIn+1.724
ification+1.518
icians+1.514
ified+1.507
itect+1.498
Neg logit contributions
berman-1.422
HAEL-1.373
tti-1.364
tails-1.333
mma-1.305
Token to
Token ID284
Feature activation+5.76e-01

Pos logit contributions
berman+3.197
tti+3.028
HAEL+2.986
 Heck+2.888
tails+2.842
Neg logit contributions
edIn-7.025
itect-6.434
icians-6.369
ification-6.216
ifiers-6.209
Token advise
Token ID18595
Feature activation+1.40e+00

Pos logit contributions
berman+1.561
tti+1.497
HAEL+1.473
tails+1.446
 Heck+1.437
Neg logit contributions
edIn-2.078
icians-1.812
itect-1.798
ification-1.792
ified-1.779
Token half
Token ID2063
Feature activation+3.79e-01

Pos logit contributions
berman+1.344
tti+1.290
HAEL+1.285
tails+1.243
 Heck+1.242
Neg logit contributions
edIn-1.883
itect-1.635
icians-1.629
ification-1.609
ified-1.597
Token right
Token ID826
Feature activation+1.05e+00

Pos logit contributions
berman+0.990
tti+0.952
HAEL+0.942
 Heck+0.915
tails+0.913
Neg logit contributions
edIn-1.407
itect-1.223
icians-1.215
ification-1.200
ified-1.187
Token;
Token ID26
Feature activation+3.20e-01

Pos logit contributions
berman+2.065
tti+1.937
HAEL+1.912
tails+1.836
 Gamble+1.826
Neg logit contributions
edIn-4.544
itect-4.036
icians-4.026
ification-3.941
ified-3.919
Token none
Token ID4844
Feature activation-1.35e-01

Pos logit contributions
berman+0.858
tti+0.826
HAEL+0.820
tails+0.795
 Heck+0.793
Neg logit contributions
edIn-1.165
icians-1.013
itect-1.011
ification-1.005
ified-1.000
Token of
Token ID286
Feature activation+9.63e-01

Pos logit contributions
edIn+0.557
icians+0.496
ification+0.494
itect+0.493
ified+0.492
Neg logit contributions
berman-0.294
tti-0.279
HAEL-0.278
tails-0.268
 Heck-0.263
Token O
Token ID440
Feature activation+3.53e+00

Pos logit contributions
berman+2.342
HAEL+2.214
tti+2.201
 Heck+2.186
 Gamble+2.166
Neg logit contributions
edIn-3.708
itect-3.277
icians-3.237
ification-3.208
ified-3.187
Token'
Token ID6
Feature activation+1.66e+00

Pos logit contributions
berman+9.197
tti+8.762
train+8.303
DI+8.236
HAEL+8.229
Neg logit contributions
edIn-11.818
icter-10.464
icians-10.134
itect-10.052
acters-9.706
TokenBrian
Token ID24761
Feature activation-4.89e-01

Pos logit contributions
berman+4.013
HAEL+3.785
tti+3.699
tails+3.660
HO+3.584
Neg logit contributions
edIn-6.484
icians-5.648
itect-5.634
icter-5.596
icipated-5.514
Token's
Token ID338
Feature activation+2.34e-01

Pos logit contributions
edIn+1.606
icians+1.388
ification+1.384
itect+1.378
ified+1.374
Neg logit contributions
berman-1.471
tti-1.419
HAEL-1.418
tails-1.383
 Heck-1.362
Token work
Token ID670
Feature activation+9.60e-01

Pos logit contributions
berman+0.625
tti+0.603
HAEL+0.599
tails+0.585
 Heck+0.580
Neg logit contributions
edIn-0.846
icians-0.739
itect-0.738
ification-0.737
ified-0.731
Token was
Token ID373
Feature activation-2.39e-01

Pos logit contributions
berman+2.553
tti+2.473
HAEL+2.445
tails+2.418
 Heck+2.387
Neg logit contributions
edIn-3.448
itect-2.952
icians-2.947
ification-2.887
ified-2.862
Token,
Token ID11
Feature activation+1.32e-01

Pos logit contributions
edIn+2.394
ification+2.119
icians+2.103
ified+2.099
itect+2.092
Neg logit contributions
berman-1.571
HAEL-1.515
tti-1.494
tails-1.450
mma-1.429
Token on
Token ID319
Feature activation+1.68e-01

Pos logit contributions
berman+0.385
tti+0.373
HAEL+0.371
tails+0.363
 Heck+0.359
Neg logit contributions
edIn-0.443
icians-0.385
itect-0.382
ification-0.381
ified-0.379
Token a
Token ID257
Feature activation+9.81e-02

Pos logit contributions
berman+0.458
tti+0.444
HAEL+0.438
tails+0.430
 Heck+0.424
Neg logit contributions
edIn-0.598
icians-0.526
itect-0.523
ification-0.521
ified-0.518
Token mission
Token ID4365
Feature activation+5.12e-01

Pos logit contributions
berman+0.230
tti+0.220
HAEL+0.220
tails+0.213
 Heck+0.209
Neg logit contributions
edIn-0.386
icians-0.343
ification-0.342
itect-0.341
ified-0.340
Token designated
Token ID11032
Feature activation-1.35e+00

Pos logit contributions
berman+1.096
tti+1.055
HAEL+1.030
tails+1.006
 Heck+0.988
Neg logit contributions
edIn-2.105
icians-1.887
itect-1.878
ification-1.853
ified-1.850
Token O
Token ID440
Feature activation+3.50e+00

Pos logit contributions
edIn+5.181
ification+4.676
ified+4.646
itect+4.527
ifiers+4.508
Neg logit contributions
berman-3.158
HAEL-3.078
tails-2.941
tti-2.933
mma-2.804
TokenA
Token ID32
Feature activation+8.51e-01

Pos logit contributions
berman+8.060
DI+7.669
tti+7.622
HAEL+7.556
HO+7.491
Neg logit contributions
edIn-12.300
icians-11.212
icter-11.086
itect-11.004
ified-10.610
Token-
Token ID12
Feature activation+5.26e-01

Pos logit contributions
berman+2.060
HAEL+1.995
tti+1.971
tails+1.911
HO+1.900
Neg logit contributions
edIn-3.255
icians-2.914
ification-2.885
ified-2.854
itect-2.852
Token7
Token ID22
Feature activation+2.60e-01

Pos logit contributions
berman+1.126
HAEL+1.085
tti+1.085
tails+1.047
HO+1.020
Neg logit contributions
edIn-2.157
icians-1.943
itect-1.923
ification-1.921
ified-1.908
Token,
Token ID11
Feature activation+7.02e-01

Pos logit contributions
berman+0.542
tti+0.517
HAEL+0.516
tails+0.496
 Heck+0.485
Neg logit contributions
edIn-1.090
icians-0.978
ification-0.972
itect-0.969
ified-0.967
Token was
Token ID373
Feature activation+1.00e+00

Pos logit contributions
berman+1.980
tti+1.930
HAEL+1.885
tails+1.878
 Heck+1.839
Neg logit contributions
edIn-2.385
itect-2.080
icians-2.073
ification-2.055
ified-2.043
Token to
Token ID284
Feature activation-4.09e-01

Pos logit contributions
edIn+1.986
ification+1.821
ified+1.805
icians+1.793
itect+1.768
Neg logit contributions
berman-1.282
HAEL-1.230
tti-1.206
tails-1.196
senal-1.166
Token certain
Token ID1728
Feature activation+4.53e-02

Pos logit contributions
edIn+1.474
icians+1.295
ification+1.293
ified+1.285
itect+1.281
Neg logit contributions
berman-1.094
HAEL-1.053
tti-1.052
tails-1.023
 Heck-0.999
Token issues
Token ID2428
Feature activation-4.32e-01

Pos logit contributions
berman+0.122
tti+0.117
HAEL+0.117
tails+0.113
 Heck+0.112
Neg logit contributions
edIn-0.163
icians-0.143
ification-0.142
itect-0.142
ified-0.142
Token,
Token ID11
Feature activation+8.83e-02

Pos logit contributions
edIn+1.802
icians+1.621
ification+1.620
ified+1.611
itect+1.603
Neg logit contributions
berman-0.903
tti-0.856
HAEL-0.855
tails-0.826
mma-0.800
Token to
Token ID284
Feature activation-4.19e-01

Pos logit contributions
berman+0.229
HAEL+0.220
tti+0.220
tails+0.212
 Heck+0.211
Neg logit contributions
edIn-0.327
icians-0.287
itect-0.287
ification-0.286
ified-0.285
Token O
Token ID440
Feature activation+3.48e+00

Pos logit contributions
edIn+1.375
icians+1.189
ification+1.186
itect+1.181
ified+1.178
Neg logit contributions
berman-1.262
tti-1.217
HAEL-1.217
tails-1.187
 Heck-1.169
Token'
Token ID6
Feature activation+1.76e+00

Pos logit contributions
berman+8.957
tti+8.562
HO+8.218
HAEL+8.160
mouth+8.033
Neg logit contributions
edIn-11.893
icter-10.618
itect-9.977
icians-9.902
acters-9.892
TokenNeill
Token ID26538
Feature activation+3.03e-01

Pos logit contributions
berman+2.712
HAEL+2.612
tti+2.425
HO+2.351
 Heck+2.273
Neg logit contributions
edIn-8.272
icter-7.460
icians-7.370
itect-7.345
ification-7.276
Token's
Token ID338
Feature activation+8.56e-01

Pos logit contributions
berman+0.850
tti+0.819
HAEL+0.818
 Heck+0.792
tails+0.792
Neg logit contributions
edIn-1.059
itect-0.920
icians-0.915
ification-0.907
ified-0.903
Token open
Token ID1280
Feature activation+7.53e-01

Pos logit contributions
berman+2.053
tti+2.004
HAEL+1.975
 Heck+1.948
tails+1.909
Neg logit contributions
edIn-3.266
itect-2.900
icians-2.855
ification-2.825
icter-2.801
Token-
Token ID12
Feature activation+4.66e-01

Pos logit contributions
berman+1.923
tti+1.863
HAEL+1.838
tails+1.813
 Heck+1.801
Neg logit contributions
edIn-2.783
itect-2.430
icians-2.406
ification-2.376
ified-2.366
Tokens
Token ID82
Feature activation+1.90e-01

Pos logit contributions
berman+0.142
tti+0.137
HAEL+0.136
tails+0.133
 Heck+0.130
Neg logit contributions
edIn-0.188
icians-0.165
ification-0.164
itect-0.164
ified-0.163
Token largest
Token ID4387
Feature activation+4.05e-01

Pos logit contributions
berman+0.477
tti+0.457
HAEL+0.456
tails+0.442
 Heck+0.435
Neg logit contributions
edIn-0.717
icians-0.633
ification-0.631
itect-0.628
ified-0.627
Token capacity
Token ID5339
Feature activation+7.01e-02

Pos logit contributions
berman+1.040
tti+0.997
HAEL+0.983
 Heck+0.961
tails+0.954
Neg logit contributions
edIn-1.511
icians-1.328
ification-1.315
itect-1.307
ified-1.302
Token cartridge
Token ID26904
Feature activation+6.46e-01

Pos logit contributions
berman+0.172
tti+0.164
HAEL+0.164
tails+0.159
 Heck+0.156
Neg logit contributions
edIn-0.269
icians-0.238
ification-0.237
itect-0.236
ified-0.236
Token,
Token ID11
Feature activation-5.76e-02

Pos logit contributions
berman+1.505
tti+1.444
HAEL+1.416
 Heck+1.380
tails+1.378
Neg logit contributions
edIn-2.572
icians-2.269
itect-2.246
ification-2.239
ified-2.223
Token O
Token ID440
Feature activation+3.48e+00

Pos logit contributions
edIn+0.211
icians+0.185
ification+0.184
itect+0.184
ified+0.183
Neg logit contributions
berman-0.151
tti-0.146
HAEL-0.145
tails-0.140
 Heck-0.140
Tokencar
Token ID7718
Feature activation+2.20e-01

Pos logit contributions
berman+6.799
tti+6.625
train+6.165
cycl+6.122
DI+6.033
Neg logit contributions
edIn-13.502
icter-12.132
itect-12.035
ifiers-12.033
icians-12.023
Tokenina
Token ID1437
Feature activation-8.05e-01

Pos logit contributions
berman+0.622
HAEL+0.599
tti+0.597
tails+0.582
 Heck+0.574
Neg logit contributions
edIn-0.758
ification-0.664
icians-0.663
ified-0.660
itect-0.659
Token of
Token ID286
Feature activation-1.47e-01

Pos logit contributions
edIn+3.234
ification+2.884
icians+2.883
itect+2.878
ified+2.864
Neg logit contributions
berman-1.808
HAEL-1.735
tti-1.708
tails-1.684
mma-1.611
Token Time
Token ID3862
Feature activation+1.55e+00

Pos logit contributions
edIn+0.582
ification+0.520
ified+0.516
icians+0.515
itect+0.514
Neg logit contributions
berman-0.345
HAEL-0.331
tti-0.322
tails-0.310
mma-0.306
Token was
Token ID373
Feature activation+3.56e-01

Pos logit contributions
berman+3.752
tti+3.730
HAEL+3.536
 Heck+3.528
 Gamble+3.496
Neg logit contributions
edIn-5.738
icians-5.038
itect-4.940
ification-4.932
ifiers-4.889
Tokencos
Token ID6966
Feature activation-1.15e+00

Pos logit contributions
berman+1.243
tti+1.159
HAEL+1.118
tails+1.113
 Heck+1.068
Neg logit contributions
edIn-3.035
itect-2.695
ification-2.679
icians-2.673
ified-2.661
Token such
Token ID884
Feature activation+1.25e+00

Pos logit contributions
edIn+3.829
ification+3.427
ified+3.388
icians+3.380
itect+3.353
Neg logit contributions
berman-3.281
HAEL-3.166
tti-3.146
tails-3.093
mma-3.019
Token as
Token ID355
Feature activation+8.17e-01

Pos logit contributions
berman+2.524
tti+2.417
HAEL+2.379
tails+2.290
 Heck+2.252
Neg logit contributions
edIn-5.355
icians-4.760
itect-4.728
ification-4.695
ified-4.675
Token BT
Token ID22205
Feature activation+1.42e-01

Pos logit contributions
berman+1.763
tti+1.697
HAEL+1.667
 Heck+1.652
 Gamble+1.644
Neg logit contributions
edIn-3.338
icians-2.980
itect-2.966
ification-2.942
ified-2.923
Token,
Token ID11
Feature activation+7.66e-01

Pos logit contributions
berman+0.350
tti+0.337
HAEL+0.336
tails+0.324
 Heck+0.321
Neg logit contributions
edIn-0.540
icians-0.476
itect-0.474
ification-0.473
ified-0.470
Token O
Token ID440
Feature activation+3.47e+00

Pos logit contributions
berman+1.707
tti+1.651
HAEL+1.630
 Heck+1.594
 Gamble+1.593
Neg logit contributions
edIn-3.079
icians-2.735
itect-2.723
ification-2.708
ified-2.689
Token2
Token ID17
Feature activation+1.23e+00

Pos logit contributions
DI+7.510
tti+7.427
berman+7.425
train+7.017
mma+6.976
Neg logit contributions
edIn-12.695
icter-11.912
icians-11.358
itect-11.118
icipated-11.002
Token and
Token ID290
Feature activation+1.66e+00

Pos logit contributions
berman+2.911
tti+2.820
HAEL+2.779
 Gamble+2.711
 Heck+2.694
Neg logit contributions
edIn-4.717
icians-4.107
itect-4.093
ification-4.054
ified-4.036
Token Virgin
Token ID5283
Feature activation+1.12e+00

Pos logit contributions
berman+3.374
 Gamble+3.334
tti+3.315
 Heck+3.294
HAEL+3.155
Neg logit contributions
edIn-6.786
itect-6.012
icians-5.997
icter-5.923
ification-5.912
Token having
Token ID1719
Feature activation-6.98e-03

Pos logit contributions
tti+2.448
berman+2.445
 Gamble+2.419
HAEL+2.358
 Heck+2.345
Neg logit contributions
edIn-4.404
icians-3.922
itect-3.877
icter-3.816
acters-3.790
Token blocked
Token ID10226
Feature activation+7.46e-01

Pos logit contributions
edIn+0.023
icians+0.020
itect+0.020
ification+0.020
ified+0.020
Neg logit contributions
berman-0.021
tti-0.020
HAEL-0.020
tails-0.020
 Heck-0.020
Token before
Token ID878
Feature activation-3.23e-01

Pos logit contributions
berman+2.234
tti+2.156
HAEL+2.087
tails+2.051
 Heck+2.039
Neg logit contributions
edIn-4.275
icians-3.746
itect-3.736
ified-3.672
ification-3.670
Token the
Token ID262
Feature activation-4.76e-01

Pos logit contributions
edIn+1.188
icians+1.045
ification+1.042
itect+1.038
ified+1.036
Neg logit contributions
berman-0.841
tti-0.808
HAEL-0.807
tails-0.783
 Heck-0.772
Token program
Token ID1430
Feature activation-2.48e-02

Pos logit contributions
edIn+1.866
ification+1.670
icians+1.669
ified+1.658
itect+1.652
Neg logit contributions
berman-1.113
HAEL-1.072
tti-1.065
tails-1.034
mma-1.012
Token was
Token ID373
Feature activation-2.73e-01

Pos logit contributions
edIn+0.093
icians+0.082
itect+0.081
ification+0.081
ified+0.081
Neg logit contributions
berman-0.063
tti-0.060
HAEL-0.060
tails-0.058
 Heck-0.057
Token finally
Token ID3443
Feature activation-2.82e-01

Pos logit contributions
edIn+0.866
ification+0.750
icians+0.749
ified+0.745
itect+0.742
Neg logit contributions
berman-0.848
HAEL-0.821
tti-0.816
tails-0.799
 Heck-0.783
Token declass
Token ID42794
Feature activation-4.69e+00

Pos logit contributions
edIn+0.890
ification+0.771
icians+0.769
ified+0.766
itect+0.762
Neg logit contributions
berman-0.880
HAEL-0.853
tti-0.848
tails-0.828
 Heck-0.813
Tokenified
Token ID1431
Feature activation-1.72e+00

Pos logit contributions
ified+6.520
ification+5.720
ifying+3.959
edIn+3.873
ifiers+3.812
Neg logit contributions
senal-23.292
berman-21.651
HAEL-21.337
tails-21.080
 Heck-20.961
Token in
Token ID287
Feature activation-8.83e-01

Pos logit contributions
edIn+6.388
ification+5.856
ified+5.811
icians+5.695
itect+5.660
Neg logit contributions
berman-4.131
HAEL-3.957
tti-3.879
tails-3.862
mma-3.691
Token 2011
Token ID2813
Feature activation+4.23e-01

Pos logit contributions
edIn+2.747
ification+2.419
ified+2.405
icians+2.396
itect+2.359
Neg logit contributions
berman-2.733
HAEL-2.661
tti-2.641
tails-2.586
mma-2.539
Token.
Token ID13
Feature activation-2.69e-01

Pos logit contributions
berman+0.865
tti+0.828
HAEL+0.819
tails+0.785
 Heck+0.780
Neg logit contributions
edIn-1.791
icians-1.597
itect-1.585
ification-1.579
ified-1.574
Token That
Token ID1320
Feature activation+1.39e-01

Pos logit contributions
edIn+0.972
icians+0.853
ification+0.851
itect+0.847
ified+0.846
Neg logit contributions
berman-0.717
tti-0.690
HAEL-0.689
tails-0.669
 Heck-0.661
Token 2008
Token ID3648
Feature activation-1.08e-01

Pos logit contributions
edIn+0.133
icians+0.113
ification+0.113
ified+0.112
itect+0.112
Neg logit contributions
berman-0.150
HAEL-0.145
tti-0.145
tails-0.141
 Heck-0.139
Token election
Token ID3071
Feature activation-4.03e-01

Pos logit contributions
edIn+0.410
icians+0.362
ification+0.360
itect+0.360
ified+0.358
Neg logit contributions
berman-0.271
tti-0.259
HAEL-0.258
tails-0.252
 Heck-0.248
Token.
Token ID13
Feature activation+1.17e-01

Pos logit contributions
edIn+1.662
icians+1.486
ification+1.484
ified+1.476
itect+1.475
Neg logit contributions
berman-0.871
tti-0.829
HAEL-0.829
tails-0.801
 Heck-0.779
Token
Token ID198
Feature activation-5.03e-01

Pos logit contributions
berman+0.312
tti+0.302
HAEL+0.300
 Heck+0.296
 Gamble+0.290
Neg logit contributions
edIn-0.426
icians-0.375
itect-0.370
ification-0.370
ified-0.368
Token
Token ID198
Feature activation-5.51e-01

Pos logit contributions
edIn+1.549
ification+1.391
ified+1.385
itect+1.364
icians+1.358
Neg logit contributions
berman-1.571
senal-1.524
HAEL-1.516
tti-1.494
tails-1.468
TokenChrist
Token ID10684
Feature activation-4.56e+00

Pos logit contributions
edIn+1.920
icians+1.675
ification+1.673
itect+1.663
ified+1.662
Neg logit contributions
berman-1.545
tti-1.486
HAEL-1.486
tails-1.445
 Heck-1.421
Tokenie
Token ID494
Feature activation-1.20e+00

Pos logit contributions
ification+7.589
ified+7.576
edIn+7.150
ifiers+6.777
itect+6.748
Neg logit contributions
senal-17.641
HAEL-16.681
tails-16.619
 unnecess-16.254
berman-16.194
Token is
Token ID318
Feature activation-1.33e-01

Pos logit contributions
edIn+3.968
ification+3.471
icians+3.455
ified+3.435
itect+3.429
Neg logit contributions
berman-3.477
HAEL-3.373
tti-3.333
tails-3.280
mma-3.225
Token widely
Token ID6768
Feature activation-3.41e-01

Pos logit contributions
edIn+0.459
icians+0.399
ification+0.398
itect+0.396
ified+0.395
Neg logit contributions
berman-0.381
tti-0.367
HAEL-0.366
tails-0.357
 Heck-0.352
Token considered
Token ID3177
Feature activation-2.58e-01

Pos logit contributions
edIn+1.026
icians+0.876
ification+0.874
itect+0.868
ified+0.867
Neg logit contributions
berman-1.120
HAEL-1.083
tti-1.083
tails-1.058
 Heck-1.043
Token to
Token ID284
Feature activation-7.61e-01

Pos logit contributions
edIn+0.973
icians+0.858
ification+0.856
itect+0.853
ified+0.851
Neg logit contributions
berman-0.650
tti-0.622
HAEL-0.622
tails-0.603
 Heck-0.592
Token exit
Token ID8420
Feature activation-2.15e-01

Pos logit contributions
edIn+3.466
ified+3.030
ification+3.028
icians+3.012
itect+2.977
Neg logit contributions
berman-2.764
HAEL-2.665
tti-2.645
tails-2.613
mma-2.569
Token polls
Token ID9231
Feature activation-1.47e+00

Pos logit contributions
edIn+0.662
icians+0.560
ification+0.558
itect+0.557
ified+0.553
Neg logit contributions
berman-0.695
HAEL-0.673
tti-0.673
tails-0.658
 Heck-0.651
Token.
Token ID13
Feature activation-1.31e-01

Pos logit contributions
edIn+5.386
ified+4.881
ification+4.862
icians+4.821
itect+4.725
Neg logit contributions
berman-3.598
tti-3.489
HAEL-3.470
tails-3.428
mma-3.367
Token
Token ID198
Feature activation-4.39e-01

Pos logit contributions
edIn+0.479
icians+0.421
ification+0.418
itect+0.417
ified+0.416
Neg logit contributions
berman-0.342
tti-0.330
HAEL-0.330
tails-0.319
 Heck-0.319
Token
Token ID198
Feature activation-4.33e-01

Pos logit contributions
edIn+1.373
ification+1.224
ified+1.219
itect+1.203
icians+1.198
Neg logit contributions
berman-1.360
HAEL-1.303
tti-1.294
senal-1.291
tails-1.271
TokenChrist
Token ID10684
Feature activation-4.33e+00

Pos logit contributions
edIn+1.512
icians+1.322
ification+1.318
itect+1.312
ified+1.309
Neg logit contributions
berman-1.208
tti-1.163
HAEL-1.163
tails-1.131
 Heck-1.111
Tokenie
Token ID494
Feature activation-1.14e+00

Pos logit contributions
ification+5.393
ified+5.235
ifiers+4.642
edIn+4.600
icians+4.565
Neg logit contributions
senal-18.898
HAEL-18.090
tails-18.030
tti-17.598
mma-17.445
Token
Token ID447
Feature activation+3.29e-02

Pos logit contributions
edIn+3.773
ification+3.320
icians+3.309
ified+3.304
itect+3.255
Neg logit contributions
berman-3.294
HAEL-3.213
tti-3.150
tails-3.109
mma-3.051
Token
Token ID247
Feature activation+6.14e-01

Pos logit contributions
berman+0.092
tti+0.089
HAEL+0.089
tails+0.086
 Heck+0.085
Neg logit contributions
edIn-0.115
icians-0.100
ification-0.100
itect-0.099
ified-0.099
Tokens
Token ID82
Feature activation+3.85e-01

Pos logit contributions
berman+1.768
tti+1.716
HAEL+1.696
tails+1.648
 Heck+1.640
Neg logit contributions
edIn-2.076
icians-1.805
itect-1.791
ification-1.790
ified-1.773
Token showing
Token ID4478
Feature activation+5.65e-01

Pos logit contributions
berman+1.089
tti+1.050
HAEL+1.041
 Heck+1.017
tails+1.014
Neg logit contributions
edIn-1.320
itect-1.156
icians-1.156
ification-1.143
ified-1.133
Token humiliating
Token ID37743
Feature activation-1.33e+00

Pos logit contributions
edIn+4.698
ification+4.129
ified+4.122
icians+4.092
itect+4.089
Neg logit contributions
berman-3.543
tti-3.394
HAEL-3.368
tails-3.233
 Heck-3.188
Token defeat
Token ID7433
Feature activation-1.17e+00

Pos logit contributions
edIn+3.232
ified+2.711
ification+2.700
itect+2.634
icians+2.520
Neg logit contributions
berman-5.003
tti-4.860
HAEL-4.831
tails-4.759
HO-4.704
Token to
Token ID284
Feature activation-1.43e+00

Pos logit contributions
edIn+4.287
ification+3.869
ified+3.828
icians+3.806
itect+3.789
Neg logit contributions
berman-2.906
HAEL-2.770
tti-2.708
tails-2.687
mma-2.639
Token the
Token ID262
Feature activation-5.92e-01

Pos logit contributions
edIn+4.730
ification+4.133
icians+4.119
ified+4.071
itect+4.019
Neg logit contributions
berman-4.103
HAEL-4.015
tti-4.004
tails-3.885
mma-3.883
Token euros
Token ID21138
Feature activation-9.70e-01

Pos logit contributions
edIn+1.984
icians+1.730
ification+1.722
ified+1.708
itect+1.705
Neg logit contributions
berman-1.725
HAEL-1.675
tti-1.669
tails-1.622
 Heck-1.599
Tokencept
Token ID984
Feature activation-4.30e+00

Pos logit contributions
edIn+1.272
ification+0.954
icians+0.950
ified+0.927
itect+0.902
Neg logit contributions
berman-4.674
HAEL-4.653
tti-4.583
 Gamble-4.533
tails-4.527
Tokenic
Token ID291
Feature activation-3.20e-05

Pos logit contributions
ification+3.319
icians+3.203
ified+3.180
ics+3.055
edIn+2.544
Neg logit contributions
senal-22.296
HAEL-20.573
 unnecess-20.063
 Gamble-19.899
 Heck-19.612
Token UK
Token ID3482
Feature activation+1.09e+00

Pos logit contributions
edIn+0.000
icians+0.000
ification+0.000
ified+0.000
itect+0.000
Neg logit contributions
berman-0.000
tti-0.000
HAEL-0.000
tails-0.000
 Heck-0.000
Token IP
Token ID6101
Feature activation+2.08e+00

Pos logit contributions
berman+1.837
tti+1.721
HAEL+1.709
tails+1.641
 Heck+1.630
Neg logit contributions
edIn-4.978
itect-4.504
icians-4.488
ification-4.449
ified-4.428
Token party
Token ID2151
Feature activation+1.97e-01

Pos logit contributions
berman+4.653
HAEL+4.584
tti+4.333
HO+4.282
 Heck+4.274
Neg logit contributions
edIn-8.039
ifiers-7.294
ification-7.168
ified-7.159
itect-7.158
Token in
Token ID287
Feature activation-5.40e-01

Pos logit contributions
berman+0.431
tti+0.413
HAEL+0.412
tails+0.396
 Heck+0.391
Neg logit contributions
edIn-0.805
icians-0.718
itect-0.713
ification-0.713
ified-0.711
Token
Token ID447
Feature activation-3.69e-01

Pos logit contributions
edIn+1.124
icians+0.994
ification+0.992
itect+0.987
ified+0.987
Neg logit contributions
berman-0.761
HAEL-0.728
tti-0.728
tails-0.705
 Heck-0.692
Token
Token ID251
Feature activation-1.43e+00

Pos logit contributions
edIn+1.294
icians+1.130
ification+1.126
itect+1.122
ified+1.119
Neg logit contributions
berman-1.028
tti-0.988
HAEL-0.988
tails-0.961
 Heck-0.944
Token system
Token ID1080
Feature activation-8.98e-03

Pos logit contributions
edIn+5.192
ification+4.636
icians+4.614
ified+4.611
itect+4.591
Neg logit contributions
berman-3.653
HAEL-3.484
tti-3.470
tails-3.362
 Heck-3.274
Token has
Token ID468
Feature activation-1.61e+00

Pos logit contributions
edIn+0.034
icians+0.030
ification+0.030
itect+0.030
ified+0.029
Neg logit contributions
berman-0.023
HAEL-0.022
tti-0.022
tails-0.021
 Heck-0.021
Token been
Token ID587
Feature activation-2.65e-01

Pos logit contributions
edIn+5.180
ification+4.545
ified+4.531
icians+4.522
itect+4.498
Neg logit contributions
berman-4.798
HAEL-4.607
tti-4.534
tails-4.506
mma-4.382
Token declass
Token ID42794
Feature activation-4.27e+00

Pos logit contributions
edIn+0.877
icians+0.760
ification+0.759
itect+0.755
ified+0.754
Neg logit contributions
berman-0.786
tti-0.758
HAEL-0.758
tails-0.739
 Heck-0.727
Tokenified
Token ID1431
Feature activation-1.67e+00

Pos logit contributions
ified+5.640
ification+4.889
edIn+4.545
ifiers+3.669
ifying+3.585
Neg logit contributions
berman-19.772
HAEL-19.462
senal-19.288
tails-19.267
tti-19.128
Token,
Token ID11
Feature activation-1.09e+00

Pos logit contributions
edIn+6.146
ification+5.612
ified+5.573
icians+5.479
itect+5.478
Neg logit contributions
berman-4.048
HAEL-3.861
tti-3.834
tails-3.746
mma-3.638
Token although
Token ID3584
Feature activation-1.27e+00

Pos logit contributions
edIn+3.760
ification+3.327
icians+3.315
ified+3.300
itect+3.283
Neg logit contributions
berman-3.015
HAEL-2.899
tti-2.887
tails-2.810
mma-2.768
Token it
Token ID340
Feature activation+3.33e-01

Pos logit contributions
edIn+4.265
ification+3.802
ified+3.768
icians+3.768
itect+3.702
Neg logit contributions
berman-3.596
HAEL-3.457
tti-3.417
tails-3.363
mma-3.291
Token is
Token ID318
Feature activation+5.99e-01

Pos logit contributions
berman+0.842
tti+0.812
HAEL+0.795
tails+0.786
 Heck+0.770
Neg logit contributions
edIn-1.259
icians-1.095
itect-1.090
ification-1.084
ified-1.080
Token US
Token ID1294
Feature activation+4.34e-01

Pos logit contributions
berman+0.538
tti+0.518
HAEL+0.515
tails+0.504
 Heck+0.499
Neg logit contributions
edIn-0.699
icians-0.609
itect-0.606
ification-0.605
ified-0.601
Token,
Token ID11
Feature activation-5.39e-01

Pos logit contributions
berman+0.900
tti+0.856
HAEL+0.851
 Heck+0.819
tails+0.817
Neg logit contributions
edIn-1.817
icians-1.621
itect-1.605
ified-1.598
ification-1.594
Token where
Token ID810
Feature activation-5.36e-01

Pos logit contributions
edIn+1.932
icians+1.694
ification+1.689
itect+1.682
ified+1.679
Neg logit contributions
berman-1.457
tti-1.401
HAEL-1.399
tails-1.360
 Heck-1.338
Token 11
Token ID1367
Feature activation+4.73e-01

Pos logit contributions
edIn+1.917
icians+1.681
ification+1.678
itect+1.669
ified+1.667
Neg logit contributions
berman-1.452
HAEL-1.395
tti-1.395
tails-1.355
 Heck-1.329
Token b
Token ID275
Feature activation-3.44e-01

Pos logit contributions
berman+1.128
tti+1.108
HAEL+1.080
tails+1.064
 Heck+1.045
Neg logit contributions
edIn-1.840
ification-1.617
icians-1.614
ified-1.608
itect-1.608
Tokenidd
Token ID1638
Feature activation-4.26e+00

Pos logit contributions
edIn+1.445
icians+1.290
ification+1.289
itect+1.284
ified+1.282
Neg logit contributions
berman-0.720
tti-0.685
HAEL-0.685
tails-0.660
 Heck-0.644
Tokeners
Token ID364
Feature activation-2.23e+00

Pos logit contributions
edIn+10.774
ification+9.872
ifiers+9.702
ified+9.673
icians+9.619
Neg logit contributions
senal-14.029
HAEL-13.723
berman-13.529
mma-12.766
HO-12.713
Token have
Token ID423
Feature activation-2.05e+00

Pos logit contributions
edIn+6.679
ification+6.175
ified+6.090
icians+6.004
ifiers+5.956
Neg logit contributions
berman-6.679
HAEL-6.466
tti-6.409
tails-6.327
mma-6.236
Token sent
Token ID1908
Feature activation+6.78e-01

Pos logit contributions
edIn+5.708
ified+5.029
ification+5.027
icians+4.882
ifiers+4.836
Neg logit contributions
berman-6.815
HAEL-6.685
tti-6.502
tails-6.497
mma-6.362
Token the
Token ID262
Feature activation-1.37e-01

Pos logit contributions
berman+1.680
tti+1.599
 Heck+1.587
tails+1.578
HAEL+1.571
Neg logit contributions
edIn-2.561
itect-2.271
icians-2.249
ification-2.216
ified-2.208
Token price
Token ID2756
Feature activation+5.19e-02

Pos logit contributions
edIn+0.474
icians+0.412
itect+0.410
ification+0.409
ified+0.406
Neg logit contributions
berman-0.387
tti-0.375
HAEL-0.372
tails-0.364
 Heck-0.361
Token leak
Token ID13044
Feature activation+1.02e+00

Pos logit contributions
edIn+3.785
ification+3.323
icians+3.314
ified+3.309
itect+3.257
Neg logit contributions
berman-3.350
HAEL-3.235
tti-3.203
tails-3.135
mma-3.051
Token isn
Token ID2125
Feature activation-8.44e-01

Pos logit contributions
berman+2.443
tti+2.398
HAEL+2.324
tails+2.286
 Heck+2.280
Neg logit contributions
edIn-3.897
itect-3.433
icians-3.410
ification-3.342
ifiers-3.317
Token't
Token ID470
Feature activation-5.50e-01

Pos logit contributions
edIn+1.978
ification+1.762
ified+1.758
itect+1.687
icians+1.687
Neg logit contributions
berman-3.210
senal-3.158
HAEL-3.142
tti-3.076
tails-3.029
Token a
Token ID257
Feature activation-8.60e-01

Pos logit contributions
edIn+1.832
ification+1.605
ified+1.599
icians+1.595
itect+1.576
Neg logit contributions
berman-1.615
HAEL-1.563
tti-1.552
tails-1.513
mma-1.486
Token '
Token ID705
Feature activation-2.85e-01

Pos logit contributions
edIn+2.955
ification+2.591
icians+2.581
ified+2.576
itect+2.562
Neg logit contributions
berman-2.434
HAEL-2.353
tti-2.342
tails-2.275
mma-2.234
Tokencons
Token ID5936
Feature activation-4.19e+00

Pos logit contributions
edIn+0.967
icians+0.841
ification+0.838
itect+0.834
ified+0.833
Neg logit contributions
berman-0.825
tti-0.795
HAEL-0.794
tails-0.774
 Heck-0.761
Tokenpiracy
Token ID8703
Feature activation-2.23e+00

Pos logit contributions
ification+5.583
ified+5.263
edIn+5.250
ularity+5.126
itect+4.930
Neg logit contributions
senal-18.251
HAEL-17.478
berman-16.653
tti-16.559
tails-16.371
Token theory
Token ID4583
Feature activation-1.72e+00

Pos logit contributions
edIn+5.183
ification+4.452
ified+4.379
icians+4.295
itect+4.269
Neg logit contributions
berman-8.369
HAEL-8.176
tti-8.050
tails-7.974
mma-7.802
Token'
Token ID6
Feature activation+1.57e-02

Pos logit contributions
edIn+4.696
ification+4.100
ified+4.054
icians+4.020
itect+3.956
Neg logit contributions
berman-5.881
HAEL-5.756
tti-5.722
tails-5.606
mma-5.499
Token like
Token ID588
Feature activation+1.52e-01

Pos logit contributions
berman+0.042
tti+0.041
HAEL+0.041
tails+0.039
 Heck+0.039
Neg logit contributions
edIn-0.057
icians-0.050
itect-0.049
ification-0.049
ified-0.049
Token Donald
Token ID3759
Feature activation-4.07e-01

Pos logit contributions
berman+0.406
tti+0.390
HAEL+0.387
tails+0.378
 Heck+0.377
Neg logit contributions
edIn-0.549
itect-0.483
icians-0.480
ification-0.477
ified-0.473
Token,
Token ID11
Feature activation+2.40e-01

Pos logit contributions
edIn+4.750
ification+4.344
itect+4.299
ified+4.298
icians+4.264
Neg logit contributions
berman-2.510
HAEL-2.401
tti-2.357
tails-2.347
mma-2.242
Token drew
Token ID9859
Feature activation-1.15e-01

Pos logit contributions
berman+0.621
tti+0.602
HAEL+0.586
tails+0.580
 Heck+0.576
Neg logit contributions
edIn-0.887
icians-0.773
itect-0.767
ification-0.766
ified-0.764
Token just
Token ID655
Feature activation-1.61e+00

Pos logit contributions
edIn+0.432
icians+0.380
ification+0.378
itect+0.378
ified+0.376
Neg logit contributions
berman-0.293
tti-0.283
HAEL-0.281
tails-0.274
 Heck-0.271
Token eight
Token ID3624
Feature activation-1.22e-01

Pos logit contributions
edIn+5.426
ified+4.917
ification+4.914
icians+4.855
ifiers+4.791
Neg logit contributions
berman-4.468
HAEL-4.300
tti-4.239
tails-4.233
mma-4.057
Token b
Token ID275
Feature activation-1.95e-01

Pos logit contributions
edIn+0.441
icians+0.387
ification+0.386
itect+0.384
ified+0.384
Neg logit contributions
berman-0.327
tti-0.314
HAEL-0.313
tails-0.305
 Heck-0.299
Tokenidd
Token ID1638
Feature activation-4.06e+00

Pos logit contributions
edIn+0.827
icians+0.739
ification+0.738
itect+0.735
ified+0.734
Neg logit contributions
berman-0.400
tti-0.379
HAEL-0.378
tails-0.365
 Heck-0.355
Tokeners
Token ID364
Feature activation-2.00e+00

Pos logit contributions
edIn+10.191
ification+9.340
ified+9.093
ifiers+9.077
icians+8.960
Neg logit contributions
senal-14.216
HAEL-13.499
berman-13.278
tti-12.540
HO-12.512
Token when
Token ID618
Feature activation-3.30e-01

Pos logit contributions
edIn+7.230
ification+6.742
ified+6.683
icians+6.520
itect+6.514
Neg logit contributions
berman-4.820
HAEL-4.731
tails-4.586
tti-4.583
mma-4.469
Token auction
Token ID14389
Feature activation-1.11e+00

Pos logit contributions
edIn+1.184
icians+1.040
ification+1.036
itect+1.031
ified+1.029
Neg logit contributions
berman-0.890
HAEL-0.857
tti-0.855
tails-0.832
 Heck-0.823
Tokened
Token ID276
Feature activation+3.41e-01

Pos logit contributions
edIn+3.678
icians+3.172
ification+3.165
ified+3.158
itect+3.155
Neg logit contributions
berman-3.332
tti-3.206
HAEL-3.202
tails-3.115
mma-3.069
Token by
Token ID416
Feature activation-6.64e-02

Pos logit contributions
berman+0.704
tti+0.669
HAEL+0.667
tails+0.642
 Heck+0.637
Neg logit contributions
edIn-1.438
icians-1.289
itect-1.284
ification-1.281
ified-1.273
Token),
Token ID828
Feature activation+9.97e-01

Pos logit contributions
berman+0.393
tti+0.378
HAEL+0.378
tails+0.366
 Heck+0.362
Neg logit contributions
edIn-0.546
icians-0.481
itect-0.475
ification-0.474
ified-0.471
Token Gu
Token ID1962
Feature activation+7.60e-01

Pos logit contributions
berman+2.609
tti+2.498
HAEL+2.480
 Heck+2.466
 Gamble+2.439
Neg logit contributions
edIn-3.673
itect-3.199
icians-3.186
ification-3.129
ified-3.121
Tokenilla
Token ID5049
Feature activation+8.42e-01

Pos logit contributions
berman+2.274
tti+2.183
HAEL+2.177
tails+2.116
mma+2.097
Neg logit contributions
edIn-2.513
icians-2.151
itect-2.140
ification-2.136
ified-2.121
Tokenume
Token ID2454
Feature activation+7.85e-02

Pos logit contributions
berman+2.700
tti+2.601
HAEL+2.578
mma+2.535
tails+2.513
Neg logit contributions
edIn-2.626
icians-2.193
itect-2.184
ification-2.165
ified-2.146
Token (
Token ID357
Feature activation+8.30e-01

Pos logit contributions
berman+0.169
tti+0.161
HAEL+0.160
tails+0.154
 Heck+0.152
Neg logit contributions
edIn-0.326
icians-0.291
ification-0.289
itect-0.289
ified-0.287
Tokennom
Token ID26601
Feature activation-4.02e+00

Pos logit contributions
berman+2.258
tti+2.184
HAEL+2.159
tails+2.129
train+2.086
Neg logit contributions
edIn-2.929
icians-2.589
itect-2.557
ification-2.518
ified-2.496
Tokeninated
Token ID3898
Feature activation-1.45e+00

Pos logit contributions
edIn+6.595
ified+6.131
ification+5.928
icipated+5.545
icians+5.504
Neg logit contributions
HAEL-15.879
senal-15.826
tails-15.747
berman-15.529
tti-15.453
Token five
Token ID1936
Feature activation-2.15e-01

Pos logit contributions
edIn+5.023
ification+4.462
ified+4.446
icians+4.381
itect+4.342
Neg logit contributions
berman-3.915
HAEL-3.754
tti-3.710
tails-3.682
mma-3.541
Token times
Token ID1661
Feature activation+7.71e-01

Pos logit contributions
edIn+0.898
icians+0.804
ification+0.802
itect+0.799
ified+0.799
Neg logit contributions
berman-0.454
HAEL-0.431
tti-0.429
tails-0.414
 Heck-0.403
Token for
Token ID329
Feature activation-1.94e-01

Pos logit contributions
berman+1.639
HAEL+1.556
tti+1.542
tails+1.480
 Heck+1.473
Neg logit contributions
edIn-3.205
icians-2.857
itect-2.833
ification-2.829
ified-2.802
Token Benson
Token ID33940
Feature activation+6.66e-01

Pos logit contributions
edIn+0.768
icians+0.683
ification+0.680
itect+0.678
ified+0.677
Neg logit contributions
berman-0.454
tti-0.433
HAEL-0.433
tails-0.418
 Heck-0.412
Token mentioned
Token ID4750
Feature activation-7.40e-01

Pos logit contributions
berman+1.581
tti+1.518
HAEL+1.505
tails+1.460
 Heck+1.458
Neg logit contributions
edIn-2.199
icians-1.914
itect-1.914
ification-1.890
ified-1.884
Token in
Token ID287
Feature activation-6.25e-01

Pos logit contributions
edIn+2.814
ification+2.513
ified+2.499
icians+2.498
itect+2.477
Neg logit contributions
berman-1.808
HAEL-1.733
tti-1.727
tails-1.684
mma-1.629
Token at
Token ID379
Feature activation+2.49e-01

Pos logit contributions
edIn+2.255
icians+1.982
ification+1.980
itect+1.969
ified+1.968
Neg logit contributions
berman-1.668
HAEL-1.603
tti-1.601
tails-1.556
 Heck-1.523
Token least
Token ID1551
Feature activation-1.88e-01

Pos logit contributions
berman+0.672
tti+0.651
HAEL+0.645
tails+0.633
 Heck+0.628
Neg logit contributions
edIn-0.900
icians-0.777
itect-0.770
ification-0.769
ified-0.766
Token one
Token ID530
Feature activation+6.78e-01

Pos logit contributions
edIn+0.690
icians+0.607
ification+0.605
itect+0.603
ified+0.601
Neg logit contributions
berman-0.491
tti-0.472
HAEL-0.471
tails-0.457
 Heck-0.450
Token declass
Token ID42794
Feature activation-3.98e+00

Pos logit contributions
berman+1.742
tti+1.683
HAEL+1.651
 Heck+1.640
tails+1.616
Neg logit contributions
edIn-2.512
icians-2.207
itect-2.181
ification-2.165
ified-2.155
Tokenified
Token ID1431
Feature activation-1.29e+00

Pos logit contributions
ified+5.520
ification+5.341
edIn+4.604
ifying+3.921
ifiers+3.871
Neg logit contributions
berman-18.268
HAEL-17.857
tails-17.692
senal-17.676
tti-17.674
Token document
Token ID3188
Feature activation-4.63e-01

Pos logit contributions
edIn+4.355
ification+3.940
ified+3.916
icians+3.838
itect+3.833
Neg logit contributions
berman-3.584
HAEL-3.479
tti-3.443
tails-3.381
mma-3.267
Token dating
Token ID10691
Feature activation-1.40e+00

Pos logit contributions
edIn+1.817
icians+1.616
ification+1.615
ified+1.605
itect+1.605
Neg logit contributions
berman-1.091
HAEL-1.043
tti-1.041
tails-1.008
 Heck-0.985
Token from
Token ID422
Feature activation-7.13e-01

Pos logit contributions
edIn+5.101
ification+4.651
ified+4.599
icians+4.587
ifiers+4.487
Neg logit contributions
berman-3.455
HAEL-3.355
tti-3.284
tails-3.245
mma-3.147
Token late
Token ID2739
Feature activation+1.02e+00

Pos logit contributions
edIn+2.266
ification+1.977
icians+1.963
ified+1.957
itect+1.942
Neg logit contributions
berman-2.187
HAEL-2.123
tti-2.107
tails-2.073
mma-2.027
Token-
Token ID12
Feature activation-5.76e-01

Pos logit contributions
edIn+0.187
icians+0.163
itect+0.162
ification+0.161
ified+0.160
Neg logit contributions
berman-0.149
tti-0.144
HAEL-0.144
tails-0.140
 Heck-0.137
Tokeno
Token ID78
Feature activation+5.27e-01

Pos logit contributions
edIn+1.921
ification+1.669
icians+1.669
ified+1.660
itect+1.657
Neg logit contributions
berman-1.690
tti-1.632
HAEL-1.631
tails-1.583
 Heck-1.569
Tokenvert
Token ID1851
Feature activation-5.77e-01

Pos logit contributions
berman+1.503
tti+1.416
tails+1.373
HAEL+1.370
 Gamble+1.356
Neg logit contributions
edIn-1.810
icians-1.594
itect-1.577
ifiers-1.558
ification-1.556
Tokenime
Token ID524
Feature activation-2.25e-02

Pos logit contributions
edIn+1.934
ification+1.701
icians+1.694
itect+1.691
ified+1.688
Neg logit contributions
berman-1.680
tti-1.622
HAEL-1.618
tails-1.582
 Heck-1.548
Token goal
Token ID3061
Feature activation-3.17e-01

Pos logit contributions
edIn+0.081
icians+0.071
itect+0.071
ification+0.071
ified+0.070
Neg logit contributions
berman-0.060
tti-0.058
HAEL-0.058
tails-0.056
 Heck-0.055
Token clin
Token ID5327
Feature activation-3.97e+00

Pos logit contributions
edIn+1.212
icians+1.073
ification+1.069
itect+1.066
ified+1.063
Neg logit contributions
berman-0.779
tti-0.747
HAEL-0.745
tails-0.722
 Heck-0.709
Tokenched
Token ID1740
Feature activation-1.52e+00

Pos logit contributions
ified+6.393
ification+5.909
edIn+5.710
icians+5.085
ifiers+5.051
Neg logit contributions
senal-17.592
HAEL-17.123
 Gamble-15.926
berman-15.863
 Heck-15.777
Token New
Token ID968
Feature activation-7.41e-01

Pos logit contributions
edIn+5.021
ified+4.429
ification+4.403
icians+4.343
itect+4.229
Neg logit contributions
berman-4.370
HAEL-4.271
tti-4.214
tails-4.092
mma-4.023
Token Jersey
Token ID8221
Feature activation-2.00e+00

Pos logit contributions
edIn+2.579
ification+2.243
icians+2.243
ified+2.229
itect+2.220
Neg logit contributions
berman-2.061
HAEL-2.010
tti-1.996
tails-1.935
mma-1.911
Token
Token ID447
Feature activation-4.05e-01

Pos logit contributions
edIn+6.157
ification+5.447
ified+5.422
icians+5.285
itect+5.205
Neg logit contributions
berman-5.995
HAEL-5.971
tti-5.753
tails-5.690
mma-5.656
Token
Token ID247
Feature activation-4.76e-01

Pos logit contributions
edIn+1.180
icians+0.997
ification+0.993
ified+0.992
itect+0.988
Neg logit contributions
berman-1.342
tti-1.304
HAEL-1.295
tails-1.289
 Heck-1.253
Token and
Token ID290
Feature activation+8.82e-01

Pos logit contributions
berman+0.397
tti+0.383
HAEL+0.378
tails+0.368
 Heck+0.367
Neg logit contributions
edIn-0.676
icians-0.597
ification-0.594
itect-0.594
ified-0.591
Token the
Token ID262
Feature activation+2.03e-01

Pos logit contributions
berman+2.128
tti+2.065
HAEL+2.047
 Heck+1.993
 Gamble+1.985
Neg logit contributions
edIn-3.395
icians-2.975
itect-2.975
ification-2.948
ified-2.920
Token Giant
Token ID17384
Feature activation+2.61e-01

Pos logit contributions
berman+0.475
tti+0.459
HAEL+0.456
tails+0.443
 Heck+0.439
Neg logit contributions
edIn-0.801
icians-0.708
ification-0.706
itect-0.705
ified-0.702
Token Peach
Token ID33230
Feature activation-1.42e-01

Pos logit contributions
berman+0.603
tti+0.578
HAEL+0.569
tails+0.561
 Heck+0.554
Neg logit contributions
edIn-1.039
icians-0.921
ification-0.918
itect-0.916
ified-0.910
Token (
Token ID357
Feature activation+3.25e-01

Pos logit contributions
edIn+0.589
icians+0.526
ification+0.525
itect+0.523
ified+0.522
Neg logit contributions
berman-0.307
HAEL-0.291
tti-0.291
tails-0.281
 Heck-0.274
Tokeninit
Token ID15003
Feature activation-3.96e+00

Pos logit contributions
berman+0.823
tti+0.791
HAEL+0.790
tails+0.769
mma+0.750
Neg logit contributions
edIn-1.212
icians-1.072
itect-1.063
ification-1.058
ified-1.049
Tokenially
Token ID1927
Feature activation-1.25e+00

Pos logit contributions
edIn+8.375
ified+7.954
ification+7.857
itect+7.111
icipated+7.094
Neg logit contributions
berman-14.205
HAEL-14.021
tti-13.445
HO-13.337
mma-13.259
Token titled
Token ID11946
Feature activation-9.61e-01

Pos logit contributions
edIn+4.027
ification+3.593
ified+3.580
itect+3.503
icians+3.499
Neg logit contributions
berman-3.701
HAEL-3.561
tti-3.509
tails-3.451
mma-3.373
Token James
Token ID3700
Feature activation-8.11e-01

Pos logit contributions
edIn+3.628
ification+3.239
ified+3.231
icians+3.218
itect+3.209
Neg logit contributions
berman-2.364
HAEL-2.256
tti-2.231
tails-2.176
mma-2.112
Token and
Token ID290
Feature activation-5.92e-01

Pos logit contributions
edIn+2.968
ification+2.619
icians+2.615
ified+2.607
itect+2.599
Neg logit contributions
berman-2.115
HAEL-2.033
tti-2.019
tails-1.959
 Heck-1.917
Token the
Token ID262
Feature activation-9.43e-01

Pos logit contributions
edIn+2.114
ification+1.861
icians+1.860
ified+1.851
itect+1.844
Neg logit contributions
berman-1.595
HAEL-1.536
tti-1.524
tails-1.480
mma-1.451
Token dinosaurs
Token ID27199
Feature activation-1.56e+00

Pos logit contributions
berman+3.517
tti+3.453
HAEL+3.353
tails+3.318
 Heck+3.316
Neg logit contributions
edIn-4.601
icians-3.960
itect-3.930
ification-3.847
icter-3.810
Token do
Token ID466
Feature activation+1.72e+00

Pos logit contributions
edIn+4.593
ification+4.229
ified+4.207
icians+4.123
itect+4.085
Neg logit contributions
berman-4.813
HAEL-4.775
tti-4.673
tails-4.601
mma-4.511
Token while
Token ID981
Feature activation-7.25e-02

Pos logit contributions
berman+3.507
tti+3.286
HAEL+3.244
 Heck+3.134
tails+3.126
Neg logit contributions
edIn-7.295
icians-6.410
itect-6.327
ification-6.240
icter-6.239
Token nesting
Token ID46282
Feature activation+4.49e-01

Pos logit contributions
edIn+0.255
icians+0.223
ification+0.221
itect+0.221
ified+0.220
Neg logit contributions
berman-0.201
tti-0.193
HAEL-0.192
tails-0.189
 Heck-0.186
Token (
Token ID357
Feature activation-2.48e-02

Pos logit contributions
berman+0.932
tti+0.884
HAEL+0.875
tails+0.857
 Heck+0.837
Neg logit contributions
edIn-1.889
icians-1.700
ification-1.684
itect-1.680
ified-1.670
Tokenscient
Token ID25346
Feature activation-3.92e+00

Pos logit contributions
edIn+0.087
icians+0.076
ification+0.075
itect+0.075
ified+0.075
Neg logit contributions
berman-0.070
tti-0.067
HAEL-0.067
tails-0.065
 Heck-0.064
Tokenists
Token ID1023
Feature activation-1.72e+00

Pos logit contributions
edIn+8.319
icians+7.973
ified+7.836
ification+7.812
ifiers+7.342
Neg logit contributions
HAEL-13.794
mma-13.760
berman-13.716
tti-13.592
 Heck-13.209
Token think
Token ID892
Feature activation-7.94e-01

Pos logit contributions
edIn+5.363
ification+4.900
ified+4.886
icians+4.834
itect+4.751
Neg logit contributions
berman-4.909
HAEL-4.849
tti-4.765
tails-4.707
mma-4.607
Token some
Token ID617
Feature activation+1.06e-01

Pos logit contributions
edIn+2.732
ification+2.415
icians+2.400
ified+2.395
itect+2.371
Neg logit contributions
berman-2.206
HAEL-2.146
tti-2.110
tails-2.057
mma-2.006
Token species
Token ID4693
Feature activation-9.00e-01

Pos logit contributions
berman+0.263
tti+0.253
HAEL+0.251
tails+0.245
 Heck+0.240
Neg logit contributions
edIn-0.401
icians-0.354
ification-0.352
itect-0.352
ified-0.350
Token sat
Token ID3332
Feature activation-9.28e-01

Pos logit contributions
edIn+3.060
ification+2.711
icians+2.697
ified+2.692
itect+2.684
Neg logit contributions
berman-2.537
HAEL-2.463
tti-2.443
tails-2.387
 Heck-2.338
Token arts
Token ID10848
Feature activation-2.77e-01

Pos logit contributions
berman+2.182
HAEL+2.115
tti+2.110
tails+2.092
 Gamble+2.038
Neg logit contributions
edIn-3.043
itect-2.625
icians-2.621
ified-2.587
ification-2.584
Token in
Token ID287
Feature activation-8.86e-01

Pos logit contributions
edIn+1.093
icians+0.969
ification+0.965
itect+0.963
ified+0.961
Neg logit contributions
berman-0.647
tti-0.620
HAEL-0.619
tails-0.600
 Heck-0.587
Token the
Token ID262
Feature activation-2.15e-01

Pos logit contributions
edIn+2.916
ification+2.536
icians+2.533
itect+2.517
ified+2.515
Neg logit contributions
berman-2.635
HAEL-2.551
tti-2.539
tails-2.473
mma-2.425
Token post
Token ID1281
Feature activation+1.12e+00

Pos logit contributions
edIn+0.854
icians+0.761
ification+0.761
ified+0.757
itect+0.755
Neg logit contributions
berman-0.499
HAEL-0.478
tti-0.475
tails-0.459
mma-0.447
Token-
Token ID12
Feature activation+4.02e-01

Pos logit contributions
berman+2.842
tti+2.730
HAEL+2.666
 Heck+2.633
 Gamble+2.620
Neg logit contributions
edIn-4.194
icians-3.606
itect-3.582
ification-3.540
ified-3.497
Tokenconf
Token ID10414
Feature activation-3.89e+00

Pos logit contributions
berman+0.993
tti+0.946
HAEL+0.936
tails+0.928
 Heck+0.898
Neg logit contributions
edIn-1.541
icians-1.358
itect-1.346
ification-1.344
ified-1.339
Tokenlict
Token ID13758
Feature activation+1.76e-01

Pos logit contributions
edIn+6.166
ification+5.846
ified+5.795
essed+5.138
icians+4.834
Neg logit contributions
HAEL-15.875
senal-15.849
tti-15.262
berman-15.250
 Heck-14.884
Token capital
Token ID3139
Feature activation-2.74e-01

Pos logit contributions
berman+0.427
tti+0.409
HAEL+0.408
tails+0.396
 Heck+0.389
Neg logit contributions
edIn-0.681
icians-0.603
ification-0.601
itect-0.599
ified-0.598
Token and
Token ID290
Feature activation-5.85e-01

Pos logit contributions
edIn+1.115
icians+0.994
ification+0.992
itect+0.988
ified+0.987
Neg logit contributions
berman-0.606
tti-0.577
HAEL-0.577
tails-0.557
 Heck-0.545
Token her
Token ID607
Feature activation-4.95e-01

Pos logit contributions
edIn+2.099
icians+1.851
ification+1.848
ified+1.837
itect+1.836
Neg logit contributions
berman-1.568
HAEL-1.512
tti-1.505
tails-1.465
 Heck-1.435
Token drive
Token ID3708
Feature activation+1.46e+00

Pos logit contributions
edIn+1.792
ification+1.578
icians+1.574
ified+1.567
itect+1.558
Neg logit contributions
berman-1.325
HAEL-1.273
tti-1.266
tails-1.229
 Heck-1.206
Token called
Token ID1444
Feature activation+6.27e-01

Pos logit contributions
edIn+5.995
ified+5.513
ification+5.475
icians+5.311
ifiers+5.286
Neg logit contributions
berman-6.187
HAEL-6.050
tails-5.846
tti-5.775
mma-5.724
Token these
Token ID777
Feature activation+1.32e+00

Pos logit contributions
berman+1.465
tti+1.402
HAEL+1.374
 Heck+1.349
tails+1.346
Neg logit contributions
edIn-2.468
itect-2.207
icians-2.185
ification-2.173
ified-2.153
Token accusations
Token ID14227
Feature activation+1.75e-01

Pos logit contributions
berman+3.339
tti+3.237
tails+3.160
 Heck+3.150
HAEL+3.101
Neg logit contributions
edIn-4.834
itect-4.289
icians-4.188
ification-4.122
icter-4.108
Token a
Token ID257
Feature activation-8.65e-01

Pos logit contributions
berman+0.458
tti+0.439
HAEL+0.438
tails+0.426
 Heck+0.420
Neg logit contributions
edIn-0.645
icians-0.567
itect-0.563
ification-0.563
ified-0.560
Token '
Token ID705
Feature activation-2.97e-01

Pos logit contributions
edIn+3.070
ification+2.708
icians+2.694
ified+2.693
itect+2.679
Neg logit contributions
berman-2.350
HAEL-2.270
tti-2.261
tails-2.188
mma-2.153
Tokencons
Token ID5936
Feature activation-3.88e+00

Pos logit contributions
edIn+1.018
icians+0.886
ification+0.881
itect+0.879
ified+0.876
Neg logit contributions
berman-0.853
tti-0.822
HAEL-0.819
tails-0.802
 Heck-0.786
Tokenpiracy
Token ID8703
Feature activation-1.56e+00

Pos logit contributions
edIn+5.803
ification+5.676
ified+5.531
ervatives+5.206
ularity+5.044
Neg logit contributions
HAEL-16.031
berman-15.573
tails-15.310
tti-15.301
senal-15.061
Token theory
Token ID4583
Feature activation-1.48e+00

Pos logit contributions
edIn+3.898
ification+3.396
ified+3.349
icians+3.314
itect+3.291
Neg logit contributions
berman-5.640
HAEL-5.533
tti-5.453
tails-5.404
mma-5.285
Token.'
Token ID2637
Feature activation-1.37e-01

Pos logit contributions
edIn+4.553
ification+4.075
ified+4.037
icians+3.999
itect+3.947
Neg logit contributions
berman-4.552
HAEL-4.460
tti-4.404
tails-4.291
 Heck-4.210
Token
Token ID198
Feature activation+9.70e-03

Pos logit contributions
edIn+0.482
icians+0.420
itect+0.419
ification+0.419
ified+0.415
Neg logit contributions
berman-0.378
tti-0.365
HAEL-0.363
tails-0.354
 Heck-0.351
Token
Token ID198
Feature activation+2.82e-01

Pos logit contributions
berman+0.028
HAEL+0.027
tti+0.027
tails+0.027
 Heck+0.026
Neg logit contributions
edIn-0.033
ification-0.029
icians-0.028
ified-0.028
itect-0.028
Token one
Token ID530
Feature activation-2.75e-01

Pos logit contributions
berman+0.452
tti+0.435
HAEL+0.434
tails+0.420
 Heck+0.416
Neg logit contributions
edIn-0.605
icians-0.528
ification-0.527
itect-0.525
ified-0.523
Token of
Token ID286
Feature activation-1.02e-01

Pos logit contributions
edIn+1.132
icians+1.012
ification+1.011
ified+1.005
itect+1.005
Neg logit contributions
berman-0.596
HAEL-0.567
tti-0.567
tails-0.548
mma-0.532
Token the
Token ID262
Feature activation-4.73e-01

Pos logit contributions
edIn+0.384
icians+0.338
ification+0.337
itect+0.336
ified+0.335
Neg logit contributions
berman-0.260
HAEL-0.249
tti-0.249
tails-0.241
 Heck-0.238
Token more
Token ID517
Feature activation-4.39e-01

Pos logit contributions
edIn+1.677
ification+1.476
icians+1.475
ified+1.467
itect+1.466
Neg logit contributions
berman-1.285
HAEL-1.234
tti-1.230
tails-1.198
 Heck-1.175
Token devastating
Token ID14101
Feature activation+2.84e-01

Pos logit contributions
edIn+1.695
ification+1.504
icians+1.503
ified+1.496
itect+1.491
Neg logit contributions
berman-1.057
HAEL-1.012
tti-1.010
tails-0.978
 Heck-0.955
Tokensequ
Token ID3107
Feature activation-3.86e+00

Pos logit contributions
berman+0.733
tti+0.704
HAEL+0.701
tails+0.682
 Heck+0.672
Neg logit contributions
edIn-1.054
icians-0.926
ification-0.924
itect-0.921
ified-0.917
Tokenences
Token ID3007
Feature activation-7.05e-01

Pos logit contributions
edIn+8.943
icians+8.447
ified+8.326
ification+8.258
ifiers+7.989
Neg logit contributions
HAEL-12.908
senal-12.656
 Heck-12.225
 Gamble-12.084
mma-11.911
Token in
Token ID287
Feature activation-3.34e-01

Pos logit contributions
edIn+2.810
icians+2.521
ification+2.513
ified+2.504
itect+2.484
Neg logit contributions
berman-1.602
HAEL-1.524
tti-1.517
tails-1.484
mma-1.434
Token movie
Token ID3807
Feature activation+8.62e-02

Pos logit contributions
edIn+1.262
icians+1.114
ification+1.112
itect+1.107
ified+1.105
Neg logit contributions
berman-0.840
tti-0.805
HAEL-0.804
tails-0.780
 Heck-0.765
Token history
Token ID2106
Feature activation-3.06e-01

Pos logit contributions
berman+0.263
tti+0.254
HAEL+0.252
tails+0.246
 Heck+0.243
Neg logit contributions
edIn-0.282
icians-0.241
ification-0.238
itect-0.238
ified-0.237
Token.
Token ID13
Feature activation+1.02e-01

Pos logit contributions
edIn+1.248
icians+1.122
ification+1.120
ified+1.115
itect+1.112
Neg logit contributions
berman-0.665
HAEL-0.636
tti-0.631
tails-0.614
 Heck-0.596
Token such
Token ID884
Feature activation+1.90e+00

Pos logit contributions
edIn+3.914
ification+3.493
icians+3.482
ified+3.465
ifiers+3.381
Neg logit contributions
berman-2.832
HAEL-2.741
tti-2.698
tails-2.644
mma-2.584
Token services
Token ID2594
Feature activation+1.31e+00

Pos logit contributions
berman+3.867
 Heck+3.766
tti+3.694
 Gamble+3.637
HAEL+3.619
Neg logit contributions
edIn-7.606
itect-6.885
icter-6.698
icians-6.689
osate-6.618
Token remains
Token ID3793
Feature activation-2.78e-01

Pos logit contributions
berman+3.299
tti+3.141
HAEL+3.099
 Heck+3.076
tails+3.043
Neg logit contributions
edIn-4.924
itect-4.276
icians-4.218
icter-4.215
ification-4.122
Token a
Token ID257
Feature activation-6.48e-01

Pos logit contributions
edIn+1.001
ification+0.881
icians+0.877
ified+0.877
itect+0.866
Neg logit contributions
berman-0.741
HAEL-0.714
tti-0.713
tails-0.690
 Gamble-0.673
Token min
Token ID949
Feature activation-2.64e+00

Pos logit contributions
edIn+2.286
ification+2.003
icians+2.002
ified+1.995
itect+1.984
Neg logit contributions
berman-1.781
tti-1.716
HAEL-1.715
tails-1.666
 Heck-1.624
Tokenusc
Token ID16241
Feature activation-3.81e+00

Pos logit contributions
ified+5.770
ification+5.702
edIn+5.694
ificant+5.242
icians+5.220
Neg logit contributions
HAEL-9.536
berman-9.434
tti-9.378
tails-9.262
HO-9.044
Tokenule
Token ID2261
Feature activation-9.56e-01

Pos logit contributions
ification+4.486
ified+4.303
ularity+3.803
edIn+3.479
itect+3.412
Neg logit contributions
senal-18.470
berman-17.497
tails-17.237
tti-16.812
 Gamble-16.600
Token fraction
Token ID13390
Feature activation-4.99e-01

Pos logit contributions
edIn+3.245
ification+2.882
ified+2.878
icians+2.827
itect+2.792
Neg logit contributions
berman-2.710
HAEL-2.639
tti-2.631
tails-2.578
mma-2.463
Token of
Token ID286
Feature activation-2.25e-01

Pos logit contributions
edIn+2.029
icians+1.820
ification+1.819
ified+1.811
itect+1.804
Neg logit contributions
berman-1.096
HAEL-1.048
tti-1.047
tails-1.014
 Heck-0.978
Token the
Token ID262
Feature activation-4.52e-01

Pos logit contributions
edIn+0.831
icians+0.732
ification+0.730
itect+0.726
ified+0.725
Neg logit contributions
berman-0.586
tti-0.563
HAEL-0.562
tails-0.546
 Heck-0.535
Token school
Token ID1524
Feature activation-8.52e-01

Pos logit contributions
edIn+1.559
icians+1.364
ification+1.362
ified+1.353
itect+1.343
Neg logit contributions
berman-1.281
tti-1.236
HAEL-1.234
tails-1.201
mma-1.176
Tokenawareness
Token ID47812
Feature activation-1.46e+00

Pos logit contributions
berman+0.496
tti+0.479
HAEL+0.473
tails+0.469
train+0.455
Neg logit contributions
edIn-0.634
icians-0.553
itect-0.547
ification-0.540
ified-0.539
Token regarding
Token ID5115
Feature activation-1.23e+00

Pos logit contributions
edIn+5.207
ification+4.840
ified+4.757
icians+4.724
itect+4.669
Neg logit contributions
berman-3.736
HAEL-3.605
tti-3.514
tails-3.473
 Heck-3.392
Token incorporation
Token ID43619
Feature activation+1.89e-01

Pos logit contributions
edIn+4.278
ification+3.852
ified+3.819
icians+3.793
itect+3.736
Neg logit contributions
berman-3.311
HAEL-3.244
tti-3.191
tails-3.104
mma-3.031
Token"
Token ID1
Feature activation+2.39e-01

Pos logit contributions
berman+0.442
tti+0.421
HAEL+0.418
tails+0.406
 Heck+0.400
Neg logit contributions
edIn-0.752
icians-0.665
itect-0.662
ification-0.659
ified-0.657
Token (
Token ID357
Feature activation-5.74e-01

Pos logit contributions
berman+0.541
tti+0.517
HAEL+0.514
tails+0.497
 Heck+0.490
Neg logit contributions
edIn-0.967
icians-0.858
itect-0.851
ification-0.850
ified-0.845
TokenNe
Token ID8199
Feature activation-3.77e+00

Pos logit contributions
edIn+2.508
icians+2.255
ification+2.254
ified+2.244
itect+2.243
Neg logit contributions
berman-1.091
HAEL-1.035
tti-1.031
tails-0.990
 Heck-0.968
Tokenh
Token ID71
Feature activation-1.56e+00

Pos logit contributions
ification+5.249
ified+5.139
icians+4.758
itect+4.744
edIn+4.734
Neg logit contributions
senal-16.804
HAEL-15.350
 unnecess-15.145
 Gamble-14.746
tails-14.453
Tokenring
Token ID1806
Feature activation-1.55e+00

Pos logit contributions
edIn+4.489
ification+4.398
ified+4.318
icians+4.233
ifiers+4.207
Neg logit contributions
senal-5.019
HAEL-4.524
 Gamble-4.513
berman-4.465
tti-4.418
Token 86
Token ID9849
Feature activation+7.10e-01

Pos logit contributions
edIn+5.386
ification+4.829
ified+4.821
icians+4.746
itect+4.737
Neg logit contributions
berman-4.113
HAEL-4.009
tti-3.895
tails-3.852
mma-3.723
Token).
Token ID737
Feature activation-8.54e-02

Pos logit contributions
berman+2.334
tti+2.273
HAEL+2.259
mma+2.220
tails+2.201
Neg logit contributions
edIn-2.125
icians-1.791
ification-1.759
itect-1.755
ified-1.739
Token B
Token ID347
Feature activation+1.23e-01

Pos logit contributions
edIn+0.316
icians+0.278
ification+0.278
itect+0.277
ified+0.276
Neg logit contributions
berman-0.221
tti-0.212
HAEL-0.212
tails-0.206
 Heck-0.202
Token.
Token ID13
Feature activation-1.40e-01

Pos logit contributions
edIn+7.955
ification+7.312
icians+7.302
ified+7.252
itect+7.155
Neg logit contributions
berman-5.493
HAEL-5.442
tti-5.250
senal-5.162
 Gamble-5.138
Token Rand
Token ID8790
Feature activation-1.34e+00

Pos logit contributions
edIn+0.536
icians+0.473
ification+0.471
itect+0.470
ified+0.469
Neg logit contributions
berman-0.347
tti-0.333
HAEL-0.332
tails-0.322
 Heck-0.318
Token Paul
Token ID3362
Feature activation-6.15e-01

Pos logit contributions
edIn+3.782
icians+3.374
ification+3.368
ified+3.364
itect+3.298
Neg logit contributions
berman-4.362
HAEL-4.269
tti-4.206
tails-4.201
mma-4.147
Token is
Token ID318
Feature activation-5.77e-01

Pos logit contributions
edIn+2.286
ification+2.022
icians+2.022
ified+2.012
itect+2.004
Neg logit contributions
berman-1.564
HAEL-1.501
tti-1.499
tails-1.454
 Heck-1.422
Token "
Token ID366
Feature activation+2.47e-01

Pos logit contributions
edIn+1.990
ification+1.757
icians+1.750
ified+1.745
itect+1.733
Neg logit contributions
berman-1.613
HAEL-1.558
tti-1.550
tails-1.514
 Heck-1.472
Tokenbas
Token ID12093
Feature activation-3.76e+00

Pos logit contributions
berman+0.646
tti+0.620
HAEL+0.612
tails+0.608
train+0.593
Neg logit contributions
edIn-0.906
icians-0.797
itect-0.790
ification-0.783
ified-0.778
Tokenically
Token ID1146
Feature activation-2.86e-01

Pos logit contributions
edIn+5.899
ified+5.323
icians+5.314
ification+5.308
itect+4.749
Neg logit contributions
tails-15.688
HAEL-15.611
tti-15.508
berman-15.482
senal-15.402
Token an
Token ID281
Feature activation-1.52e-01

Pos logit contributions
edIn+1.024
icians+0.892
itect+0.888
ification+0.885
ified+0.878
Neg logit contributions
berman-0.783
tti-0.749
HAEL-0.747
tails-0.731
 Heck-0.722
Token isolation
Token ID15133
Feature activation-5.08e-02

Pos logit contributions
edIn+0.590
ification+0.524
icians+0.523
ified+0.521
itect+0.521
Neg logit contributions
berman-0.367
HAEL-0.352
tti-0.351
tails-0.340
mma-0.332
Tokenist
Token ID396
Feature activation+1.17e-01

Pos logit contributions
edIn+0.160
icians+0.138
ification+0.137
itect+0.136
ified+0.136
Neg logit contributions
berman-0.160
HAEL-0.154
tti-0.154
tails-0.150
 Heck-0.148
Token,"
Token ID553
Feature activation-2.59e-01

Pos logit contributions
berman+0.295
tti+0.280
HAEL+0.279
tails+0.271
 Heck+0.270
Neg logit contributions
edIn-0.443
icians-0.390
ification-0.386
itect-0.386
ified-0.385
Token You
Token ID921
Feature activation-1.09e+00

Pos logit contributions
berman+0.005
tti+0.005
HAEL+0.005
tails+0.005
 Heck+0.005
Neg logit contributions
edIn-0.008
ification-0.007
icians-0.007
ified-0.007
itect-0.007
Token will
Token ID481
Feature activation-1.33e+00

Pos logit contributions
edIn+2.833
ification+2.494
ified+2.463
itect+2.429
icians+2.403
Neg logit contributions
berman-3.823
HAEL-3.761
tti-3.746
senal-3.654
tails-3.651
Token receive
Token ID3328
Feature activation-9.80e-01

Pos logit contributions
edIn+3.163
ification+2.840
ified+2.805
icians+2.698
itect+2.694
Neg logit contributions
berman-4.934
tti-4.852
HAEL-4.828
senal-4.739
tails-4.704
Token emails
Token ID7237
Feature activation-4.30e-01

Pos logit contributions
edIn+3.083
ification+2.792
ified+2.776
icians+2.769
ifiers+2.704
Neg logit contributions
berman-2.916
tti-2.845
HAEL-2.809
mma-2.704
tails-2.699
Token containing
Token ID7268
Feature activation-1.32e+00

Pos logit contributions
edIn+1.083
ification+0.943
ified+0.929
icians+0.922
itect+0.898
Neg logit contributions
berman-1.576
tti-1.544
HAEL-1.542
tails-1.505
mma-1.483
Token news
Token ID1705
Feature activation-3.75e+00

Pos logit contributions
edIn+3.824
ification+3.518
ified+3.489
icians+3.361
ifiers+3.292
Neg logit contributions
berman-4.078
HAEL-4.074
senal-3.997
tti-3.989
tails-3.881
Token content
Token ID2695
Feature activation-1.69e+00

Pos logit contributions
ification+6.569
ified+6.225
edIn+6.139
icians+5.739
ifiers+5.663
Neg logit contributions
senal-15.298
HAEL-13.598
berman-13.399
tti-13.388
mma-12.947
Token,
Token ID837
Feature activation-2.16e+00

Pos logit contributions
edIn+5.762
ification+5.356
ified+5.298
icians+5.288
itect+5.095
Neg logit contributions
berman-4.514
senal-4.336
HAEL-4.232
tti-4.204
tails-4.080
Token updates
Token ID5992
Feature activation-2.98e+00

Pos logit contributions
edIn+4.244
icians+3.746
ification+3.689
itect+3.498
ified+3.486
Neg logit contributions
berman-8.493
senal-8.479
HAEL-8.440
tti-8.227
tails-8.108
Token and
Token ID290
Feature activation-1.37e+00

Pos logit contributions
edIn+6.043
ification+6.024
ified+5.930
icians+5.706
itect+5.464
Neg logit contributions
senal-11.333
berman-10.599
HAEL-10.463
tti-10.222
tails-10.144
Token promotions
Token ID20699
Feature activation-1.24e+00

Pos logit contributions
edIn+4.050
ification+3.579
ified+3.565
icians+3.467
itect+3.377
Neg logit contributions
berman-4.399
HAEL-4.382
tti-4.338
senal-4.247
mma-4.247
Token,
Token ID11
Feature activation+2.36e-01

Pos logit contributions
berman+2.870
tti+2.787
HAEL+2.718
 Heck+2.635
 Gamble+2.623
Neg logit contributions
edIn-5.705
icians-4.974
itect-4.971
ification-4.921
ified-4.901
Token it
Token ID340
Feature activation+1.69e+00

Pos logit contributions
berman+0.636
tti+0.613
HAEL+0.609
tails+0.591
 Heck+0.586
Neg logit contributions
edIn-0.851
icians-0.742
itect-0.738
ification-0.737
ified-0.734
Token
Token ID447
Feature activation+1.02e+00

Pos logit contributions
tti+4.554
berman+4.543
HAEL+4.358
tails+4.288
train+4.229
Neg logit contributions
edIn-5.934
itect-4.914
icians-4.914
ification-4.868
ifiers-4.866
Token
Token ID247
Feature activation+7.31e-01

Pos logit contributions
berman+3.004
tti+2.917
HAEL+2.902
tails+2.822
 Heck+2.803
Neg logit contributions
edIn-3.413
icians-2.973
ification-2.963
itect-2.936
ified-2.926
Tokens
Token ID82
Feature activation+1.17e+00

Pos logit contributions
berman+1.842
tti+1.830
tails+1.766
HAEL+1.765
mma+1.717
Neg logit contributions
edIn-2.740
itect-2.358
icians-2.358
ification-2.354
ified-2.342
Token always
Token ID1464
Feature activation+2.37e+00

Pos logit contributions
berman+2.951
tti+2.878
HAEL+2.829
 Gamble+2.754
 Heck+2.746
Neg logit contributions
edIn-4.402
itect-3.793
icians-3.774
ification-3.747
ified-3.719
Token men
Token ID1450
Feature activation+6.51e-01

Pos logit contributions
tti+5.625
berman+5.601
 Gamble+5.475
HAEL+5.425
 Heck+5.361
Neg logit contributions
edIn-8.795
icter-7.342
itect-7.342
icians-7.313
ification-7.238
Token.
Token ID13
Feature activation+6.27e-01

Pos logit contributions
berman+1.428
tti+1.372
HAEL+1.336
tails+1.285
 Heck+1.276
Neg logit contributions
edIn-2.699
icians-2.340
itect-2.336
ification-2.317
ified-2.307
Token Then
Token ID3244
Feature activation+1.07e+00

Pos logit contributions
berman+1.538
tti+1.498
HAEL+1.483
 Heck+1.457
tails+1.435
Neg logit contributions
edIn-2.402
icians-2.111
ification-2.082
itect-2.080
ified-2.075
Token I
Token ID314
Feature activation+6.43e-01

Pos logit contributions
berman+2.649
tti+2.549
HAEL+2.507
tails+2.434
 Heck+2.415
Neg logit contributions
edIn-4.104
icians-3.531
itect-3.524
ification-3.499
ified-3.495
Token
Token ID447
Feature activation+1.00e+00

Pos logit contributions
berman+1.833
tti+1.798
HAEL+1.748
tails+1.700
 Heck+1.687
Neg logit contributions
edIn-2.258
icians-1.896
itect-1.892
ification-1.881
ified-1.872
TokenAbout
Token ID8585
Feature activation+1.10e-01

Pos logit contributions
edIn+0.725
icians+0.640
ification+0.639
itect+0.636
ified+0.635
Neg logit contributions
berman-0.489
tti-0.469
HAEL-0.469
tails-0.455
 Heck-0.446
Token that
Token ID326
Feature activation+8.32e-03

Pos logit contributions
berman+0.287
tti+0.276
HAEL+0.275
tails+0.267
 Heck+0.263
Neg logit contributions
edIn-0.404
icians-0.355
ification-0.354
itect-0.353
ified-0.352
Token time
Token ID640
Feature activation+3.14e-01

Pos logit contributions
berman+0.020
tti+0.020
HAEL+0.020
tails+0.019
 Heck+0.019
Neg logit contributions
edIn-0.032
icians-0.028
ification-0.028
itect-0.028
ified-0.028
Token,
Token ID11
Feature activation-2.11e-02

Pos logit contributions
berman+0.732
tti+0.701
HAEL+0.698
tails+0.674
 Heck+0.664
Neg logit contributions
edIn-1.245
icians-1.105
ification-1.101
itect-1.099
ified-1.095
Token the
Token ID262
Feature activation-2.32e-01

Pos logit contributions
edIn+0.080
icians+0.071
ification+0.071
itect+0.070
ified+0.070
Neg logit contributions
berman-0.053
HAEL-0.050
tti-0.050
tails-0.049
 Heck-0.048
Token L
Token ID406
Feature activation+2.54e+00

Pos logit contributions
edIn+0.877
icians+0.776
ification+0.776
ified+0.771
itect+0.771
Neg logit contributions
berman-0.583
HAEL-0.558
tti-0.556
tails-0.540
 Heck-0.528
TokenSO
Token ID15821
Feature activation+6.11e-01

Pos logit contributions
berman+6.262
HAEL+6.109
tti+6.066
HO+6.014
DI+5.876
Neg logit contributions
edIn-9.086
itect-7.803
ification-7.679
icians-7.593
ifiers-7.571
Token came
Token ID1625
Feature activation+8.74e-01

Pos logit contributions
berman+1.613
tti+1.567
HAEL+1.561
tails+1.508
 Heck+1.489
Neg logit contributions
edIn-2.223
icians-1.937
ification-1.924
itect-1.921
ified-1.911
Token up
Token ID510
Feature activation-1.56e-01

Pos logit contributions
berman+1.925
tti+1.844
HAEL+1.784
tails+1.768
 Heck+1.748
Neg logit contributions
edIn-3.582
itect-3.154
icians-3.151
ification-3.074
ified-3.066
Token on
Token ID319
Feature activation+6.19e-01

Pos logit contributions
edIn+0.626
icians+0.557
ification+0.556
itect+0.553
ified+0.553
Neg logit contributions
berman-0.356
tti-0.340
HAEL-0.339
tails-0.328
 Heck-0.321
Token tower
Token ID10580
Feature activation-7.49e-01

Pos logit contributions
berman+1.568
tti+1.522
HAEL+1.498
tails+1.458
 Heck+1.446
Neg logit contributions
edIn-2.313
icians-2.031
itect-2.028
ification-2.019
ified-2.007
Token as
Token ID355
Feature activation-2.98e-01

Pos logit contributions
berman+0.297
tti+0.282
HAEL+0.281
tails+0.273
 Heck+0.267
Neg logit contributions
edIn-0.558
icians-0.496
itect-0.494
ification-0.494
ified-0.491
Token much
Token ID881
Feature activation+1.59e+00

Pos logit contributions
edIn+0.824
icians+0.692
ification+0.689
itect+0.686
ified+0.684
Neg logit contributions
berman-1.051
tti-1.019
HAEL-1.018
tails-0.997
 Heck-0.984
Token as
Token ID355
Feature activation+8.40e-02

Pos logit contributions
berman+3.329
tti+3.160
 Heck+3.070
HAEL+3.054
 Gamble+3.026
Neg logit contributions
edIn-6.524
icians-5.820
itect-5.784
ification-5.696
ified-5.635
Token the
Token ID262
Feature activation+2.96e-02

Pos logit contributions
berman+0.222
tti+0.213
HAEL+0.213
tails+0.207
 Heck+0.205
Neg logit contributions
edIn-0.305
icians-0.268
ification-0.267
itect-0.267
ified-0.266
Token U
Token ID471
Feature activation+1.31e+00

Pos logit contributions
berman+0.074
tti+0.071
HAEL+0.070
tails+0.068
 Heck+0.067
Neg logit contributions
edIn-0.112
icians-0.099
ification-0.099
itect-0.099
ified-0.098
Token.
Token ID13
Feature activation+2.16e+00

Pos logit contributions
berman+2.512
tti+2.395
HAEL+2.348
tails+2.267
mma+2.232
Neg logit contributions
edIn-5.751
icians-5.113
itect-5.082
ification-5.047
icter-5.043
TokenS
Token ID50
Feature activation+6.62e-01

Pos logit contributions
berman+3.212
tti+3.023
HAEL+2.958
HO+2.937
 Heck+2.824
Neg logit contributions
edIn-10.103
icter-9.232
itect-9.054
icians-8.996
icipated-8.906
Token.
Token ID13
Feature activation+1.45e+00

Pos logit contributions
berman+1.310
tti+1.228
HAEL+1.226
tails+1.173
 Heck+1.158
Neg logit contributions
edIn-2.855
icians-2.541
ification-2.535
itect-2.530
ified-2.514
Token did
Token ID750
Feature activation+9.11e-01

Pos logit contributions
berman+3.301
tti+3.107
 Heck+3.075
HAEL+3.047
 Gamble+3.012
Neg logit contributions
edIn-5.671
icians-5.057
ification-5.030
itect-5.010
ifiers-4.979
Token on
Token ID319
Feature activation+6.38e-01

Pos logit contributions
berman+1.877
tti+1.787
HAEL+1.746
 Heck+1.703
tails+1.689
Neg logit contributions
edIn-3.838
icians-3.410
itect-3.391
ification-3.356
ified-3.336
Token passenger
Token ID11849
Feature activation-6.70e-01

Pos logit contributions
berman+1.591
tti+1.511
HAEL+1.497
 Heck+1.477
tails+1.477
Neg logit contributions
edIn-2.394
icians-2.120
itect-2.119
ification-2.095
ified-2.079
Token.
Token ID13
Feature activation-1.48e-01

Pos logit contributions
edIn+3.298
ification+2.958
ified+2.938
itect+2.936
icians+2.930
Neg logit contributions
berman-1.991
HAEL-1.909
tti-1.882
tails-1.853
mma-1.799
Token Because
Token ID4362
Feature activation+5.87e-02

Pos logit contributions
edIn+0.551
icians+0.486
ification+0.484
itect+0.482
ified+0.481
Neg logit contributions
berman-0.378
tti-0.363
HAEL-0.363
tails-0.352
 Heck-0.347
Token despite
Token ID3805
Feature activation-1.46e+00

Pos logit contributions
berman+0.147
tti+0.141
HAEL+0.141
tails+0.136
 Heck+0.134
Neg logit contributions
edIn-0.222
icians-0.196
ification-0.195
itect-0.195
ified-0.194
Token his
Token ID465
Feature activation-2.85e-01

Pos logit contributions
edIn+4.928
ification+4.350
ified+4.312
icians+4.287
itect+4.277
Neg logit contributions
berman-4.093
HAEL-3.945
tti-3.925
tails-3.848
mma-3.791
Token best
Token ID1266
Feature activation-1.50e-01

Pos logit contributions
edIn+1.052
icians+0.926
ification+0.924
itect+0.919
ified+0.918
Neg logit contributions
berman-0.743
tti-0.713
HAEL-0.713
tails-0.692
 Heck-0.679
Token efforts
Token ID4040
Feature activation+1.95e+00

Pos logit contributions
edIn+0.689
icians+0.622
ification+0.621
itect+0.619
ified+0.618
Neg logit contributions
berman-0.254
tti-0.238
HAEL-0.237
tails-0.227
 Heck-0.220
Token,
Token ID11
Feature activation+1.83e-01

Pos logit contributions
berman+3.672
tti+3.578
HAEL+3.480
 Heck+3.405
HO+3.349
Neg logit contributions
edIn-8.284
icians-7.317
itect-7.278
ified-7.171
ifiers-7.168
Token the
Token ID262
Feature activation+1.99e-01

Pos logit contributions
berman+0.480
HAEL+0.463
tti+0.463
 Heck+0.446
tails+0.446
Neg logit contributions
edIn-0.670
icians-0.587
itect-0.582
ification-0.580
ified-0.579
Token life
Token ID1204
Feature activation+4.66e-02

Pos logit contributions
berman+0.519
tti+0.499
HAEL+0.496
tails+0.485
 Heck+0.481
Neg logit contributions
edIn-0.731
icians-0.640
ification-0.635
itect-0.634
ified-0.631
Token could
Token ID714
Feature activation+3.24e-01

Pos logit contributions
berman+0.110
tti+0.106
HAEL+0.105
tails+0.102
 Heck+0.101
Neg logit contributions
edIn-0.183
icians-0.161
itect-0.161
ification-0.160
ified-0.160
Token never
Token ID1239
Feature activation+3.78e-01

Pos logit contributions
berman+0.918
tti+0.888
HAEL+0.880
tails+0.861
 Heck+0.846
Neg logit contributions
edIn-1.129
icians-0.966
ification-0.964
itect-0.964
ified-0.959
Token medical
Token ID3315
Feature activation-5.53e-02

Pos logit contributions
edIn+0.950
icians+0.835
ification+0.833
itect+0.830
ified+0.829
Neg logit contributions
berman-0.684
tti-0.656
HAEL-0.656
tails-0.637
 Heck-0.625
Token school
Token ID1524
Feature activation-9.83e-01

Pos logit contributions
edIn+0.219
icians+0.193
itect+0.193
ification+0.192
ified+0.191
Neg logit contributions
berman-0.129
tti-0.123
HAEL-0.123
tails-0.120
 Heck-0.118
Token.
Token ID13
Feature activation-2.17e-01

Pos logit contributions
edIn+3.886
ification+3.517
icians+3.488
ified+3.482
itect+3.472
Neg logit contributions
berman-2.264
HAEL-2.150
tti-2.146
tails-2.053
mma-2.024
Token Harvard
Token ID11131
Feature activation-3.36e-01

Pos logit contributions
edIn+0.781
icians+0.685
ification+0.684
itect+0.681
ified+0.680
Neg logit contributions
berman-0.583
HAEL-0.559
tti-0.559
tails-0.543
 Heck-0.532
Token professor
Token ID6240
Feature activation-7.32e-01

Pos logit contributions
edIn+1.245
icians+1.095
ification+1.092
itect+1.087
ified+1.085
Neg logit contributions
berman-0.871
tti-0.836
HAEL-0.835
tails-0.811
 Heck-0.797
Token E
Token ID412
Feature activation+2.51e+00

Pos logit contributions
edIn+2.766
icians+2.473
ification+2.472
ified+2.458
itect+2.443
Neg logit contributions
berman-1.803
tti-1.729
HAEL-1.721
tails-1.677
mma-1.637
Token.
Token ID13
Feature activation+2.46e+00

Pos logit contributions
tti+8.731
berman+8.694
tails+8.317
HAEL+8.314
 Gamble+8.195
Neg logit contributions
edIn-6.413
itect-5.261
ification-5.138
ifiers-5.134
icians-5.081
Token H
Token ID367
Feature activation+1.47e+00

Pos logit contributions
HAEL+4.727
berman+4.700
 Heck+4.615
 Gamble+4.560
tti+4.502
Neg logit contributions
edIn-10.176
icter-8.914
itect-8.847
ifiers-8.802
icians-8.762
Token.
Token ID13
Feature activation+2.42e+00

Pos logit contributions
berman+2.949
tti+2.790
 Gamble+2.707
HAEL+2.670
 Heck+2.654
Neg logit contributions
edIn-6.215
itect-5.445
icians-5.430
ification-5.426
ified-5.383
Token Clarke
Token ID19635
Feature activation-1.14e+00

Pos logit contributions
 Heck+5.418
 Gamble+5.411
berman+5.183
HAEL+4.959
tti+4.892
Neg logit contributions
edIn-9.348
icter-8.101
icians-8.093
itect-7.963
ification-7.950
Token used
Token ID973
Feature activation+1.41e+00

Pos logit contributions
edIn+4.058
ification+3.623
ified+3.600
icians+3.574
itect+3.565
Neg logit contributions
berman-2.988
HAEL-2.903
tti-2.832
tails-2.807
mma-2.750
Token with
Token ID351
Feature activation+4.35e-01

Pos logit contributions
edIn+3.119
ification+2.797
icians+2.785
ified+2.784
itect+2.764
Neg logit contributions
berman-1.826
HAEL-1.748
tti-1.735
tails-1.704
 Heck-1.646
Token the
Token ID262
Feature activation-1.01e-01

Pos logit contributions
berman+1.109
tti+1.069
HAEL+1.054
tails+1.033
 Heck+1.028
Neg logit contributions
edIn-1.620
icians-1.427
itect-1.418
ification-1.410
ified-1.402
Token glacier
Token ID44539
Feature activation-3.96e-01

Pos logit contributions
edIn+0.369
icians+0.325
ification+0.324
itect+0.322
ified+0.322
Neg logit contributions
berman-0.268
tti-0.257
HAEL-0.257
tails-0.249
 Heck-0.245
Token,
Token ID11
Feature activation-2.35e-01

Pos logit contributions
edIn+1.419
icians+1.245
ification+1.243
itect+1.236
ified+1.235
Neg logit contributions
berman-1.071
HAEL-1.029
tti-1.029
tails-0.999
 Heck-0.982
Token anyway
Token ID6949
Feature activation-3.75e-02

Pos logit contributions
edIn+0.678
icians+0.574
ification+0.571
itect+0.568
ified+0.566
Neg logit contributions
berman-0.800
tti-0.776
HAEL-0.774
tails-0.758
 Heck-0.748
Token)
Token ID8
Feature activation+7.50e-01

Pos logit contributions
edIn+0.115
icians+0.098
ification+0.097
itect+0.097
ified+0.096
Neg logit contributions
berman-0.121
tti-0.118
HAEL-0.117
tails-0.115
 Heck-0.113
Token and
Token ID290
Feature activation-1.64e-01

Pos logit contributions
berman+1.896
tti+1.855
HAEL+1.809
tails+1.775
 Heck+1.772
Neg logit contributions
edIn-2.821
icians-2.455
itect-2.398
ification-2.384
ified-2.381
Token in
Token ID287
Feature activation+4.89e-02

Pos logit contributions
edIn+0.590
icians+0.518
ification+0.517
itect+0.514
ified+0.514
Neg logit contributions
berman-0.442
HAEL-0.425
tti-0.424
tails-0.412
 Heck-0.405
Token effect
Token ID1245
Feature activation+1.35e+00

Pos logit contributions
berman+0.135
tti+0.130
HAEL+0.128
tails+0.127
 Heck+0.125
Neg logit contributions
edIn-0.173
icians-0.151
itect-0.149
ification-0.149
ified-0.148
Token
Token ID564
Feature activation-1.07e-01

Pos logit contributions
berman+3.261
tti+3.195
tails+3.135
HAEL+3.054
 Heck+3.029
Neg logit contributions
edIn-5.104
itect-4.449
icians-4.441
ification-4.372
icipated-4.359
Token
Token ID250
Feature activation-7.12e-02

Pos logit contributions
edIn+0.377
icians+0.330
ification+0.330
itect+0.328
ified+0.327
Neg logit contributions
berman-0.297
tti-0.286
HAEL-0.285
tails-0.278
 Heck-0.274
Token
Token ID247
Feature activation+1.72e-01

Pos logit contributions
edIn+0.221
icians+0.189
ification+0.188
ified+0.188
itect+0.188
Neg logit contributions
berman-0.241
HAEL-0.233
tti-0.233
tails-0.229
 Heck-0.224
Tokens
Token ID82
Feature activation+1.51e-01

Pos logit contributions
berman+0.446
tti+0.432
HAEL+0.422
tails+0.419
mma+0.410
Neg logit contributions
edIn-0.638
ification-0.554
icians-0.552
itect-0.552
ified-0.551
Token legal
Token ID2742
Feature activation+1.06e+00

Pos logit contributions
berman+0.439
tti+0.422
HAEL+0.417
tails+0.411
 Heck+0.408
Neg logit contributions
edIn-0.511
itect-0.445
icians-0.441
ification-0.441
ified-0.438
Token cases
Token ID2663
Feature activation-7.16e-01

Pos logit contributions
berman+2.619
tti+2.519
tails+2.449
 Heck+2.442
train+2.433
Neg logit contributions
edIn-3.939
itect-3.496
ification-3.406
icians-3.383
ified-3.362
Token are
Token ID389
Feature activation+1.03e-03

Pos logit contributions
edIn+2.561
icians+2.247
ification+2.241
itect+2.230
ified+2.227
Neg logit contributions
berman-1.938
HAEL-1.863
tti-1.863
tails-1.810
 Heck-1.778
Token filed
Token ID5717
Feature activation+6.80e-01

Pos logit contributions
berman+0.003
tti+0.003
HAEL+0.003
tails+0.003
 Heck+0.003
Neg logit contributions
edIn-0.003
itect-0.003
icians-0.003
ification-0.003
ified-0.003
Token.
Token ID13
Feature activation+9.35e-02

Pos logit contributions
berman+1.407
tti+1.326
HAEL+1.303
tails+1.265
 Heck+1.250
Neg logit contributions
edIn-2.865
icians-2.560
itect-2.553
ification-2.535
ified-2.517
Token Whatever
Token ID15935
Feature activation+4.95e-01

Pos logit contributions
berman+0.248
tti+0.240
HAEL+0.239
 Heck+0.233
tails+0.232
Neg logit contributions
edIn-0.340
icians-0.298
ification-0.296
itect-0.295
ified-0.294
Token recon
Token ID8195
Feature activation-1.56e+00

Pos logit contributions
berman+1.284
tti+1.242
HAEL+1.216
tails+1.212
 Heck+1.195
Neg logit contributions
edIn-1.809
itect-1.606
icians-1.584
ification-1.580
ified-1.573
Tokenfigured
Token ID46296
Feature activation-8.41e-01

Pos logit contributions
edIn+5.451
ification+4.927
ified+4.872
itect+4.864
icians+4.847
Neg logit contributions
berman-4.182
HAEL-4.029
tti-3.902
mma-3.821
tails-3.779
Token Supreme
Token ID5617
Feature activation-9.50e-01

Pos logit contributions
edIn+3.031
ification+2.688
icians+2.681
ified+2.670
itect+2.641
Neg logit contributions
berman-2.217
HAEL-2.159
tti-2.132
tails-2.080
mma-2.030
Token song
Token ID3496
Feature activation-1.32e+00

Pos logit contributions
edIn+1.390
icians+1.209
ification+1.206
itect+1.202
ified+1.198
Neg logit contributions
berman-1.138
tti-1.095
HAEL-1.094
tails-1.067
 Heck-1.052
Token]
Token ID60
Feature activation+6.98e-01

Pos logit contributions
edIn+4.428
ification+4.019
ified+3.990
icians+3.979
itect+3.917
Neg logit contributions
berman-3.682
HAEL-3.545
tti-3.531
tails-3.428
 Heck-3.361
Token One
Token ID1881
Feature activation+5.89e-01

Pos logit contributions
berman+1.665
tti+1.603
HAEL+1.595
 Heck+1.551
tails+1.538
Neg logit contributions
edIn-2.718
icians-2.400
itect-2.394
ification-2.385
ified-2.374
Token,
Token ID11
Feature activation+1.10e+00

Pos logit contributions
berman+1.330
tti+1.283
HAEL+1.261
tails+1.222
 Heck+1.217
Neg logit contributions
edIn-2.365
icians-2.097
itect-2.091
ification-2.073
ified-2.067
Token two
Token ID734
Feature activation+1.15e+00

Pos logit contributions
berman+2.811
tti+2.700
HAEL+2.669
 Heck+2.610
tails+2.570
Neg logit contributions
edIn-4.132
itect-3.610
icians-3.574
ification-3.538
ified-3.526
Token,
Token ID11
Feature activation+1.07e+00

Pos logit contributions
berman+2.145
tti+2.051
HAEL+1.992
tails+1.973
 Heck+1.943
Neg logit contributions
edIn-5.092
itect-4.534
icians-4.472
ification-4.444
ified-4.417
Token three
Token ID1115
Feature activation+1.07e+00

Pos logit contributions
berman+2.193
tti+2.089
HAEL+2.049
 Heck+2.016
tails+1.969
Neg logit contributions
edIn-4.514
itect-4.024
icians-3.975
ified-3.946
ification-3.939
Token,
Token ID11
Feature activation+5.80e-01

Pos logit contributions
berman+2.146
tti+2.073
HAEL+2.011
tails+1.983
 Heck+1.966
Neg logit contributions
edIn-4.553
itect-4.052
icians-4.007
ification-3.987
ified-3.964
Token four
Token ID1440
Feature activation+6.44e-01

Pos logit contributions
berman+1.329
tti+1.274
HAEL+1.270
tails+1.224
 Heck+1.214
Neg logit contributions
edIn-2.318
icians-2.040
itect-2.033
ification-2.029
ified-2.018
Token.
Token ID13
Feature activation+6.56e-01

Pos logit contributions
berman+1.364
tti+1.307
HAEL+1.287
tails+1.255
 Heck+1.235
Neg logit contributions
edIn-2.688
itect-2.386
icians-2.379
ification-2.372
ified-2.358
Token
Token ID198
Feature activation+2.02e-01

Pos logit contributions
berman+1.599
tti+1.547
HAEL+1.542
 Heck+1.517
tails+1.491
Neg logit contributions
edIn-2.514
icians-2.211
itect-2.198
ification-2.196
ified-2.185
Token it
Token ID340
Feature activation+3.08e-01

Pos logit contributions
edIn+1.335
ification+1.176
icians+1.176
ified+1.169
itect+1.166
Neg logit contributions
berman-0.961
HAEL-0.922
tti-0.920
tails-0.895
 Heck-0.875
Token will
Token ID481
Feature activation+4.50e-01

Pos logit contributions
berman+0.878
tti+0.854
HAEL+0.834
tails+0.828
 Heck+0.811
Neg logit contributions
edIn-1.070
icians-0.915
itect-0.907
ification-0.903
ified-0.900
Token consider
Token ID2074
Feature activation+8.03e-02

Pos logit contributions
berman+1.286
tti+1.237
HAEL+1.216
tails+1.198
 Heck+1.183
Neg logit contributions
edIn-1.563
icians-1.345
ification-1.332
itect-1.330
ified-1.323
Token the
Token ID262
Feature activation+2.53e-01

Pos logit contributions
berman+0.205
tti+0.197
HAEL+0.197
tails+0.191
 Heck+0.189
Neg logit contributions
edIn-0.299
icians-0.264
ification-0.263
itect-0.262
ified-0.261
Token role
Token ID2597
Feature activation+1.07e+00

Pos logit contributions
berman+0.667
tti+0.642
HAEL+0.636
tails+0.622
 Heck+0.621
Neg logit contributions
edIn-0.922
icians-0.807
itect-0.805
ification-0.797
ified-0.794
Token of
Token ID286
Feature activation+6.19e-01

Pos logit contributions
berman+2.031
tti+1.910
HAEL+1.892
 Heck+1.837
 Gamble+1.825
Neg logit contributions
edIn-4.625
itect-4.124
icians-4.101
ification-4.056
ified-4.046
Token ment
Token ID6229
Feature activation+1.33e+00

Pos logit contributions
berman+1.428
tti+1.367
HAEL+1.349
 Heck+1.322
tails+1.316
Neg logit contributions
edIn-2.437
itect-2.161
icians-2.152
ification-2.135
ified-2.122
Tokenhol
Token ID3937
Feature activation+6.99e-01

Pos logit contributions
berman+1.916
tails+1.811
tti+1.810
HAEL+1.753
mma+1.680
Neg logit contributions
edIn-6.414
icians-5.564
acters-5.506
icter-5.495
itect-5.494
Token and
Token ID290
Feature activation+1.14e+00

Pos logit contributions
berman+1.483
tti+1.429
HAEL+1.394
tails+1.369
 Heck+1.342
Neg logit contributions
edIn-2.909
icians-2.572
itect-2.568
ification-2.530
ified-2.525
Token other
Token ID584
Feature activation+1.57e+00

Pos logit contributions
berman+2.432
tti+2.327
HAEL+2.277
 Heck+2.249
 Gamble+2.248
Neg logit contributions
edIn-4.688
itect-4.172
icians-4.165
ification-4.097
ified-4.077
Token flavors
Token ID17361
Feature activation+9.54e-02

Pos logit contributions
berman+3.179
tti+3.125
 Gamble+3.078
 Heck+3.042
HAEL+3.039
Neg logit contributions
edIn-6.388
itect-5.748
icians-5.645
icter-5.525
ification-5.506
Token is
Token ID318
Feature activation-5.06e-02

Pos logit contributions
edIn+3.853
ification+3.438
icians+3.423
ified+3.408
itect+3.385
Neg logit contributions
berman-2.961
HAEL-2.870
tti-2.802
tails-2.731
mma-2.698
Token on
Token ID319
Feature activation-5.74e-01

Pos logit contributions
edIn+0.182
icians+0.160
ification+0.159
itect+0.158
ified+0.158
Neg logit contributions
berman-0.136
tti-0.131
HAEL-0.131
tails-0.127
 Heck-0.126
Token the
Token ID262
Feature activation-7.21e-01

Pos logit contributions
edIn+2.050
ification+1.797
icians+1.797
ified+1.785
itect+1.784
Neg logit contributions
berman-1.552
HAEL-1.492
tti-1.489
tails-1.448
 Heck-1.418
Token way
Token ID835
Feature activation+2.94e-01

Pos logit contributions
edIn+2.645
ification+2.347
ified+2.337
icians+2.327
itect+2.321
Neg logit contributions
berman-1.851
HAEL-1.792
tti-1.768
tails-1.712
mma-1.690
Token to
Token ID284
Feature activation-5.93e-01

Pos logit contributions
berman+0.677
tti+0.647
HAEL+0.643
tails+0.624
 Heck+0.612
Neg logit contributions
edIn-1.177
icians-1.042
itect-1.036
ification-1.034
ified-1.029
Token failing
Token ID9894
Feature activation+9.71e-01

Pos logit contributions
edIn+2.101
ification+1.851
icians+1.847
ified+1.835
itect+1.832
Neg logit contributions
berman-1.615
HAEL-1.559
tti-1.557
tails-1.507
mma-1.478
Token.
Token ID13
Feature activation+5.94e-02

Pos logit contributions
berman+2.308
tti+2.209
HAEL+2.186
tails+2.172
 Heck+2.145
Neg logit contributions
edIn-3.736
icians-3.323
ification-3.279
itect-3.272
ified-3.264
Token If
Token ID1002
Feature activation+6.58e-01

Pos logit contributions
berman+0.155
tti+0.149
HAEL+0.149
tails+0.144
 Heck+0.143
Neg logit contributions
edIn-0.219
icians-0.192
ification-0.191
itect-0.191
ified-0.190
Token you
Token ID345
Feature activation+9.56e-01

Pos logit contributions
berman+1.675
tti+1.611
HAEL+1.595
 Heck+1.565
tails+1.552
Neg logit contributions
edIn-2.454
icians-2.145
itect-2.136
ification-2.116
ified-2.105
Token want
Token ID765
Feature activation+1.69e+00

Pos logit contributions
berman+2.723
tti+2.634
HAEL+2.564
 Heck+2.543
 Gamble+2.525
Neg logit contributions
edIn-3.313
icians-2.819
itect-2.807
ification-2.783
ified-2.770
Token to
Token ID284
Feature activation+9.62e-01

Pos logit contributions
berman+3.580
tti+3.536
HAEL+3.394
 Heck+3.357
tails+3.343
Neg logit contributions
edIn-6.786
itect-5.968
icians-5.953
ified-5.850
ification-5.841
Token the
Token ID262
Feature activation-7.58e-01

Pos logit contributions
edIn+0.627
icians+0.552
ification+0.550
itect+0.548
ified+0.547
Neg logit contributions
berman-0.439
tti-0.421
HAEL-0.421
tails-0.409
 Heck-0.402
Token party
Token ID2151
Feature activation-8.98e-01

Pos logit contributions
edIn+2.684
ification+2.373
icians+2.368
ified+2.355
itect+2.346
Neg logit contributions
berman-2.052
HAEL-1.984
tti-1.969
tails-1.904
mma-1.882
Token explores
Token ID25409
Feature activation-8.07e-01

Pos logit contributions
edIn+3.106
ification+2.772
icians+2.755
ified+2.751
itect+2.726
Neg logit contributions
berman-2.463
HAEL-2.398
tti-2.372
tails-2.291
mma-2.256
Token and
Token ID290
Feature activation-2.56e-01

Pos logit contributions
edIn+2.857
ification+2.517
ified+2.501
icians+2.493
itect+2.490
Neg logit contributions
berman-2.201
HAEL-2.110
tti-2.093
tails-2.029
mma-1.999
Token discovers
Token ID27472
Feature activation-8.23e-01

Pos logit contributions
edIn+0.918
icians+0.806
ification+0.805
itect+0.800
ified+0.800
Neg logit contributions
berman-0.689
HAEL-0.663
tti-0.662
tails-0.642
 Heck-0.631
Token the
Token ID262
Feature activation-7.48e-01

Pos logit contributions
edIn+2.919
ification+2.580
ified+2.561
icians+2.553
itect+2.544
Neg logit contributions
berman-2.238
HAEL-2.152
tti-2.121
tails-2.062
mma-2.027
Token discrepancy
Token ID34466
Feature activation-5.31e-01

Pos logit contributions
edIn+2.722
ification+2.406
icians+2.396
ified+2.392
itect+2.379
Neg logit contributions
berman-1.968
HAEL-1.888
tti-1.874
tails-1.817
mma-1.790
Token.
Token ID13
Feature activation+2.45e-01

Pos logit contributions
edIn+2.099
ification+1.882
icians+1.876
ified+1.869
itect+1.863
Neg logit contributions
berman-1.228
HAEL-1.172
tti-1.167
tails-1.130
 Heck-1.098
Token
Token ID198
Feature activation-4.21e-03

Pos logit contributions
berman+0.645
tti+0.626
HAEL+0.623
 Heck+0.607
tails+0.606
Neg logit contributions
edIn-0.892
icians-0.783
ification-0.776
itect-0.773
ified-0.772
Token
Token ID198
Feature activation-7.91e-02

Pos logit contributions
edIn+0.014
ification+0.012
ified+0.012
icians+0.012
itect+0.012
Neg logit contributions
berman-0.012
HAEL-0.012
tti-0.012
tails-0.012
 Heck-0.011
TokenHow
Token ID2437
Feature activation-1.30e+00

Pos logit contributions
edIn+0.284
icians+0.249
ification+0.248
itect+0.247
ified+0.247
Neg logit contributions
berman-0.213
tti-0.205
HAEL-0.205
tails-0.199
 Heck-0.196
Token takes
Token ID2753
Feature activation-9.80e-01

Pos logit contributions
edIn+0.453
ification+0.401
icians+0.401
ified+0.398
itect+0.397
Neg logit contributions
berman-0.321
tti-0.308
HAEL-0.306
tails-0.297
 Heck-0.292
Token steps
Token ID4831
Feature activation-6.65e-01

Pos logit contributions
edIn+2.824
ification+2.441
ified+2.431
ifiers+2.348
icians+2.344
Neg logit contributions
tti-3.277
HAEL-3.238
berman-3.210
tails-3.100
mma-3.098
Token to
Token ID284
Feature activation-1.32e+00

Pos logit contributions
edIn+2.270
ification+2.157
ified+2.129
itect+2.093
icians+2.063
Neg logit contributions
HAEL-1.705
tails-1.697
berman-1.688
tti-1.653
senal-1.637
Token open
Token ID1280
Feature activation-1.79e-01

Pos logit contributions
edIn+3.634
ified+3.609
ification+3.591
itect+3.486
icians+3.476
Neg logit contributions
tti-4.024
HAEL-3.933
berman-3.820
 Klux-3.792
mma-3.772
Token flights
Token ID13956
Feature activation+2.11e-01

Pos logit contributions
edIn+0.664
ification+0.591
ified+0.590
icians+0.587
itect+0.579
Neg logit contributions
berman-0.461
HAEL-0.446
tti-0.441
tails-0.431
 Heck-0.417
Token to
Token ID284
Feature activation-8.46e-01

Pos logit contributions
berman+0.500
HAEL+0.484
tti+0.481
tails+0.467
 Heck+0.452
Neg logit contributions
edIn-0.824
ification-0.734
ified-0.731
icians-0.731
itect-0.720
Token US
Token ID1294
Feature activation-2.60e-01

Pos logit contributions
edIn+2.603
ification+2.388
ified+2.383
icians+2.339
itect+2.290
Neg logit contributions
berman-2.560
HAEL-2.540
tti-2.533
tails-2.473
mma-2.412
Token on
Token ID319
Feature activation-4.02e-01

Pos logit contributions
edIn+0.986
ification+0.924
ified+0.924
ifiers+0.911
icians+0.890
Neg logit contributions
berman-0.628
tti-0.608
HAEL-0.603
mma-0.584
tails-0.580
Token sidelines
Token ID29394
Feature activation-1.42e+00

Pos logit contributions
edIn+1.559
ification+1.391
ified+1.382
icians+1.377
ifiers+1.355
Neg logit contributions
berman-0.945
HAEL-0.937
tti-0.912
tails-0.896
mma-0.854
Token of
Token ID286
Feature activation-5.81e-01

Pos logit contributions
edIn+5.055
ification+4.725
ified+4.641
itect+4.570
icians+4.546
Neg logit contributions
senal-3.510
berman-3.478
tti-3.358
tails-3.340
HAEL-3.279
Token Trump
Token ID1301
Feature activation-8.30e-01

Pos logit contributions
edIn+2.108
icians+1.925
ification+1.909
ified+1.902
itect+1.865
Neg logit contributions
berman-1.483
tti-1.447
HAEL-1.442
tails-1.396
train-1.360
Token
Token ID251
Feature activation-4.03e-01

Pos logit contributions
berman+0.573
HAEL+0.553
tti+0.553
tails+0.538
 Heck+0.532
Neg logit contributions
edIn-0.607
icians-0.527
ification-0.524
itect-0.522
ified-0.520
Token Zone
Token ID13035
Feature activation+5.17e-01

Pos logit contributions
edIn+1.499
icians+1.321
ification+1.319
itect+1.312
ified+1.311
Neg logit contributions
berman-1.036
HAEL-0.993
tti-0.993
tails-0.963
 Heck-0.945
Token Threat
Token ID25238
Feature activation+2.78e-01

Pos logit contributions
berman+1.535
tti+1.492
HAEL+1.458
tails+1.436
 Heck+1.433
Neg logit contributions
edIn-1.699
icians-1.479
itect-1.451
ified-1.451
ification-1.450
Token
Token ID198
Feature activation+5.53e-01

Pos logit contributions
berman+0.762
tti+0.735
HAEL+0.727
tails+0.711
 Heck+0.705
Neg logit contributions
edIn-0.984
icians-0.867
itect-0.852
ified-0.850
ification-0.850
Token
Token ID198
Feature activation+6.04e-02

Pos logit contributions
berman+1.520
tti+1.470
HAEL+1.460
tails+1.426
 Heck+1.406
Neg logit contributions
edIn-1.962
icians-1.709
itect-1.690
ification-1.690
ified-1.680
TokenSur
Token ID14214
Feature activation-1.03e+00

Pos logit contributions
berman+0.153
HAEL+0.147
tti+0.147
tails+0.142
 Heck+0.139
Neg logit contributions
edIn-0.226
icians-0.201
ification-0.199
itect-0.199
ified-0.198
Tokenprisingly
Token ID20859
Feature activation-4.60e-01

Pos logit contributions
edIn+3.543
ification+3.102
icians+3.087
ified+3.084
itect+3.068
Neg logit contributions
berman-2.913
HAEL-2.834
tti-2.816
tails-2.716
mma-2.696
Token,
Token ID11
Feature activation-2.86e-01

Pos logit contributions
edIn+1.898
icians+1.707
ification+1.707
ified+1.701
itect+1.695
Neg logit contributions
berman-0.969
HAEL-0.938
tti-0.917
tails-0.896
mma-0.863
Token Wallace
Token ID17161
Feature activation-2.00e-01

Pos logit contributions
edIn+1.081
ification+0.954
icians+0.953
ified+0.949
itect+0.948
Neg logit contributions
berman-0.713
HAEL-0.686
tti-0.684
tails-0.664
mma-0.649
Token caught
Token ID4978
Feature activation+5.29e-01

Pos logit contributions
edIn+0.710
icians+0.622
ification+0.618
itect+0.616
ified+0.615
Neg logit contributions
berman-0.547
tti-0.528
HAEL-0.524
tails-0.511
 Heck-0.504
Token nine
Token ID5193
Feature activation+5.19e-01

Pos logit contributions
berman+1.450
tti+1.396
HAEL+1.384
tails+1.370
 Heck+1.360
Neg logit contributions
edIn-1.871
icians-1.632
itect-1.620
ification-1.615
ified-1.604
Token he
Token ID339
Feature activation-1.68e-01

Pos logit contributions
berman+0.336
tti+0.324
HAEL+0.322
tails+0.314
 Heck+0.312
Neg logit contributions
edIn-0.400
icians-0.347
itect-0.345
ification-0.344
ified-0.343
Token will
Token ID481
Feature activation+3.13e-01

Pos logit contributions
edIn+0.589
icians+0.510
ification+0.506
itect+0.506
ified+0.504
Neg logit contributions
berman-0.473
tti-0.457
HAEL-0.453
tails-0.442
 Heck-0.435
Token be
Token ID307
Feature activation+6.20e-01

Pos logit contributions
berman+0.856
tti+0.827
HAEL+0.810
tails+0.795
 Heck+0.795
Neg logit contributions
edIn-1.122
icians-0.966
itect-0.955
ification-0.954
ified-0.951
Token impe
Token ID18516
Feature activation-1.16e-01

Pos logit contributions
berman+1.612
tti+1.550
HAEL+1.522
 Heck+1.510
tails+1.502
Neg logit contributions
edIn-2.290
itect-1.989
icians-1.977
ification-1.955
ified-1.939
Tokenached
Token ID2317
Feature activation-2.14e-01

Pos logit contributions
edIn+0.317
icians+0.265
ification+0.265
itect+0.263
ified+0.263
Neg logit contributions
berman-0.410
HAEL-0.398
tti-0.398
tails-0.390
 Heck-0.385
Token,
Token ID11
Feature activation-5.39e-01

Pos logit contributions
edIn+0.818
icians+0.725
ification+0.725
itect+0.721
ified+0.720
Neg logit contributions
berman-0.526
HAEL-0.504
tti-0.503
tails-0.488
 Heck-0.478
Token
Token ID447
Feature activation-4.99e-01

Pos logit contributions
edIn+1.618
icians+1.383
ification+1.383
itect+1.372
ified+1.371
Neg logit contributions
berman-1.763
HAEL-1.707
tti-1.706
tails-1.668
 Heck-1.641
Token
Token ID251
Feature activation-1.59e+00

Pos logit contributions
edIn+1.180
ification+0.955
icians+0.951
itect+0.946
ified+0.945
Neg logit contributions
berman-1.950
HAEL-1.901
tti-1.898
tails-1.864
 Heck-1.834
Token she
Token ID673
Feature activation-8.93e-01

Pos logit contributions
edIn+5.545
ification+4.951
ified+4.931
icians+4.857
itect+4.835
Neg logit contributions
berman-4.216
HAEL-4.038
tti-4.005
tails-3.948
 Heck-3.781
Token said
Token ID531
Feature activation+3.94e-01

Pos logit contributions
edIn+2.844
ification+2.484
ified+2.468
icians+2.465
itect+2.452
Neg logit contributions
berman-2.717
HAEL-2.631
tti-2.613
tails-2.570
 Heck-2.510
Token.
Token ID13
Feature activation-9.08e-02

Pos logit contributions
berman+0.819
tti+0.780
HAEL+0.778
tails+0.743
 Heck+0.740
Neg logit contributions
edIn-1.654
icians-1.481
itect-1.472
ification-1.469
ified-1.461
Token I
Token ID314
Feature activation-1.99e-01

Pos logit contributions
berman+0.862
tti+0.834
HAEL+0.824
 Heck+0.818
tails+0.805
Neg logit contributions
edIn-1.305
icians-1.149
ification-1.139
itect-1.133
ified-1.131
Token know
Token ID760
Feature activation-1.81e-01

Pos logit contributions
edIn+0.663
icians+0.574
ification+0.572
itect+0.570
ified+0.568
Neg logit contributions
berman-0.589
tti-0.568
HAEL-0.566
tails-0.552
 Heck-0.544
Token I
Token ID314
Feature activation-8.01e-01

Pos logit contributions
edIn+0.668
ification+0.595
icians+0.594
ified+0.591
itect+0.589
Neg logit contributions
berman-0.466
HAEL-0.450
tti-0.445
tails-0.436
mma-0.421
Token
Token ID447
Feature activation+9.00e-01

Pos logit contributions
edIn+2.591
ification+2.271
icians+2.263
ified+2.247
itect+2.241
Neg logit contributions
berman-2.398
HAEL-2.327
tti-2.304
tails-2.269
 Heck-2.222
Token
Token ID247
Feature activation+3.76e-01

Pos logit contributions
berman+2.613
tti+2.541
HAEL+2.525
tails+2.442
 Heck+2.436
Neg logit contributions
edIn-2.999
icians-2.636
ification-2.614
itect-2.601
ified-2.573
Tokenm
Token ID76
Feature activation-4.72e-01

Pos logit contributions
berman+0.951
tti+0.921
HAEL+0.903
tails+0.882
mma+0.878
Neg logit contributions
edIn-1.420
icians-1.252
ification-1.244
itect-1.237
ified-1.236
Token not
Token ID407
Feature activation-1.02e+00

Pos logit contributions
edIn+1.664
ification+1.472
icians+1.468
ified+1.461
itect+1.456
Neg logit contributions
berman-1.290
HAEL-1.242
tti-1.240
tails-1.209
 Heck-1.178
Token the
Token ID262
Feature activation-1.34e+00

Pos logit contributions
edIn+4.032
ification+3.678
ified+3.637
icians+3.631
itect+3.604
Neg logit contributions
berman-2.289
HAEL-2.226
tti-2.186
tails-2.133
mma-2.037
Token only
Token ID691
Feature activation-2.88e-01

Pos logit contributions
edIn+3.890
ification+3.365
ified+3.347
itect+3.334
icians+3.289
Neg logit contributions
berman-4.413
HAEL-4.315
tti-4.236
tails-4.156
mma-4.089
Token one
Token ID530
Feature activation+5.07e-01

Pos logit contributions
edIn+0.966
ification+0.838
icians+0.838
ified+0.834
itect+0.833
Neg logit contributions
berman-0.847
HAEL-0.818
tti-0.815
tails-0.797
 Heck-0.780
Token.
Token ID13
Feature activation+5.80e-01

Pos logit contributions
berman+1.365
tti+1.316
HAEL+1.301
tails+1.274
 Heck+1.266
Neg logit contributions
edIn-1.828
icians-1.592
itect-1.583
ification-1.565
ified-1.558
Token that
Token ID326
Feature activation-1.36e+00

Pos logit contributions
berman+2.220
tti+2.142
HAEL+2.058
 Heck+2.029
tails+2.021
Neg logit contributions
edIn-4.610
icians-4.017
itect-3.988
ification-3.950
ified-3.946
Token will
Token ID481
Feature activation-1.13e+00

Pos logit contributions
edIn+4.493
icians+3.957
ification+3.946
itect+3.908
ified+3.898
Neg logit contributions
berman-3.956
HAEL-3.833
tti-3.744
tails-3.693
mma-3.638
Token be
Token ID307
Feature activation-6.44e-01

Pos logit contributions
edIn+3.602
ification+3.204
icians+3.190
ified+3.177
itect+3.162
Neg logit contributions
berman-3.358
HAEL-3.288
tti-3.203
tails-3.146
mma-3.105
Token
Token ID198
Feature activation+1.58e-01

Pos logit contributions
edIn+2.185
ification+1.941
ified+1.930
icians+1.924
itect+1.915
Neg logit contributions
berman-1.835
HAEL-1.769
tti-1.747
tails-1.706
mma-1.670
Token
Token ID198
Feature activation+4.01e-01

Pos logit contributions
berman+0.458
HAEL+0.441
tti+0.440
tails+0.428
 Heck+0.421
Neg logit contributions
edIn-0.535
ification-0.468
icians-0.467
ified-0.465
itect-0.464
Tokenapp
Token ID1324
Feature activation-2.90e+00

Pos logit contributions
berman+1.139
tti+1.097
HAEL+1.081
tails+1.078
train+1.049
Neg logit contributions
edIn-1.386
icians-1.201
itect-1.190
ification-1.187
ified-1.173
Tokenreci
Token ID29102
Feature activation-1.35e+00

Pos logit contributions
edIn+7.550
itect+6.607
ified+6.431
icians+6.367
ification+6.349
Neg logit contributions
berman-9.786
HAEL-9.431
tti-9.374
 Gamble-9.102
mma-9.094
Tokenated
Token ID515
Feature activation-2.52e-01

Pos logit contributions
edIn+4.981
ified+4.537
itect+4.423
ification+4.416
icians+4.333
Neg logit contributions
berman-3.446
HAEL-3.327
tti-3.228
 Heck-3.181
 Gamble-3.175
Token by
Token ID416
Feature activation-4.09e-01

Pos logit contributions
edIn+0.990
ification+0.886
icians+0.886
ified+0.882
itect+0.880
Neg logit contributions
berman-0.585
HAEL-0.559
tti-0.558
tails-0.540
mma-0.525
Token all
Token ID477
Feature activation+9.18e-01

Pos logit contributions
edIn+1.500
icians+1.328
ification+1.322
itect+1.317
ified+1.313
Neg logit contributions
berman-1.065
HAEL-1.027
tti-1.022
tails-0.988
mma-0.969
Token lovers
Token ID20175
Feature activation+5.57e-01

Pos logit contributions
berman+2.168
tti+2.105
HAEL+2.034
 Heck+2.029
tails+2.020
Neg logit contributions
edIn-3.540
ification-3.102
ified-3.091
icians-3.091
itect-3.079
Token dinosaurs
Token ID27199
Feature activation-1.56e+00

Pos logit contributions
berman+3.517
tti+3.453
HAEL+3.353
tails+3.318
 Heck+3.316
Neg logit contributions
edIn-4.601
icians-3.960
itect-3.930
ification-3.847
icter-3.810
Token do
Token ID466
Feature activation+1.72e+00

Pos logit contributions
edIn+4.593
ification+4.229
ified+4.207
icians+4.123
itect+4.085
Neg logit contributions
berman-4.813
HAEL-4.775
tti-4.673
tails-4.601
mma-4.511
Token while
Token ID981
Feature activation-7.25e-02

Pos logit contributions
berman+3.507
tti+3.286
HAEL+3.244
 Heck+3.134
tails+3.126
Neg logit contributions
edIn-7.295
icians-6.410
itect-6.327
ification-6.240
icter-6.239
Token nesting
Token ID46282
Feature activation+4.49e-01

Pos logit contributions
edIn+0.255
icians+0.223
ification+0.221
itect+0.221
ified+0.220
Neg logit contributions
berman-0.201
tti-0.193
HAEL-0.192
tails-0.189
 Heck-0.186
Token (
Token ID357
Feature activation-2.48e-02

Pos logit contributions
berman+0.932
tti+0.884
HAEL+0.875
tails+0.857
 Heck+0.837
Neg logit contributions
edIn-1.889
icians-1.700
ification-1.684
itect-1.680
ified-1.670
Tokenscient
Token ID25346
Feature activation-3.92e+00

Pos logit contributions
edIn+0.087
icians+0.076
ification+0.075
itect+0.075
ified+0.075
Neg logit contributions
berman-0.070
tti-0.067
HAEL-0.067
tails-0.065
 Heck-0.064
Tokenists
Token ID1023
Feature activation-1.72e+00

Pos logit contributions
edIn+8.319
icians+7.973
ified+7.836
ification+7.812
ifiers+7.342
Neg logit contributions
HAEL-13.794
mma-13.760
berman-13.716
tti-13.592
 Heck-13.209
Token think
Token ID892
Feature activation-7.94e-01

Pos logit contributions
edIn+5.363
ification+4.900
ified+4.886
icians+4.834
itect+4.751
Neg logit contributions
berman-4.909
HAEL-4.849
tti-4.765
tails-4.707
mma-4.607
Token some
Token ID617
Feature activation+1.06e-01

Pos logit contributions
edIn+2.732
ification+2.415
icians+2.400
ified+2.395
itect+2.371
Neg logit contributions
berman-2.206
HAEL-2.146
tti-2.110
tails-2.057
mma-2.006
Token species
Token ID4693
Feature activation-9.00e-01

Pos logit contributions
berman+0.263
tti+0.253
HAEL+0.251
tails+0.245
 Heck+0.240
Neg logit contributions
edIn-0.401
icians-0.354
ification-0.352
itect-0.352
ified-0.350
Token sat
Token ID3332
Feature activation-9.28e-01

Pos logit contributions
edIn+3.060
ification+2.711
icians+2.697
ified+2.692
itect+2.684
Neg logit contributions
berman-2.537
HAEL-2.463
tti-2.443
tails-2.387
 Heck-2.338
Token-
Token ID12
Feature activation-8.20e-01

Pos logit contributions
edIn+3.245
ification+2.889
ified+2.874
icians+2.869
itect+2.831
Neg logit contributions
berman-3.059
HAEL-2.896
tti-2.883
 Heck-2.766
tails-2.755
Tokenf
Token ID69
Feature activation-1.15e+00

Pos logit contributions
edIn+2.862
ification+2.647
icians+2.623
ified+2.618
itect+2.572
Neg logit contributions
berman-2.184
HAEL-2.119
tti-2.065
 Heck-2.004
 Gamble-1.963
Tokeninance
Token ID14149
Feature activation-6.00e-02

Pos logit contributions
edIn+4.102
icians+3.924
ification+3.895
ified+3.828
itect+3.806
Neg logit contributions
HAEL-2.964
berman-2.892
senal-2.780
 Heck-2.741
tti-2.730
Token,
Token ID11
Feature activation-7.81e-01

Pos logit contributions
edIn+0.260
icians+0.234
ification+0.234
itect+0.233
ified+0.233
Neg logit contributions
berman-0.117
HAEL-0.110
tti-0.110
tails-0.106
 Heck-0.103
Token wh
Token ID348
Feature activation-2.85e+00

Pos logit contributions
edIn+2.913
ification+2.607
icians+2.602
ified+2.591
itect+2.587
Neg logit contributions
berman-1.953
HAEL-1.873
tti-1.851
tails-1.826
 Heck-1.762
Tokenitt
Token ID715
Feature activation-3.21e+00

Pos logit contributions
edIn+8.208
icians+7.941
ification+7.887
ified+7.823
itect+7.746
Neg logit contributions
HAEL-8.611
senal-8.223
berman-8.154
HO-7.861
 Gamble-7.822
Tokenles
Token ID829
Feature activation-1.90e+00

Pos logit contributions
icians+9.211
ification+9.010
edIn+8.937
ified+8.932
itect+8.586
Neg logit contributions
senal-10.594
HAEL-9.118
 Gamble-8.797
 Heck-8.547
berman-8.534
Tokenea
Token ID18213
Feature activation-2.12e+00

Pos logit contributions
edIn+5.725
ification+5.304
ified+5.281
itect+5.126
icians+5.121
Neg logit contributions
senal-5.652
HAEL-5.589
berman-5.508
 Heck-5.447
tti-5.442
Token-
Token ID12
Feature activation-1.21e+00

Pos logit contributions
edIn+6.107
itect+5.417
ification+5.397
icians+5.385
ified+5.376
Neg logit contributions
berman-6.740
HAEL-6.546
tails-6.522
tti-6.473
 Gamble-6.257
Token375
Token ID22318
Feature activation-5.22e-01

Pos logit contributions
edIn+4.972
ification+4.506
ified+4.487
icians+4.486
itect+4.476
Neg logit contributions
berman-2.470
HAEL-2.448
tti-2.339
tails-2.309
 Heck-2.296
Token7
Token ID22
Feature activation-1.04e+00

Pos logit contributions
edIn+2.099
ification+1.891
itect+1.884
icians+1.880
ified+1.880
Neg logit contributions
berman-1.159
HAEL-1.100
tti-1.087
tails-1.063
 Gamble-1.036
Token mentioned
Token ID4750
Feature activation-7.40e-01

Pos logit contributions
berman+1.581
tti+1.518
HAEL+1.505
tails+1.460
 Heck+1.458
Neg logit contributions
edIn-2.199
icians-1.914
itect-1.914
ification-1.890
ified-1.884
Token in
Token ID287
Feature activation-6.25e-01

Pos logit contributions
edIn+2.814
ification+2.513
ified+2.499
icians+2.498
itect+2.477
Neg logit contributions
berman-1.808
HAEL-1.733
tti-1.727
tails-1.684
mma-1.629
Token at
Token ID379
Feature activation+2.49e-01

Pos logit contributions
edIn+2.255
icians+1.982
ification+1.980
itect+1.969
ified+1.968
Neg logit contributions
berman-1.668
HAEL-1.603
tti-1.601
tails-1.556
 Heck-1.523
Token least
Token ID1551
Feature activation-1.88e-01

Pos logit contributions
berman+0.672
tti+0.651
HAEL+0.645
tails+0.633
 Heck+0.628
Neg logit contributions
edIn-0.900
icians-0.777
itect-0.770
ification-0.769
ified-0.766
Token one
Token ID530
Feature activation+6.78e-01

Pos logit contributions
edIn+0.690
icians+0.607
ification+0.605
itect+0.603
ified+0.601
Neg logit contributions
berman-0.491
tti-0.472
HAEL-0.471
tails-0.457
 Heck-0.450
Token declass
Token ID42794
Feature activation-3.98e+00

Pos logit contributions
berman+1.742
tti+1.683
HAEL+1.651
 Heck+1.640
tails+1.616
Neg logit contributions
edIn-2.512
icians-2.207
itect-2.181
ification-2.165
ified-2.155
Tokenified
Token ID1431
Feature activation-1.29e+00

Pos logit contributions
ified+5.520
ification+5.341
edIn+4.604
ifying+3.921
ifiers+3.871
Neg logit contributions
berman-18.268
HAEL-17.857
tails-17.692
senal-17.676
tti-17.674
Token document
Token ID3188
Feature activation-4.63e-01

Pos logit contributions
edIn+4.355
ification+3.940
ified+3.916
icians+3.838
itect+3.833
Neg logit contributions
berman-3.584
HAEL-3.479
tti-3.443
tails-3.381
mma-3.267
Token dating
Token ID10691
Feature activation-1.40e+00

Pos logit contributions
edIn+1.817
icians+1.616
ification+1.615
ified+1.605
itect+1.605
Neg logit contributions
berman-1.091
HAEL-1.043
tti-1.041
tails-1.008
 Heck-0.985
Token from
Token ID422
Feature activation-7.13e-01

Pos logit contributions
edIn+5.101
ification+4.651
ified+4.599
icians+4.587
ifiers+4.487
Neg logit contributions
berman-3.455
HAEL-3.355
tti-3.284
tails-3.245
mma-3.147
Token late
Token ID2739
Feature activation+1.02e+00

Pos logit contributions
edIn+2.266
ification+1.977
icians+1.963
ified+1.957
itect+1.942
Neg logit contributions
berman-2.187
HAEL-2.123
tti-2.107
tails-2.073
mma-2.027
Token all
Token ID477
Feature activation+1.65e+00

Pos logit contributions
berman+1.159
tti+1.114
HAEL+1.083
 Heck+1.074
tails+1.071
Neg logit contributions
edIn-1.455
icians-1.261
itect-1.258
ification-1.245
ified-1.234
Token non
Token ID1729
Feature activation+6.98e-01

Pos logit contributions
berman+3.148
tti+3.033
 Heck+2.838
HAEL+2.832
train+2.815
Neg logit contributions
edIn-6.937
itect-6.169
icians-6.158
osate-6.131
ification-6.113
Tokenfarm
Token ID43323
Feature activation-6.33e-03

Pos logit contributions
berman+1.814
tti+1.765
HAEL+1.703
tails+1.698
train+1.693
Neg logit contributions
edIn-2.574
icians-2.213
ification-2.208
itect-2.198
ified-2.174
Token sectors
Token ID16020
Feature activation+1.02e+00

Pos logit contributions
edIn+0.024
icians+0.021
ification+0.021
itect+0.021
ified+0.021
Neg logit contributions
berman-0.015
tti-0.015
HAEL-0.015
tails-0.014
 Heck-0.014
Token (
Token ID357
Feature activation-5.17e-01

Pos logit contributions
berman+2.061
tti+1.996
HAEL+1.943
 Heck+1.870
tails+1.866
Neg logit contributions
edIn-4.290
icians-3.813
itect-3.783
ification-3.762
ified-3.733
Tokenauthor
Token ID9800
Feature activation-3.50e+00

Pos logit contributions
edIn+1.982
ification+1.755
icians+1.754
ified+1.748
itect+1.745
Neg logit contributions
berman-1.260
HAEL-1.209
tti-1.205
tails-1.168
 Heck-1.145
Token
Token ID447
Feature activation-1.02e+00

Pos logit contributions
edIn+11.660
ification+11.085
ified+11.010
icians+10.615
itect+10.427
Neg logit contributions
berman-8.570
HAEL-8.157
tti-7.946
tails-7.926
 Klux-7.718
Token
Token ID247
Feature activation-3.43e-01

Pos logit contributions
edIn+3.504
icians+3.013
itect+3.009
ification+2.995
ified+2.976
Neg logit contributions
berman-2.898
tti-2.771
HAEL-2.769
tails-2.705
mma-2.647
Tokens
Token ID82
Feature activation-1.11e+00

Pos logit contributions
edIn+1.351
icians+1.200
ification+1.198
itect+1.192
ified+1.192
Neg logit contributions
berman-0.804
HAEL-0.767
tti-0.767
tails-0.743
 Heck-0.725
Token analysis
Token ID3781
Feature activation-3.75e-02

Pos logit contributions
edIn+3.774
ification+3.336
icians+3.322
ified+3.316
itect+3.283
Neg logit contributions
berman-3.103
HAEL-3.003
tti-2.971
tails-2.923
 Heck-2.819
Token of
Token ID286
Feature activation-5.77e-01

Pos logit contributions
edIn+0.132
icians+0.115
ification+0.115
itect+0.115
ified+0.114
Neg logit contributions
berman-0.104
tti-0.101
HAEL-0.100
tails-0.097
 Heck-0.096