TOP ACTIVATIONS
MAX = 7.707

ment ? And what better way to get people to pay
<|endoftext|> What better way to raise awareness of an
with two openings on the defensive line , hopes are high
. On the left : Bo Scar b rough
irrational , shall seem rational enough . [ 20
and Cody Mand ell , center , were also try out
R eds kins defensive players take a water break
long as outlets on the left and in the center let
or the day after G ant Heart . He was visiting
: it 's just a rumor . But given the growing
rather that they were stupid enough to expect a piece from
have been better under new defensive coordinator Dennis Allen the past
for References : <|endoftext|> It took until Sunday morning for a
…. " Ah ." " Ste lla
energy goals . <|endoftext|> Media playback is unsupported on your device
iquette and Manual of Polit eness , 18 76 .
. Part 6 [ edit ] It
que , excellent on the left , helped create the second
not going to cave just c uz he sends me a
winner of the UFC 216 interim title showdown between Tony Ferguson

MIN ACTIVATIONS
MIN = -7.903

? ( Think of The Simpsons and the mon or ail
Magic iterations of My Little Pony . It gave me an
f 4 b be 66 IEEE 802 . 11 b gn
year both The Terminator and Transformers debut . W
Has bro , Barbie , Lego , Toys R Us ,
. Though shows like Or phan Black and The Vampire Di
As far as I can tell , there are three big
prev _ state : Option < Arc < Board >> ,
" -- images ", required = True , help =" path
bind directive : < body ng - controller ="
Angular tutorial : < body ng - controller ="
episode was a little TO O simple [ laughs ].
pub struct Own ed < T > { ... }
I am against the First Amendment . My tweets reflected my
: Own ed < T > , akin to
Property ' H KC U :\ Control Panel \ Desktop '
relay network protocol or I BL T ) and move virtually
set dir = c \ :\ tmp : */ This sets
top toy brands include Has bro , Barbie , Lego ,
voters , according to Real Clear Politics , said a

INTERVAL 3.804 - 7.707
CONTAINS 0.483%

Conclusion This post only repeats some basic information about
this page and make fun of and mock Child Mol estation
. And there were many others . Yet being
re ment , les Cors aires l oy aux rest ants
, when I want to feel it . And I think

INTERVAL -0.098 - 3.804
CONTAINS 52.810%

is in many cases a balancing act . Do you hire
One is its op r p ressive spect re , p
ickson will return to full training this week after an abdominal
10 years with the Harper Conservatives . There were high hopes
It will reduce the problem of student debt , which

INTERVAL -4.001 - -0.098
CONTAINS 46.273%

4 - 1 - 2 to more of a 4 -
really likely that Amazon is going to go all 1984 on
was a result of that overwhelming stress . Being on the
nn - drops - re za - as lan - after
5 )) sq K ernel = c v 2 . get

INTERVAL -7.903 - -4.001
CONTAINS 0.433%

. Los Angeles , CA : Western Psychological Services .
, your body goes into what is known as the post
Current Population Survey data ( IP U MS - C PS
and upsetting places . Ne onom icon , for example ,
pub struct Shared < ' a , T :
Tokenment
Token ID434
Feature activation+7.26e-01

Pos logit contributions
ahime+0.065
usterity+0.065
 Berks+0.058
groupon+0.056
Origin+0.055
Neg logit contributions
 Deb-0.089
ourke-0.088
 Vand-0.086
$$-0.085
 「-0.085
Token?
Token ID30
Feature activation-3.59e-02

Pos logit contributions
 Deb+0.421
ourke+0.410
 Vand+0.400
$$+0.396
 「+0.395
Neg logit contributions
ahime-0.543
usterity-0.538
 Berks-0.498
groupon-0.486
Origin-0.476
Token And
Token ID843
Feature activation+9.52e-02

Pos logit contributions
ahime+0.027
usterity+0.027
 Berks+0.025
groupon+0.024
Origin+0.024
Neg logit contributions
 Deb-0.020
ourke-0.020
 Vand-0.019
$$-0.019
 「-0.019
Token what
Token ID644
Feature activation+1.02e+00

Pos logit contributions
 Deb+0.059
ourke+0.057
 Vand+0.056
$$+0.056
 「+0.055
Neg logit contributions
ahime-0.067
usterity-0.067
 Berks-0.062
groupon-0.060
adobe-0.059
Token better
Token ID1365
Feature activation+1.54e+00

Pos logit contributions
 Deb+0.662
ourke+0.643
 Vand+0.630
$$+0.624
 「+0.622
Neg logit contributions
ahime-0.698
usterity-0.694
 Berks-0.634
groupon-0.617
Origin-0.604
Token way
Token ID835
Feature activation+7.71e+00

Pos logit contributions
 Deb+0.336
ourke+0.309
 Vand+0.287
$$+0.281
 「+0.276
Neg logit contributions
ahime-1.720
usterity-1.713
 Berks-1.621
groupon-1.598
Origin-1.578
Token to
Token ID284
Feature activation+3.19e+00

Pos logit contributions
 Deb+3.709
ourke+3.450
 Vand+3.431
 「+3.381
$$+3.337
Neg logit contributions
ahime-6.486
usterity-6.441
 Berks-5.976
adobe-5.768
Origin-5.687
Token get
Token ID651
Feature activation+4.20e-02

Pos logit contributions
 Deb+2.198
ourke+2.099
 Vand+2.088
 「+2.071
$$+2.067
Neg logit contributions
ahime-2.084
usterity-2.053
 Berks-1.861
groupon-1.803
adobe-1.774
Token people
Token ID661
Feature activation-3.43e-01

Pos logit contributions
 Deb+0.027
ourke+0.027
 Vand+0.026
$$+0.026
 「+0.026
Neg logit contributions
ahime-0.028
usterity-0.028
 Berks-0.026
groupon-0.025
Origin-0.025
Token to
Token ID284
Feature activation+3.82e-01

Pos logit contributions
ahime+0.233
usterity+0.232
 Berks+0.214
groupon+0.208
Origin+0.203
Neg logit contributions
 Deb-0.219
ourke-0.216
 Vand-0.209
$$-0.208
 「-0.208
Token pay
Token ID1414
Feature activation+4.00e+00

Pos logit contributions
 Deb+0.244
ourke+0.239
 Vand+0.232
$$+0.230
 「+0.229
Neg logit contributions
ahime-0.261
usterity-0.261
 Berks-0.240
groupon-0.233
adobe-0.227
Token
Token ID447
Feature activation+1.65e-01

Pos logit contributions
 Deb+0.156
ourke+0.151
 Vand+0.148
$$+0.146
 「+0.146
Neg logit contributions
ahime-0.190
usterity-0.189
 Berks-0.174
groupon-0.169
Origin-0.166
Token
Token ID251
Feature activation-7.61e-01

Pos logit contributions
 Deb+0.089
ourke+0.086
 Vand+0.084
 「+0.083
$$+0.083
Neg logit contributions
ahime-0.130
usterity-0.130
 Berks-0.120
groupon-0.118
Origin-0.115
Token<|endoftext|>
Token ID50256
Feature activation-9.24e-01

Pos logit contributions
ahime+0.562
usterity+0.560
 Berks+0.518
groupon+0.507
Origin+0.496
Neg logit contributions
 Deb-0.444
ourke-0.434
 Vand-0.421
$$-0.416
 「-0.415
TokenWhat
Token ID2061
Feature activation-5.23e-01

Pos logit contributions
usterity+0.633
ahime+0.632
 Berks+0.575
groupon+0.570
Origin+0.563
Neg logit contributions
 Deb-0.597
ourke-0.575
 Vand-0.568
 「-0.559
$$-0.550
Token better
Token ID1365
Feature activation+1.15e+00

Pos logit contributions
usterity+0.359
ahime+0.358
 Berks+0.328
groupon+0.320
Origin+0.315
Neg logit contributions
 Deb-0.331
ourke-0.324
 Vand-0.316
$$-0.315
 「-0.313
Token way
Token ID835
Feature activation+7.63e+00

Pos logit contributions
 Deb+0.335
ourke+0.314
 Vand+0.298
$$+0.293
 「+0.290
Neg logit contributions
ahime-1.198
usterity-1.193
 Berks-1.125
groupon-1.106
Origin-1.092
Token to
Token ID284
Feature activation+3.29e+00

Pos logit contributions
 Deb+3.525
 Vand+3.300
ourke+3.259
$$+3.229
 「+3.219
Neg logit contributions
usterity-6.502
ahime-6.501
 Berks-6.045
adobe-5.837
Origin-5.773
Token raise
Token ID5298
Feature activation+1.50e+00

Pos logit contributions
 Deb+2.196
ourke+2.085
 Vand+2.085
 「+2.068
$$+2.065
Neg logit contributions
ahime-2.216
usterity-2.180
 Berks-1.990
groupon-1.930
adobe-1.898
Token awareness
Token ID9359
Feature activation+8.01e-01

Pos logit contributions
 Deb+0.910
ourke+0.880
 Vand+0.862
$$+0.854
 「+0.851
Neg logit contributions
ahime-1.092
usterity-1.085
 Berks-0.996
groupon-0.972
Origin-0.952
Token of
Token ID286
Feature activation+4.29e-01

Pos logit contributions
 Deb+0.514
ourke+0.496
 Vand+0.488
$$+0.484
 「+0.481
Neg logit contributions
ahime-0.556
usterity-0.552
 Berks-0.505
groupon-0.490
adobe-0.482
Token an
Token ID281
Feature activation+1.24e-01

Pos logit contributions
 Deb+0.272
ourke+0.265
 Vand+0.259
$$+0.257
 「+0.256
Neg logit contributions
ahime-0.298
usterity-0.297
 Berks-0.272
groupon-0.265
Origin-0.259
Token with
Token ID351
Feature activation-3.48e-02

Pos logit contributions
ahime+0.369
usterity+0.367
 Berks+0.337
groupon+0.327
Origin+0.319
Neg logit contributions
 Deb-0.371
ourke-0.364
 Vand-0.354
$$-0.352
 「-0.349
Token two
Token ID734
Feature activation-8.92e-01

Pos logit contributions
ahime+0.024
usterity+0.024
 Berks+0.022
groupon+0.022
Origin+0.021
Neg logit contributions
 Deb-0.022
ourke-0.021
 Vand-0.020
 「-0.020
$$-0.020
Token openings
Token ID28431
Feature activation+7.77e-01

Pos logit contributions
usterity+0.655
ahime+0.643
 Berks+0.610
groupon+0.582
Origin+0.576
Neg logit contributions
ourke-0.522
 Deb-0.520
$$-0.494
 Vand-0.489
 「-0.483
Token on
Token ID319
Feature activation+2.48e-01

Pos logit contributions
 Deb+0.510
ourke+0.494
 Vand+0.485
$$+0.481
 「+0.480
Neg logit contributions
ahime-0.526
usterity-0.522
 Berks-0.476
groupon-0.463
Origin-0.453
Token the
Token ID262
Feature activation+1.15e+00

Pos logit contributions
 Deb+0.153
ourke+0.150
 Vand+0.145
$$+0.144
 「+0.143
Neg logit contributions
usterity-0.176
ahime-0.176
 Berks-0.162
groupon-0.157
adobe-0.154
Token defensive
Token ID6110
Feature activation+7.31e+00

Pos logit contributions
 Deb+0.631
ourke+0.615
 Vand+0.590
$$+0.588
 「+0.586
Neg logit contributions
usterity-0.887
ahime-0.887
 Berks-0.827
groupon-0.802
adobe-0.785
Token line
Token ID1627
Feature activation+2.91e-01

Pos logit contributions
 Deb+3.697
 Vand+3.543
ourke+3.471
 「+3.458
$$+3.452
Neg logit contributions
ahime-6.041
usterity-5.878
Origin-5.353
adobe-5.332
 Berks-5.321
Token,
Token ID11
Feature activation+3.54e-01

Pos logit contributions
 Deb+0.193
ourke+0.187
 Vand+0.183
$$+0.182
 「+0.181
Neg logit contributions
ahime-0.195
usterity-0.193
 Berks-0.176
groupon-0.172
adobe-0.168
Token hopes
Token ID7176
Feature activation+2.55e-01

Pos logit contributions
 Deb+0.224
ourke+0.219
 Vand+0.213
$$+0.211
 「+0.211
Neg logit contributions
ahime-0.246
usterity-0.244
 Berks-0.225
groupon-0.219
Origin-0.214
Token are
Token ID389
Feature activation-1.78e+00

Pos logit contributions
 Deb+0.154
ourke+0.150
 Vand+0.146
$$+0.146
 「+0.145
Neg logit contributions
ahime-0.184
usterity-0.182
 Berks-0.169
groupon-0.164
Origin-0.161
Token high
Token ID1029
Feature activation-8.59e-01

Pos logit contributions
ahime+1.330
usterity+1.315
 Berks+1.231
groupon+1.202
Origin+1.170
Neg logit contributions
 Deb-1.023
ourke-0.998
 Vand-0.958
 「-0.958
$$-0.957
Token.
Token ID13
Feature activation-2.66e-01

Pos logit contributions
 Deb+0.242
ourke+0.235
 Vand+0.230
$$+0.228
 「+0.228
Neg logit contributions
ahime-0.238
usterity-0.237
 Berks-0.215
groupon-0.210
Origin-0.205
Token
Token ID198
Feature activation+1.09e+00

Pos logit contributions
ahime+0.199
usterity+0.198
 Berks+0.183
groupon+0.179
Origin+0.175
Neg logit contributions
 Deb-0.153
ourke-0.149
 Vand-0.145
$$-0.143
 「-0.143
Token
Token ID198
Feature activation+8.84e-01

Pos logit contributions
 Deb+0.630
ourke+0.612
 Vand+0.597
$$+0.589
 「+0.589
Neg logit contributions
ahime-0.818
usterity-0.814
 Berks-0.750
groupon-0.735
Origin-0.720
TokenOn
Token ID2202
Feature activation+7.61e-01

Pos logit contributions
 Deb+0.546
ourke+0.529
 Vand+0.518
 「+0.512
$$+0.512
Neg logit contributions
ahime-0.631
usterity-0.628
 Berks-0.575
groupon-0.562
Origin-0.552
Token the
Token ID262
Feature activation+2.65e+00

Pos logit contributions
 Deb+0.493
ourke+0.480
 Vand+0.470
$$+0.467
 「+0.465
Neg logit contributions
ahime-0.518
usterity-0.516
 Berks-0.470
groupon-0.459
Origin-0.449
Token left
Token ID1364
Feature activation+7.15e+00

Pos logit contributions
 Deb+1.624
ourke+1.570
 Vand+1.539
$$+1.522
 「+1.520
Neg logit contributions
ahime-1.909
usterity-1.894
 Berks-1.737
groupon-1.693
adobe-1.660
Token:
Token ID25
Feature activation+1.96e+00

Pos logit contributions
 Deb+4.132
ourke+3.857
 Vand+3.844
 「+3.825
$$+3.779
Neg logit contributions
ahime-5.388
usterity-5.304
 Berks-4.855
groupon-4.759
adobe-4.702
Token Bo
Token ID3248
Feature activation-4.54e-01

Pos logit contributions
 Deb+1.177
ourke+1.139
 Vand+1.115
$$+1.104
 「+1.101
Neg logit contributions
ahime-1.430
usterity-1.421
 Berks-1.305
groupon-1.273
Origin-1.248
Token Scar
Token ID12089
Feature activation+1.72e+00

Pos logit contributions
usterity+0.330
ahime+0.330
 Berks+0.304
groupon+0.296
Origin+0.288
Neg logit contributions
 Deb-0.270
ourke-0.263
 Vand-0.256
 「-0.255
$$-0.251
Tokenb
Token ID65
Feature activation-3.14e+00

Pos logit contributions
 Deb+1.064
ourke+1.030
 Vand+1.010
$$+1.000
 「+0.996
Neg logit contributions
ahime-1.231
usterity-1.225
 Berks-1.121
groupon-1.094
Origin-1.072
Tokenrough
Token ID740
Feature activation-1.44e+00

Pos logit contributions
usterity+2.327
ahime+2.274
 Berks+2.104
groupon+2.066
urger+2.061
Neg logit contributions
 Deb-1.795
ourke-1.700
 Vand-1.696
 「-1.669
 Lama-1.668
Token irrational
Token ID25086
Feature activation+5.02e-01

Pos logit contributions
 Deb+1.589
ourke+1.522
 Vand+1.500
 「+1.494
$$+1.479
Neg logit contributions
ahime-1.957
usterity-1.936
 Berks-1.780
groupon-1.738
adobe-1.706
Token,
Token ID11
Feature activation+1.04e+00

Pos logit contributions
 Deb+0.327
ourke+0.317
 Vand+0.311
$$+0.309
 「+0.308
Neg logit contributions
ahime-0.342
usterity-0.339
 Berks-0.309
groupon-0.301
adobe-0.295
Token shall
Token ID2236
Feature activation-1.34e+00

Pos logit contributions
 Deb+0.663
ourke+0.643
 Vand+0.630
$$+0.624
 「+0.623
Neg logit contributions
ahime-0.722
usterity-0.717
 Berks-0.656
groupon-0.639
adobe-0.626
Token seem
Token ID1283
Feature activation+3.40e+00

Pos logit contributions
usterity+0.972
ahime+0.962
 Berks+0.873
groupon+0.865
fore+0.851
Neg logit contributions
 Deb-0.799
ourke-0.785
 Vand-0.771
$$-0.744
 「-0.741
Token rational
Token ID9377
Feature activation+1.06e+00

Pos logit contributions
 Deb+2.080
ourke+1.979
 「+1.969
 Vand+1.964
$$+1.940
Neg logit contributions
ahime-2.482
usterity-2.434
 Berks-2.254
groupon-2.180
adobe-2.157
Token enough
Token ID1576
Feature activation+7.08e+00

Pos logit contributions
 Deb+0.680
ourke+0.659
 Vand+0.647
$$+0.641
 「+0.639
Neg logit contributions
ahime-0.738
usterity-0.733
 Berks-0.670
groupon-0.653
Origin-0.639
Token.
Token ID13
Feature activation+5.58e-01

Pos logit contributions
 Deb+3.915
 「+3.760
ourke+3.729
$$+3.688
 Vand+3.664
Neg logit contributions
ahime-5.420
usterity-5.404
 Berks-5.038
groupon-4.814
adobe-4.805
Token
Token ID447
Feature activation-4.38e-01

Pos logit contributions
 Deb+0.314
ourke+0.308
 Vand+0.298
$$+0.295
 「+0.294
Neg logit contributions
ahime-0.423
usterity-0.422
 Berks-0.390
groupon-0.381
Origin-0.376
Token
Token ID251
Feature activation+1.00e-01

Pos logit contributions
ahime+0.341
usterity+0.339
 Berks+0.314
groupon+0.307
Origin+0.301
Neg logit contributions
 Deb-0.242
ourke-0.234
 Vand-0.228
$$-0.225
 「-0.224
Token[
Token ID58
Feature activation+1.43e+00

Pos logit contributions
 Deb+0.055
ourke+0.054
 Vand+0.052
$$+0.051
 「+0.051
Neg logit contributions
ahime-0.078
usterity-0.077
 Berks-0.072
groupon-0.070
Origin-0.069
Token20
Token ID1238
Feature activation-2.32e+00

Pos logit contributions
 Deb+0.910
ourke+0.882
$$+0.868
 Vand+0.859
 「+0.857
Neg logit contributions
ahime-1.000
usterity-0.991
 Berks-0.907
groupon-0.869
adobe-0.859
Token and
Token ID290
Feature activation-1.56e-01

Pos logit contributions
 Deb+0.446
ourke+0.434
 Vand+0.424
$$+0.421
 「+0.419
Neg logit contributions
ahime-0.491
usterity-0.487
 Berks-0.449
groupon-0.435
Origin-0.426
Token Cody
Token ID27035
Feature activation+5.37e-01

Pos logit contributions
usterity+0.112
ahime+0.111
 Berks+0.104
groupon+0.100
Origin+0.098
Neg logit contributions
 Deb-0.092
ourke-0.091
$$-0.088
 「-0.088
 Vand-0.087
Token Mand
Token ID13314
Feature activation+1.85e+00

Pos logit contributions
 Deb+0.322
ourke+0.317
$$+0.306
 Vand+0.306
 「+0.305
Neg logit contributions
ahime-0.385
usterity-0.384
 Berks-0.357
groupon-0.345
Origin-0.337
Tokenell
Token ID695
Feature activation-5.84e-03

Pos logit contributions
 Deb+1.075
ourke+1.039
 Vand+1.017
$$+1.006
 「+1.003
Neg logit contributions
ahime-1.394
usterity-1.386
 Berks-1.276
groupon-1.245
adobe-1.222
Token,
Token ID11
Feature activation+5.35e-01

Pos logit contributions
ahime+0.004
usterity+0.004
 Berks+0.004
groupon+0.004
adobe+0.003
Neg logit contributions
 Deb-0.004
ourke-0.004
 Vand-0.004
$$-0.004
 「-0.004
Token center
Token ID3641
Feature activation+7.06e+00

Pos logit contributions
 Deb+0.382
ourke+0.372
 Vand+0.365
$$+0.363
 「+0.362
Neg logit contributions
ahime-0.328
usterity-0.327
 Berks-0.297
groupon-0.286
Origin-0.279
Token,
Token ID11
Feature activation+1.51e+00

Pos logit contributions
 Deb+4.154
ourke+3.943
 Vand+3.870
 「+3.847
$$+3.790
Neg logit contributions
ahime-5.215
usterity-5.053
 Berks-4.638
groupon-4.616
adobe-4.594
Token were
Token ID547
Feature activation+6.44e-01

Pos logit contributions
 Deb+0.944
ourke+0.916
 Vand+0.897
$$+0.889
 「+0.885
Neg logit contributions
ahime-1.068
usterity-1.061
 Berks-0.973
groupon-0.947
Origin-0.927
Token also
Token ID635
Feature activation-2.58e-01

Pos logit contributions
 Deb+0.411
ourke+0.401
 Vand+0.389
$$+0.389
 「+0.387
Neg logit contributions
ahime-0.442
usterity-0.441
 Berks-0.406
groupon-0.394
adobe-0.385
Token try
Token ID1949
Feature activation+2.03e+00

Pos logit contributions
usterity+0.173
ahime+0.172
 Berks+0.160
groupon+0.154
adobe+0.151
Neg logit contributions
 Deb-0.167
ourke-0.164
$$-0.159
 Vand-0.158
 「-0.158
Tokenout
Token ID448
Feature activation+5.41e-01

Pos logit contributions
 Deb+1.605
ourke+1.565
 Vand+1.541
$$+1.529
 「+1.526
Neg logit contributions
ahime-1.104
usterity-1.094
 Berks-0.973
groupon-0.941
Origin-0.915
Token
Token ID198
Feature activation-3.09e-01

Pos logit contributions
ahime+0.644
usterity+0.643
 Berks+0.602
groupon+0.583
Origin+0.568
Neg logit contributions
ourke-0.560
 Deb-0.556
 Vand-0.528
$$-0.528
 「-0.526
Token
Token ID198
Feature activation-2.85e-01

Pos logit contributions
ahime+0.220
usterity+0.220
 Berks+0.203
groupon+0.202
Origin+0.197
Neg logit contributions
 Deb-0.185
ourke-0.182
 Vand-0.177
 「-0.174
$$-0.173
TokenR
Token ID49
Feature activation-5.37e-01

Pos logit contributions
ahime+0.207
usterity+0.206
 Berks+0.189
groupon+0.185
Origin+0.182
Neg logit contributions
 Deb-0.172
ourke-0.167
 Vand-0.163
 「-0.161
$$-0.161
Tokeneds
Token ID5379
Feature activation-3.30e-01

Pos logit contributions
ahime+0.358
usterity+0.354
 Berks+0.323
groupon+0.311
Origin+0.309
Neg logit contributions
 Deb-0.355
 Vand-0.340
ourke-0.340
 「-0.335
$$-0.332
Tokenkins
Token ID5331
Feature activation+1.65e+00

Pos logit contributions
usterity+0.237
ahime+0.237
 Berks+0.218
groupon+0.212
Origin+0.210
Neg logit contributions
 Deb-0.202
ourke-0.197
 Vand-0.190
$$-0.190
 「-0.188
Token defensive
Token ID6110
Feature activation+7.06e+00

Pos logit contributions
 Deb+0.895
ourke+0.863
 Vand+0.843
$$+0.834
 「+0.831
Neg logit contributions
ahime-1.300
usterity-1.292
 Berks-1.195
groupon-1.168
Origin-1.147
Token players
Token ID1938
Feature activation+4.16e-02

Pos logit contributions
 Deb+3.169
 Vand+2.969
ourke+2.958
 「+2.885
$$+2.854
Neg logit contributions
ahime-6.220
usterity-6.144
adobe-5.597
 Berks-5.596
groupon-5.513
Token take
Token ID1011
Feature activation+4.41e-01

Pos logit contributions
 Deb+0.026
ourke+0.026
$$+0.025
 Vand+0.025
 「+0.025
Neg logit contributions
ahime-0.029
usterity-0.029
 Berks-0.026
groupon-0.025
Origin-0.025
Token a
Token ID257
Feature activation-1.66e+00

Pos logit contributions
 Deb+0.250
ourke+0.247
 Vand+0.237
$$+0.237
 「+0.234
Neg logit contributions
ahime-0.334
usterity-0.331
 Berks-0.308
groupon-0.299
adobe-0.293
Token water
Token ID1660
Feature activation+1.61e+00

Pos logit contributions
usterity+1.144
ahime+1.126
 Berks+1.044
groupon+1.003
Origin+0.976
Neg logit contributions
 Deb-1.054
ourke-1.051
 Vand-1.003
$$-1.002
 「-0.991
Token break
Token ID2270
Feature activation+1.80e+00

Pos logit contributions
 Deb+0.945
ourke+0.916
 Vand+0.895
$$+0.886
 「+0.883
Neg logit contributions
ahime-1.198
usterity-1.191
 Berks-1.096
groupon-1.070
adobe-1.049
Token long
Token ID890
Feature activation+1.16e+00

Pos logit contributions
 Deb+0.365
ourke+0.358
 Vand+0.348
$$+0.347
 「+0.345
Neg logit contributions
ahime-0.393
usterity-0.393
 Berks-0.361
groupon-0.351
Origin-0.344
Token as
Token ID355
Feature activation+1.71e+00

Pos logit contributions
 Deb+0.834
ourke+0.800
 Vand+0.794
 「+0.784
$$+0.782
Neg logit contributions
ahime-0.732
usterity-0.720
 Berks-0.648
groupon-0.631
adobe-0.618
Token outlets
Token ID12527
Feature activation+2.68e+00

Pos logit contributions
 Deb+1.003
ourke+0.975
 Vand+0.950
$$+0.943
 「+0.938
Neg logit contributions
ahime-1.270
usterity-1.265
 Berks-1.166
groupon-1.138
Origin-1.116
Token on
Token ID319
Feature activation+3.79e-01

Pos logit contributions
 Deb+1.481
ourke+1.419
 Vand+1.392
 「+1.380
$$+1.375
Neg logit contributions
ahime-2.106
usterity-2.085
 Berks-1.925
groupon-1.882
Origin-1.848
Token the
Token ID262
Feature activation+2.59e+00

Pos logit contributions
 Deb+0.241
ourke+0.234
 Vand+0.229
$$+0.227
 「+0.226
Neg logit contributions
ahime-0.263
usterity-0.262
 Berks-0.240
groupon-0.234
Origin-0.229
Token left
Token ID1364
Feature activation+6.90e+00

Pos logit contributions
 Deb+1.767
ourke+1.705
 Vand+1.683
 「+1.661
$$+1.650
Neg logit contributions
ahime-1.709
usterity-1.672
 Berks-1.518
groupon-1.478
adobe-1.456
Token and
Token ID290
Feature activation+1.52e+00

Pos logit contributions
 Deb+4.410
 「+4.248
ourke+4.189
 Vand+4.142
$$+4.118
Neg logit contributions
ahime-4.848
usterity-4.658
 Berks-4.273
groupon-4.121
Origin-4.054
Token in
Token ID287
Feature activation+9.24e-01

Pos logit contributions
 Deb+1.012
ourke+0.978
 Vand+0.972
 「+0.963
$$+0.952
Neg logit contributions
ahime-1.034
usterity-1.002
 Berks-0.903
groupon-0.887
adobe-0.877
Token the
Token ID262
Feature activation+1.16e+00

Pos logit contributions
 Deb+0.578
ourke+0.561
 Vand+0.549
$$+0.545
 「+0.543
Neg logit contributions
ahime-0.651
usterity-0.647
 Berks-0.593
groupon-0.578
Origin-0.566
Token center
Token ID3641
Feature activation+4.90e+00

Pos logit contributions
 Deb+0.783
ourke+0.759
 Vand+0.747
$$+0.739
 「+0.738
Neg logit contributions
ahime-0.760
usterity-0.753
 Berks-0.683
groupon-0.666
adobe-0.651
Token let
Token ID1309
Feature activation+3.00e+00

Pos logit contributions
 Deb+3.269
ourke+3.135
 Vand+3.116
 「+3.110
$$+3.059
Neg logit contributions
ahime-3.315
usterity-3.198
 Berks-2.935
groupon-2.838
Origin-2.794
Token or
Token ID393
Feature activation-2.98e+00

Pos logit contributions
ahime+2.048
usterity+2.040
 Berks+1.905
groupon+1.833
Origin+1.812
Neg logit contributions
 Deb-2.125
ourke-2.107
$$-2.034
 Vand-2.026
 「-1.995
Token the
Token ID262
Feature activation-1.51e+00

Pos logit contributions
ahime+1.983
usterity+1.972
 Berks+1.816
groupon+1.761
Origin+1.742
Neg logit contributions
 Deb-1.927
ourke-1.873
 Vand-1.836
$$-1.807
 「-1.792
Token day
Token ID1110
Feature activation-1.38e+00

Pos logit contributions
usterity+1.024
ahime+1.019
 Berks+0.938
groupon+0.909
Origin+0.894
Neg logit contributions
 Deb-0.970
ourke-0.946
 Vand-0.925
$$-0.917
 「-0.908
Token after
Token ID706
Feature activation-1.57e+00

Pos logit contributions
ahime+1.001
usterity+0.997
 Berks+0.928
groupon+0.902
Origin+0.890
Neg logit contributions
 Deb-0.816
ourke-0.794
 Vand-0.773
$$-0.767
 「-0.758
Token G
Token ID402
Feature activation+1.08e-01

Pos logit contributions
ahime+1.066
usterity+1.064
 Berks+0.985
groupon+0.951
Origin+0.939
Neg logit contributions
 Deb-0.991
ourke-0.977
$$-0.944
 Vand-0.942
 「-0.927
Tokenant
Token ID415
Feature activation+6.83e+00

Pos logit contributions
 Deb+0.068
ourke+0.066
 Vand+0.065
 「+0.064
$$+0.064
Neg logit contributions
ahime-0.075
usterity-0.075
 Berks-0.069
groupon-0.067
Origin-0.066
Token Heart
Token ID8894
Feature activation+2.63e+00

Pos logit contributions
 Deb+4.487
ourke+4.230
 Vand+4.213
 「+4.138
$$+4.087
Neg logit contributions
usterity-4.593
ahime-4.560
 Berks-4.148
groupon-4.067
adobe-3.988
Token.
Token ID13
Feature activation-3.64e-02

Pos logit contributions
 Deb+1.590
ourke+1.533
 Vand+1.505
 「+1.491
$$+1.490
Neg logit contributions
ahime-1.933
usterity-1.911
 Berks-1.754
groupon-1.715
adobe-1.682
Token He
Token ID679
Feature activation-9.15e-01

Pos logit contributions
ahime+0.027
usterity+0.026
 Berks+0.024
groupon+0.024
Origin+0.023
Neg logit contributions
 Deb-0.022
ourke-0.021
 Vand-0.021
$$-0.020
 「-0.020
Token was
Token ID373
Feature activation-6.21e-01

Pos logit contributions
ahime+0.676
usterity+0.672
 Berks+0.619
groupon+0.604
Origin+0.594
Neg logit contributions
 Deb-0.538
ourke-0.523
 Vand-0.509
$$-0.502
 「-0.501
Token visiting
Token ID10013
Feature activation-3.04e+00

Pos logit contributions
ahime+0.430
usterity+0.428
 Berks+0.392
groupon+0.381
Origin+0.373
Neg logit contributions
 Deb-0.395
ourke-0.384
 Vand-0.375
$$-0.372
 「-0.371
Token:
Token ID25
Feature activation-2.04e-01

Pos logit contributions
ahime+0.674
usterity+0.670
 Berks+0.623
groupon+0.599
Origin+0.592
Neg logit contributions
 Deb-0.658
ourke-0.657
$$-0.636
 Vand-0.629
 「-0.624
Token it
Token ID340
Feature activation+1.63e+00

Pos logit contributions
ahime+0.150
usterity+0.149
 Berks+0.139
groupon+0.135
Origin+0.132
Neg logit contributions
 Deb-0.119
ourke-0.117
 Vand-0.113
$$-0.112
 「-0.112
Token's
Token ID338
Feature activation+2.11e+00

Pos logit contributions
 Deb+0.993
ourke+0.953
 Vand+0.938
$$+0.933
 「+0.932
Neg logit contributions
ahime-1.195
usterity-1.186
 Berks-1.080
groupon-1.055
adobe-1.040
Token just
Token ID655
Feature activation+3.65e+00

Pos logit contributions
 Deb+1.229
ourke+1.174
 Vand+1.159
 「+1.143
$$+1.140
Neg logit contributions
ahime-1.600
usterity-1.586
 Berks-1.452
groupon-1.423
adobe-1.402
Token a
Token ID257
Feature activation+2.80e+00

Pos logit contributions
 Deb+2.110
ourke+1.987
 Vand+1.987
 「+1.959
$$+1.943
Neg logit contributions
ahime-2.810
usterity-2.769
 Berks-2.515
groupon-2.478
adobe-2.454
Token rumor
Token ID24989
Feature activation+6.81e+00

Pos logit contributions
 Deb+1.120
ourke+1.043
 Vand+1.039
$$+1.014
 「+1.012
Neg logit contributions
ahime-2.636
usterity-2.604
 Berks-2.423
groupon-2.392
adobe-2.377
Token.
Token ID13
Feature activation+1.71e+00

Pos logit contributions
 Deb+3.982
 「+3.690
$$+3.686
 Vand+3.671
ourke+3.574
Neg logit contributions
ahime-5.115
usterity-5.033
 Berks-4.540
adobe-4.456
groupon-4.450
Token But
Token ID887
Feature activation+7.29e-02

Pos logit contributions
 Deb+0.958
ourke+0.922
 Vand+0.903
$$+0.894
 「+0.891
Neg logit contributions
ahime-1.318
usterity-1.309
 Berks-1.207
groupon-1.179
adobe-1.158
Token given
Token ID1813
Feature activation+7.93e-02

Pos logit contributions
 Deb+0.045
ourke+0.045
$$+0.043
 Vand+0.043
 「+0.043
Neg logit contributions
ahime-0.051
usterity-0.051
 Berks-0.047
groupon-0.045
Origin-0.044
Token the
Token ID262
Feature activation-1.98e-01

Pos logit contributions
 Deb+0.049
ourke+0.048
 Vand+0.047
$$+0.047
 「+0.046
Neg logit contributions
ahime-0.056
usterity-0.056
 Berks-0.051
groupon-0.050
Origin-0.049
Token growing
Token ID3957
Feature activation-3.63e-01

Pos logit contributions
ahime+0.137
usterity+0.136
 Berks+0.127
groupon+0.122
Origin+0.120
Neg logit contributions
 Deb-0.124
ourke-0.123
$$-0.118
 Vand-0.118
 「-0.118
Token rather
Token ID2138
Feature activation+9.63e-02

Pos logit contributions
 Deb+0.369
ourke+0.358
 Vand+0.351
$$+0.348
 「+0.346
Neg logit contributions
ahime-0.427
usterity-0.425
 Berks-0.390
groupon-0.380
Origin-0.372
Token that
Token ID326
Feature activation+1.83e+00

Pos logit contributions
 Deb+0.062
ourke+0.061
 Vand+0.059
$$+0.059
 「+0.059
Neg logit contributions
ahime-0.065
usterity-0.065
 Berks-0.059
groupon-0.058
Origin-0.057
Token they
Token ID484
Feature activation+1.38e+00

Pos logit contributions
 Deb+1.052
ourke+1.014
 Vand+0.994
$$+0.982
 「+0.981
Neg logit contributions
ahime-1.385
usterity-1.375
 Berks-1.266
groupon-1.237
Origin-1.213
Token were
Token ID547
Feature activation+2.17e+00

Pos logit contributions
 Deb+0.912
ourke+0.885
 Vand+0.868
$$+0.861
 「+0.859
Neg logit contributions
ahime-0.928
usterity-0.921
 Berks-0.839
groupon-0.817
Origin-0.800
Token stupid
Token ID8531
Feature activation+2.11e+00

Pos logit contributions
 Deb+1.355
ourke+1.306
 Vand+1.286
 「+1.273
$$+1.272
Neg logit contributions
ahime-1.539
usterity-1.523
 Berks-1.392
groupon-1.358
Origin-1.334
Token enough
Token ID1576
Feature activation+6.80e+00

Pos logit contributions
 Deb+1.014
ourke+0.971
 Vand+0.947
$$+0.938
 「+0.932
Neg logit contributions
ahime-1.801
usterity-1.791
 Berks-1.665
groupon-1.629
Origin-1.604
Token to
Token ID284
Feature activation+2.08e+00

Pos logit contributions
 Deb+3.220
ourke+2.991
$$+2.982
 「+2.951
 Vand+2.908
Neg logit contributions
ahime-5.794
usterity-5.763
 Berks-5.338
groupon-5.202
Origin-5.095
Token expect
Token ID1607
Feature activation+8.10e-01

Pos logit contributions
 Deb+1.346
ourke+1.306
 Vand+1.280
$$+1.269
 「+1.265
Neg logit contributions
ahime-1.426
usterity-1.416
 Berks-1.293
groupon-1.259
Origin-1.233
Token a
Token ID257
Feature activation-6.98e-01

Pos logit contributions
 Deb+0.460
ourke+0.447
 Vand+0.435
$$+0.432
 「+0.429
Neg logit contributions
ahime-0.615
usterity-0.613
 Berks-0.566
groupon-0.551
Origin-0.543
Token piece
Token ID3704
Feature activation-7.28e-01

Pos logit contributions
usterity+0.495
ahime+0.492
 Berks+0.453
groupon+0.439
Origin+0.430
Neg logit contributions
 Deb-0.432
ourke-0.420
 Vand-0.409
$$-0.406
 「-0.405
Token from
Token ID422
Feature activation+2.02e-01

Pos logit contributions
ahime+0.460
usterity+0.460
 Berks+0.416
groupon+0.405
Origin+0.396
Neg logit contributions
 Deb-0.503
ourke-0.490
 Vand-0.481
$$-0.475
 「-0.475
Token have
Token ID423
Feature activation-5.08e-01

Pos logit contributions
 Deb+0.108
ourke+0.105
 Vand+0.103
$$+0.102
 「+0.102
Neg logit contributions
ahime-0.122
usterity-0.121
 Berks-0.111
groupon-0.108
Origin-0.106
Token been
Token ID587
Feature activation-2.73e-01

Pos logit contributions
usterity+0.356
ahime+0.355
 Berks+0.333
groupon+0.318
Origin+0.309
Neg logit contributions
ourke-0.312
 Deb-0.308
$$-0.297
 「-0.295
 Vand-0.292
Token better
Token ID1365
Feature activation-8.73e-01

Pos logit contributions
usterity+0.188
ahime+0.187
 Berks+0.173
groupon+0.167
adobe+0.163
Neg logit contributions
 Deb-0.172
ourke-0.170
$$-0.164
 「-0.164
 Vand-0.163
Token under
Token ID739
Feature activation+7.43e-01

Pos logit contributions
ahime+0.609
usterity+0.606
 Berks+0.555
groupon+0.540
adobe+0.528
Neg logit contributions
 Deb-0.551
ourke-0.537
 Vand-0.524
$$-0.520
 「-0.519
Token new
Token ID649
Feature activation+1.67e+00

Pos logit contributions
ourke+0.413
 Deb+0.413
 「+0.396
$$+0.396
 Vand+0.393
Neg logit contributions
usterity-0.565
ahime-0.559
 Berks-0.523
groupon-0.504
adobe-0.493
Token defensive
Token ID6110
Feature activation+6.72e+00

Pos logit contributions
 Deb+0.843
ourke+0.815
 Vand+0.791
$$+0.784
 「+0.782
Neg logit contributions
ahime-1.375
usterity-1.368
 Berks-1.270
groupon-1.241
adobe-1.219
Token coordinator
Token ID16052
Feature activation+3.56e+00

Pos logit contributions
 Deb+2.032
ourke+1.819
 Vand+1.819
$$+1.708
 「+1.656
Neg logit contributions
ahime-6.977
usterity-6.903
 Berks-6.392
groupon-6.360
Origin-6.335
Token Dennis
Token ID16902
Feature activation+1.32e-01

Pos logit contributions
 Deb+2.012
ourke+1.963
 Vand+1.896
 「+1.889
$$+1.884
Neg logit contributions
ahime-2.712
usterity-2.697
 Berks-2.495
groupon-2.433
adobe-2.387
Token Allen
Token ID9659
Feature activation+7.82e-01

Pos logit contributions
ourke+0.081
 Deb+0.076
Sov+0.073
mble+0.072
 「+0.072
Neg logit contributions
 Berks-0.091
usterity-0.091
ahime-0.088
groupon-0.085
fore-0.084
Token the
Token ID262
Feature activation-1.88e+00

Pos logit contributions
 Deb+0.488
ourke+0.472
 Vand+0.463
$$+0.459
 「+0.457
Neg logit contributions
ahime-0.554
usterity-0.551
 Berks-0.505
groupon-0.492
adobe-0.482
Token past
Token ID1613
Feature activation+1.30e+00

Pos logit contributions
usterity+1.309
ahime+1.306
 Berks+1.230
groupon+1.179
Origin+1.146
Neg logit contributions
ourke-1.151
 Deb-1.145
$$-1.101
 「-1.089
 Vand-1.081
Token for
Token ID329
Feature activation+3.84e-01

Pos logit contributions
ahime+0.830
usterity+0.823
 Berks+0.762
groupon+0.741
Origin+0.727
Neg logit contributions
 Deb-0.682
ourke-0.665
 Vand-0.650
$$-0.648
 「-0.639
Token References
Token ID31458
Feature activation+1.55e+00

Pos logit contributions
 Deb+0.221
ourke+0.214
 Vand+0.209
$$+0.207
 「+0.206
Neg logit contributions
ahime-0.291
usterity-0.289
 Berks-0.266
groupon-0.260
Origin-0.255
Token:
Token ID25
Feature activation+8.45e-01

Pos logit contributions
 Deb+0.868
ourke+0.833
 Vand+0.818
 「+0.808
$$+0.804
Neg logit contributions
ahime-1.209
usterity-1.202
 Berks-1.104
groupon-1.082
adobe-1.063
Token<|endoftext|>
Token ID50256
Feature activation-5.90e-01

Pos logit contributions
 Deb+0.482
ourke+0.465
 Vand+0.455
$$+0.450
 「+0.449
Neg logit contributions
ahime-0.646
usterity-0.642
 Berks-0.591
groupon-0.578
adobe-0.567
TokenIt
Token ID1026
Feature activation+1.51e+00

Pos logit contributions
usterity+0.404
ahime+0.403
 Berks+0.367
groupon+0.363
Origin+0.358
Neg logit contributions
 Deb-0.381
ourke-0.368
 Vand-0.363
 「-0.357
$$-0.353
Token took
Token ID1718
Feature activation+6.70e+00

Pos logit contributions
 Deb+0.895
ourke+0.861
 Vand+0.844
$$+0.839
 「+0.836
Neg logit contributions
ahime-1.122
usterity-1.112
 Berks-1.023
groupon-0.998
Origin-0.978
Token until
Token ID1566
Feature activation+3.69e+00

Pos logit contributions
 Deb+4.256
 Vand+4.043
 「+3.896
ourke+3.859
$$+3.856
Neg logit contributions
ahime-4.757
usterity-4.640
 Berks-4.133
groupon-4.108
adobe-4.064
Token Sunday
Token ID3502
Feature activation+1.87e+00

Pos logit contributions
 Deb+2.613
 Vand+2.491
ourke+2.472
 「+2.451
$$+2.430
Neg logit contributions
ahime-2.354
usterity-2.308
 Berks-2.059
groupon-2.026
adobe-1.984
Token morning
Token ID3329
Feature activation+1.95e+00

Pos logit contributions
 Deb+1.125
ourke+1.083
 Vand+1.066
$$+1.052
 「+1.051
Neg logit contributions
ahime-1.372
usterity-1.359
 Berks-1.243
groupon-1.215
Origin-1.190
Token for
Token ID329
Feature activation-6.88e-01

Pos logit contributions
 Deb+1.151
ourke+1.108
 Vand+1.090
 「+1.075
$$+1.075
Neg logit contributions
ahime-1.457
usterity-1.445
 Berks-1.324
groupon-1.295
Origin-1.268
Token a
Token ID257
Feature activation+1.39e+00

Pos logit contributions
ahime+0.474
usterity+0.474
 Berks+0.440
groupon+0.425
Origin+0.416
Neg logit contributions
 Deb-0.429
ourke-0.424
$$-0.411
 Vand-0.409
 「-0.407
Token….
Token ID11580
Feature activation+1.97e+00

Pos logit contributions
ahime+0.230
usterity+0.228
 Berks+0.211
groupon+0.205
Origin+0.200
Neg logit contributions
 Deb-0.199
ourke-0.195
 Vand-0.190
$$-0.189
 「-0.187
Token
Token ID198
Feature activation+3.02e+00

Pos logit contributions
 Deb+1.133
ourke+1.093
 Vand+1.070
$$+1.059
 「+1.058
Neg logit contributions
ahime-1.494
usterity-1.486
 Berks-1.367
groupon-1.336
adobe-1.311
Token
Token ID198
Feature activation+2.78e+00

Pos logit contributions
 Deb+1.620
ourke+1.529
$$+1.526
 Vand+1.510
 「+1.500
Neg logit contributions
ahime-2.463
usterity-2.438
 Berks-2.246
groupon-2.151
adobe-2.137
Token"
Token ID1
Feature activation+8.99e-01

Pos logit contributions
 Deb+1.631
ourke+1.579
 Vand+1.547
$$+1.543
 「+1.538
Neg logit contributions
ahime-2.077
usterity-2.061
 Berks-1.898
groupon-1.841
adobe-1.812
TokenAh
Token ID10910
Feature activation-7.82e-01

Pos logit contributions
 Deb+0.527
ourke+0.512
 Vand+0.498
$$+0.489
 「+0.487
Neg logit contributions
ahime-0.666
usterity-0.663
 Berks-0.612
groupon-0.600
Origin-0.594
Token."
Token ID526
Feature activation+6.66e+00

Pos logit contributions
ahime+0.535
usterity+0.529
 Berks+0.482
groupon+0.469
Origin+0.459
Neg logit contributions
 Deb-0.505
ourke-0.495
 Vand-0.485
$$-0.475
 「-0.473
Token
Token ID198
Feature activation+3.27e+00

Pos logit contributions
 Deb+3.315
 「+3.175
 Vand+3.016
ourke+2.966
$$+2.949
Neg logit contributions
ahime-5.649
usterity-5.618
 Berks-5.086
groupon-5.078
Origin-4.969
Token
Token ID198
Feature activation+2.62e+00

Pos logit contributions
 Deb+1.749
ourke+1.643
$$+1.642
 Vand+1.632
 「+1.619
Neg logit contributions
ahime-2.668
usterity-2.640
 Berks-2.426
groupon-2.327
adobe-2.315
Token"
Token ID1
Feature activation-6.91e-01

Pos logit contributions
 Deb+1.477
ourke+1.428
 Vand+1.396
$$+1.390
 「+1.385
Neg logit contributions
ahime-2.014
usterity-1.999
 Berks-1.845
groupon-1.793
adobe-1.765
TokenSte
Token ID7447
Feature activation+2.64e+00

Pos logit contributions
usterity+0.486
ahime+0.485
 Berks+0.447
groupon+0.442
Origin+0.442
Neg logit contributions
 Deb-0.424
ourke-0.417
 Vand-0.402
$$-0.389
 「-0.388
Tokenlla
Token ID8466
Feature activation-4.74e-01

Pos logit contributions
 Deb+2.636
ourke+2.592
 Vand+2.553
$$+2.547
 「+2.540
Neg logit contributions
ahime-0.877
usterity-0.865
 Berks-0.713
groupon-0.652
Origin-0.627
Token energy
Token ID2568
Feature activation+5.40e-01

Pos logit contributions
 Deb+1.135
ourke+1.095
 Vand+1.075
$$+1.061
 「+1.059
Neg logit contributions
ahime-1.458
usterity-1.447
 Berks-1.332
groupon-1.300
adobe-1.278
Token goals
Token ID4661
Feature activation+2.17e+00

Pos logit contributions
 Deb+0.330
ourke+0.320
 Vand+0.313
$$+0.310
 「+0.310
Neg logit contributions
ahime-0.390
usterity-0.388
 Berks-0.355
groupon-0.346
Origin-0.340
Token.
Token ID13
Feature activation+1.22e+00

Pos logit contributions
 Deb+1.349
ourke+1.287
 Vand+1.273
$$+1.257
 「+1.257
Neg logit contributions
usterity-1.557
ahime-1.554
 Berks-1.428
groupon-1.380
Origin-1.363
Token<|endoftext|>
Token ID50256
Feature activation-3.44e-01

Pos logit contributions
 Deb+0.685
ourke+0.655
 Vand+0.646
$$+0.638
 「+0.636
Neg logit contributions
ahime-0.940
usterity-0.934
 Berks-0.860
groupon-0.840
Origin-0.825
TokenMedia
Token ID13152
Feature activation+3.05e+00

Pos logit contributions
ahime+0.236
usterity+0.236
 Berks+0.214
groupon+0.211
Origin+0.208
Neg logit contributions
 Deb-0.223
ourke-0.215
 Vand-0.212
 「-0.209
$$-0.207
Token playback
Token ID16388
Feature activation+6.60e+00

Pos logit contributions
 Deb+1.163
ourke+1.091
 Vand+1.060
 「+1.039
$$+1.039
Neg logit contributions
ahime-2.906
usterity-2.888
 Berks-2.708
groupon-2.659
adobe-2.625
Token is
Token ID318
Feature activation+6.68e-01

Pos logit contributions
 Deb+3.611
ourke+3.448
 Vand+3.259
$$+3.258
 Lama+3.255
Neg logit contributions
ahime-5.377
usterity-5.334
 Berks-4.772
adobe-4.668
groupon-4.470
Token unsupported
Token ID24222
Feature activation+1.28e+00

Pos logit contributions
 Deb+0.345
ourke+0.336
 Vand+0.326
$$+0.324
 「+0.321
Neg logit contributions
usterity-0.541
ahime-0.538
 Berks-0.501
groupon-0.490
Origin-0.480
Token on
Token ID319
Feature activation-6.23e-02

Pos logit contributions
 Deb+0.875
ourke+0.849
 Vand+0.834
$$+0.828
 「+0.825
Neg logit contributions
ahime-0.832
usterity-0.824
 Berks-0.747
groupon-0.722
adobe-0.710
Token your
Token ID534
Feature activation-1.10e+00

Pos logit contributions
ahime+0.043
usterity+0.042
 Berks+0.039
groupon+0.037
adobe+0.037
Neg logit contributions
 Deb-0.041
ourke-0.039
 Vand-0.039
$$-0.038
 「-0.038
Token device
Token ID3335
Feature activation+1.63e+00

Pos logit contributions
ahime+0.798
usterity+0.789
 Berks+0.724
groupon+0.721
Origin+0.705
Neg logit contributions
 Deb-0.661
ourke-0.638
 Vand-0.633
$$-0.624
 「-0.620
Tokeniquette
Token ID40387
Feature activation+3.41e+00

Pos logit contributions
 Deb+1.592
ourke+1.551
 Vand+1.524
$$+1.513
 「+1.509
Neg logit contributions
ahime-1.235
usterity-1.225
 Berks-1.099
groupon-1.064
Origin-1.038
Token and
Token ID290
Feature activation+1.30e+00

Pos logit contributions
 Deb+2.104
 Vand+1.985
ourke+1.980
 「+1.970
$$+1.955
Neg logit contributions
ahime-2.482
usterity-2.461
 Berks-2.218
groupon-2.171
adobe-2.151
Token Manual
Token ID17969
Feature activation+3.67e-01

Pos logit contributions
 Deb+0.760
ourke+0.731
 Vand+0.718
$$+0.709
 「+0.708
Neg logit contributions
ahime-0.973
usterity-0.967
 Berks-0.888
groupon-0.867
adobe-0.852
Token of
Token ID286
Feature activation+2.30e-01

Pos logit contributions
 Deb+0.230
ourke+0.222
 Vand+0.218
$$+0.216
 「+0.215
Neg logit contributions
ahime-0.260
usterity-0.258
 Berks-0.236
groupon-0.230
adobe-0.225
Token Polit
Token ID7793
Feature activation+1.11e+00

Pos logit contributions
 Deb+0.133
ourke+0.130
 Vand+0.126
$$+0.126
 「+0.125
Neg logit contributions
ahime-0.172
usterity-0.171
 Berks-0.158
groupon-0.154
Origin-0.151
Tokeneness
Token ID9449
Feature activation+6.59e+00

Pos logit contributions
 Deb+0.540
ourke+0.519
 Vand+0.505
$$+0.499
 「+0.497
Neg logit contributions
ahime-0.935
usterity-0.930
 Berks-0.864
groupon-0.846
Origin-0.832
Token,
Token ID11
Feature activation+1.78e+00

Pos logit contributions
 Deb+3.963
 Vand+3.734
 「+3.733
ourke+3.661
$$+3.640
Neg logit contributions
ahime-4.839
usterity-4.771
 Berks-4.254
adobe-4.195
groupon-4.178
Token 18
Token ID1248
Feature activation-5.38e-01

Pos logit contributions
 Deb+1.272
ourke+1.224
 Vand+1.216
 「+1.201
$$+1.196
Neg logit contributions
ahime-1.109
usterity-1.104
 Berks-0.980
groupon-0.961
adobe-0.943
Token76
Token ID4304
Feature activation+1.07e+00

Pos logit contributions
ahime+0.396
usterity+0.392
 Berks+0.367
groupon+0.361
Origin+0.354
Neg logit contributions
 Deb-0.312
ourke-0.306
 Vand-0.294
$$-0.291
 「-0.290
Token.
Token ID13
Feature activation+1.92e-01

Pos logit contributions
 Deb+0.667
ourke+0.638
 Vand+0.632
 「+0.625
$$+0.624
Neg logit contributions
ahime-0.762
usterity-0.756
 Berks-0.687
groupon-0.670
adobe-0.661
Token
Token ID198
Feature activation+4.65e-01

Pos logit contributions
 Deb+0.106
ourke+0.102
 Vand+0.100
 「+0.099
$$+0.099
Neg logit contributions
ahime-0.151
usterity-0.149
 Berks-0.137
groupon-0.134
adobe-0.132
Token.
Token ID13
Feature activation+3.09e-01

Pos logit contributions
ahime+0.466
usterity+0.462
 Berks+0.422
groupon+0.412
Origin+0.405
Neg logit contributions
 Deb-0.446
ourke-0.436
 Vand-0.425
$$-0.421
 「-0.418
Token
Token ID198
Feature activation+7.75e-01

Pos logit contributions
 Deb+0.181
ourke+0.179
 Vand+0.172
$$+0.171
 「+0.169
Neg logit contributions
ahime-0.227
usterity-0.225
 Berks-0.209
groupon-0.203
Origin-0.200
Token
Token ID198
Feature activation+8.46e-01

Pos logit contributions
 Deb+0.448
ourke+0.435
 Vand+0.424
$$+0.419
 「+0.418
Neg logit contributions
ahime-0.581
usterity-0.578
 Berks-0.533
groupon-0.522
Origin-0.512
TokenPart
Token ID7841
Feature activation+8.18e-01

Pos logit contributions
 Deb+0.549
ourke+0.533
 Vand+0.522
$$+0.513
 「+0.513
Neg logit contributions
ahime-0.577
usterity-0.575
 Berks-0.524
groupon-0.513
Origin-0.505
Token 6
Token ID718
Feature activation+3.11e+00

Pos logit contributions
 Deb+0.507
ourke+0.492
 Vand+0.481
$$+0.478
 「+0.474
Neg logit contributions
ahime-0.582
usterity-0.577
 Berks-0.530
groupon-0.517
Origin-0.507
Token [
Token ID685
Feature activation+6.51e+00

Pos logit contributions
 Deb+1.789
ourke+1.710
 「+1.687
 Vand+1.683
$$+1.661
Neg logit contributions
ahime-2.358
usterity-2.353
 Berks-2.162
groupon-2.109
adobe-2.083
Token edit
Token ID4370
Feature activation+2.27e+00

Pos logit contributions
 Deb+3.664
 「+3.502
$$+3.464
ourke+3.455
 Vand+3.418
Neg logit contributions
ahime-4.947
usterity-4.923
 Berks-4.523
adobe-4.392
groupon-4.381
Token ]
Token ID2361
Feature activation+2.18e+00

Pos logit contributions
 Deb+1.259
ourke+1.214
 Vand+1.187
$$+1.174
 「+1.172
Neg logit contributions
ahime-1.762
usterity-1.752
 Berks-1.617
groupon-1.580
adobe-1.551
Token
Token ID198
Feature activation+1.93e+00

Pos logit contributions
 Deb+1.240
ourke+1.194
 Vand+1.171
$$+1.159
 「+1.156
Neg logit contributions
ahime-1.668
usterity-1.656
 Berks-1.527
groupon-1.488
adobe-1.463
Token
Token ID198
Feature activation+2.20e+00

Pos logit contributions
 Deb+1.082
ourke+1.037
 Vand+1.018
$$+1.013
 「+1.007
Neg logit contributions
ahime-1.505
usterity-1.492
 Berks-1.376
groupon-1.334
adobe-1.315
TokenIt
Token ID1026
Feature activation+3.65e-01

Pos logit contributions
 Deb+1.356
ourke+1.313
 Vand+1.287
$$+1.283
 「+1.278
Neg logit contributions
ahime-1.573
usterity-1.560
 Berks-1.432
groupon-1.389
adobe-1.364
Tokenque
Token ID4188
Feature activation+4.93e-01

Pos logit contributions
 Deb+0.747
ourke+0.725
 Vand+0.717
 「+0.710
$$+0.709
Neg logit contributions
ahime-0.560
usterity-0.555
 Berks-0.496
groupon-0.485
Origin-0.470
Token,
Token ID11
Feature activation+1.77e-01

Pos logit contributions
 Deb+0.303
ourke+0.298
 Vand+0.288
$$+0.286
 「+0.284
Neg logit contributions
ahime-0.348
usterity-0.346
 Berks-0.321
groupon-0.312
Origin-0.305
Token excellent
Token ID6275
Feature activation-8.49e-01

Pos logit contributions
 Deb+0.111
ourke+0.110
$$+0.107
 Vand+0.106
 「+0.106
Neg logit contributions
ahime-0.122
usterity-0.122
 Berks-0.113
groupon-0.109
Origin-0.106
Token on
Token ID319
Feature activation+1.12e+00

Pos logit contributions
ahime+0.576
usterity+0.573
 Berks+0.523
groupon+0.509
Origin+0.498
Neg logit contributions
 Deb-0.550
ourke-0.538
 Vand-0.525
$$-0.523
 「-0.521
Token the
Token ID262
Feature activation+1.68e+00

Pos logit contributions
 Deb+0.698
ourke+0.679
 Vand+0.664
$$+0.659
 「+0.657
Neg logit contributions
ahime-0.790
usterity-0.784
 Berks-0.718
groupon-0.701
adobe-0.686
Token left
Token ID1364
Feature activation+6.51e+00

Pos logit contributions
 Deb+0.966
ourke+0.922
 Vand+0.908
 「+0.893
$$+0.891
Neg logit contributions
ahime-1.280
usterity-1.269
 Berks-1.164
groupon-1.139
Origin-1.122
Token,
Token ID11
Feature activation+1.56e+00

Pos logit contributions
 Deb+3.751
 Vand+3.488
ourke+3.442
 「+3.409
$$+3.369
Neg logit contributions
ahime-4.964
usterity-4.898
 Berks-4.432
groupon-4.314
Origin-4.273
Token helped
Token ID4193
Feature activation-5.00e-01

Pos logit contributions
 Deb+0.948
ourke+0.923
 Vand+0.900
$$+0.893
 「+0.889
Neg logit contributions
ahime-1.127
usterity-1.120
 Berks-1.032
groupon-1.005
Origin-0.984
Token create
Token ID2251
Feature activation+1.02e+00

Pos logit contributions
ahime+0.360
usterity+0.356
 Berks+0.332
groupon+0.321
adobe+0.316
Neg logit contributions
 Deb-0.300
ourke-0.294
$$-0.286
 Vand-0.284
 「-0.283
Token the
Token ID262
Feature activation-9.64e-01

Pos logit contributions
 Deb+0.594
ourke+0.581
 Vand+0.563
$$+0.563
 「+0.559
Neg logit contributions
ahime-0.756
usterity-0.752
 Berks-0.697
groupon-0.677
Origin-0.665
Token second
Token ID1218
Feature activation-1.79e-01

Pos logit contributions
usterity+0.721
ahime+0.721
 Berks+0.672
groupon+0.650
Origin+0.639
Neg logit contributions
 Deb-0.550
ourke-0.539
$$-0.522
 Vand-0.522
 「-0.517
Token not
Token ID407
Feature activation-1.78e-01

Pos logit contributions
 Deb+0.866
ourke+0.836
 Vand+0.820
$$+0.811
 「+0.810
Neg logit contributions
ahime-1.029
usterity-1.021
 Berks-0.934
groupon-0.913
adobe-0.896
Token going
Token ID1016
Feature activation-1.23e+00

Pos logit contributions
ahime+0.122
usterity+0.122
 Berks+0.111
groupon+0.108
Origin+0.106
Neg logit contributions
 Deb-0.114
ourke-0.112
 Vand-0.109
$$-0.108
 「-0.108
Token to
Token ID284
Feature activation-1.39e-01

Pos logit contributions
ahime+0.887
usterity+0.878
 Berks+0.815
groupon+0.792
Origin+0.769
Neg logit contributions
 Deb-0.740
ourke-0.720
 Vand-0.704
$$-0.695
 「-0.693
Token cave
Token ID11527
Feature activation+7.34e-01

Pos logit contributions
ahime+0.098
usterity+0.098
 Berks+0.091
groupon+0.088
Origin+0.085
Neg logit contributions
 Deb-0.085
ourke-0.083
 Vand-0.081
$$-0.080
 「-0.080
Token just
Token ID655
Feature activation+8.04e-01

Pos logit contributions
 Deb+0.460
ourke+0.446
 Vand+0.437
$$+0.433
 「+0.432
Neg logit contributions
ahime-0.519
usterity-0.515
 Berks-0.472
groupon-0.460
Origin-0.450
Token c
Token ID269
Feature activation+6.50e+00

Pos logit contributions
 Deb+0.536
ourke+0.520
 Vand+0.511
$$+0.506
 「+0.505
Neg logit contributions
ahime-0.538
usterity-0.533
 Berks-0.485
groupon-0.472
adobe-0.462
Tokenuz
Token ID10277
Feature activation+2.41e+00

Pos logit contributions
 Deb+4.072
ourke+3.957
$$+3.869
 「+3.843
 Vand+3.834
Neg logit contributions
ahime-4.597
usterity-4.548
 Berks-4.119
groupon-4.006
adobe-4.001
Token he
Token ID339
Feature activation+2.54e+00

Pos logit contributions
 Deb+1.472
ourke+1.417
 Vand+1.392
$$+1.377
 「+1.376
Neg logit contributions
ahime-1.756
usterity-1.739
 Berks-1.588
groupon-1.554
adobe-1.528
Token sends
Token ID12800
Feature activation+2.12e+00

Pos logit contributions
 Deb+1.564
ourke+1.510
 Vand+1.480
$$+1.474
 「+1.470
Neg logit contributions
ahime-1.834
usterity-1.820
 Berks-1.660
groupon-1.622
adobe-1.599
Token me
Token ID502
Feature activation+2.57e+00

Pos logit contributions
 Deb+1.230
ourke+1.191
 Vand+1.164
$$+1.151
 「+1.149
Neg logit contributions
ahime-1.595
usterity-1.586
 Berks-1.463
groupon-1.427
Origin-1.398
Token a
Token ID257
Feature activation-1.28e-01

Pos logit contributions
 Deb+1.455
ourke+1.405
 Vand+1.374
$$+1.359
 「+1.356
Neg logit contributions
ahime-1.972
usterity-1.960
 Berks-1.808
groupon-1.766
Origin-1.733
Token winner
Token ID8464
Feature activation-1.01e+00

Pos logit contributions
usterity+0.391
ahime+0.391
 Berks+0.361
groupon+0.350
Origin+0.343
Neg logit contributions
 Deb-0.327
ourke-0.320
 Vand-0.309
$$-0.309
 「-0.307
Token of
Token ID286
Feature activation+5.96e-02

Pos logit contributions
ahime+0.624
usterity+0.621
 Berks+0.566
groupon+0.550
Origin+0.537
Neg logit contributions
 Deb-0.709
ourke-0.696
 Vand-0.679
$$-0.676
 「-0.672
Token the
Token ID262
Feature activation+1.52e-01

Pos logit contributions
 Deb+0.036
ourke+0.035
 Vand+0.034
$$+0.034
 「+0.034
Neg logit contributions
ahime-0.043
usterity-0.043
 Berks-0.040
groupon-0.039
Origin-0.038
Token UFC
Token ID11448
Feature activation+8.06e-01

Pos logit contributions
 Deb+0.097
ourke+0.094
 Vand+0.092
$$+0.091
 「+0.091
Neg logit contributions
ahime-0.106
usterity-0.105
 Berks-0.096
groupon-0.093
adobe-0.091
Token 216
Token ID26881
Feature activation+1.72e+00

Pos logit contributions
 Deb+0.520
ourke+0.504
 Vand+0.494
$$+0.490
 「+0.489
Neg logit contributions
ahime-0.554
usterity-0.551
 Berks-0.503
groupon-0.490
Origin-0.479
Token interim
Token ID19303
Feature activation+6.49e+00

Pos logit contributions
 Deb+1.110
ourke+1.057
 Vand+1.049
$$+1.035
 「+1.035
Neg logit contributions
ahime-1.211
usterity-1.192
 Berks-1.080
groupon-1.049
adobe-1.045
Token title
Token ID3670
Feature activation+2.20e+00

Pos logit contributions
 Deb+3.351
 Vand+3.187
 「+3.118
ourke+3.046
$$+3.018
Neg logit contributions
ahime-5.340
usterity-5.258
 Berks-4.859
adobe-4.731
groupon-4.695
Token showdown
Token ID33338
Feature activation+5.35e-01

Pos logit contributions
 Deb+1.456
ourke+1.384
 Vand+1.371
 「+1.355
$$+1.343
Neg logit contributions
ahime-1.511
usterity-1.505
 Berks-1.361
groupon-1.321
adobe-1.311
Token between
Token ID1022
Feature activation-8.55e-01

Pos logit contributions
 Deb+0.355
ourke+0.342
 Vand+0.338
 「+0.334
$$+0.334
Neg logit contributions
ahime-0.362
usterity-0.360
 Berks-0.326
groupon-0.317
adobe-0.311
Token Tony
Token ID8832
Feature activation-3.76e-02

Pos logit contributions
usterity+0.639
ahime+0.637
 Berks+0.594
groupon+0.578
Origin+0.568
Neg logit contributions
 Deb-0.482
ourke-0.474
$$-0.460
 Vand-0.457
 「-0.454
Token Ferguson
Token ID15031
Feature activation+7.54e-01

Pos logit contributions
usterity+0.027
ahime+0.027
 Berks+0.025
groupon+0.024
Origin+0.024
Neg logit contributions
 Deb-0.022
ourke-0.022
$$-0.021
 Vand-0.021
 「-0.021
Token?
Token ID30
Feature activation-1.05e+00

Pos logit contributions
 Deb+0.141
ourke+0.136
 Vand+0.133
$$+0.131
 「+0.131
Neg logit contributions
ahime-0.214
usterity-0.213
 Berks-0.198
groupon-0.193
Origin-0.190
Token (
Token ID357
Feature activation+1.08e+00

Pos logit contributions
ahime+0.791
usterity+0.790
 Berks+0.741
groupon+0.722
Origin+0.706
Neg logit contributions
 Deb-0.590
ourke-0.584
 Vand-0.558
$$-0.558
 「-0.553
TokenThink
Token ID22073
Feature activation-4.29e-01

Pos logit contributions
 Deb+0.679
ourke+0.658
 Vand+0.645
$$+0.637
 「+0.637
Neg logit contributions
ahime-0.753
usterity-0.749
 Berks-0.686
groupon-0.670
Origin-0.657
Token of
Token ID286
Feature activation+2.37e+00

Pos logit contributions
ahime+0.274
usterity+0.274
 Berks+0.249
groupon+0.241
Origin+0.236
Neg logit contributions
 Deb-0.295
ourke-0.287
 Vand-0.281
$$-0.280
 「-0.278
Token The
Token ID383
Feature activation-2.03e+00

Pos logit contributions
 Deb+1.456
ourke+1.401
 Vand+1.383
 「+1.366
$$+1.362
Neg logit contributions
ahime-1.706
usterity-1.695
 Berks-1.538
groupon-1.506
Origin-1.480
Token Simpsons
Token ID34376
Feature activation-7.90e+00

Pos logit contributions
ahime+1.410
usterity+1.396
 Berks+1.309
groupon+1.258
Origin+1.233
Neg logit contributions
 Deb-1.260
ourke-1.245
$$-1.206
 「-1.199
 Vand-1.197
Token and
Token ID290
Feature activation-1.09e+00

Pos logit contributions
ahime+5.091
usterity+4.974
 Berks+4.734
groupon+4.610
Origin+4.513
Neg logit contributions
 Deb-4.861
ourke-4.771
Sov-4.675
 Vand-4.632
$$-4.625
Token the
Token ID262
Feature activation-2.16e-02

Pos logit contributions
ahime+0.767
usterity+0.763
 Berks+0.710
groupon+0.687
Origin+0.671
Neg logit contributions
 Deb-0.665
ourke-0.654
$$-0.634
 Vand-0.633
 「-0.627
Token mon
Token ID937
Feature activation-8.30e-01

Pos logit contributions
ahime+0.015
usterity+0.015
 Berks+0.014
groupon+0.013
Origin+0.013
Neg logit contributions
 Deb-0.014
ourke-0.013
$$-0.013
 Vand-0.013
 「-0.013
Tokenor
Token ID273
Feature activation+2.02e+00

Pos logit contributions
ahime+0.658
usterity+0.654
 Berks+0.608
groupon+0.592
adobe+0.583
Neg logit contributions
 Deb-0.444
ourke-0.426
 Vand-0.416
$$-0.412
 「-0.405
Tokenail
Token ID603
Feature activation-2.21e-01

Pos logit contributions
 Deb+1.178
ourke+1.143
 Vand+1.113
$$+1.105
 「+1.100
Neg logit contributions
ahime-1.517
usterity-1.506
 Berks-1.388
groupon-1.356
Origin-1.332
Token Magic
Token ID6139
Feature activation-7.27e-01

Pos logit contributions
 Deb+0.117
ourke+0.113
 Vand+0.111
$$+0.110
 「+0.110
Neg logit contributions
ahime-0.136
usterity-0.135
 Berks-0.124
groupon-0.121
Origin-0.119
Token iterations
Token ID34820
Feature activation+1.19e+00

Pos logit contributions
ahime+0.485
usterity+0.478
 Berks+0.439
groupon+0.427
Origin+0.418
Neg logit contributions
 Deb-0.481
ourke-0.471
 Vand-0.461
$$-0.457
 「-0.454
Token of
Token ID286
Feature activation+4.20e-01

Pos logit contributions
 Deb+0.767
ourke+0.742
 Vand+0.728
$$+0.723
 「+0.722
Neg logit contributions
ahime-0.813
usterity-0.810
 Berks-0.738
groupon-0.718
adobe-0.703
Token My
Token ID2011
Feature activation-6.89e-01

Pos logit contributions
 Deb+0.255
ourke+0.247
 Vand+0.242
$$+0.239
 「+0.239
Neg logit contributions
ahime-0.305
usterity-0.303
 Berks-0.278
groupon-0.271
Origin-0.266
Token Little
Token ID7703
Feature activation-2.64e+00

Pos logit contributions
ahime+0.628
usterity+0.624
 Berks+0.585
groupon+0.573
Origin+0.565
Neg logit contributions
 Deb-0.289
ourke-0.278
 Vand-0.268
$$-0.265
 「-0.262
Token Pony
Token ID30377
Feature activation-7.74e+00

Pos logit contributions
ahime+1.259
usterity+1.248
 Berks+1.113
groupon+1.064
Origin+1.035
Neg logit contributions
 Deb-2.210
ourke-2.199
$$-2.140
 Vand-2.140
 「-2.133
Token.
Token ID13
Feature activation-6.37e-01

Pos logit contributions
ahime+4.863
usterity+4.595
 Berks+4.407
Origin+4.294
groupon+4.252
Neg logit contributions
ourke-5.031
 Deb-4.911
$$-4.830
 Vand-4.792
 Lama-4.758
Token It
Token ID632
Feature activation-6.80e-01

Pos logit contributions
ahime+0.461
usterity+0.458
 Berks+0.425
groupon+0.415
Origin+0.411
Neg logit contributions
 Deb-0.379
ourke-0.373
 Vand-0.361
$$-0.356
 「-0.355
Token gave
Token ID2921
Feature activation+1.04e+00

Pos logit contributions
ahime+0.481
usterity+0.478
 Berks+0.440
groupon+0.428
Origin+0.420
Neg logit contributions
 Deb-0.420
ourke-0.410
 Vand-0.400
$$-0.394
 「-0.392
Token me
Token ID502
Feature activation+1.78e+00

Pos logit contributions
 Deb+0.558
ourke+0.538
 Vand+0.526
$$+0.520
 「+0.518
Neg logit contributions
ahime-0.827
usterity-0.822
 Berks-0.761
groupon-0.744
Origin-0.730
Token an
Token ID281
Feature activation+1.05e+00

Pos logit contributions
 Deb+1.053
ourke+1.015
 Vand+0.997
$$+0.988
 「+0.986
Neg logit contributions
ahime-1.325
usterity-1.321
 Berks-1.211
groupon-1.183
adobe-1.161
Tokenf
Token ID69
Feature activation-3.22e+00

Pos logit contributions
ahime+1.213
usterity+1.212
 Berks+1.116
groupon+1.115
adobe+1.083
Neg logit contributions
 Deb-0.941
ourke-0.927
 Vand-0.897
 「-0.876
$$-0.866
Token4
Token ID19
Feature activation-2.47e+00

Pos logit contributions
ahime+2.634
usterity+2.614
 Berks+2.411
groupon+2.387
adobe+2.363
Neg logit contributions
 Deb-1.639
ourke-1.586
 Vand-1.545
$$-1.494
 「-1.489
Tokenb
Token ID65
Feature activation-4.26e+00

Pos logit contributions
ahime+1.694
usterity+1.671
 Berks+1.532
groupon+1.518
adobe+1.470
Neg logit contributions
 Deb-1.580
ourke-1.552
 Vand-1.522
 「-1.488
$$-1.484
Tokenbe
Token ID1350
Feature activation-2.81e+00

Pos logit contributions
ahime+3.102
usterity+3.098
groupon+2.896
fore+2.858
adobe+2.792
Neg logit contributions
 Deb-2.438
ourke-2.377
 Vand-2.346
Sov-2.336
 Lama-2.288
Token66
Token ID2791
Feature activation-3.53e+00

Pos logit contributions
ahime+2.221
usterity+2.192
 Berks+2.031
groupon+1.999
Origin+1.956
Neg logit contributions
 Deb-1.510
ourke-1.478
 Vand-1.415
 「-1.383
$$-1.380
Token IEEE
Token ID40552
Feature activation-7.73e+00

Pos logit contributions
ahime+2.252
usterity+2.232
 Berks+2.055
groupon+1.985
adobe+1.947
Neg logit contributions
ourke-2.361
 Deb-2.361
 Vand-2.263
$$-2.254
Sov-2.227
Token 802
Token ID33121
Feature activation-2.86e+00

Pos logit contributions
ahime+3.992
usterity+3.803
groupon+3.656
 Berks+3.536
Origin+3.505
Neg logit contributions
ourke-5.800
 Deb-5.716
Sov-5.597
 Lama-5.504
mble-5.497
Token.
Token ID13
Feature activation-7.57e-01

Pos logit contributions
ahime+1.705
usterity+1.705
groupon+1.607
Origin+1.547
 Berks+1.543
Neg logit contributions
 Deb-1.994
ourke-1.975
 Vand-1.909
 「-1.889
 Seah-1.854
Token11
Token ID1157
Feature activation-1.42e+00

Pos logit contributions
ahime+0.593
usterity+0.593
groupon+0.561
Origin+0.546
 Berks+0.545
Neg logit contributions
 Deb-0.403
ourke-0.388
 Vand-0.374
 「-0.369
 Lama-0.359
Tokenb
Token ID65
Feature activation-3.25e+00

Pos logit contributions
ahime+1.018
usterity+1.011
 Berks+0.927
groupon+0.904
Origin+0.886
Neg logit contributions
 Deb-0.878
ourke-0.851
 Vand-0.834
$$-0.825
 「-0.823
Tokengn
Token ID4593
Feature activation-1.40e+00

Pos logit contributions
usterity+1.160
ahime+1.155
groupon+0.963
 Berks+0.947
adobe+0.900
Neg logit contributions
 Deb-3.160
ourke-3.055
 Vand-3.038
 「-2.984
$$-2.974
Token year
Token ID614
Feature activation-1.75e+00

Pos logit contributions
ahime+0.533
usterity+0.532
 Berks+0.493
groupon+0.479
Origin+0.474
Neg logit contributions
 Deb-0.366
ourke-0.359
$$-0.346
 Vand-0.344
 「-0.340
Token both
Token ID1111
Feature activation-1.32e+00

Pos logit contributions
ahime+1.143
usterity+1.133
 Berks+1.033
groupon+1.005
Origin+0.984
Neg logit contributions
 Deb-1.177
ourke-1.151
 Vand-1.123
$$-1.117
 「-1.110
Token The
Token ID383
Feature activation-1.58e+00

Pos logit contributions
ahime+0.912
usterity+0.912
 Berks+0.839
groupon+0.816
Origin+0.801
Neg logit contributions
 Deb-0.830
ourke-0.820
$$-0.792
 Vand-0.788
 「-0.779
Token Terminator
Token ID41830
Feature activation-3.62e+00

Pos logit contributions
ahime+1.094
usterity+1.084
 Berks+1.005
groupon+0.966
Origin+0.955
Neg logit contributions
 Deb-0.987
ourke-0.971
$$-0.946
 「-0.935
 Vand-0.934
Token and
Token ID290
Feature activation-4.30e-01

Pos logit contributions
ahime+2.361
usterity+2.336
 Berks+2.117
groupon+2.079
Origin+2.043
Neg logit contributions
 Deb-2.359
ourke-2.335
 Vand-2.272
$$-2.260
Sov-2.200
Token Transformers
Token ID39185
Feature activation-7.67e+00

Pos logit contributions
ahime+0.317
usterity+0.315
 Berks+0.291
groupon+0.283
Origin+0.278
Neg logit contributions
 Deb-0.254
ourke-0.247
 Vand-0.241
$$-0.239
 「-0.238
Token debut
Token ID8886
Feature activation+9.30e-02

Pos logit contributions
usterity+4.704
ahime+4.671
Origin+4.285
 Berks+4.262
groupon+4.191
Neg logit contributions
ourke-4.929
 Deb-4.714
$$-4.665
 Vand-4.568
 Lama-4.499
Token.
Token ID13
Feature activation+2.64e-01

Pos logit contributions
 Deb+0.060
ourke+0.058
 Vand+0.057
$$+0.056
 「+0.056
Neg logit contributions
ahime-0.064
usterity-0.064
 Berks-0.058
groupon-0.057
adobe-0.056
Token
Token ID198
Feature activation-1.32e-01

Pos logit contributions
 Deb+0.149
ourke+0.143
 Vand+0.141
 「+0.139
$$+0.139
Neg logit contributions
ahime-0.204
usterity-0.203
 Berks-0.187
groupon-0.183
adobe-0.179
Token
Token ID198
Feature activation-2.25e-01

Pos logit contributions
ahime+0.095
usterity+0.095
 Berks+0.088
groupon+0.087
Origin+0.085
Neg logit contributions
 Deb-0.079
ourke-0.077
 Vand-0.075
 「-0.074
$$-0.074
TokenW
Token ID54
Feature activation-2.09e+00

Pos logit contributions
ahime+0.154
usterity+0.153
 Berks+0.139
groupon+0.137
Origin+0.135
Neg logit contributions
 Deb-0.146
ourke-0.142
 Vand-0.139
 「-0.137
$$-0.136
Token Has
Token ID7875
Feature activation-9.77e-01

Pos logit contributions
 Deb+0.133
ourke+0.130
 Vand+0.126
$$+0.125
 「+0.125
Neg logit contributions
ahime-0.164
usterity-0.163
 Berks-0.150
groupon-0.146
Origin-0.144
Tokenbro
Token ID7957
Feature activation-7.06e+00

Pos logit contributions
ahime+0.550
usterity+0.533
 Berks+0.481
groupon+0.470
Origin+0.460
Neg logit contributions
 Deb-0.751
ourke-0.741
$$-0.722
 Vand-0.721
 「-0.719
Token,
Token ID11
Feature activation+7.23e-03

Pos logit contributions
ahime+4.166
usterity+4.025
 Berks+3.844
Origin+3.705
groupon+3.641
Neg logit contributions
ourke-4.789
 Deb-4.779
 Vand-4.595
$$-4.588
Sov-4.549
Token Barbie
Token ID46829
Feature activation-3.71e+00

Pos logit contributions
 Deb+0.004
ourke+0.004
 Vand+0.004
$$+0.004
 「+0.004
Neg logit contributions
ahime-0.005
usterity-0.005
 Berks-0.005
groupon-0.005
Origin-0.005
Token,
Token ID11
Feature activation-8.11e-01

Pos logit contributions
ahime+2.217
usterity+2.213
 Berks+2.073
groupon+1.974
Origin+1.948
Neg logit contributions
 Deb-2.550
ourke-2.532
 Vand-2.466
$$-2.438
Sov-2.426
Token Lego
Token ID33198
Feature activation-7.67e+00

Pos logit contributions
ahime+0.576
usterity+0.570
 Berks+0.536
groupon+0.516
Origin+0.510
Neg logit contributions
ourke-0.488
 Deb-0.487
$$-0.468
 Vand-0.465
 「-0.463
Token,
Token ID11
Feature activation-8.09e-01

Pos logit contributions
ahime+4.290
usterity+4.262
 Berks+3.975
Origin+3.815
groupon+3.769
Neg logit contributions
ourke-5.382
 Deb-5.312
 Vand-5.136
$$-5.126
 「-5.084
Token Toys
Token ID35397
Feature activation-1.82e+00

Pos logit contributions
ahime+0.573
usterity+0.568
 Berks+0.534
groupon+0.514
Origin+0.508
Neg logit contributions
ourke-0.486
 Deb-0.486
$$-0.466
 Vand-0.463
 「-0.462
Token R
Token ID371
Feature activation+1.12e+00

Pos logit contributions
ahime+1.241
usterity+1.208
 Berks+1.131
groupon+1.109
Origin+1.090
Neg logit contributions
ourke-1.137
 Deb-1.137
 Vand-1.101
$$-1.088
 「-1.085
Token Us
Token ID4021
Feature activation-1.38e+00

Pos logit contributions
 Deb+0.583
ourke+0.561
 Vand+0.541
$$+0.540
 「+0.531
Neg logit contributions
ahime-0.918
usterity-0.906
 Berks-0.836
groupon-0.820
adobe-0.808
Token,
Token ID11
Feature activation-5.77e-01

Pos logit contributions
ahime+0.894
usterity+0.888
 Berks+0.811
groupon+0.787
Origin+0.775
Neg logit contributions
 Deb-0.938
ourke-0.916
 Vand-0.897
$$-0.887
 「-0.884
Token.
Token ID13
Feature activation-8.39e-01

Pos logit contributions
ahime+1.466
usterity+1.453
 Berks+1.328
groupon+1.282
adobe+1.250
Neg logit contributions
 Deb-1.555
ourke-1.521
$$-1.485
 Vand-1.480
 「-1.469
Token Though
Token ID7486
Feature activation-2.73e+00

Pos logit contributions
ahime+0.616
usterity+0.610
 Berks+0.570
groupon+0.555
Origin+0.544
Neg logit contributions
 Deb-0.486
ourke-0.485
 Vand-0.463
$$-0.460
 「-0.459
Token shows
Token ID2523
Feature activation-3.27e+00

Pos logit contributions
ahime+1.869
usterity+1.841
 Berks+1.696
groupon+1.652
Origin+1.621
Neg logit contributions
 Deb-1.721
ourke-1.708
$$-1.659
 Vand-1.655
 「-1.632
Token like
Token ID588
Feature activation+7.10e-01

Pos logit contributions
ahime+2.594
usterity+2.587
 Berks+2.412
groupon+2.353
Origin+2.327
Neg logit contributions
 Deb-1.660
ourke-1.637
 Vand-1.582
$$-1.567
 「-1.546
Token Or
Token ID1471
Feature activation-2.40e+00

Pos logit contributions
 Deb+0.475
ourke+0.459
 Vand+0.452
$$+0.447
 「+0.447
Neg logit contributions
ahime-0.474
usterity-0.470
 Berks-0.427
groupon-0.416
adobe-0.407
Tokenphan
Token ID19080
Feature activation-7.57e+00

Pos logit contributions
ahime+1.200
usterity+1.185
 Berks+1.044
groupon+1.006
Origin+0.977
Neg logit contributions
 Deb-1.994
ourke-1.943
 Vand-1.922
$$-1.914
 「-1.907
Token Black
Token ID2619
Feature activation-1.73e+00

Pos logit contributions
usterity+4.288
ahime+4.251
 Berks+4.059
groupon+3.770
Origin+3.770
Neg logit contributions
ourke-5.374
 Vand-5.206
Sov-5.160
 「-5.145
 Deb-5.140
Token and
Token ID290
Feature activation-7.90e-02

Pos logit contributions
ahime+1.165
usterity+1.158
 Berks+1.057
groupon+1.029
Origin+1.013
Neg logit contributions
 Deb-1.120
ourke-1.093
 Vand-1.069
$$-1.057
 「-1.050
Token The
Token ID383
Feature activation-2.64e+00

Pos logit contributions
ahime+0.055
usterity+0.055
 Berks+0.050
groupon+0.049
Origin+0.048
Neg logit contributions
 Deb-0.050
ourke-0.049
 Vand-0.048
$$-0.047
 「-0.047
Token Vampire
Token ID21463
Feature activation-3.77e+00

Pos logit contributions
usterity+1.701
ahime+1.692
 Berks+1.576
groupon+1.504
Origin+1.478
Neg logit contributions
ourke-1.744
 Deb-1.732
$$-1.684
 「-1.673
 Vand-1.671
Token Di
Token ID6031
Feature activation-3.62e+00

Pos logit contributions
usterity+2.047
ahime+2.013
 Berks+1.860
groupon+1.770
Origin+1.736
Neg logit contributions
 Deb-2.843
ourke-2.836
$$-2.738
Sov-2.735
 Vand-2.735
Token As
Token ID1081
Feature activation+5.42e-01

Pos logit contributions
 Deb+0.212
ourke+0.211
 Vand+0.201
$$+0.201
 「+0.200
Neg logit contributions
usterity-0.277
ahime-0.277
 Berks-0.258
groupon-0.251
Origin-0.245
Token far
Token ID1290
Feature activation-3.77e+00

Pos logit contributions
 Deb+0.329
ourke+0.322
 Vand+0.312
$$+0.311
 「+0.310
Neg logit contributions
ahime-0.390
usterity-0.389
 Berks-0.357
groupon-0.348
Origin-0.340
Token as
Token ID355
Feature activation+1.46e+00

Pos logit contributions
ahime+2.125
usterity+2.113
 Berks+1.909
groupon+1.841
Origin+1.786
Neg logit contributions
 Deb-2.841
ourke-2.791
 Vand-2.747
$$-2.721
 「-2.715
Token I
Token ID314
Feature activation-5.10e-01

Pos logit contributions
 Deb+0.873
ourke+0.838
 Vand+0.826
$$+0.814
 「+0.813
Neg logit contributions
ahime-1.079
usterity-1.070
 Berks-0.980
groupon-0.958
adobe-0.943
Token can
Token ID460
Feature activation-1.85e+00

Pos logit contributions
ahime+0.320
usterity+0.318
 Berks+0.288
groupon+0.279
Origin+0.273
Neg logit contributions
 Deb-0.360
ourke-0.350
 Vand-0.344
$$-0.341
 「-0.340
Token tell
Token ID1560
Feature activation-7.54e+00

Pos logit contributions
usterity+1.142
ahime+1.125
 Berks+1.028
groupon+0.999
trust+0.977
Neg logit contributions
 Deb-1.292
ourke-1.282
 Vand-1.246
$$-1.226
 「-1.220
Token,
Token ID11
Feature activation-9.51e-01

Pos logit contributions
usterity+4.125
ahime+4.011
 Berks+3.849
groupon+3.619
fore+3.536
Neg logit contributions
ourke-5.481
 Deb-5.303
$$-5.246
Sov-5.165
 Vand-5.162
Token there
Token ID612
Feature activation+2.05e+00

Pos logit contributions
usterity+0.661
ahime+0.659
 Berks+0.613
groupon+0.594
Origin+0.577
Neg logit contributions
 Deb-0.586
ourke-0.583
$$-0.559
 Vand-0.556
 「-0.554
Token are
Token ID389
Feature activation-1.26e+00

Pos logit contributions
 Deb+1.216
ourke+1.172
 Vand+1.147
$$+1.138
 「+1.138
Neg logit contributions
ahime-1.532
usterity-1.520
 Berks-1.395
groupon-1.361
adobe-1.339
Token three
Token ID1115
Feature activation-9.73e-01

Pos logit contributions
usterity+0.864
ahime+0.863
 Berks+0.800
groupon+0.771
Origin+0.752
Neg logit contributions
 Deb-0.787
ourke-0.785
$$-0.753
 Vand-0.749
 「-0.745
Token big
Token ID1263
Feature activation+3.78e-01

Pos logit contributions
usterity+0.649
ahime+0.647
 Berks+0.595
groupon+0.578
Origin+0.560
Neg logit contributions
 Deb-0.633
ourke-0.628
$$-0.605
 Vand-0.602
 「-0.598
Token prev
Token ID8654
Feature activation-9.96e-01

Pos logit contributions
ahime+1.726
usterity+1.691
 Berks+1.571
Origin+1.533
groupon+1.512
Neg logit contributions
 Deb-1.404
ourke-1.402
 Vand-1.347
 「-1.335
$$-1.318
Token_
Token ID62
Feature activation-1.18e+00

Pos logit contributions
ahime+0.678
usterity+0.674
 Berks+0.615
groupon+0.601
Origin+0.593
Neg logit contributions
 Deb-0.642
ourke-0.629
 Vand-0.614
 「-0.606
$$-0.605
Tokenstate
Token ID5219
Feature activation+9.72e-01

Pos logit contributions
ahime+0.905
usterity+0.896
 Berks+0.826
groupon+0.814
Origin+0.801
Neg logit contributions
 Deb-0.665
ourke-0.646
 Vand-0.630
 「-0.620
$$-0.614
Token :
Token ID1058
Feature activation-5.66e+00

Pos logit contributions
 Deb+0.643
ourke+0.621
 Vand+0.611
$$+0.606
 「+0.605
Neg logit contributions
ahime-0.655
usterity-0.651
 Berks-0.592
groupon-0.577
adobe-0.565
Token Option
Token ID16018
Feature activation-7.48e-01

Pos logit contributions
ahime+3.857
usterity+3.760
 Berks+3.607
groupon+3.431
Origin+3.391
Neg logit contributions
ourke-3.472
 Deb-3.331
Sov-3.287
 Vand-3.266
$$-3.211
Token <
Token ID1279
Feature activation-7.47e+00

Pos logit contributions
ahime+0.453
usterity+0.450
 Berks+0.405
groupon+0.393
adobe+0.383
Neg logit contributions
 Deb-0.545
ourke-0.530
 Vand-0.521
$$-0.517
 「-0.516
Token Arc
Token ID10173
Feature activation+1.39e+00

Pos logit contributions
ahime+4.137
usterity+4.136
 Berks+3.893
Origin+3.806
groupon+3.715
Neg logit contributions
ourke-5.280
 Deb-5.137
 Vand-5.034
Sov-4.995
 「-4.985
Token <
Token ID1279
Feature activation-3.49e+00

Pos logit contributions
 Deb+0.841
ourke+0.807
 Vand+0.793
$$+0.785
 「+0.783
Neg logit contributions
ahime-1.013
usterity-1.007
 Berks-0.924
groupon-0.902
adobe-0.882
Token Board
Token ID5926
Feature activation-1.06e+00

Pos logit contributions
ahime+2.413
usterity+2.399
 Berks+2.270
groupon+2.181
Origin+2.170
Neg logit contributions
ourke-2.104
 Deb-2.061
 「-1.997
 Vand-1.995
$$-1.981
Token >>
Token ID9609
Feature activation-3.65e+00

Pos logit contributions
ahime+0.786
usterity+0.783
 Berks+0.724
groupon+0.706
Origin+0.704
Neg logit contributions
 Deb-0.608
ourke-0.598
 Vand-0.580
 「-0.574
$$-0.571
Token,
Token ID837
Feature activation-4.01e+00

Pos logit contributions
ahime+2.290
usterity+2.278
 Berks+2.088
groupon+2.005
Origin+2.002
Neg logit contributions
 Deb-2.481
ourke-2.439
 Vand-2.389
$$-2.349
 「-2.348
Token "
Token ID366
Feature activation-2.39e+00

Pos logit contributions
ahime+1.974
usterity+1.965
 Berks+1.808
groupon+1.807
Origin+1.775
Neg logit contributions
ourke-1.925
 Deb-1.909
 Vand-1.824
Sov-1.805
$$-1.792
Token--
Token ID438
Feature activation-7.76e-02

Pos logit contributions
usterity+1.734
ahime+1.733
groupon+1.605
 Berks+1.583
Origin+1.568
Neg logit contributions
 Deb-1.436
ourke-1.389
 Vand-1.338
 「-1.330
 Lama-1.296
Tokenimages
Token ID17566
Feature activation+4.82e-01

Pos logit contributions
ahime+0.045
usterity+0.045
 Berks+0.040
groupon+0.039
Origin+0.038
Neg logit contributions
 Deb-0.059
ourke-0.057
 Vand-0.056
 「-0.056
$$-0.055
Token",
Token ID1600
Feature activation-2.10e+00

Pos logit contributions
 Deb+0.305
ourke+0.296
 Vand+0.290
 「+0.287
$$+0.286
Neg logit contributions
ahime-0.337
usterity-0.336
 Berks-0.306
groupon-0.300
Origin-0.294
Token required
Token ID2672
Feature activation-2.06e+00

Pos logit contributions
ahime+1.442
usterity+1.437
 Berks+1.322
groupon+1.281
Origin+1.257
Neg logit contributions
 Deb-1.340
ourke-1.321
 Vand-1.269
$$-1.254
 「-1.247
Token=
Token ID28
Feature activation-7.42e+00

Pos logit contributions
usterity+1.092
ahime+1.091
groupon+0.993
Origin+0.968
 Berks+0.967
Neg logit contributions
 Deb-1.597
ourke-1.579
 Vand-1.541
 「-1.525
 Lama-1.498
TokenTrue
Token ID17821
Feature activation-4.42e+00

Pos logit contributions
Origin+2.749
groupon+2.623
usterity+2.533
ahime+2.410
fore+2.326
Neg logit contributions
ourke-6.720
 ende-6.622
 Deb-6.609
mble-6.591
 unden-6.539
Token,
Token ID11
Feature activation-5.50e+00

Pos logit contributions
usterity+2.262
ahime+2.230
groupon+2.137
Origin+2.046
fore+2.015
Neg logit contributions
ourke-3.346
 Deb-3.317
 Vand-3.259
 unden-3.199
 Seah-3.197
Token help
Token ID1037
Feature activation-2.01e+00

Pos logit contributions
usterity+3.166
ahime+2.991
groupon+2.812
 Berks+2.805
Origin+2.718
Neg logit contributions
ourke-3.916
 Deb-3.878
 Vand-3.806
Sov-3.759
 「-3.690
Token="
Token ID2625
Feature activation-3.62e+00

Pos logit contributions
ahime+1.364
usterity+1.361
groupon+1.256
 Berks+1.238
Origin+1.238
Neg logit contributions
 Deb-1.264
ourke-1.243
 Vand-1.215
 「-1.173
 Lama-1.163
Tokenpath
Token ID6978
Feature activation-1.26e+00

Pos logit contributions
ahime+1.417
usterity+1.387
groupon+1.264
Origin+1.185
fore+1.180
Neg logit contributions
 Deb-3.397
 Vand-3.273
ourke-3.253
 「-3.213
 Seah-3.199
Tokenbind
Token ID21653
Feature activation+8.82e-01

Pos logit contributions
ahime+0.012
usterity+0.012
 Berks+0.011
groupon+0.011
Origin+0.011
Neg logit contributions
 Deb-0.012
ourke-0.012
 Vand-0.011
 「-0.011
$$-0.011
Token directive
Token ID22644
Feature activation-1.78e+00

Pos logit contributions
 Deb+0.603
ourke+0.585
 Vand+0.575
$$+0.570
 「+0.569
Neg logit contributions
ahime-0.573
usterity-0.568
 Berks-0.516
groupon-0.502
adobe-0.491
Token:
Token ID25
Feature activation-1.38e+00

Pos logit contributions
ahime+1.200
usterity+1.186
 Berks+1.100
groupon+1.062
Origin+1.050
Neg logit contributions
 Deb-1.146
ourke-1.126
 Vand-1.092
$$-1.074
Sov-1.068
Token
Token ID198
Feature activation+2.80e-01

Pos logit contributions
ahime+1.009
usterity+1.008
 Berks+0.929
groupon+0.904
Origin+0.892
Neg logit contributions
 Deb-0.823
ourke-0.801
 Vand-0.780
$$-0.766
 「-0.761
Token
Token ID198
Feature activation+6.15e-01

Pos logit contributions
 Deb+0.164
ourke+0.159
 Vand+0.155
 「+0.153
$$+0.153
Neg logit contributions
ahime-0.207
usterity-0.207
 Berks-0.190
groupon-0.187
Origin-0.184
Token<
Token ID27
Feature activation-7.29e+00

Pos logit contributions
 Deb+0.406
ourke+0.393
 Vand+0.386
 「+0.381
$$+0.380
Neg logit contributions
ahime-0.415
usterity-0.412
 Berks-0.375
groupon-0.367
Origin-0.359
Tokenbody
Token ID2618
Feature activation-2.19e-01

Pos logit contributions
ahime+4.063
usterity+4.026
fore+3.711
groupon+3.642
Origin+3.584
Neg logit contributions
 Deb-5.371
ourke-5.278
 Vand-5.241
 「-5.054
 Rover-4.972
Token ng
Token ID23370
Feature activation+3.49e-01

Pos logit contributions
ahime+0.166
usterity+0.165
 Berks+0.152
groupon+0.148
adobe+0.145
Neg logit contributions
 Deb-0.126
ourke-0.122
 Vand-0.119
$$-0.118
 「-0.118
Token-
Token ID12
Feature activation+5.35e-02

Pos logit contributions
 Deb+0.274
ourke+0.267
 Vand+0.263
 「+0.260
$$+0.260
Neg logit contributions
ahime-0.191
usterity-0.190
 Berks-0.169
groupon-0.165
Origin-0.160
Tokencontroller
Token ID36500
Feature activation+9.28e-01

Pos logit contributions
 Deb+0.044
ourke+0.043
 Vand+0.042
 「+0.042
$$+0.041
Neg logit contributions
ahime-0.028
usterity-0.027
 Berks-0.024
groupon-0.024
Origin-0.023
Token="
Token ID2625
Feature activation-4.78e+00

Pos logit contributions
 Deb+0.505
ourke+0.485
$$+0.477
 Vand+0.473
 「+0.473
Neg logit contributions
ahime-0.732
usterity-0.730
 Berks-0.672
groupon-0.656
adobe-0.648
Token Angular
Token ID28147
Feature activation-2.72e+00

Pos logit contributions
ahime+0.469
usterity+0.467
 Berks+0.431
groupon+0.420
Origin+0.413
Neg logit contributions
 Deb-0.389
ourke-0.380
 Vand-0.368
$$-0.365
 「-0.363
Token tutorial
Token ID11808
Feature activation+1.29e+00

Pos logit contributions
ahime+1.953
usterity+1.939
 Berks+1.799
Origin+1.741
groupon+1.736
Neg logit contributions
 Deb-1.611
ourke-1.588
 Vand-1.554
 「-1.520
$$-1.516
Token:
Token ID25
Feature activation+1.61e-01

Pos logit contributions
 Deb+0.815
ourke+0.792
 Vand+0.775
$$+0.767
 「+0.765
Neg logit contributions
ahime-0.907
usterity-0.900
 Berks-0.824
groupon-0.803
Origin-0.787
Token
Token ID198
Feature activation+1.55e+00

Pos logit contributions
 Deb+0.094
ourke+0.091
 Vand+0.089
$$+0.088
 「+0.087
Neg logit contributions
ahime-0.120
usterity-0.119
 Berks-0.110
groupon-0.107
Origin-0.105
Token
Token ID198
Feature activation+1.64e+00

Pos logit contributions
 Deb+0.878
ourke+0.845
 Vand+0.828
$$+0.823
 「+0.818
Neg logit contributions
ahime-1.197
usterity-1.188
 Berks-1.095
groupon-1.064
adobe-1.047
Token<
Token ID27
Feature activation-7.28e+00

Pos logit contributions
 Deb+1.024
ourke+0.992
 Vand+0.972
$$+0.964
 「+0.961
Neg logit contributions
ahime-1.164
usterity-1.155
 Berks-1.059
groupon-1.031
adobe-1.010
Tokenbody
Token ID2618
Feature activation+8.12e-01

Pos logit contributions
ahime+4.602
usterity+4.549
groupon+4.110
fore+4.096
 Berks+4.089
Neg logit contributions
 Deb-4.826
ourke-4.808
 Vand-4.696
 「-4.591
 Lama-4.489
Token ng
Token ID23370
Feature activation+2.87e-01

Pos logit contributions
 Deb+0.511
ourke+0.492
 Vand+0.485
$$+0.483
 「+0.482
Neg logit contributions
ahime-0.573
usterity-0.570
 Berks-0.523
groupon-0.505
adobe-0.498
Token-
Token ID12
Feature activation+2.85e-01

Pos logit contributions
 Deb+0.217
ourke+0.210
 Vand+0.208
$$+0.207
 「+0.206
Neg logit contributions
ahime-0.167
usterity-0.165
 Berks-0.147
groupon-0.142
adobe-0.140
Tokencontroller
Token ID36500
Feature activation+1.32e+00

Pos logit contributions
 Deb+0.182
ourke+0.176
 Vand+0.173
$$+0.171
 「+0.171
Neg logit contributions
ahime-0.199
usterity-0.197
 Berks-0.180
groupon-0.176
Origin-0.172
Token="
Token ID2625
Feature activation-5.30e+00

Pos logit contributions
 Deb+0.741
ourke+0.711
 Vand+0.699
$$+0.693
 「+0.689
Neg logit contributions
ahime-1.024
usterity-1.019
 Berks-0.938
groupon-0.917
adobe-0.902
Token episode
Token ID4471
Feature activation-1.41e+00

Pos logit contributions
ahime+0.012
usterity+0.012
 Berks+0.011
groupon+0.010
Origin+0.010
Neg logit contributions
 Deb-0.010
ourke-0.009
 Vand-0.009
$$-0.009
 「-0.009
Token was
Token ID373
Feature activation+1.16e+00

Pos logit contributions
ahime+0.976
usterity+0.965
 Berks+0.893
groupon+0.864
Origin+0.851
Neg logit contributions
 Deb-0.885
ourke-0.874
 Vand-0.843
$$-0.840
 「-0.829
Token a
Token ID257
Feature activation+1.14e+00

Pos logit contributions
 Deb+0.718
ourke+0.690
 Vand+0.680
 「+0.673
$$+0.671
Neg logit contributions
ahime-0.828
usterity-0.823
 Berks-0.752
groupon-0.735
adobe-0.721
Token little
Token ID1310
Feature activation-9.72e-01

Pos logit contributions
 Deb+0.685
ourke+0.662
 Vand+0.649
$$+0.642
 「+0.641
Neg logit contributions
ahime-0.834
usterity-0.827
 Berks-0.760
groupon-0.742
adobe-0.728
Token TO
Token ID5390
Feature activation-8.73e-01

Pos logit contributions
usterity+0.666
ahime+0.664
 Berks+0.611
groupon+0.588
Origin+0.579
Neg logit contributions
 Deb-0.620
ourke-0.608
 Vand-0.589
$$-0.588
 「-0.582
TokenO
Token ID46
Feature activation-7.18e+00

Pos logit contributions
ahime+0.726
usterity+0.721
 Berks+0.671
groupon+0.654
Origin+0.648
Neg logit contributions
 Deb-0.433
ourke-0.415
 Vand-0.409
 「-0.400
$$-0.398
Token simple
Token ID2829
Feature activation+1.52e+00

Pos logit contributions
ahime+4.590
usterity+4.583
 Berks+4.232
fore+4.020
Origin+3.988
Neg logit contributions
 Deb-4.624
ourke-4.621
$$-4.438
 Vand-4.415
Sov-4.382
Token [
Token ID685
Feature activation+1.51e+00

Pos logit contributions
 Deb+0.957
ourke+0.923
 Vand+0.908
$$+0.901
 「+0.900
Neg logit contributions
ahime-1.065
usterity-1.060
 Berks-0.968
groupon-0.942
adobe-0.927
Tokenlaughs
Token ID28124
Feature activation-2.20e+00

Pos logit contributions
 Deb+1.084
ourke+1.055
 Vand+1.036
$$+1.032
 「+1.027
Neg logit contributions
ahime-0.930
usterity-0.924
 Berks-0.833
groupon-0.805
adobe-0.788
Token].
Token ID4083
Feature activation-7.18e-01

Pos logit contributions
usterity+1.787
ahime+1.773
 Berks+1.665
groupon+1.617
Origin+1.600
Neg logit contributions
 Deb-1.103
ourke-1.084
 Vand-1.042
 「-1.028
$$-1.026
Token
Token ID198
Feature activation-1.27e+00

Pos logit contributions
ahime+0.515
usterity+0.513
 Berks+0.480
groupon+0.466
Origin+0.457
Neg logit contributions
ourke-0.427
 Deb-0.423
 Vand-0.402
$$-0.401
 「-0.398
Token
Token ID198
Feature activation+7.90e-01

Pos logit contributions
 Deb+0.447
ourke+0.434
 Vand+0.424
 「+0.418
$$+0.418
Neg logit contributions
ahime-0.575
usterity-0.573
 Berks-0.528
groupon-0.518
Origin-0.508
Tokenpub
Token ID12984
Feature activation-3.62e+00

Pos logit contributions
 Deb+0.514
ourke+0.497
 Vand+0.489
 「+0.483
$$+0.481
Neg logit contributions
ahime-0.541
usterity-0.537
 Berks-0.489
groupon-0.479
Origin-0.469
Token struct
Token ID2878
Feature activation-3.05e+00

Pos logit contributions
ahime+2.758
usterity+2.753
 Berks+2.553
groupon+2.493
Origin+2.471
Neg logit contributions
 Deb-1.999
ourke-1.967
 Vand-1.888
$$-1.877
 「-1.873
Token Own
Token ID11744
Feature activation-6.48e-01

Pos logit contributions
ahime+2.265
usterity+2.235
 Berks+2.113
groupon+2.040
Origin+2.017
Neg logit contributions
ourke-1.723
 Deb-1.700
$$-1.635
 Vand-1.621
Sov-1.619
Tokened
Token ID276
Feature activation-2.34e+00

Pos logit contributions
ahime+0.331
usterity+0.327
 Berks+0.290
groupon+0.279
Origin+0.272
Neg logit contributions
 Deb-0.532
ourke-0.520
 Vand-0.512
$$-0.508
 「-0.507
Token <
Token ID1279
Feature activation-7.18e+00

Pos logit contributions
ahime+1.472
usterity+1.455
 Berks+1.315
groupon+1.290
Origin+1.289
Neg logit contributions
 Deb-1.636
ourke-1.594
 Vand-1.561
$$-1.542
 「-1.536
Token T
Token ID309
Feature activation+1.36e+00

Pos logit contributions
usterity+4.742
ahime+4.723
 Berks+4.456
Origin+4.419
groupon+4.331
Neg logit contributions
ourke-4.329
 Deb-4.267
 「-4.159
 Vand-4.136
Sov-4.071
Token >
Token ID1875
Feature activation-4.68e+00

Pos logit contributions
 Deb+0.825
ourke+0.795
 Vand+0.777
$$+0.770
 「+0.766
Neg logit contributions
ahime-0.987
usterity-0.983
 Berks-0.901
groupon-0.880
adobe-0.859
Token {
Token ID1391
Feature activation-4.20e+00

Pos logit contributions
ahime+2.790
usterity+2.726
 Berks+2.530
Origin+2.435
groupon+2.417
Neg logit contributions
 Deb-3.254
ourke-3.243
 Vand-3.146
Sov-3.139
$$-3.136
Token...
Token ID2644
Feature activation-2.47e+00

Pos logit contributions
usterity+2.729
ahime+2.728
 Berks+2.506
Origin+2.446
groupon+2.438
Neg logit contributions
ourke-2.714
 Deb-2.697
 「-2.604
 Vand-2.603
Sov-2.595
Token }
Token ID1782
Feature activation+1.36e-01

Pos logit contributions
ahime+1.513
usterity+1.491
 Berks+1.366
groupon+1.314
Origin+1.302
Neg logit contributions
 Deb-1.738
ourke-1.719
 Vand-1.672
 「-1.660
$$-1.659
Token I
Token ID314
Feature activation-9.59e-01

Pos logit contributions
ahime+1.136
usterity+1.134
 Berks+1.047
groupon+1.013
Origin+0.993
Neg logit contributions
 Deb-1.091
ourke-1.068
$$-1.039
 Vand-1.038
 「-1.031
Token am
Token ID716
Feature activation-7.66e-01

Pos logit contributions
ahime+0.665
usterity+0.663
 Berks+0.608
groupon+0.593
Origin+0.581
Neg logit contributions
 Deb-0.605
ourke-0.589
 Vand-0.574
$$-0.570
 「-0.565
Token against
Token ID1028
Feature activation+5.63e-03

Pos logit contributions
ahime+0.553
usterity+0.553
 Berks+0.510
groupon+0.494
Origin+0.486
Neg logit contributions
 Deb-0.458
ourke-0.446
 Vand-0.434
$$-0.434
 「-0.432
Token the
Token ID262
Feature activation-9.62e-01

Pos logit contributions
 Deb+0.004
ourke+0.003
 Vand+0.003
$$+0.003
 「+0.003
Neg logit contributions
ahime-0.004
usterity-0.004
 Berks-0.004
groupon-0.003
Origin-0.003
Token First
Token ID3274
Feature activation-1.65e+00

Pos logit contributions
ahime+0.650
usterity+0.650
 Berks+0.595
groupon+0.575
Origin+0.566
Neg logit contributions
 Deb-0.624
ourke-0.608
$$-0.593
 Vand-0.590
 「-0.588
Token Amendment
Token ID8441
Feature activation-7.17e+00

Pos logit contributions
ahime+1.193
usterity+1.187
 Berks+1.087
groupon+1.061
adobe+1.040
Neg logit contributions
 Deb-1.011
ourke-0.975
 Vand-0.958
$$-0.948
 「-0.944
Token.
Token ID13
Feature activation-1.42e+00

Pos logit contributions
usterity+4.115
ahime+4.098
Origin+3.620
 Berks+3.618
groupon+3.613
Neg logit contributions
 Deb-4.970
ourke-4.938
 Vand-4.801
Sov-4.724
$$-4.722
Token My
Token ID2011
Feature activation-1.66e+00

Pos logit contributions
ahime+1.051
usterity+1.050
 Berks+0.978
groupon+0.951
Origin+0.934
Neg logit contributions
 Deb-0.819
ourke-0.809
 Vand-0.778
$$-0.775
 「-0.772
Token tweets
Token ID12665
Feature activation-1.05e+00

Pos logit contributions
ahime+1.190
usterity+1.189
 Berks+1.096
groupon+1.061
Origin+1.048
Neg logit contributions
 Deb-1.001
ourke-0.980
$$-0.959
 Vand-0.953
 「-0.942
Token reflected
Token ID12548
Feature activation+3.57e-01

Pos logit contributions
ahime+0.721
usterity+0.719
 Berks+0.658
groupon+0.642
Origin+0.630
Neg logit contributions
 Deb-0.672
ourke-0.659
 Vand-0.643
$$-0.636
 「-0.632
Token my
Token ID616
Feature activation-4.45e-01

Pos logit contributions
 Deb+0.218
ourke+0.212
 Vand+0.207
$$+0.206
 「+0.205
Neg logit contributions
ahime-0.256
usterity-0.255
 Berks-0.234
groupon-0.228
Origin-0.224
Token:
Token ID25
Feature activation+2.10e+00

Pos logit contributions
ahime+0.100
usterity+0.100
 Berks+0.091
groupon+0.089
Origin+0.087
Neg logit contributions
 Deb-0.091
ourke-0.088
 Vand-0.086
$$-0.085
 「-0.085
Token
Token ID198
Feature activation+2.32e+00

Pos logit contributions
 Deb+1.226
ourke+1.172
 Vand+1.160
 「+1.146
$$+1.146
Neg logit contributions
ahime-1.588
usterity-1.572
 Berks-1.443
groupon-1.414
adobe-1.385
Token
Token ID198
Feature activation+2.48e+00

Pos logit contributions
 Deb+1.283
ourke+1.223
$$+1.205
 Vand+1.205
 「+1.191
Neg logit contributions
ahime-1.830
usterity-1.812
 Berks-1.670
groupon-1.613
adobe-1.591
TokenOwn
Token ID23858
Feature activation+2.72e-01

Pos logit contributions
 Deb+1.634
ourke+1.592
$$+1.571
 Vand+1.555
 「+1.543
Neg logit contributions
ahime-1.662
usterity-1.642
 Berks-1.506
groupon-1.445
adobe-1.413
Tokened
Token ID276
Feature activation-1.70e+00

Pos logit contributions
 Deb+0.198
ourke+0.193
 Vand+0.189
$$+0.188
 「+0.187
Neg logit contributions
ahime-0.165
usterity-0.164
 Berks-0.148
groupon-0.143
Origin-0.140
Token<
Token ID27
Feature activation-7.14e+00

Pos logit contributions
ahime+1.195
usterity+1.188
 Berks+1.093
groupon+1.060
Origin+1.053
Neg logit contributions
 Deb-1.047
ourke-1.031
 Vand-0.999
 「-0.983
$$-0.982
TokenT
Token ID51
Feature activation-9.21e-02

Pos logit contributions
usterity+4.822
ahime+4.793
 Berks+4.500
Origin+4.468
groupon+4.419
Neg logit contributions
ourke-4.315
 Deb-4.196
 「-4.082
 Vand-4.072
 airst-4.006
Token>
Token ID29
Feature activation-3.77e+00

Pos logit contributions
ahime+0.062
usterity+0.062
 Berks+0.056
groupon+0.055
Origin+0.054
Neg logit contributions
 Deb-0.061
ourke-0.059
 Vand-0.058
$$-0.057
 「-0.057
Token,
Token ID837
Feature activation-3.70e+00

Pos logit contributions
ahime+2.452
usterity+2.428
 Berks+2.267
groupon+2.180
Origin+2.172
Neg logit contributions
 Deb-2.440
ourke-2.422
 Vand-2.346
 「-2.324
$$-2.316
Token akin
Token ID22107
Feature activation+1.02e+00

Pos logit contributions
ahime+2.563
usterity+2.531
 Berks+2.384
groupon+2.280
trust+2.268
Neg logit contributions
ourke-2.248
 Deb-2.237
 Vand-2.140
Sov-2.137
$$-2.130
Token to
Token ID284
Feature activation+1.92e+00

Pos logit contributions
 Deb+0.555
ourke+0.535
 Vand+0.521
 「+0.518
$$+0.517
Neg logit contributions
ahime-0.814
usterity-0.806
 Berks-0.745
groupon-0.730
adobe-0.717
TokenProperty
Token ID21746
Feature activation-2.26e-01

Pos logit contributions
 Deb+0.376
$$+0.355
ourke+0.354
 Vand+0.353
 「+0.352
Neg logit contributions
ahime-0.488
usterity-0.478
 Berks-0.441
groupon-0.429
adobe-0.420
Token '
Token ID705
Feature activation-2.28e+00

Pos logit contributions
ahime+0.166
usterity+0.164
 Berks+0.151
groupon+0.147
adobe+0.144
Neg logit contributions
 Deb-0.137
ourke-0.132
 Vand-0.129
$$-0.128
 「-0.128
TokenH
Token ID39
Feature activation-1.56e+00

Pos logit contributions
ahime+1.528
usterity+1.522
 Berks+1.374
groupon+1.360
Origin+1.342
Neg logit contributions
 Deb-1.508
ourke-1.465
 Vand-1.440
 「-1.421
$$-1.399
TokenKC
Token ID36222
Feature activation-1.28e+00

Pos logit contributions
ahime+1.026
usterity+1.017
 Berks+0.922
groupon+0.908
Origin+0.894
Neg logit contributions
 Deb-1.058
ourke-1.020
 Vand-1.005
 「-0.997
$$-0.983
TokenU
Token ID52
Feature activation+8.22e-02

Pos logit contributions
ahime+0.968
usterity+0.963
 Berks+0.887
groupon+0.869
Origin+0.854
Neg logit contributions
 Deb-0.734
ourke-0.710
 Vand-0.694
 「-0.684
$$-0.681
Token:\
Token ID7479
Feature activation-7.11e+00

Pos logit contributions
 Deb+0.058
ourke+0.056
 Vand+0.055
$$+0.054
 「+0.054
Neg logit contributions
ahime-0.052
usterity-0.052
 Berks-0.047
groupon-0.045
Origin-0.044
TokenControl
Token ID15988
Feature activation-5.65e-01

Pos logit contributions
usterity+4.935
ahime+4.899
Origin+4.654
groupon+4.554
 Berks+4.539
Neg logit contributions
 Deb-4.242
ourke-4.226
 Vand-4.027
 「-3.983
 Lama-3.968
Token Panel
Token ID18810
Feature activation-3.05e-01

Pos logit contributions
usterity+0.324
ahime+0.324
 Berks+0.292
groupon+0.285
Origin+0.282
Neg logit contributions
 Deb-0.419
ourke-0.416
 Vand-0.410
 「-0.403
$$-0.398
Token\
Token ID59
Feature activation-5.97e+00

Pos logit contributions
ahime+0.199
usterity+0.198
 Berks+0.180
groupon+0.175
Origin+0.172
Neg logit contributions
 Deb-0.207
ourke-0.202
 Vand-0.198
$$-0.195
 「-0.195
TokenDesktop
Token ID36881
Feature activation+1.08e+00

Pos logit contributions
ahime+3.953
usterity+3.893
Origin+3.708
groupon+3.595
 Berks+3.570
Neg logit contributions
 Deb-3.831
ourke-3.738
 Vand-3.637
 「-3.623
 Lama-3.609
Token'
Token ID6
Feature activation-3.21e-01

Pos logit contributions
 Deb+0.667
ourke+0.644
 Vand+0.632
$$+0.629
 「+0.625
Neg logit contributions
ahime-0.777
usterity-0.770
 Berks-0.707
groupon-0.688
adobe-0.675
Token relay
Token ID24248
Feature activation+1.33e+00

Pos logit contributions
 Deb+0.337
ourke+0.328
$$+0.319
 Vand+0.318
 「+0.316
Neg logit contributions
ahime-0.392
usterity-0.388
 Berks-0.358
groupon-0.347
Origin-0.341
Token network
Token ID3127
Feature activation-2.31e+00

Pos logit contributions
 Deb+0.822
ourke+0.796
 Vand+0.780
$$+0.773
 「+0.771
Neg logit contributions
ahime-0.948
usterity-0.941
 Berks-0.863
groupon-0.841
Origin-0.824
Token protocol
Token ID8435
Feature activation-2.51e+00

Pos logit contributions
ahime+1.553
usterity+1.517
 Berks+1.400
groupon+1.357
Origin+1.329
Neg logit contributions
 Deb-1.511
ourke-1.471
 Vand-1.434
$$-1.428
 「-1.424
Token or
Token ID393
Feature activation+4.67e-01

Pos logit contributions
ahime+1.657
usterity+1.610
 Berks+1.493
groupon+1.447
adobe+1.417
Neg logit contributions
 Deb-1.663
ourke-1.618
 Vand-1.589
 「-1.572
$$-1.567
Token I
Token ID314
Feature activation-7.01e-01

Pos logit contributions
 Deb+0.295
ourke+0.286
 Vand+0.280
$$+0.278
 「+0.277
Neg logit contributions
ahime-0.327
usterity-0.325
 Berks-0.298
groupon-0.290
Origin-0.284
TokenBL
Token ID9148
Feature activation-7.07e+00

Pos logit contributions
ahime+0.360
usterity+0.354
 Berks+0.317
groupon+0.300
Origin+0.298
Neg logit contributions
 Deb-0.573
ourke-0.554
 Vand-0.552
 「-0.546
$$-0.545
TokenT
Token ID51
Feature activation-3.47e-01

Pos logit contributions
ahime+4.846
usterity+4.563
 Berks+4.233
groupon+4.230
trust+4.148
Neg logit contributions
 Deb-4.426
 「-4.265
 Fey-4.155
 Vand-4.127
$$-4.113
Token)
Token ID8
Feature activation+7.37e-02

Pos logit contributions
ahime+0.234
usterity+0.231
 Berks+0.212
groupon+0.206
Origin+0.202
Neg logit contributions
 Deb-0.228
ourke-0.221
 Vand-0.217
$$-0.215
 「-0.215
Token and
Token ID290
Feature activation+6.44e-01

Pos logit contributions
 Deb+0.046
ourke+0.045
 Vand+0.044
$$+0.044
 「+0.044
Neg logit contributions
ahime-0.052
usterity-0.051
 Berks-0.047
groupon-0.046
adobe-0.045
Token move
Token ID1445
Feature activation-1.17e+00

Pos logit contributions
 Deb+0.420
ourke+0.408
 Vand+0.399
$$+0.396
 「+0.395
Neg logit contributions
ahime-0.437
usterity-0.434
 Berks-0.397
groupon-0.386
Origin-0.378
Token virtually
Token ID9826
Feature activation+3.26e+00

Pos logit contributions
ahime+0.807
usterity+0.796
 Berks+0.740
groupon+0.715
Origin+0.704
Neg logit contributions
 Deb-0.737
ourke-0.727
$$-0.702
 Vand-0.701
 「-0.693
Tokenset
Token ID2617
Feature activation+1.54e+00

Pos logit contributions
 Deb+0.935
ourke+0.914
 Vand+0.902
$$+0.899
 「+0.894
Neg logit contributions
ahime-0.488
usterity-0.485
 Berks-0.420
groupon-0.403
Origin-0.389
Token dir
Token ID26672
Feature activation+1.35e+00

Pos logit contributions
 Deb+1.017
ourke+0.985
 Vand+0.969
$$+0.961
 「+0.958
Neg logit contributions
ahime-1.039
usterity-1.034
 Berks-0.940
groupon-0.916
Origin-0.896
Token=
Token ID28
Feature activation-1.25e+00

Pos logit contributions
 Deb+0.925
ourke+0.898
 Vand+0.883
$$+0.879
 「+0.874
Neg logit contributions
ahime-0.866
usterity-0.863
 Berks-0.784
groupon-0.761
adobe-0.742
Tokenc
Token ID66
Feature activation-2.19e-01

Pos logit contributions
ahime+0.936
usterity+0.919
 Berks+0.847
groupon+0.834
adobe+0.825
Neg logit contributions
 Deb-0.734
ourke-0.712
 Vand-0.695
 「-0.685
$$-0.671
Token\
Token ID59
Feature activation-4.36e+00

Pos logit contributions
ahime+0.144
usterity+0.141
 Berks+0.128
groupon+0.126
Origin+0.123
Neg logit contributions
 Deb-0.148
ourke-0.144
 Vand-0.141
 「-0.139
$$-0.138
Token:\
Token ID7479
Feature activation-7.06e+00

Pos logit contributions
ahime+3.051
usterity+2.967
 Berks+2.723
groupon+2.705
fore+2.703
Neg logit contributions
 Deb-2.695
ourke-2.633
 Vand-2.549
 「-2.502
 Lama-2.495
Tokentmp
Token ID22065
Feature activation-1.52e+00

Pos logit contributions
ahime+4.931
usterity+4.747
groupon+4.390
fore+4.386
 Berks+4.373
Neg logit contributions
 Deb-4.290
ourke-4.178
 Vand-4.058
 Lama-3.985
 「-3.953
Token:
Token ID25
Feature activation-2.00e+00

Pos logit contributions
ahime+1.040
usterity+1.026
 Berks+0.932
groupon+0.918
adobe+0.901
Neg logit contributions
 Deb-0.989
ourke-0.968
 Vand-0.940
 「-0.924
 Lama-0.912
Token */
Token ID9466
Feature activation+1.14e+00

Pos logit contributions
ahime+1.850
usterity+1.822
 Berks+1.708
groupon+1.687
adobe+1.666
Neg logit contributions
 Deb-0.811
ourke-0.780
 Vand-0.752
 「-0.728
 Lama-0.710
Token This
Token ID770
Feature activation-2.50e-01

Pos logit contributions
 Deb+0.613
ourke+0.596
 Vand+0.579
$$+0.571
 「+0.570
Neg logit contributions
ahime-0.899
usterity-0.893
 Berks-0.829
groupon-0.810
Origin-0.795
Token sets
Token ID5621
Feature activation+1.64e+00

Pos logit contributions
ahime+0.167
usterity+0.166
 Berks+0.152
groupon+0.148
Origin+0.145
Neg logit contributions
 Deb-0.164
ourke-0.161
 Vand-0.157
$$-0.155
 「-0.154
Token top
Token ID1353
Feature activation-2.60e+00

Pos logit contributions
usterity+0.592
ahime+0.588
 Berks+0.543
groupon+0.525
Origin+0.518
Neg logit contributions
 Deb-0.626
ourke-0.618
$$-0.598
 Vand-0.597
 「-0.588
Token toy
Token ID13373
Feature activation-1.20e+00

Pos logit contributions
ahime+1.368
usterity+1.366
 Berks+1.244
groupon+1.193
Origin+1.173
Neg logit contributions
ourke-2.032
 Deb-2.022
$$-1.953
 Vand-1.943
 「-1.917
Token brands
Token ID11394
Feature activation-2.24e+00

Pos logit contributions
ahime+0.745
usterity+0.740
 Berks+0.674
groupon+0.655
Origin+0.641
Neg logit contributions
 Deb-0.840
ourke-0.823
 Vand-0.804
$$-0.801
 「-0.793
Token include
Token ID2291
Feature activation+2.24e-01

Pos logit contributions
ahime+1.406
usterity+1.398
 Berks+1.284
groupon+1.240
Origin+1.228
Neg logit contributions
 Deb-1.519
ourke-1.511
 Vand-1.453
$$-1.437
Sov-1.417
Token Has
Token ID7875
Feature activation-9.77e-01

Pos logit contributions
 Deb+0.133
ourke+0.130
 Vand+0.126
$$+0.125
 「+0.125
Neg logit contributions
ahime-0.164
usterity-0.163
 Berks-0.150
groupon-0.146
Origin-0.144
Tokenbro
Token ID7957
Feature activation-7.06e+00

Pos logit contributions
ahime+0.550
usterity+0.533
 Berks+0.481
groupon+0.470
Origin+0.460
Neg logit contributions
 Deb-0.751
ourke-0.741
$$-0.722
 Vand-0.721
 「-0.719
Token,
Token ID11
Feature activation+7.23e-03

Pos logit contributions
ahime+4.166
usterity+4.025
 Berks+3.844
Origin+3.705
groupon+3.641
Neg logit contributions
ourke-4.789
 Deb-4.779
 Vand-4.595
$$-4.588
Sov-4.549
Token Barbie
Token ID46829
Feature activation-3.71e+00

Pos logit contributions
 Deb+0.004
ourke+0.004
 Vand+0.004
$$+0.004
 「+0.004
Neg logit contributions
ahime-0.005
usterity-0.005
 Berks-0.005
groupon-0.005
Origin-0.005
Token,
Token ID11
Feature activation-8.11e-01

Pos logit contributions
ahime+2.217
usterity+2.213
 Berks+2.073
groupon+1.974
Origin+1.948
Neg logit contributions
 Deb-2.550
ourke-2.532
 Vand-2.466
$$-2.438
Sov-2.426
Token Lego
Token ID33198
Feature activation-7.67e+00

Pos logit contributions
ahime+0.576
usterity+0.570
 Berks+0.536
groupon+0.516
Origin+0.510
Neg logit contributions
ourke-0.488
 Deb-0.487
$$-0.468
 Vand-0.465
 「-0.463
Token,
Token ID11
Feature activation-8.09e-01

Pos logit contributions
ahime+4.290
usterity+4.262
 Berks+3.975
Origin+3.815
groupon+3.769
Neg logit contributions
ourke-5.382
 Deb-5.312
 Vand-5.136
$$-5.126
 「-5.084
Token voters
Token ID4446
Feature activation-2.01e+00

Pos logit contributions
ahime+1.356
usterity+1.353
 Berks+1.282
groupon+1.232
Origin+1.207
Neg logit contributions
 Deb-1.068
ourke-1.054
$$-1.029
 Vand-1.019
 「-1.013
Token,
Token ID11
Feature activation+2.53e-01

Pos logit contributions
ahime+1.262
usterity+1.247
 Berks+1.142
groupon+1.111
Origin+1.079
Neg logit contributions
 Deb-1.394
ourke-1.367
 Vand-1.340
$$-1.334
 「-1.322
Token according
Token ID1864
Feature activation+7.90e-01

Pos logit contributions
 Deb+0.158
ourke+0.155
 Vand+0.150
$$+0.149
 「+0.148
Neg logit contributions
ahime-0.176
usterity-0.175
 Berks-0.162
groupon-0.158
Origin-0.154
Token to
Token ID284
Feature activation-1.27e+00

Pos logit contributions
 Deb+0.452
ourke+0.441
 Vand+0.428
$$+0.424
 「+0.423
Neg logit contributions
ahime-0.593
usterity-0.589
 Berks-0.547
groupon-0.538
Origin-0.526
Token Real
Token ID6416
Feature activation-3.60e+00

Pos logit contributions
ahime+0.869
usterity+0.868
 Berks+0.804
groupon+0.775
Origin+0.758
Neg logit contributions
 Deb-0.805
ourke-0.797
$$-0.771
 Vand-0.769
 「-0.766
TokenClear
Token ID19856
Feature activation-6.99e+00

Pos logit contributions
usterity+2.066
ahime+2.047
 Berks+1.906
groupon+1.843
Origin+1.792
Neg logit contributions
ourke-2.607
 Deb-2.598
 「-2.519
$$-2.508
 Vand-2.506
TokenPolitics
Token ID43921
Feature activation-1.50e+00

Pos logit contributions
usterity+4.457
groupon+4.119
ahime+4.108
 Berks+4.032
Origin+4.031
Neg logit contributions
ourke-4.539
 Rover-4.404
 Vand-4.303
 Fey-4.255
 「-4.227
Token,
Token ID11
Feature activation+1.12e-01

Pos logit contributions
ahime+1.030
usterity+1.021
 Berks+0.930
groupon+0.905
adobe+0.890
Neg logit contributions
 Deb-0.978
ourke-0.944
 Vand-0.925
$$-0.920
 「-0.918
Token said
Token ID531
Feature activation-1.65e+00

Pos logit contributions
 Deb+0.071
ourke+0.070
 Vand+0.068
$$+0.067
 「+0.067
Neg logit contributions
ahime-0.078
usterity-0.077
 Berks-0.071
groupon-0.069
Origin-0.068
Token a
Token ID257
Feature activation-1.09e+00

Pos logit contributions
usterity+1.139
ahime+1.133
 Berks+1.053
groupon+1.013
Origin+0.995
Neg logit contributions
 Deb-1.034
ourke-1.014
$$-0.994
 Vand-0.986
 「-0.970
Token
Token ID564
Feature activation-5.78e-01

Pos logit contributions
usterity+0.770
ahime+0.763
 Berks+0.703
groupon+0.678
Origin+0.662
Neg logit contributions
 Deb-0.685
ourke-0.666
 Vand-0.651
$$-0.647
 「-0.643
TokenConclusion
Token ID21481
Feature activation-7.19e-01

Pos logit contributions
 Deb+0.500
ourke+0.484
 Vand+0.475
 「+0.470
$$+0.468
Neg logit contributions
ahime-0.556
usterity-0.555
 Berks-0.506
groupon-0.496
Origin-0.487
Token
Token ID198
Feature activation+2.58e-01

Pos logit contributions
ahime+0.536
usterity+0.534
 Berks+0.490
groupon+0.479
Origin+0.471
Neg logit contributions
 Deb-0.419
ourke-0.408
 Vand-0.397
$$-0.394
 「-0.392
Token
Token ID198
Feature activation+3.65e-01

Pos logit contributions
 Deb+0.151
ourke+0.147
 Vand+0.143
 「+0.141
$$+0.141
Neg logit contributions
ahime-0.190
usterity-0.189
 Berks-0.175
groupon-0.172
Origin-0.168
TokenThis
Token ID1212
Feature activation-6.39e-01

Pos logit contributions
 Deb+0.231
ourke+0.224
 Vand+0.219
 「+0.217
$$+0.214
Neg logit contributions
ahime-0.254
usterity-0.254
 Berks-0.232
groupon-0.228
Origin-0.224
Token post
Token ID1281
Feature activation-8.00e-01

Pos logit contributions
ahime+0.412
usterity+0.410
 Berks+0.373
groupon+0.362
Origin+0.355
Neg logit contributions
 Deb-0.434
ourke-0.426
 Vand-0.416
$$-0.414
 「-0.412
Token only
Token ID691
Feature activation+3.82e+00

Pos logit contributions
ahime+0.535
usterity+0.531
 Berks+0.484
groupon+0.471
adobe+0.461
Neg logit contributions
 Deb-0.529
ourke-0.515
 Vand-0.505
$$-0.500
 「-0.499
Token repeats
Token ID29819
Feature activation-8.96e-03

Pos logit contributions
 Deb+2.350
ourke+2.233
 Vand+2.210
 「+2.191
$$+2.189
Neg logit contributions
ahime-2.795
usterity-2.750
 Berks-2.489
groupon-2.435
Origin-2.419
Token some
Token ID617
Feature activation-5.29e-01

Pos logit contributions
ahime+0.006
usterity+0.006
 Berks+0.006
groupon+0.006
Origin+0.005
Neg logit contributions
 Deb-0.006
ourke-0.005
$$-0.005
 「-0.005
 Vand-0.005
Token basic
Token ID4096
Feature activation-2.04e-01

Pos logit contributions
ahime+0.335
usterity+0.335
 Berks+0.306
groupon+0.297
Origin+0.289
Neg logit contributions
 Deb-0.362
ourke-0.357
$$-0.348
 Vand-0.347
 「-0.345
Token information
Token ID1321
Feature activation-4.00e+00

Pos logit contributions
ahime+0.150
usterity+0.150
 Berks+0.138
groupon+0.135
Origin+0.132
Neg logit contributions
 Deb-0.119
ourke-0.117
 Vand-0.113
$$-0.113
 「-0.112
Token about
Token ID546
Feature activation-3.75e-01

Pos logit contributions
ahime+2.391
usterity+2.374
 Berks+2.206
groupon+2.118
Origin+2.089
Neg logit contributions
ourke-2.791
 Deb-2.727
$$-2.669
 Vand-2.637
 「-2.629
Token this
Token ID428
Feature activation+2.22e-01

Pos logit contributions
ahime+0.028
usterity+0.028
 Berks+0.026
groupon+0.025
Origin+0.024
Neg logit contributions
 Deb-0.024
ourke-0.023
 Vand-0.022
$$-0.022
 「-0.022
Token page
Token ID2443
Feature activation-9.94e-01

Pos logit contributions
 Deb+0.138
ourke+0.135
 Vand+0.132
$$+0.131
 「+0.130
Neg logit contributions
ahime-0.155
usterity-0.155
 Berks-0.142
groupon-0.139
Origin-0.136
Token and
Token ID290
Feature activation+9.78e-01

Pos logit contributions
ahime+0.664
usterity+0.663
 Berks+0.612
groupon+0.596
Origin+0.583
Neg logit contributions
 Deb-0.642
ourke-0.631
 Vand-0.610
$$-0.606
 「-0.602
Token make
Token ID787
Feature activation+3.30e-01

Pos logit contributions
 Deb+0.624
ourke+0.606
 Vand+0.593
$$+0.588
 「+0.586
Neg logit contributions
ahime-0.678
usterity-0.673
 Berks-0.617
groupon-0.600
Origin-0.588
Token fun
Token ID1257
Feature activation+1.52e+00

Pos logit contributions
 Deb+0.189
ourke+0.187
 Vand+0.180
$$+0.179
 「+0.178
Neg logit contributions
ahime-0.246
usterity-0.243
 Berks-0.227
groupon-0.220
Origin-0.217
Token of
Token ID286
Feature activation+5.56e+00

Pos logit contributions
 Deb+1.011
ourke+0.971
 Vand+0.960
$$+0.947
 「+0.947
Neg logit contributions
ahime-1.027
usterity-1.017
 Berks-0.924
groupon-0.903
adobe-0.880
Token and
Token ID290
Feature activation+4.62e-01

Pos logit contributions
 Deb+3.316
 Vand+3.110
ourke+3.075
$$+3.044
 「+3.033
Neg logit contributions
ahime-4.176
usterity-4.130
 Berks-3.715
groupon-3.665
adobe-3.655
Token mock
Token ID15290
Feature activation-2.74e-01

Pos logit contributions
 Deb+0.264
ourke+0.258
 Vand+0.250
$$+0.248
 「+0.247
Neg logit contributions
ahime-0.347
usterity-0.346
 Berks-0.320
groupon-0.313
Origin-0.307
Token Child
Token ID5932
Feature activation-1.28e+00

Pos logit contributions
ahime+0.195
usterity+0.194
 Berks+0.179
groupon+0.174
Origin+0.171
Neg logit contributions
 Deb-0.167
ourke-0.164
 Vand-0.159
$$-0.158
 「-0.158
Token Mol
Token ID17958
Feature activation+2.94e-01

Pos logit contributions
ahime+0.915
usterity+0.913
 Berks+0.845
groupon+0.823
Origin+0.810
Neg logit contributions
 Deb-0.767
ourke-0.754
 Vand-0.732
 「-0.730
$$-0.728
Tokenestation
Token ID27364
Feature activation+1.80e+00

Pos logit contributions
 Deb+0.200
ourke+0.194
 Vand+0.190
$$+0.189
 「+0.188
Neg logit contributions
ahime-0.192
usterity-0.191
 Berks-0.174
groupon-0.169
Origin-0.165
Token.
Token ID13
Feature activation-1.37e+00

Pos logit contributions
 Deb+1.846
ourke+1.752
 Vand+1.730
 「+1.717
$$+1.712
Neg logit contributions
ahime-2.451
usterity-2.450
 Berks-2.232
groupon-2.176
adobe-2.156
Token And
Token ID843
Feature activation-1.98e+00

Pos logit contributions
ahime+0.925
usterity+0.921
 Berks+0.874
groupon+0.844
Origin+0.817
Neg logit contributions
ourke-0.854
 Deb-0.839
$$-0.808
 Vand-0.808
 「-0.806
Token there
Token ID612
Feature activation+1.20e+00

Pos logit contributions
ahime+1.288
usterity+1.288
 Berks+1.204
groupon+1.161
Origin+1.126
Neg logit contributions
 Deb-1.272
ourke-1.265
$$-1.233
 Vand-1.227
 「-1.220
Token were
Token ID547
Feature activation-1.42e+00

Pos logit contributions
 Deb+0.711
ourke+0.687
 Vand+0.673
$$+0.666
 「+0.665
Neg logit contributions
ahime-0.890
usterity-0.884
 Berks-0.813
groupon-0.793
adobe-0.778
Token many
Token ID867
Feature activation+4.90e-01

Pos logit contributions
usterity+0.971
ahime+0.969
 Berks+0.905
groupon+0.873
Origin+0.850
Neg logit contributions
 Deb-0.888
ourke-0.881
$$-0.851
 Vand-0.848
 「-0.841
Token others
Token ID1854
Feature activation+4.45e+00

Pos logit contributions
 Deb+0.312
ourke+0.303
 Vand+0.296
$$+0.294
 「+0.293
Neg logit contributions
ahime-0.339
usterity-0.338
 Berks-0.310
groupon-0.301
Origin-0.295
Token.
Token ID13
Feature activation+1.25e+00

Pos logit contributions
 Deb+2.706
ourke+2.571
 Vand+2.559
 「+2.521
$$+2.516
Neg logit contributions
ahime-3.299
usterity-3.266
 Berks-2.943
groupon-2.876
adobe-2.849
Token
Token ID198
Feature activation+4.86e-01

Pos logit contributions
 Deb+0.747
ourke+0.732
 Vand+0.709
$$+0.705
 「+0.703
Neg logit contributions
ahime-0.905
usterity-0.899
 Berks-0.832
groupon-0.810
Origin-0.793
Token
Token ID198
Feature activation+5.20e-01

Pos logit contributions
 Deb+0.286
ourke+0.279
 Vand+0.272
 「+0.268
$$+0.267
Neg logit contributions
ahime-0.356
usterity-0.355
 Berks-0.327
groupon-0.323
Origin-0.316
TokenYet
Token ID11486
Feature activation+5.98e-01

Pos logit contributions
 Deb+0.344
ourke+0.334
 Vand+0.329
 「+0.324
$$+0.322
Neg logit contributions
ahime-0.345
usterity-0.345
 Berks-0.314
groupon-0.309
Origin-0.304
Token being
Token ID852
Feature activation-2.61e+00

Pos logit contributions
 Deb+0.393
ourke+0.382
 Vand+0.374
$$+0.371
 「+0.370
Neg logit contributions
ahime-0.403
usterity-0.400
 Berks-0.366
groupon-0.355
Origin-0.348
Tokenre
Token ID260
Feature activation+1.86e+00

Pos logit contributions
 Deb+1.227
ourke+1.189
 Vand+1.165
$$+1.150
 「+1.148
Neg logit contributions
ahime-1.422
usterity-1.417
 Berks-1.294
groupon-1.262
adobe-1.242
Tokenment
Token ID434
Feature activation+1.99e+00

Pos logit contributions
 Deb+1.094
ourke+1.057
 Vand+1.035
$$+1.025
 「+1.022
Neg logit contributions
ahime-1.381
usterity-1.373
 Berks-1.263
groupon-1.233
adobe-1.209
Token,
Token ID11
Feature activation-5.84e-01

Pos logit contributions
 Deb+1.120
ourke+1.081
 Vand+1.057
$$+1.046
 「+1.043
Neg logit contributions
ahime-1.532
usterity-1.522
 Berks-1.404
groupon-1.372
Origin-1.347
Token les
Token ID10287
Feature activation+2.43e+00

Pos logit contributions
ahime+0.460
usterity+0.454
 Berks+0.425
groupon+0.412
Origin+0.407
Neg logit contributions
 Deb-0.310
ourke-0.307
 Vand-0.293
$$-0.291
 「-0.290
Token Cors
Token ID26978
Feature activation+3.88e+00

Pos logit contributions
 Deb+1.465
ourke+1.404
 Vand+1.388
$$+1.364
 「+1.363
Neg logit contributions
ahime-1.780
usterity-1.769
 Berks-1.621
groupon-1.584
adobe-1.555
Tokenaires
Token ID17693
Feature activation+4.19e+00

Pos logit contributions
 Deb+1.600
ourke+1.529
 Vand+1.475
$$+1.452
 「+1.448
Neg logit contributions
ahime-3.563
usterity-3.553
 Berks-3.320
groupon-3.260
Origin-3.208
Token l
Token ID300
Feature activation+2.32e+00

Pos logit contributions
 Deb+2.420
ourke+2.289
 Vand+2.280
 「+2.245
$$+2.242
Neg logit contributions
ahime-3.173
usterity-3.163
 Berks-2.899
groupon-2.851
adobe-2.801
Tokenoy
Token ID726
Feature activation+1.60e+00

Pos logit contributions
 Deb+1.256
ourke+1.211
 Vand+1.183
$$+1.170
 「+1.167
Neg logit contributions
ahime-1.833
usterity-1.823
 Berks-1.686
groupon-1.648
Origin-1.618
Tokenaux
Token ID14644
Feature activation+2.75e+00

Pos logit contributions
 Deb+0.962
ourke+0.932
 Vand+0.911
$$+0.904
 「+0.901
Neg logit contributions
ahime-1.176
usterity-1.166
 Berks-1.073
groupon-1.046
Origin-1.027
Token rest
Token ID1334
Feature activation+1.56e+00

Pos logit contributions
 Deb+1.565
ourke+1.497
 Vand+1.476
$$+1.454
 「+1.453
Neg logit contributions
ahime-2.112
usterity-2.099
 Berks-1.932
groupon-1.891
adobe-1.858
Tokenants
Token ID1187
Feature activation+1.76e+00

Pos logit contributions
 Deb+0.940
ourke+0.908
 Vand+0.889
$$+0.881
 「+0.879
Neg logit contributions
ahime-1.144
usterity-1.138
 Berks-1.045
groupon-1.022
Origin-1.001
Token,
Token ID11
Feature activation-2.12e+00

Pos logit contributions
 Deb+1.133
ourke+1.073
 Vand+1.070
 「+1.068
$$+1.058
Neg logit contributions
ahime-1.315
usterity-1.282
 Berks-1.171
groupon-1.136
adobe-1.120
Token when
Token ID618
Feature activation-7.59e-02

Pos logit contributions
usterity+1.491
ahime+1.485
 Berks+1.380
groupon+1.342
Origin+1.308
Neg logit contributions
 Deb-1.301
ourke-1.277
 Vand-1.240
$$-1.227
 「-1.211
Token I
Token ID314
Feature activation+5.47e-01

Pos logit contributions
ahime+0.057
usterity+0.057
 Berks+0.052
groupon+0.051
Origin+0.050
Neg logit contributions
 Deb-0.044
ourke-0.043
 Vand-0.042
$$-0.041
 「-0.041
Token want
Token ID765
Feature activation+1.69e+00

Pos logit contributions
 Deb+0.356
ourke+0.345
 Vand+0.338
$$+0.335
 「+0.335
Neg logit contributions
ahime-0.374
usterity-0.371
 Berks-0.339
groupon-0.330
Origin-0.323
Token to
Token ID284
Feature activation+7.87e-01

Pos logit contributions
 Deb+0.930
ourke+0.885
 Vand+0.872
 「+0.865
$$+0.862
Neg logit contributions
ahime-1.337
usterity-1.319
 Berks-1.214
groupon-1.189
adobe-1.171
Token feel
Token ID1254
Feature activation+3.91e+00

Pos logit contributions
 Deb+0.491
ourke+0.474
 Vand+0.466
$$+0.462
 「+0.462
Neg logit contributions
ahime-0.561
usterity-0.555
 Berks-0.508
groupon-0.495
Origin-0.485
Token it
Token ID340
Feature activation-1.52e-01

Pos logit contributions
 Deb+2.249
 Vand+2.125
 「+2.118
ourke+2.101
$$+2.087
Neg logit contributions
ahime-3.067
usterity-2.963
 Berks-2.705
groupon-2.655
Origin-2.608
Token.
Token ID13
Feature activation-1.35e+00

Pos logit contributions
ahime+0.105
usterity+0.104
 Berks+0.095
groupon+0.093
adobe+0.091
Neg logit contributions
 Deb-0.097
ourke-0.094
 Vand-0.093
$$-0.092
 「-0.092
Token And
Token ID843
Feature activation-1.88e+00

Pos logit contributions
usterity+0.972
ahime+0.970
 Berks+0.910
groupon+0.881
Origin+0.863
Neg logit contributions
ourke-0.798
 Deb-0.792
 Vand-0.757
$$-0.754
 「-0.745
Token I
Token ID314
Feature activation+1.06e-01

Pos logit contributions
usterity+1.317
ahime+1.311
 Berks+1.219
groupon+1.180
Origin+1.156
Neg logit contributions
 Deb-1.153
ourke-1.146
$$-1.107
 Vand-1.101
 「-1.090
Token think
Token ID892
Feature activation-1.01e+00

Pos logit contributions
 Deb+0.070
ourke+0.068
 Vand+0.067
$$+0.066
 「+0.066
Neg logit contributions
ahime-0.071
usterity-0.070
 Berks-0.064
groupon-0.062
Origin-0.061
Token is
Token ID318
Feature activation-5.77e-01

Pos logit contributions
ahime+0.367
usterity+0.364
 Berks+0.333
groupon+0.325
Origin+0.318
Neg logit contributions
 Deb-0.334
ourke-0.323
 Vand-0.317
$$-0.314
 「-0.313
Token in
Token ID287
Feature activation+5.90e-01

Pos logit contributions
ahime+0.395
usterity+0.395
 Berks+0.361
groupon+0.353
Origin+0.344
Neg logit contributions
 Deb-0.369
ourke-0.361
 Vand-0.352
 「-0.347
$$-0.347
Token many
Token ID867
Feature activation+8.01e-01

Pos logit contributions
 Deb+0.371
ourke+0.361
 Vand+0.353
$$+0.349
 「+0.348
Neg logit contributions
ahime-0.415
usterity-0.411
 Berks-0.377
groupon-0.367
Origin-0.359
Token cases
Token ID2663
Feature activation+1.08e+00

Pos logit contributions
 Deb+0.342
ourke+0.327
 Vand+0.316
$$+0.312
 「+0.311
Neg logit contributions
ahime-0.724
usterity-0.721
 Berks-0.674
groupon-0.661
Origin-0.650
Token a
Token ID257
Feature activation+1.32e+00

Pos logit contributions
 Deb+0.689
ourke+0.667
 Vand+0.655
$$+0.649
 「+0.647
Neg logit contributions
ahime-0.746
usterity-0.741
 Berks-0.677
groupon-0.659
adobe-0.646
Token balancing
Token ID22486
Feature activation+2.46e-01

Pos logit contributions
 Deb+0.825
ourke+0.799
 Vand+0.783
$$+0.776
 「+0.774
Neg logit contributions
ahime-0.937
usterity-0.929
 Berks-0.851
groupon-0.830
adobe-0.814
Token act
Token ID719
Feature activation+1.96e-01

Pos logit contributions
 Deb+0.200
ourke+0.195
 Vand+0.192
$$+0.191
 「+0.191
Neg logit contributions
ahime-0.128
usterity-0.127
 Berks-0.112
groupon-0.108
adobe-0.105
Token.
Token ID13
Feature activation+1.67e-01

Pos logit contributions
 Deb+0.128
ourke+0.124
 Vand+0.122
$$+0.121
 「+0.121
Neg logit contributions
ahime-0.134
usterity-0.133
 Berks-0.121
groupon-0.118
adobe-0.115
Token Do
Token ID2141
Feature activation-4.53e-01

Pos logit contributions
 Deb+0.096
ourke+0.095
 Vand+0.091
$$+0.090
 「+0.090
Neg logit contributions
ahime-0.125
usterity-0.124
 Berks-0.115
groupon-0.113
Origin-0.110
Token you
Token ID345
Feature activation+9.85e-01

Pos logit contributions
ahime+0.356
usterity+0.355
 Berks+0.328
groupon+0.320
Origin+0.314
Neg logit contributions
 Deb-0.247
ourke-0.239
 Vand-0.233
$$-0.230
 「-0.230
Token hire
Token ID11078
Feature activation+1.75e+00

Pos logit contributions
 Deb+0.654
ourke+0.636
 Vand+0.624
$$+0.618
 「+0.616
Neg logit contributions
ahime-0.658
usterity-0.653
 Berks-0.595
groupon-0.579
Origin-0.566
Token One
Token ID1881
Feature activation+5.14e-01

Pos logit contributions
ahime+0.103
usterity+0.103
 Berks+0.095
groupon+0.092
Origin+0.090
Neg logit contributions
 Deb-0.086
ourke-0.085
$$-0.082
 Vand-0.082
 「-0.081
Token is
Token ID318
Feature activation+3.65e-01

Pos logit contributions
 Deb+0.331
ourke+0.322
 Vand+0.315
$$+0.312
 「+0.311
Neg logit contributions
ahime-0.353
usterity-0.351
 Berks-0.320
groupon-0.312
Origin-0.306
Token its
Token ID663
Feature activation+1.02e+00

Pos logit contributions
 Deb+0.206
ourke+0.200
 Vand+0.195
$$+0.193
 「+0.192
Neg logit contributions
ahime-0.279
usterity-0.279
 Berks-0.256
groupon-0.250
Origin-0.246
Token op
Token ID1034
Feature activation+1.30e+00

Pos logit contributions
 Deb+0.514
ourke+0.497
 Vand+0.485
$$+0.480
 「+0.476
Neg logit contributions
ahime-0.834
usterity-0.833
 Berks-0.771
groupon-0.754
Origin-0.743
Tokenr
Token ID81
Feature activation-1.37e+00

Pos logit contributions
 Deb+0.900
ourke+0.875
 Vand+0.859
$$+0.852
 「+0.851
Neg logit contributions
ahime-0.832
usterity-0.826
 Berks-0.749
groupon-0.729
adobe-0.711
Tokenp
Token ID79
Feature activation+1.67e-02

Pos logit contributions
ahime+0.999
usterity+0.993
 Berks+0.907
groupon+0.887
Origin+0.872
Neg logit contributions
 Deb-0.819
ourke-0.790
 Vand-0.778
$$-0.768
 「-0.764
Tokenressive
Token ID3314
Feature activation+1.45e+00

Pos logit contributions
 Deb+0.011
ourke+0.010
 Vand+0.010
$$+0.010
 「+0.010
Neg logit contributions
ahime-0.012
usterity-0.012
 Berks-0.011
groupon-0.010
adobe-0.010
Token spect
Token ID5444
Feature activation+1.80e+00

Pos logit contributions
 Deb+0.857
ourke+0.831
 Vand+0.813
$$+0.806
 「+0.802
Neg logit contributions
ahime-1.067
usterity-1.063
 Berks-0.975
groupon-0.951
Origin-0.935
Tokenre
Token ID260
Feature activation-3.40e-01

Pos logit contributions
 Deb+1.127
ourke+1.091
 Vand+1.070
$$+1.060
 「+1.057
Neg logit contributions
ahime-1.273
usterity-1.266
 Berks-1.159
groupon-1.130
Origin-1.107
Token,
Token ID11
Feature activation+1.27e+00

Pos logit contributions
ahime+0.229
usterity+0.229
 Berks+0.208
groupon+0.203
Origin+0.201
Neg logit contributions
 Deb-0.221
ourke-0.216
 Vand-0.211
$$-0.208
 「-0.208
Tokenp
Token ID79
Feature activation-1.45e+00

Pos logit contributions
 Deb+0.795
ourke+0.771
 Vand+0.755
$$+0.747
 「+0.747
Neg logit contributions
ahime-0.899
usterity-0.894
 Berks-0.817
groupon-0.798
Origin-0.784
Tokenickson
Token ID46381
Feature activation+1.75e-01

Pos logit contributions
 Deb+0.501
ourke+0.483
 Vand+0.474
 「+0.470
$$+0.468
Neg logit contributions
ahime-0.640
usterity-0.634
 Berks-0.586
groupon-0.571
Origin-0.559
Token will
Token ID481
Feature activation-5.75e-01

Pos logit contributions
 Deb+0.114
ourke+0.111
 Vand+0.109
$$+0.108
 「+0.107
Neg logit contributions
ahime-0.118
usterity-0.118
 Berks-0.107
groupon-0.105
Origin-0.102
Token return
Token ID1441
Feature activation-1.93e+00

Pos logit contributions
usterity+0.408
ahime+0.407
 Berks+0.373
groupon+0.366
Origin+0.357
Neg logit contributions
 Deb-0.352
ourke-0.348
 Vand-0.335
$$-0.331
 「-0.329
Token to
Token ID284
Feature activation-2.12e+00

Pos logit contributions
ahime+1.318
usterity+1.305
 Berks+1.207
groupon+1.189
Origin+1.165
Neg logit contributions
 Deb-1.205
ourke-1.202
 Vand-1.151
$$-1.147
 「-1.140
Token full
Token ID1336
Feature activation-1.06e+00

Pos logit contributions
ahime+1.353
usterity+1.348
 Berks+1.230
groupon+1.194
Origin+1.169
Neg logit contributions
 Deb-1.447
ourke-1.425
 Vand-1.383
$$-1.379
 「-1.376
Token training
Token ID3047
Feature activation+1.74e+00

Pos logit contributions
ahime+0.719
usterity+0.716
 Berks+0.652
groupon+0.638
Origin+0.624
Neg logit contributions
 Deb-0.688
ourke-0.674
 Vand-0.655
$$-0.651
 「-0.650
Token this
Token ID428
Feature activation-8.31e-01

Pos logit contributions
 Deb+1.105
ourke+1.054
 Vand+1.051
$$+1.034
 「+1.032
Neg logit contributions
ahime-1.228
usterity-1.219
 Berks-1.114
groupon-1.079
adobe-1.068
Token week
Token ID1285
Feature activation+8.77e-02

Pos logit contributions
ahime+0.556
usterity+0.553
 Berks+0.508
groupon+0.493
Origin+0.483
Neg logit contributions
 Deb-0.540
ourke-0.531
 Vand-0.516
$$-0.513
 「-0.511
Token after
Token ID706
Feature activation+1.48e-01

Pos logit contributions
 Deb+0.059
ourke+0.058
 Vand+0.056
$$+0.056
 「+0.056
Neg logit contributions
ahime-0.057
usterity-0.057
 Berks-0.052
groupon-0.051
Origin-0.049
Token an
Token ID281
Feature activation-3.32e-01

Pos logit contributions
 Deb+0.086
ourke+0.085
$$+0.082
 Vand+0.082
 「+0.081
Neg logit contributions
usterity-0.110
ahime-0.110
 Berks-0.102
groupon-0.099
Origin-0.097
Token abdominal
Token ID32692
Feature activation+4.75e-01

Pos logit contributions
ahime+0.239
usterity+0.238
 Berks+0.219
groupon+0.213
Origin+0.210
Neg logit contributions
 Deb-0.201
ourke-0.197
$$-0.191
 Vand-0.191
 「-0.188
Token 10
Token ID838
Feature activation-1.34e+00

Pos logit contributions
 Deb+0.474
ourke+0.462
 Vand+0.451
$$+0.447
 「+0.446
Neg logit contributions
ahime-0.501
usterity-0.498
 Berks-0.454
groupon-0.442
Origin-0.432
Token years
Token ID812
Feature activation-3.11e-01

Pos logit contributions
ahime+1.008
usterity+1.007
 Berks+0.921
groupon+0.903
adobe+0.879
Neg logit contributions
 Deb-0.768
ourke-0.748
 Vand-0.733
$$-0.723
 「-0.719
Token with
Token ID351
Feature activation-4.20e-01

Pos logit contributions
usterity+0.204
ahime+0.204
 Berks+0.186
groupon+0.181
adobe+0.176
Neg logit contributions
 Deb-0.207
ourke-0.203
 Vand-0.198
$$-0.196
 「-0.196
Token the
Token ID262
Feature activation+4.13e-01

Pos logit contributions
usterity+0.298
ahime+0.297
 Berks+0.273
groupon+0.265
Origin+0.259
Neg logit contributions
 Deb-0.257
ourke-0.252
 Vand-0.246
$$-0.243
 「-0.242
Token Harper
Token ID12686
Feature activation+4.78e-01

Pos logit contributions
 Deb+0.308
ourke+0.301
 Vand+0.296
$$+0.294
 「+0.293
Neg logit contributions
ahime-0.240
usterity-0.240
 Berks-0.215
groupon-0.208
Origin-0.203
Token Conservatives
Token ID17897
Feature activation+2.77e+00

Pos logit contributions
 Deb+0.338
ourke+0.330
 Vand+0.323
 「+0.320
$$+0.319
Neg logit contributions
usterity-0.298
ahime-0.297
 Berks-0.268
groupon-0.260
Origin-0.253
Token.
Token ID13
Feature activation-9.56e-02

Pos logit contributions
 Deb+1.727
ourke+1.664
 Vand+1.633
$$+1.621
 「+1.616
Neg logit contributions
ahime-1.977
usterity-1.957
 Berks-1.795
groupon-1.749
adobe-1.722
Token There
Token ID1318
Feature activation+5.27e-01

Pos logit contributions
ahime+0.072
usterity+0.072
 Berks+0.067
groupon+0.065
Origin+0.064
Neg logit contributions
 Deb-0.054
ourke-0.053
 Vand-0.051
$$-0.051
 「-0.050
Token were
Token ID547
Feature activation-1.24e+00

Pos logit contributions
 Deb+0.323
ourke+0.313
 Vand+0.307
$$+0.304
 「+0.303
Neg logit contributions
ahime-0.379
usterity-0.376
 Berks-0.345
groupon-0.337
Origin-0.330
Token high
Token ID1029
Feature activation-1.03e+00

Pos logit contributions
usterity+0.840
ahime+0.834
 Berks+0.774
groupon+0.751
Origin+0.727
Neg logit contributions
 Deb-0.784
ourke-0.776
$$-0.750
 Vand-0.749
 「-0.738
Token hopes
Token ID7176
Feature activation+6.34e-01

Pos logit contributions
ahime+0.639
usterity+0.638
 Berks+0.578
groupon+0.563
adobe+0.544
Neg logit contributions
 Deb-0.724
ourke-0.711
 Vand-0.696
$$-0.693
 「-0.688
Token
Token ID250
Feature activation+2.08e-01

Pos logit contributions
ahime+0.889
usterity+0.888
 Berks+0.819
groupon+0.805
Origin+0.785
Neg logit contributions
 Deb-0.667
ourke-0.649
 Vand-0.633
$$-0.624
 「-0.622
TokenIt
Token ID1026
Feature activation+2.12e+00

Pos logit contributions
 Deb+0.122
ourke+0.118
 Vand+0.115
$$+0.114
 「+0.114
Neg logit contributions
ahime-0.155
usterity-0.155
 Berks-0.142
groupon-0.139
Origin-0.136
Token will
Token ID481
Feature activation-1.83e-02

Pos logit contributions
 Deb+1.268
ourke+1.218
 「+1.194
$$+1.194
 Vand+1.192
Neg logit contributions
ahime-1.576
usterity-1.556
 Berks-1.434
groupon-1.389
Origin-1.370
Token reduce
Token ID4646
Feature activation-2.24e+00

Pos logit contributions
ahime+0.012
usterity+0.012
 Berks+0.011
groupon+0.011
adobe+0.011
Neg logit contributions
 Deb-0.012
ourke-0.012
 Vand-0.011
$$-0.011
 「-0.011
Token the
Token ID262
Feature activation-3.98e-01

Pos logit contributions
ahime+1.522
usterity+1.516
 Berks+1.405
groupon+1.351
adobe+1.301
Neg logit contributions
 Deb-1.421
ourke-1.419
 「-1.352
 Vand-1.351
$$-1.346
Token problem
Token ID1917
Feature activation+7.04e-01

Pos logit contributions
ahime+0.281
usterity+0.279
 Berks+0.257
groupon+0.249
Origin+0.242
Neg logit contributions
 Deb-0.247
ourke-0.242
 Vand-0.235
$$-0.234
 「-0.233
Token of
Token ID286
Feature activation-1.11e+00

Pos logit contributions
 Deb+0.474
ourke+0.459
 Vand+0.452
$$+0.448
 「+0.447
Neg logit contributions
ahime-0.466
usterity-0.462
 Berks-0.421
groupon-0.409
Origin-0.401
Token student
Token ID3710
Feature activation-5.01e-01

Pos logit contributions
usterity+0.787
ahime+0.785
 Berks+0.731
groupon+0.705
adobe+0.686
Neg logit contributions
 Deb-0.673
ourke-0.661
 Vand-0.637
$$-0.634
 「-0.633
Token debt
Token ID5057
Feature activation-1.59e+00

Pos logit contributions
ahime+0.364
usterity+0.363
 Berks+0.334
groupon+0.325
Origin+0.317
Neg logit contributions
 Deb-0.302
ourke-0.295
 Vand-0.287
$$-0.284
 「-0.284
Token,
Token ID11
Feature activation+8.72e-01

Pos logit contributions
ahime+1.071
usterity+1.065
 Berks+0.966
groupon+0.940
Origin+0.920
Neg logit contributions
 Deb-1.047
ourke-1.027
 Vand-0.998
 「-0.985
$$-0.983
Token which
Token ID543
Feature activation+1.38e+00

Pos logit contributions
 Deb+0.531
ourke+0.513
 Vand+0.503
$$+0.499
 「+0.497
Neg logit contributions
ahime-0.631
usterity-0.627
 Berks-0.575
groupon-0.561
Origin-0.551
Token4
Token ID19
Feature activation-7.03e-01

Pos logit contributions
 Deb+0.353
ourke+0.340
 Vand+0.333
 「+0.328
$$+0.325
Neg logit contributions
ahime-0.558
usterity-0.553
 Berks-0.512
groupon-0.505
Origin-0.497
Token-
Token ID12
Feature activation+8.46e-01

Pos logit contributions
ahime+0.389
usterity+0.386
 Berks+0.345
groupon+0.333
Origin+0.325
Neg logit contributions
 Deb-0.544
ourke-0.533
 Vand-0.522
$$-0.520
 「-0.519
Token1
Token ID16
Feature activation+3.20e-01

Pos logit contributions
 Deb+0.454
ourke+0.437
 Vand+0.427
$$+0.422
 「+0.421
Neg logit contributions
ahime-0.674
usterity-0.670
 Berks-0.620
groupon-0.605
adobe-0.595
Token-
Token ID12
Feature activation+6.17e-01

Pos logit contributions
 Deb+0.188
ourke+0.182
 Vand+0.178
$$+0.176
 「+0.175
Neg logit contributions
ahime-0.239
usterity-0.238
 Berks-0.219
groupon-0.214
Origin-0.209
Token2
Token ID17
Feature activation+2.71e-02

Pos logit contributions
 Deb+0.276
ourke+0.264
 Vand+0.256
$$+0.253
 「+0.252
Neg logit contributions
ahime-0.547
usterity-0.544
 Berks-0.508
groupon-0.498
Origin-0.490
Token to
Token ID284
Feature activation-2.57e+00

Pos logit contributions
 Deb+0.017
ourke+0.016
 Vand+0.016
$$+0.016
 「+0.016
Neg logit contributions
ahime-0.019
usterity-0.019
 Berks-0.018
groupon-0.017
Origin-0.017
Token more
Token ID517
Feature activation-2.83e+00

Pos logit contributions
ahime+1.744
usterity+1.732
 Berks+1.614
groupon+1.548
adobe+1.525
Neg logit contributions
 Deb-1.607
ourke-1.587
$$-1.551
 Vand-1.519
 「-1.509
Token of
Token ID286
Feature activation+7.64e-01

Pos logit contributions
ahime+1.838
usterity+1.827
 Berks+1.672
groupon+1.623
Origin+1.585
Neg logit contributions
 Deb-1.864
ourke-1.857
$$-1.816
 Vand-1.790
 「-1.774
Token a
Token ID257
Feature activation+1.54e+00

Pos logit contributions
 Deb+0.419
ourke+0.404
 Vand+0.395
$$+0.392
 「+0.389
Neg logit contributions
ahime-0.599
usterity-0.595
 Berks-0.551
groupon-0.538
adobe-0.528
Token 4
Token ID604
Feature activation+7.04e-01

Pos logit contributions
 Deb+0.935
ourke+0.899
 Vand+0.885
 「+0.872
$$+0.870
Neg logit contributions
ahime-1.125
usterity-1.115
 Berks-1.021
groupon-1.000
Origin-0.982
Token-
Token ID12
Feature activation-4.91e-01

Pos logit contributions
 Deb+0.536
ourke+0.522
 Vand+0.514
$$+0.510
 「+0.508
Neg logit contributions
ahime-0.403
usterity-0.401
 Berks-0.358
groupon-0.347
adobe-0.338
Token really
Token ID1107
Feature activation+1.92e+00

Pos logit contributions
usterity+0.009
ahime+0.009
 Berks+0.008
groupon+0.008
adobe+0.008
Neg logit contributions
 Deb-0.009
ourke-0.009
 Vand-0.008
$$-0.008
 「-0.008
Token likely
Token ID1884
Feature activation+3.42e-01

Pos logit contributions
 Deb+1.240
ourke+1.191
 Vand+1.178
 「+1.168
$$+1.162
Neg logit contributions
ahime-1.326
usterity-1.314
 Berks-1.198
groupon-1.164
Origin-1.145
Token that
Token ID326
Feature activation+1.90e-01

Pos logit contributions
 Deb+0.222
ourke+0.216
 Vand+0.212
$$+0.210
 「+0.209
Neg logit contributions
ahime-0.233
usterity-0.232
 Berks-0.212
groupon-0.206
adobe-0.202
Token Amazon
Token ID6186
Feature activation-1.03e+00

Pos logit contributions
 Deb+0.128
ourke+0.126
 Vand+0.123
$$+0.122
 「+0.121
Neg logit contributions
ahime-0.123
usterity-0.123
 Berks-0.113
groupon-0.109
adobe-0.107
Token is
Token ID318
Feature activation-1.14e+00

Pos logit contributions
ahime+0.679
usterity+0.676
 Berks+0.616
groupon+0.598
Origin+0.586
Neg logit contributions
 Deb-0.691
ourke-0.672
 Vand-0.658
$$-0.653
 「-0.650
Token going
Token ID1016
Feature activation-1.78e+00

Pos logit contributions
usterity+0.751
ahime+0.748
 Berks+0.685
groupon+0.665
adobe+0.652
Neg logit contributions
 Deb-0.754
ourke-0.738
 Vand-0.720
$$-0.711
 「-0.704
Token to
Token ID284
Feature activation-6.27e-01

Pos logit contributions
ahime+1.353
usterity+1.345
 Berks+1.242
groupon+1.212
adobe+1.189
Neg logit contributions
 Deb-1.009
ourke-0.976
 Vand-0.953
$$-0.943
 「-0.937
Token go
Token ID467
Feature activation-1.27e+00

Pos logit contributions
usterity+0.430
ahime+0.428
 Berks+0.393
groupon+0.382
adobe+0.376
Neg logit contributions
 Deb-0.399
ourke-0.392
 Vand-0.379
$$-0.376
 「-0.371
Token all
Token ID477
Feature activation+3.50e-01

Pos logit contributions
ahime+0.854
usterity+0.852
 Berks+0.777
groupon+0.754
adobe+0.741
Neg logit contributions
 Deb-0.837
ourke-0.817
 Vand-0.797
$$-0.793
 「-0.783
Token 1984
Token ID12844
Feature activation-2.07e+00

Pos logit contributions
 Deb+0.242
ourke+0.233
 Vand+0.231
 「+0.229
$$+0.228
Neg logit contributions
ahime-0.227
usterity-0.223
 Berks-0.202
groupon-0.198
Origin-0.193
Token on
Token ID319
Feature activation-1.52e+00

Pos logit contributions
usterity+1.415
ahime+1.414
 Berks+1.294
groupon+1.264
adobe+1.237
Neg logit contributions
 Deb-1.318
ourke-1.286
 Vand-1.252
$$-1.246
 「-1.235
Token was
Token ID373
Feature activation+9.94e-01

Pos logit contributions
ahime+0.569
usterity+0.567
 Berks+0.519
groupon+0.507
Origin+0.497
Neg logit contributions
 Deb-0.489
ourke-0.484
 Vand-0.465
$$-0.462
 「-0.457
Token a
Token ID257
Feature activation+1.25e+00

Pos logit contributions
 Deb+0.643
ourke+0.627
 Vand+0.611
$$+0.607
 「+0.603
Neg logit contributions
ahime-0.678
usterity-0.677
 Berks-0.617
groupon-0.600
Origin-0.589
Token result
Token ID1255
Feature activation-5.40e-01

Pos logit contributions
 Deb+0.812
ourke+0.790
 Vand+0.773
$$+0.763
 「+0.761
Neg logit contributions
ahime-0.852
usterity-0.851
 Berks-0.774
groupon-0.754
Origin-0.737
Token of
Token ID286
Feature activation+2.31e+00

Pos logit contributions
ahime+0.355
usterity+0.352
 Berks+0.320
groupon+0.311
adobe+0.305
Neg logit contributions
 Deb-0.367
ourke-0.356
 Vand-0.350
$$-0.347
 「-0.346
Token that
Token ID326
Feature activation-2.70e-01

Pos logit contributions
 Deb+1.384
ourke+1.334
 Vand+1.311
$$+1.296
 「+1.295
Neg logit contributions
ahime-1.693
usterity-1.683
 Berks-1.546
groupon-1.508
adobe-1.480
Token overwhelming
Token ID9721
Feature activation-2.82e-01

Pos logit contributions
ahime+0.186
usterity+0.185
 Berks+0.169
groupon+0.165
Origin+0.161
Neg logit contributions
 Deb-0.173
ourke-0.169
 Vand-0.165
$$-0.163
 「-0.162
Token stress
Token ID5503
Feature activation-3.68e+00

Pos logit contributions
ahime+0.191
usterity+0.190
 Berks+0.173
groupon+0.169
Origin+0.165
Neg logit contributions
 Deb-0.184
ourke-0.180
 Vand-0.175
$$-0.174
 「-0.173
Token.
Token ID13
Feature activation-4.98e-01

Pos logit contributions
ahime+2.409
usterity+2.367
 Berks+2.156
groupon+2.085
Origin+2.077
Neg logit contributions
ourke-2.433
 Deb-2.426
 Vand-2.322
$$-2.312
Sov-2.280
Token Being
Token ID11204
Feature activation-3.58e+00

Pos logit contributions
usterity+0.362
ahime+0.361
 Berks+0.336
groupon+0.327
Origin+0.321
Neg logit contributions
ourke-0.294
 Deb-0.290
 Vand-0.275
$$-0.275
 「-0.271
Token on
Token ID319
Feature activation+4.90e-01

Pos logit contributions
ahime+2.261
usterity+2.257
 Berks+2.060
groupon+1.998
Origin+1.933
Neg logit contributions
ourke-2.406
 Deb-2.381
$$-2.272
 Vand-2.250
 「-2.218
Token the
Token ID262
Feature activation+1.13e+00

Pos logit contributions
 Deb+0.294
ourke+0.289
$$+0.279
 Vand+0.278
 「+0.275
Neg logit contributions
ahime-0.355
usterity-0.354
 Berks-0.325
groupon-0.316
Origin-0.311
Tokennn
Token ID20471
Feature activation+8.76e-01

Pos logit contributions
 Deb+0.208
ourke+0.201
 Vand+0.198
$$+0.196
 「+0.196
Neg logit contributions
ahime-0.190
usterity-0.188
 Berks-0.170
groupon-0.167
Origin-0.162
Token-
Token ID12
Feature activation+1.82e+00

Pos logit contributions
 Deb+0.620
ourke+0.603
 Vand+0.592
$$+0.587
 「+0.585
Neg logit contributions
ahime-0.551
usterity-0.544
 Berks-0.493
groupon-0.477
Origin-0.468
Tokendrops
Token ID49253
Feature activation+2.74e+00

Pos logit contributions
 Deb+1.189
ourke+1.156
 Vand+1.129
$$+1.122
 「+1.116
Neg logit contributions
ahime-1.244
usterity-1.235
 Berks-1.125
groupon-1.089
Origin-1.070
Token-
Token ID12
Feature activation+3.84e-01

Pos logit contributions
 Deb+2.041
ourke+1.969
 Vand+1.937
$$+1.924
 「+1.918
Neg logit contributions
ahime-1.635
usterity-1.612
 Berks-1.449
groupon-1.396
Origin-1.371
Tokenre
Token ID260
Feature activation-1.04e+00

Pos logit contributions
 Deb+0.270
ourke+0.263
 Vand+0.259
$$+0.256
 「+0.256
Neg logit contributions
ahime-0.241
usterity-0.239
 Berks-0.216
groupon-0.211
adobe-0.206
Tokenza
Token ID4496
Feature activation-1.27e+00

Pos logit contributions
ahime+0.942
usterity+0.936
 Berks+0.871
groupon+0.859
adobe+0.845
Neg logit contributions
 Deb-0.447
ourke-0.426
 Vand-0.417
 「-0.408
$$-0.405
Token-
Token ID12
Feature activation+1.49e+00

Pos logit contributions
ahime+0.711
usterity+0.706
 Berks+0.630
groupon+0.610
adobe+0.593
Neg logit contributions
 Deb-0.987
ourke-0.961
 Vand-0.946
$$-0.939
 「-0.937
Tokenas
Token ID292
Feature activation+1.24e+00

Pos logit contributions
 Deb+0.872
ourke+0.857
 Vand+0.828
$$+0.828
 「+0.819
Neg logit contributions
usterity-1.098
ahime-1.097
 Berks-1.012
groupon-0.974
Origin-0.964
Tokenlan
Token ID9620
Feature activation-3.49e-01

Pos logit contributions
 Deb+0.939
ourke+0.935
$$+0.908
 Vand+0.905
 「+0.897
Neg logit contributions
usterity-0.694
ahime-0.693
 Berks-0.635
groupon-0.584
Origin-0.581
Token-
Token ID12
Feature activation-5.68e-01

Pos logit contributions
ahime+0.202
usterity+0.201
 Berks+0.180
groupon+0.174
Origin+0.170
Neg logit contributions
 Deb-0.262
ourke-0.255
 Vand-0.251
$$-0.249
 「-0.249
Tokenafter
Token ID8499
Feature activation+4.61e-01

Pos logit contributions
ahime+0.348
usterity+0.345
 Berks+0.313
groupon+0.306
adobe+0.298
Neg logit contributions
 Deb-0.407
ourke-0.394
 Vand-0.389
 「-0.385
$$-0.384
Token 5
Token ID642
Feature activation+1.48e+00

Pos logit contributions
ahime+1.865
usterity+1.856
 Berks+1.716
groupon+1.685
adobe+1.644
Neg logit contributions
 Deb-1.853
ourke-1.814
 Vand-1.756
 「-1.711
$$-1.706
Token))
Token ID4008
Feature activation-6.03e+00

Pos logit contributions
 Deb+0.884
ourke+0.855
 Vand+0.839
$$+0.834
 「+0.828
Neg logit contributions
ahime-1.087
usterity-1.079
 Berks-0.991
groupon-0.962
adobe-0.945
Token sq
Token ID19862
Feature activation+1.49e+00

Pos logit contributions
usterity+3.836
ahime+3.800
 Berks+3.453
groupon+3.440
Origin+3.438
Neg logit contributions
ourke-3.916
 Deb-3.891
 Vand-3.686
Sov-3.628
 「-3.617
TokenK
Token ID42
Feature activation-3.25e-01

Pos logit contributions
 Deb+0.884
ourke+0.855
 Vand+0.837
$$+0.830
 「+0.826
Neg logit contributions
ahime-1.100
usterity-1.093
 Berks-1.006
groupon-0.980
adobe-0.962
Tokenernel
Token ID7948
Feature activation+4.42e-01

Pos logit contributions
ahime+0.205
usterity+0.203
groupon+0.181
 Berks+0.180
Origin+0.179
Neg logit contributions
 Deb-0.229
ourke-0.219
 Vand-0.218
 「-0.215
$$-0.212
Token =
Token ID796
Feature activation-3.61e+00

Pos logit contributions
 Deb+0.253
ourke+0.245
 Vand+0.239
 「+0.236
$$+0.236
Neg logit contributions
ahime-0.336
usterity-0.334
 Berks-0.308
groupon-0.301
Origin-0.297
Token c
Token ID269
Feature activation+1.20e+00

Pos logit contributions
ahime+2.317
usterity+2.301
 Berks+2.108
groupon+2.089
Origin+2.055
Neg logit contributions
ourke-2.382
 Deb-2.375
 Vand-2.279
$$-2.259
 「-2.227
Tokenv
Token ID85
Feature activation-1.28e+00

Pos logit contributions
 Deb+0.780
ourke+0.757
 Vand+0.742
$$+0.736
 「+0.733
Neg logit contributions
ahime-0.819
usterity-0.813
 Berks-0.742
groupon-0.722
Origin-0.707
Token2
Token ID17
Feature activation+3.67e-01

Pos logit contributions
ahime+0.954
usterity+0.953
groupon+0.900
Origin+0.874
 Berks+0.867
Neg logit contributions
 Deb-0.722
ourke-0.700
 Vand-0.686
 「-0.672
 Seah-0.663
Token.
Token ID13
Feature activation-9.59e-01

Pos logit contributions
 Deb+0.239
ourke+0.233
 Vand+0.228
 「+0.225
$$+0.223
Neg logit contributions
ahime-0.247
usterity-0.246
 Berks-0.224
groupon-0.222
Origin-0.217
Tokenget
Token ID1136
Feature activation+1.15e+00

Pos logit contributions
ahime+0.576
usterity+0.570
 Berks+0.515
groupon+0.503
Origin+0.490
Neg logit contributions
 Deb-0.700
ourke-0.682
 Vand-0.670
 「-0.664
$$-0.661
Token.
Token ID13
Feature activation-1.89e-01

Pos logit contributions
 Deb+0.004
ourke+0.004
$$+0.004
 Vand+0.004
 「+0.004
Neg logit contributions
ahime-0.004
usterity-0.004
 Berks-0.004
groupon-0.004
Origin-0.004
Token Los
Token ID5401
Feature activation+6.86e-01

Pos logit contributions
ahime+0.107
usterity+0.107
 Berks+0.098
groupon+0.094
Origin+0.091
Neg logit contributions
 Deb-0.142
ourke-0.141
$$-0.136
 Vand-0.136
 「-0.136
Token Angeles
Token ID5652
Feature activation+7.00e-01

Pos logit contributions
 Deb+0.583
ourke+0.569
 Vand+0.561
$$+0.554
 「+0.553
Neg logit contributions
ahime-0.335
usterity-0.332
 Berks-0.288
groupon-0.280
Origin-0.270
Token,
Token ID11
Feature activation-9.74e-01

Pos logit contributions
 Deb+0.464
ourke+0.448
 Vand+0.443
 「+0.434
$$+0.433
Neg logit contributions
ahime-0.473
usterity-0.472
 Berks-0.425
groupon-0.417
adobe-0.407
Token CA
Token ID7257
Feature activation+1.19e+00

Pos logit contributions
ahime+0.632
usterity+0.626
 Berks+0.574
groupon+0.556
Origin+0.546
Neg logit contributions
 Deb-0.657
ourke-0.640
 Vand-0.626
$$-0.626
 「-0.621
Token :
Token ID1058
Feature activation-4.18e+00

Pos logit contributions
 Deb+0.823
ourke+0.794
 Vand+0.791
 「+0.775
$$+0.764
Neg logit contributions
ahime-0.772
usterity-0.767
 Berks-0.685
groupon-0.672
adobe-0.652
Token Western
Token ID4885
Feature activation+5.49e-01

Pos logit contributions
ahime+2.841
usterity+2.840
 Berks+2.777
groupon+2.594
Origin+2.584
Neg logit contributions
ourke-2.541
 Deb-2.443
$$-2.412
 「-2.363
Sov-2.332
Token Psychological
Token ID30583
Feature activation+1.71e-01

Pos logit contributions
 Deb+0.343
ourke+0.330
 Vand+0.326
 「+0.321
$$+0.320
Neg logit contributions
ahime-0.390
usterity-0.388
 Berks-0.353
groupon-0.346
adobe-0.339
Token Services
Token ID6168
Feature activation-3.53e-01

Pos logit contributions
 Deb+0.100
ourke+0.098
$$+0.095
 Vand+0.095
 「+0.094
Neg logit contributions
ahime-0.126
usterity-0.125
 Berks-0.116
groupon-0.112
Origin-0.111
Token.
Token ID764
Feature activation-3.60e+00

Pos logit contributions
ahime+0.263
usterity+0.261
 Berks+0.243
groupon+0.235
adobe+0.231
Neg logit contributions
 Deb-0.205
ourke-0.200
$$-0.194
 Vand-0.194
 「-0.192
Token
Token ID198
Feature activation-3.07e-01

Pos logit contributions
usterity+2.283
ahime+2.253
 Berks+2.190
groupon+2.156
Origin+2.118
Neg logit contributions
ourke-2.312
 Deb-2.249
 airst-2.183
mble-2.171
 「-2.167
Token,
Token ID11
Feature activation-7.93e-01

Pos logit contributions
ahime+1.088
usterity+1.083
 Berks+0.987
groupon+0.960
Origin+0.938
Neg logit contributions
 Deb-1.096
ourke-1.065
 Vand-1.045
$$-1.034
 「-1.031
Token your
Token ID534
Feature activation-2.06e+00

Pos logit contributions
ahime+0.548
usterity+0.545
 Berks+0.500
groupon+0.487
Origin+0.475
Neg logit contributions
 Deb-0.506
ourke-0.492
 Vand-0.482
$$-0.476
 「-0.474
Token body
Token ID1767
Feature activation-1.39e+00

Pos logit contributions
ahime+1.188
usterity+1.183
 Berks+1.073
groupon+1.033
Origin+1.003
Neg logit contributions
 Deb-1.534
ourke-1.503
 Vand-1.473
$$-1.459
 「-1.442
Token goes
Token ID2925
Feature activation-4.12e-01

Pos logit contributions
usterity+0.944
ahime+0.943
 Berks+0.863
groupon+0.838
Origin+0.822
Neg logit contributions
 Deb-0.898
ourke-0.871
 Vand-0.853
$$-0.841
 「-0.834
Token into
Token ID656
Feature activation-2.54e+00

Pos logit contributions
ahime+0.289
usterity+0.287
 Berks+0.264
groupon+0.257
adobe+0.251
Neg logit contributions
 Deb-0.259
ourke-0.252
 Vand-0.246
$$-0.243
 「-0.242
Token what
Token ID644
Feature activation-4.43e+00

Pos logit contributions
ahime+1.827
usterity+1.823
 Berks+1.678
groupon+1.624
adobe+1.591
Neg logit contributions
 Deb-1.534
ourke-1.497
 Vand-1.457
$$-1.444
 「-1.427
Token is
Token ID318
Feature activation-1.95e+00

Pos logit contributions
usterity+2.853
ahime+2.786
 Berks+2.690
groupon+2.575
fore+2.546
Neg logit contributions
ourke-2.861
 Deb-2.818
 Vand-2.723
$$-2.722
Sov-2.673
Token known
Token ID1900
Feature activation-3.26e+00

Pos logit contributions
usterity+1.266
ahime+1.266
 Berks+1.153
groupon+1.117
Origin+1.089
Neg logit contributions
 Deb-1.321
ourke-1.291
 Vand-1.264
$$-1.253
 「-1.243
Token as
Token ID355
Feature activation-1.19e+00

Pos logit contributions
ahime+1.870
usterity+1.867
 Berks+1.685
groupon+1.627
Origin+1.581
Neg logit contributions
 Deb-2.447
ourke-2.391
 Vand-2.354
$$-2.329
 「-2.314
Token the
Token ID262
Feature activation-2.13e-01

Pos logit contributions
ahime+0.847
usterity+0.847
 Berks+0.779
groupon+0.755
Origin+0.739
Neg logit contributions
 Deb-0.725
ourke-0.706
 Vand-0.690
$$-0.684
 「-0.675
Token post
Token ID1281
Feature activation-2.00e+00

Pos logit contributions
ahime+0.151
usterity+0.150
 Berks+0.137
groupon+0.134
Origin+0.131
Neg logit contributions
 Deb-0.133
ourke-0.129
 Vand-0.127
$$-0.125
 「-0.125
Token Current
Token ID9236
Feature activation+1.26e+00

Pos logit contributions
 Deb+0.280
ourke+0.271
 Vand+0.266
 「+0.263
$$+0.263
Neg logit contributions
ahime-0.266
usterity-0.263
 Berks-0.239
groupon-0.233
Origin-0.228
Token Population
Token ID20133
Feature activation-1.43e+00

Pos logit contributions
 Deb+0.610
ourke+0.574
 Vand+0.564
$$+0.556
 「+0.555
Neg logit contributions
ahime-1.080
usterity-1.075
 Berks-0.996
groupon-0.975
adobe-0.961
Token Survey
Token ID13084
Feature activation+4.54e-01

Pos logit contributions
ahime+1.033
usterity+1.024
 Berks+0.952
groupon+0.931
Origin+0.918
Neg logit contributions
ourke-0.830
 Deb-0.828
$$-0.803
 Vand-0.795
 「-0.791
Token data
Token ID1366
Feature activation-1.43e+00

Pos logit contributions
 Deb+0.305
ourke+0.297
 Vand+0.291
$$+0.289
 「+0.288
Neg logit contributions
ahime-0.299
usterity-0.297
 Berks-0.270
groupon-0.263
Origin-0.257
Token (
Token ID357
Feature activation+6.55e-01

Pos logit contributions
ahime+0.917
usterity+0.904
 Berks+0.822
groupon+0.801
Origin+0.784
Neg logit contributions
 Deb-0.986
ourke-0.965
 Vand-0.945
$$-0.940
 「-0.931
TokenIP
Token ID4061
Feature activation-4.25e+00

Pos logit contributions
 Deb+0.415
ourke+0.402
 Vand+0.394
$$+0.390
 「+0.389
Neg logit contributions
ahime-0.459
usterity-0.456
 Berks-0.417
groupon-0.406
Origin-0.398
TokenU
Token ID52
Feature activation-2.21e+00

Pos logit contributions
ahime+2.882
usterity+2.817
 Berks+2.561
Origin+2.529
groupon+2.522
Neg logit contributions
 Deb-2.728
ourke-2.695
 Vand-2.578
 「-2.561
$$-2.554
TokenMS
Token ID5653
Feature activation+3.18e-01

Pos logit contributions
ahime+1.446
usterity+1.428
 Berks+1.300
groupon+1.268
Origin+1.246
Neg logit contributions
 Deb-1.475
ourke-1.450
 Vand-1.418
$$-1.408
 「-1.401
Token-
Token ID12
Feature activation+1.16e+00

Pos logit contributions
 Deb+0.205
ourke+0.200
 Vand+0.195
$$+0.194
 「+0.193
Neg logit contributions
ahime-0.218
usterity-0.216
 Berks-0.198
groupon-0.193
Origin-0.189
TokenC
Token ID34
Feature activation+1.05e+00

Pos logit contributions
 Deb+0.710
ourke+0.687
 Vand+0.673
$$+0.667
 「+0.665
Neg logit contributions
ahime-0.834
usterity-0.828
 Berks-0.760
groupon-0.741
Origin-0.727
TokenPS
Token ID3705
Feature activation-1.47e+00

Pos logit contributions
 Deb+0.698
ourke+0.674
 Vand+0.663
$$+0.657
 「+0.657
Neg logit contributions
ahime-0.705
usterity-0.704
 Berks-0.640
groupon-0.622
adobe-0.610
Token and
Token ID290
Feature activation+3.73e-02

Pos logit contributions
ahime+0.897
usterity+0.897
 Berks+0.831
groupon+0.811
Origin+0.792
Neg logit contributions
 Deb-0.813
ourke-0.798
$$-0.783
 Vand-0.774
 「-0.757
Token upsetting
Token ID38423
Feature activation-2.28e+00

Pos logit contributions
 Deb+0.023
ourke+0.022
 Vand+0.022
$$+0.021
 「+0.021
Neg logit contributions
ahime-0.027
usterity-0.027
 Berks-0.024
groupon-0.024
Origin-0.023
Token places
Token ID4113
Feature activation-2.68e-01

Pos logit contributions
ahime+1.548
usterity+1.537
 Berks+1.435
groupon+1.392
Origin+1.373
Neg logit contributions
 Deb-1.426
ourke-1.398
$$-1.372
 Vand-1.359
Sov-1.320
Token.
Token ID13
Feature activation+3.70e-01

Pos logit contributions
ahime+0.182
usterity+0.181
 Berks+0.166
groupon+0.162
Origin+0.159
Neg logit contributions
 Deb-0.173
ourke-0.168
 Vand-0.165
$$-0.163
 「-0.162
Token Ne
Token ID3169
Feature activation-3.75e+00

Pos logit contributions
 Deb+0.218
ourke+0.213
 Vand+0.206
$$+0.205
 「+0.204
Neg logit contributions
ahime-0.273
usterity-0.270
 Berks-0.250
groupon-0.244
Origin-0.240
Tokenonom
Token ID6326
Feature activation-4.16e+00

Pos logit contributions
ahime+2.966
usterity+2.960
 Berks+2.726
groupon+2.670
Origin+2.647
Neg logit contributions
 Deb-2.016
 Vand-1.920
ourke-1.916
$$-1.840
 「-1.828
Tokenicon
Token ID4749
Feature activation-3.65e+00

Pos logit contributions
ahime+0.913
usterity+0.855
groupon+0.600
 Berks+0.580
adobe+0.517
Neg logit contributions
 Deb-4.638
 Vand-4.526
ourke-4.468
$$-4.410
 「-4.409
Token,
Token ID11
Feature activation-2.12e+00

Pos logit contributions
ahime+2.397
usterity+2.370
 Berks+2.181
groupon+2.129
Origin+2.098
Neg logit contributions
 Deb-2.376
ourke-2.333
 Vand-2.268
$$-2.249
 「-2.226
Token for
Token ID329
Feature activation+1.83e+00

Pos logit contributions
ahime+1.407
usterity+1.391
 Berks+1.284
groupon+1.247
Origin+1.226
Neg logit contributions
 Deb-1.373
ourke-1.353
 Vand-1.315
$$-1.312
 「-1.297
Token example
Token ID1672
Feature activation+3.30e+00

Pos logit contributions
 Deb+0.924
ourke+0.882
 Vand+0.866
 「+0.851
$$+0.848
Neg logit contributions
ahime-1.515
usterity-1.513
 Berks-1.398
groupon-1.369
adobe-1.351
Token,
Token ID11
Feature activation+1.24e+00

Pos logit contributions
 Deb+2.054
ourke+1.980
 Vand+1.961
 「+1.950
$$+1.926
Neg logit contributions
usterity-2.351
ahime-2.339
 Berks-2.118
groupon-2.068
adobe-2.051
Token
Token ID198
Feature activation+7.21e-01

Pos logit contributions
usterity+2.034
ahime+2.020
 Berks+1.906
groupon+1.840
trust+1.815
Neg logit contributions
ourke-1.683
 Deb-1.662
 「-1.591
 Vand-1.590
Sov-1.568
Token
Token ID198
Feature activation+1.39e-01

Pos logit contributions
 Deb+0.416
ourke+0.404
 Vand+0.394
$$+0.389
 「+0.389
Neg logit contributions
ahime-0.542
usterity-0.540
 Berks-0.497
groupon-0.487
Origin-0.478
Tokenpub
Token ID12984
Feature activation-3.71e+00

Pos logit contributions
 Deb+0.087
ourke+0.084
 Vand+0.082
 「+0.081
$$+0.080
Neg logit contributions
ahime-0.099
usterity-0.099
 Berks-0.090
groupon-0.089
Origin-0.088
Token struct
Token ID2878
Feature activation-2.55e+00

Pos logit contributions
ahime+2.845
usterity+2.842
 Berks+2.634
groupon+2.569
Origin+2.548
Neg logit contributions
 Deb-2.037
ourke-2.005
 Vand-1.924
 「-1.913
$$-1.913
Token Shared
Token ID39403
Feature activation-7.22e-01

Pos logit contributions
ahime+1.642
usterity+1.621
 Berks+1.514
groupon+1.448
Origin+1.428
Neg logit contributions
ourke-1.699
 Deb-1.673
$$-1.618
 「-1.615
Sov-1.595
Token <
Token ID1279
Feature activation-6.16e+00

Pos logit contributions
ahime+0.389
usterity+0.386
 Berks+0.344
groupon+0.332
Origin+0.324
Neg logit contributions
 Deb-0.573
ourke-0.559
 Vand-0.550
$$-0.546
 「-0.545
Token '
Token ID705
Feature activation-7.27e-01

Pos logit contributions
usterity+4.006
ahime+3.989
 Berks+3.768
Origin+3.667
trust+3.572
Neg logit contributions
ourke-3.837
 Deb-3.772
 「-3.715
Sov-3.681
 Vand-3.651
Tokena
Token ID64
Feature activation-5.26e-01

Pos logit contributions
ahime+0.544
usterity+0.539
 Berks+0.497
groupon+0.494
Origin+0.483
Neg logit contributions
 Deb-0.417
ourke-0.406
 Vand-0.397
 「-0.393
$$-0.387
Token,
Token ID837
Feature activation-5.47e+00

Pos logit contributions
ahime+0.360
usterity+0.356
 Berks+0.325
groupon+0.317
adobe+0.310
Neg logit contributions
 Deb-0.344
ourke-0.333
 Vand-0.327
$$-0.324
 「-0.322
Token T
Token ID309
Feature activation-4.34e-01

Pos logit contributions
ahime+3.503
usterity+3.492
 Berks+3.252
groupon+3.113
Origin+3.112
Neg logit contributions
 Deb-3.554
ourke-3.547
 「-3.406
$$-3.400
 Vand-3.393
Token :
Token ID1058
Feature activation-6.62e+00

Pos logit contributions
ahime+0.323
usterity+0.321
 Berks+0.295
groupon+0.288
adobe+0.282
Neg logit contributions
 Deb-0.256
ourke-0.248
 Vand-0.243
$$-0.240
 「-0.239