TOP ACTIVATIONS
MAX = 2.626

. <|endoftext|> Abstract Background Depression presents a significant burden
grat ifications of what she calls , dry ly ,
paste and mix well . Season with salt , pepper and
Anna ." She bit her lip in a cute
doing it ? Background matters The idea
Reed makes against what he calls elect oral itis
blockchain capacity : https :// bit co int alk . org
the dungeon ( what we call our tv room in the
room and enjoy what she called ' g ems from students
life on the streets a bit more difficult .
the Conservative government is a bit like a boat without a
where they were in a bit of a familiar pattern ?
that would govern what it calls Ro java - the Kurdish
towel - lined plate . Serve hot ! 1
The film seemed every bit as sensational istic as its
121 24 International goals As of 12
ours that everybody offers a bit of leadership here and there
, because you do ,' Mrs . Obama said . '
a critic of what he called perceived integration problems among immigrants
Fiorina spoke about what she calls the War on Women in

MIN ACTIVATIONS
MIN = -2.637

Haas an s Vish war oop am ( 2013
the temple dedicated to Lord Vish nu , here known as
Standing Lord Gan esh and Vish nu D urga also have
by blocking national highway connecting Roh t ak to Delhi .
16 , violence erupted in Roh t ak city which continued
, including paraly tic and diarr hetic shell fish poisoning in
The Chronicle 2 of 15 Photo : Le a Suzuki ,
and normally none of the Vish nu temple have a shrine
Sync is turned off by default and has to be enabled
Hide Caption 4 of 15 Photos : Carly Fiorina 's political
is that it can skip default values . In my comparison
hur rying back to where Ruk ia was waiting . When
of the study is that carbon emission and climate change -
to the recent National Labor Relations Board attack on Boeing 's
The Chronicle 3 of 15 Photo : Le a Suzuki ,
ign iting speculation about secret Oval Office recordings is like a
1941 , Germany launched Operation Barbar oss a , an invasion
belt which comprises parts of Roh t ak , J ind
. V . All rights reserved . <|endoftext|> On the heels
23 22 62 13 ( Photo 11 : SA UL LO

INTERVAL 1.310 - 2.626
CONTAINS 0.130%

over several months . <|endoftext|> Outside linebacker Ryan Ker rigan grabs
slowed them down a little bit better than we could .
to use or how to call another person out . He
ils ont mont é une n ou vel le organisation ind
, the commission of inquiry treated the two parts as a

INTERVAL -0.005 - 1.310
CONTAINS 49.572%

no mercy , and his forces step up their assaults on
65 1 / 3 IP Kevin Qu ack en
going to go all 1984 on other books in your Kindle
but ask any one of the players who has don ned
traff icked thorough f ares which she considers urban thru

INTERVAL -1.321 - -0.005
CONTAINS 50.167%

bear the wh ips and sc orns of time ,
b ikers dislike the st eeper paths up to Lynd ale
get the impression that the house was moved there and then
Ann al ise . There s a huge assumption
Mech an ically , I think it worked great

INTERVAL -2.637 - -1.321
CONTAINS 0.129%

or ail it put Brock way , Og den ville
an explanation Monday of the unprecedented misc ue , along with
Q : A human resource person could work for every
don 't mess with ' em !" At that moment ,
man ovsky Museum in northern Siber a and named Ly uba
Token.
Token ID13
Feature activation-2.98e-01

Pos logit contributions
��+2.804
haar+2.236
isphere+2.118
+2.081
yrus+1.953
Neg logit contributions
Rated-1.924
 whisper-1.863
Marginal-1.683
 Minutes-1.668
arella-1.641
Token<|endoftext|>
Token ID50256
Feature activation-5.23e-02

Pos logit contributions
��+0.766
haar+0.608
isphere+0.565
+0.561
yrus+0.524
Neg logit contributions
Rated-0.580
 whisper-0.568
Marginal-0.513
arella-0.504
ktop-0.499
TokenAbstract
Token ID23839
Feature activation+6.35e-01

Pos logit contributions
��+0.132
haar+0.104
isphere+0.098
+0.097
yrus+0.089
Neg logit contributions
 whisper-0.105
Rated-0.103
 Minutes-0.094
arella-0.094
 nearer-0.093
Token
Token ID198
Feature activation+2.73e-01

Pos logit contributions
Rated+1.106
 whisper+1.074
Marginal+0.955
 Minutes+0.947
arella+0.936
Neg logit contributions
��-1.801
haar-1.456
isphere-1.380
-1.350
yrus-1.276
Token
Token ID198
Feature activation+2.53e-01

Pos logit contributions
Rated+0.482
 whisper+0.476
Marginal+0.421
arella+0.421
uries+0.418
Neg logit contributions
��-0.744
haar-0.611
isphere-0.571
-0.563
yrus-0.530
TokenBackground
Token ID21756
Feature activation+2.63e+00

Pos logit contributions
 whisper+0.530
Rated+0.525
 Minutes+0.477
arella+0.474
 nearer+0.468
Neg logit contributions
��-0.621
haar-0.485
isphere-0.455
-0.445
yrus-0.412
Token Depression
Token ID22483
Feature activation+8.96e-02

Pos logit contributions
Rated+4.879
 whisper+4.703
 Minutes+4.329
Marginal+4.249
 Speaker+4.221
Neg logit contributions
��-7.014
haar-5.558
isphere-5.237
-5.174
yrus-4.850
Token presents
Token ID10969
Feature activation+2.36e-01

Pos logit contributions
Rated+0.167
 whisper+0.162
Marginal+0.146
 Minutes+0.143
arella+0.142
Neg logit contributions
��-0.241
haar-0.194
isphere-0.185
-0.181
yrus-0.171
Token a
Token ID257
Feature activation-6.03e-02

Pos logit contributions
Rated+0.459
 whisper+0.442
Marginal+0.404
 Minutes+0.399
arella+0.395
Neg logit contributions
��-0.616
haar-0.488
isphere-0.464
-0.451
yrus-0.425
Token significant
Token ID2383
Feature activation+6.55e-01

Pos logit contributions
��+0.152
haar+0.119
isphere+0.112
+0.108
yrus+0.102
Neg logit contributions
Rated-0.125
 whisper-0.119
 Minutes-0.109
Marginal-0.109
arella-0.108
Token burden
Token ID10538
Feature activation-3.94e-01

Pos logit contributions
Rated+1.327
 whisper+1.280
 Minutes+1.164
Marginal+1.160
arella+1.148
Neg logit contributions
��-1.674
haar-1.323
isphere-1.238
-1.207
yrus-1.133
Token grat
Token ID14586
Feature activation+1.07e+00

Pos logit contributions
Rated+0.321
 whisper+0.302
Marginal+0.278
 Minutes+0.275
arella+0.274
Neg logit contributions
��-0.452
haar-0.359
isphere-0.340
-0.331
yrus-0.315
Tokenifications
Token ID6637
Feature activation+5.38e-01

Pos logit contributions
Rated+1.915
 whisper+1.860
Marginal+1.658
 Minutes+1.641
arella+1.623
Neg logit contributions
��-2.995
haar-2.424
isphere-2.297
-2.236
yrus-2.118
Token of
Token ID286
Feature activation+1.59e-01

Pos logit contributions
Rated+0.949
 whisper+0.912
Marginal+0.814
 Minutes+0.811
arella+0.806
Neg logit contributions
��-1.514
haar-1.224
isphere-1.160
-1.133
yrus-1.072
Token what
Token ID644
Feature activation+2.24e-01

Pos logit contributions
Rated+0.316
 whisper+0.302
Marginal+0.277
 Minutes+0.273
arella+0.272
Neg logit contributions
��-0.411
haar-0.325
isphere-0.308
-0.298
yrus-0.281
Token she
Token ID673
Feature activation+5.26e-01

Pos logit contributions
Rated+0.421
 whisper+0.407
Marginal+0.367
arella+0.366
 Minutes+0.363
Neg logit contributions
��-0.602
haar-0.480
isphere-0.452
-0.444
yrus-0.419
Token calls
Token ID3848
Feature activation+2.46e+00

Pos logit contributions
Rated+0.936
 whisper+0.898
Marginal+0.815
 Minutes+0.811
arella+0.796
Neg logit contributions
��-1.463
haar-1.186
isphere-1.125
-1.100
yrus-1.033
Token,
Token ID11
Feature activation+1.95e-01

Pos logit contributions
Rated+4.530
 whisper+4.505
Marginal+3.993
 Minutes+3.960
 nearer+3.910
Neg logit contributions
��-6.543
haar-5.262
isphere-4.968
-4.807
yrus-4.513
Token dry
Token ID5894
Feature activation-7.51e-01

Pos logit contributions
Rated+0.356
 whisper+0.338
Marginal+0.309
 Minutes+0.306
arella+0.301
Neg logit contributions
��-0.534
haar-0.428
isphere-0.405
-0.396
yrus-0.377
Tokenly
Token ID306
Feature activation+5.92e-01

Pos logit contributions
��+1.973
haar+1.565
isphere+1.482
+1.462
yrus+1.390
Neg logit contributions
Rated-1.445
 whisper-1.338
Marginal-1.255
 Minutes-1.238
ktop-1.226
Token,
Token ID11
Feature activation+9.60e-02

Pos logit contributions
Rated+1.055
 whisper+1.030
Marginal+0.915
 Minutes+0.906
arella+0.897
Neg logit contributions
��-1.656
haar-1.334
isphere-1.264
-1.235
yrus-1.166
Token
Token ID564
Feature activation+4.15e-02

Pos logit contributions
Rated+0.184
 whisper+0.176
Marginal+0.160
 Minutes+0.158
arella+0.157
Neg logit contributions
��-0.256
haar-0.203
isphere-0.192
-0.188
yrus-0.178
Token paste
Token ID17008
Feature activation-1.06e-01

Pos logit contributions
��+0.199
haar+0.158
isphere+0.149
+0.145
yrus+0.138
Neg logit contributions
Rated-0.151
 whisper-0.143
Marginal-0.132
 Minutes-0.130
arella-0.129
Token and
Token ID290
Feature activation-3.81e-02

Pos logit contributions
��+0.284
haar+0.230
isphere+0.216
+0.209
yrus+0.200
Neg logit contributions
Rated-0.197
 whisper-0.188
Marginal-0.172
 Minutes-0.169
arella-0.166
Token mix
Token ID5022
Feature activation+1.65e+00

Pos logit contributions
��+0.111
haar+0.089
isphere+0.084
+0.082
yrus+0.079
Neg logit contributions
Rated-0.065
 whisper-0.060
Marginal-0.056
 Minutes-0.054
arella-0.054
Token well
Token ID880
Feature activation+5.00e-01

Pos logit contributions
Rated+3.028
 whisper+2.967
Marginal+2.627
 Minutes+2.617
arella+2.607
Neg logit contributions
��-4.524
haar-3.625
isphere-3.432
-3.359
yrus-3.155
Token.
Token ID13
Feature activation-8.18e-02

Pos logit contributions
Rated+0.882
 whisper+0.854
Marginal+0.767
 Minutes+0.755
arella+0.743
Neg logit contributions
��-1.407
haar-1.137
isphere-1.073
-1.049
yrus-0.992
Token Season
Token ID7369
Feature activation+2.39e+00

Pos logit contributions
��+0.215
haar+0.170
isphere+0.158
+0.154
yrus+0.146
Neg logit contributions
Rated-0.158
 whisper-0.153
Marginal-0.139
uries-0.136
 nearer-0.136
Token with
Token ID351
Feature activation+2.92e-01

Pos logit contributions
Rated+4.101
 whisper+4.071
arella+3.535
 Minutes+3.529
Marginal+3.483
Neg logit contributions
��-6.667
haar-5.404
isphere-5.135
-5.068
yrus-4.767
Token salt
Token ID8268
Feature activation+6.81e-01

Pos logit contributions
Rated+0.682
 whisper+0.645
Marginal+0.606
uries+0.597
ktop+0.594
Neg logit contributions
��-0.660
haar-0.503
isphere-0.467
-0.445
yrus-0.418
Token,
Token ID11
Feature activation+1.06e-02

Pos logit contributions
Rated+1.225
 whisper+1.187
Marginal+1.062
 Minutes+1.051
arella+1.038
Neg logit contributions
��-1.894
haar-1.524
isphere-1.443
-1.410
yrus-1.332
Token pepper
Token ID13385
Feature activation+4.39e-01

Pos logit contributions
Rated+0.014
 whisper+0.013
Marginal+0.011
 Minutes+0.011
uries+0.011
Neg logit contributions
��-0.035
haar-0.029
isphere-0.028
-0.027
yrus-0.026
Token and
Token ID290
Feature activation+2.38e-01

Pos logit contributions
Rated+0.790
 whisper+0.768
Marginal+0.685
 Minutes+0.679
arella+0.672
Neg logit contributions
��-1.222
haar-0.984
isphere-0.931
-0.910
yrus-0.859
Token Anna
Token ID11735
Feature activation+4.58e-01

Pos logit contributions
Rated+0.129
 whisper+0.124
Marginal+0.116
 Minutes+0.113
arella+0.112
Neg logit contributions
��-0.154
haar-0.120
isphere-0.112
-0.110
yrus-0.103
Token."
Token ID526
Feature activation+4.72e-03

Pos logit contributions
Rated+0.756
 whisper+0.731
Marginal+0.648
 Minutes+0.641
arella+0.633
Neg logit contributions
��-1.342
haar-1.091
isphere-1.037
-1.016
yrus-0.963
Token
Token ID198
Feature activation-1.26e-01

Pos logit contributions
Rated+0.008
 whisper+0.008
Marginal+0.007
 Minutes+0.007
arella+0.007
Neg logit contributions
��-0.013
haar-0.011
isphere-0.010
-0.010
yrus-0.010
Token
Token ID198
Feature activation-4.13e-02

Pos logit contributions
��+0.324
haar+0.268
isphere+0.248
+0.246
yrus+0.231
Neg logit contributions
Rated-0.231
 whisper-0.229
Marginal-0.205
arella-0.203
uries-0.203
TokenShe
Token ID3347
Feature activation+5.18e-01

Pos logit contributions
��+0.115
haar+0.093
isphere+0.087
+0.087
yrus+0.081
Neg logit contributions
 whisper-0.072
Rated-0.071
 Minutes-0.063
arella-0.063
 nearer-0.062
Token bit
Token ID1643
Feature activation+2.38e+00

Pos logit contributions
Rated+0.948
 whisper+0.891
Marginal+0.826
 Minutes+0.802
arella+0.800
Neg logit contributions
��-1.429
haar-1.156
isphere-1.090
-1.056
yrus-1.010
Token her
Token ID607
Feature activation+4.73e-01

Pos logit contributions
Rated+3.340
 whisper+3.318
Marginal+2.793
 nearer+2.786
arella+2.772
Neg logit contributions
��-7.416
haar-6.136
isphere-5.880
-5.764
yrus-5.415
Token lip
Token ID10645
Feature activation+5.86e-01

Pos logit contributions
Rated+0.592
 whisper+0.531
Marginal+0.473
 Minutes+0.469
uries+0.461
Neg logit contributions
��-1.584
haar-1.320
isphere-1.259
-1.239
yrus-1.196
Token in
Token ID287
Feature activation+4.49e-03

Pos logit contributions
Rated+1.049
 whisper+1.004
Marginal+0.909
 Minutes+0.895
arella+0.884
Neg logit contributions
��-1.637
haar-1.321
isphere-1.249
-1.220
yrus-1.156
Token a
Token ID257
Feature activation-7.31e-02

Pos logit contributions
Rated+0.009
 whisper+0.009
Marginal+0.008
 Minutes+0.008
arella+0.008
Neg logit contributions
��-0.011
haar-0.009
isphere-0.008
-0.008
yrus-0.008
Token cute
Token ID13779
Feature activation+2.73e-01

Pos logit contributions
��+0.197
haar+0.159
isphere+0.149
+0.144
yrus+0.137
Neg logit contributions
Rated-0.139
 whisper-0.123
Marginal-0.119
 Minutes-0.118
arella-0.116
Token doing
Token ID1804
Feature activation-2.56e-01

Pos logit contributions
Rated+0.013
 whisper+0.012
Marginal+0.011
 Minutes+0.011
arella+0.011
Neg logit contributions
��-0.016
haar-0.013
isphere-0.012
-0.012
yrus-0.011
Token it
Token ID340
Feature activation+1.65e-01

Pos logit contributions
��+0.567
haar+0.424
isphere+0.392
+0.385
yrus+0.352
Neg logit contributions
Rated-0.608
 whisper-0.587
Marginal-0.542
arella-0.539
 Minutes-0.534
Token?
Token ID30
Feature activation-3.13e-01

Pos logit contributions
Rated+0.328
 whisper+0.318
Marginal+0.287
 Minutes+0.286
arella+0.283
Neg logit contributions
��-0.425
haar-0.337
isphere-0.317
-0.310
yrus-0.290
Token
Token ID198
Feature activation+2.98e-02

Pos logit contributions
��+0.837
haar+0.672
isphere+0.632
+0.620
yrus+0.582
Neg logit contributions
Rated-0.584
 whisper-0.570
Marginal-0.508
arella-0.504
wives-0.497
Token
Token ID198
Feature activation+5.23e-02

Pos logit contributions
Rated+0.054
 whisper+0.053
arella+0.047
Marginal+0.047
uries+0.047
Neg logit contributions
��-0.079
haar-0.065
isphere-0.060
-0.059
yrus-0.056
TokenBackground
Token ID21756
Feature activation+2.37e+00

Pos logit contributions
 whisper+0.111
Rated+0.110
arella+0.100
 Minutes+0.100
 nearer+0.099
Neg logit contributions
��-0.126
haar-0.098
isphere-0.091
-0.091
yrus-0.083
Token matters
Token ID6067
Feature activation+5.25e-01

Pos logit contributions
Rated+3.891
 whisper+3.799
 Minutes+3.368
Marginal+3.342
arella+3.252
Neg logit contributions
��-6.845
haar-5.584
isphere-5.281
-5.194
yrus-4.903
Token
Token ID198
Feature activation-5.33e-02

Pos logit contributions
Rated+0.959
 whisper+0.926
Marginal+0.833
 Minutes+0.821
arella+0.815
Neg logit contributions
��-1.445
haar-1.161
isphere-1.098
-1.073
yrus-1.016
Token
Token ID198
Feature activation-1.12e-02

Pos logit contributions
��+0.139
haar+0.115
isphere+0.106
+0.105
yrus+0.099
Neg logit contributions
Rated-0.097
 whisper-0.096
arella-0.086
Marginal-0.085
uries-0.085
TokenThe
Token ID464
Feature activation+3.16e-01

Pos logit contributions
��+0.027
haar+0.021
isphere+0.020
+0.020
yrus+0.018
Neg logit contributions
 whisper-0.024
Rated-0.023
 Minutes-0.021
arella-0.021
 nearer-0.021
Token idea
Token ID2126
Feature activation+3.30e-01

Pos logit contributions
Rated+0.569
 whisper+0.552
Marginal+0.495
arella+0.490
 Minutes+0.486
Neg logit contributions
��-0.876
haar-0.701
isphere-0.662
-0.647
yrus-0.612
Token Reed
Token ID16105
Feature activation+2.08e-01

Pos logit contributions
��+1.233
haar+0.964
isphere+0.916
+0.891
yrus+0.845
Neg logit contributions
Rated-0.979
 whisper-0.950
Marginal-0.858
 Minutes-0.850
arella-0.840
Token makes
Token ID1838
Feature activation+2.42e-01

Pos logit contributions
Rated+0.476
 whisper+0.467
Marginal+0.427
 Minutes+0.425
arella+0.420
Neg logit contributions
��-0.477
haar-0.364
isphere-0.338
-0.329
yrus-0.304
Token against
Token ID1028
Feature activation-3.86e-01

Pos logit contributions
Rated+0.453
 whisper+0.437
Marginal+0.392
 Minutes+0.391
arella+0.388
Neg logit contributions
��-0.654
haar-0.524
isphere-0.492
-0.481
yrus-0.454
Token what
Token ID644
Feature activation-1.23e-02

Pos logit contributions
��+0.963
haar+0.747
isphere+0.692
+0.675
yrus+0.642
Neg logit contributions
Rated-0.802
 whisper-0.777
Marginal-0.710
 Minutes-0.705
arella-0.700
Token he
Token ID339
Feature activation+2.69e-01

Pos logit contributions
��+0.031
haar+0.024
isphere+0.023
+0.022
yrus+0.021
Neg logit contributions
Rated-0.025
 whisper-0.024
arella-0.022
Marginal-0.022
 Minutes-0.022
Token calls
Token ID3848
Feature activation+2.32e+00

Pos logit contributions
Rated+0.473
 whisper+0.457
Marginal+0.410
 Minutes+0.407
arella+0.401
Neg logit contributions
��-0.757
haar-0.611
isphere-0.580
-0.568
yrus-0.532
Token
Token ID564
Feature activation+2.48e-01

Pos logit contributions
Rated+4.483
 whisper+4.384
Marginal+3.982
 Minutes+3.938
 Speaker+3.927
Neg logit contributions
��-5.897
haar-4.747
isphere-4.524
-4.349
yrus-4.059
Token
Token ID250
Feature activation-2.96e-02

Pos logit contributions
Rated+0.535
 whisper+0.523
Marginal+0.476
 Minutes+0.473
arella+0.469
Neg logit contributions
��-0.603
haar-0.468
isphere-0.438
-0.426
yrus-0.397
Tokenelect
Token ID9509
Feature activation-6.04e-01

Pos logit contributions
��+0.075
haar+0.059
isphere+0.055
+0.054
yrus+0.050
Neg logit contributions
Rated-0.060
 whisper-0.060
 Minutes-0.054
arella-0.053
Marginal-0.053
Tokenoral
Token ID6864
Feature activation-1.23e+00

Pos logit contributions
��+1.570
haar+1.249
isphere+1.175
+1.151
yrus+1.083
Neg logit contributions
Rated-1.164
 whisper-1.138
 Minutes-1.027
Marginal-1.022
arella-1.014
Tokenitis
Token ID11815
Feature activation-1.51e-01

Pos logit contributions
��+3.134
haar+2.420
+2.320
isphere+2.290
yrus+2.110
Neg logit contributions
Rated-2.422
 whisper-2.293
 Minutes-2.128
arella-2.101
ktop-2.095
Token blockchain
Token ID11779
Feature activation-3.35e-01

Pos logit contributions
Rated+0.310
 whisper+0.293
Marginal+0.275
arella+0.270
 Minutes+0.268
Neg logit contributions
��-0.390
haar-0.307
isphere-0.289
-0.280
yrus-0.264
Token capacity
Token ID5339
Feature activation+2.42e-02

Pos logit contributions
��+0.806
haar+0.636
isphere+0.590
+0.579
yrus+0.542
Neg logit contributions
Rated-0.715
 whisper-0.686
Marginal-0.639
 Minutes-0.626
arella-0.622
Token:
Token ID25
Feature activation-2.66e-01

Pos logit contributions
Rated+0.046
 whisper+0.045
Marginal+0.040
 Minutes+0.040
arella+0.039
Neg logit contributions
��-0.064
haar-0.052
isphere-0.049
-0.048
yrus-0.045
Token https
Token ID3740
Feature activation+3.26e-01

Pos logit contributions
��+0.651
haar+0.505
isphere+0.471
+0.463
yrus+0.428
Neg logit contributions
Rated-0.567
 whisper-0.546
Marginal-0.505
arella-0.494
 Minutes-0.493
Token://
Token ID1378
Feature activation+5.68e-01

Pos logit contributions
Rated+0.717
 whisper+0.714
Marginal+0.644
 Minutes+0.642
arella+0.639
Neg logit contributions
��-0.747
haar-0.591
isphere-0.541
-0.536
yrus-0.491
Tokenbit
Token ID2545
Feature activation+2.31e+00

Pos logit contributions
Rated+1.178
 whisper+1.148
Marginal+1.044
 Minutes+1.035
arella+1.025
Neg logit contributions
��-1.418
haar-1.118
isphere-1.051
-1.023
yrus-0.957
Tokenco
Token ID1073
Feature activation+4.81e-01

Pos logit contributions
Rated+3.662
 whisper+3.545
arella+3.096
 Minutes+3.065
Marginal+3.049
Neg logit contributions
��-6.880
haar-5.566
isphere-5.262
-5.169
yrus-4.867
Tokenint
Token ID600
Feature activation+2.60e-01

Pos logit contributions
Rated+0.876
 whisper+0.846
Marginal+0.766
 Minutes+0.751
arella+0.737
Neg logit contributions
��-1.318
haar-1.074
isphere-1.022
-0.981
yrus-0.938
Tokenalk
Token ID971
Feature activation+2.67e-01

Pos logit contributions
Rated+0.449
 whisper+0.431
Marginal+0.386
 Minutes+0.380
 nearer+0.373
Neg logit contributions
��-0.745
haar-0.600
isphere-0.575
-0.564
yrus-0.537
Token.
Token ID13
Feature activation-1.33e-02

Pos logit contributions
Rated+0.492
 whisper+0.475
Marginal+0.433
 Minutes+0.419
arella+0.416
Neg logit contributions
��-0.721
haar-0.588
isphere-0.556
-0.538
yrus-0.513
Tokenorg
Token ID2398
Feature activation+6.99e-01

Pos logit contributions
��+0.028
haar+0.021
isphere+0.019
+0.018
yrus+0.016
Neg logit contributions
Rated-0.034
 whisper-0.032
Marginal-0.030
arella-0.030
 Minutes-0.030
Token the
Token ID262
Feature activation-2.12e-01

Pos logit contributions
��+0.709
haar+0.561
isphere+0.527
+0.519
yrus+0.486
Neg logit contributions
Rated-0.533
 whisper-0.508
Marginal-0.475
arella-0.462
 Minutes-0.459
Token dungeon
Token ID18974
Feature activation-2.14e-01

Pos logit contributions
��+0.550
haar+0.440
isphere+0.415
+0.401
yrus+0.382
Neg logit contributions
Rated-0.410
 whisper-0.393
Marginal-0.363
arella-0.355
 Minutes-0.355
Token (
Token ID357
Feature activation-2.43e-01

Pos logit contributions
��+0.577
haar+0.466
isphere+0.441
+0.430
yrus+0.406
Neg logit contributions
Rated-0.394
 whisper-0.376
Marginal-0.345
 Minutes-0.340
arella-0.335
Tokenwhat
Token ID10919
Feature activation-2.72e-01

Pos logit contributions
��+0.610
haar+0.481
isphere+0.449
+0.441
yrus+0.410
Neg logit contributions
Rated-0.497
 whisper-0.489
Marginal-0.443
 Minutes-0.442
arella-0.438
Token we
Token ID356
Feature activation+3.79e-01

Pos logit contributions
��+0.711
haar+0.569
isphere+0.537
+0.521
yrus+0.492
Neg logit contributions
Rated-0.527
 whisper-0.508
Marginal-0.465
arella-0.460
 Minutes-0.457
Token call
Token ID869
Feature activation+2.26e+00

Pos logit contributions
Rated+0.616
 whisper+0.589
Marginal+0.531
 Minutes+0.526
arella+0.516
Neg logit contributions
��-1.114
haar-0.915
isphere-0.867
-0.849
yrus-0.804
Token our
Token ID674
Feature activation+7.35e-02

Pos logit contributions
Rated+4.369
 whisper+4.331
 Minutes+3.855
 Speaker+3.797
Marginal+3.795
Neg logit contributions
��-5.744
haar-4.585
isphere-4.354
-4.174
yrus-3.946
Token tv
Token ID31557
Feature activation+5.46e-01

Pos logit contributions
Rated+0.136
 whisper+0.131
Marginal+0.119
 Minutes+0.117
arella+0.116
Neg logit contributions
��-0.200
haar-0.161
isphere-0.152
-0.148
yrus-0.140
Token room
Token ID2119
Feature activation-1.54e-01

Pos logit contributions
Rated+1.037
 whisper+1.007
Marginal+0.912
 Minutes+0.901
arella+0.888
Neg logit contributions
��-1.456
haar-1.173
isphere-1.111
-1.073
yrus-1.022
Token in
Token ID287
Feature activation-1.75e-01

Pos logit contributions
��+0.404
haar+0.324
isphere+0.307
+0.297
yrus+0.281
Neg logit contributions
Rated-0.297
 whisper-0.286
Marginal-0.261
 Minutes-0.258
arella-0.254
Token the
Token ID262
Feature activation-2.77e-01

Pos logit contributions
��+0.443
haar+0.348
isphere+0.325
+0.320
yrus+0.299
Neg logit contributions
Rated-0.357
 whisper-0.345
Marginal-0.315
 Minutes-0.310
arella-0.310
Token room
Token ID2119
Feature activation+2.05e-01

Pos logit contributions
Rated+1.523
 whisper+1.470
Marginal+1.335
arella+1.322
 Minutes+1.314
Neg logit contributions
��-2.239
haar-1.790
isphere-1.704
-1.647
yrus-1.560
Token and
Token ID290
Feature activation+1.73e-01

Pos logit contributions
Rated+0.361
 whisper+0.340
Marginal+0.318
 Minutes+0.307
arella+0.304
Neg logit contributions
��-0.572
haar-0.462
isphere-0.443
-0.429
yrus-0.408
Token enjoy
Token ID2883
Feature activation+3.39e-01

Pos logit contributions
Rated+0.305
 whisper+0.274
Marginal+0.267
arella+0.260
+0.258
Neg logit contributions
��-0.487
haar-0.389
isphere-0.374
-0.355
yrus-0.348
Token what
Token ID644
Feature activation+4.07e-01

Pos logit contributions
Rated+0.717
 whisper+0.687
Marginal+0.639
arella+0.627
 Minutes+0.623
Neg logit contributions
��-0.839
haar-0.647
isphere-0.611
-0.588
yrus-0.554
Token she
Token ID673
Feature activation+7.37e-01

Pos logit contributions
Rated+0.851
 whisper+0.816
Marginal+0.757
arella+0.745
 Minutes+0.730
Neg logit contributions
��-1.017
haar-0.787
isphere-0.743
-0.708
yrus-0.674
Token called
Token ID1444
Feature activation+2.15e+00

Pos logit contributions
Rated+1.332
 whisper+1.276
Marginal+1.163
 Minutes+1.146
arella+1.127
Neg logit contributions
��-2.047
haar-1.649
isphere-1.565
-1.517
yrus-1.432
Token '
Token ID705
Feature activation+9.71e-01

Pos logit contributions
Rated+3.696
 whisper+3.628
 Minutes+3.199
Marginal+3.186
arella+3.119
Neg logit contributions
��-6.066
haar-4.940
isphere-4.666
-4.585
yrus-4.316
Tokeng
Token ID70
Feature activation+6.46e-01

Pos logit contributions
Rated+2.081
 whisper+2.038
Marginal+1.849
 Minutes+1.840
arella+1.829
Neg logit contributions
��-2.368
haar-1.839
isphere-1.720
-1.677
yrus-1.563
Tokenems
Token ID5232
Feature activation-2.50e-01

Pos logit contributions
Rated+1.249
 whisper+1.218
Marginal+1.094
 Minutes+1.078
arella+1.063
Neg logit contributions
��-1.707
haar-1.363
isphere-1.287
-1.234
yrus-1.195
Token from
Token ID422
Feature activation+1.22e-01

Pos logit contributions
��+0.688
haar+0.556
isphere+0.533
+0.514
yrus+0.486
Neg logit contributions
Rated-0.452
 whisper-0.432
Marginal-0.394
 Minutes-0.387
arella-0.385
Token students
Token ID2444
Feature activation+5.26e-01

Pos logit contributions
Rated+0.258
 whisper+0.248
Marginal+0.233
arella+0.226
 Minutes+0.223
Neg logit contributions
��-0.304
haar-0.235
isphere-0.221
-0.212
yrus-0.203
Token life
Token ID1204
Feature activation+9.53e-02

Pos logit contributions
Rated+0.007
 whisper+0.007
Marginal+0.006
 Minutes+0.006
arella+0.006
Neg logit contributions
��-0.010
haar-0.008
isphere-0.007
-0.007
yrus-0.007
Token on
Token ID319
Feature activation-6.62e-02

Pos logit contributions
Rated+0.179
 whisper+0.171
Marginal+0.158
 Minutes+0.155
arella+0.155
Neg logit contributions
��-0.254
haar-0.204
isphere-0.191
-0.185
yrus-0.176
Token the
Token ID262
Feature activation-2.11e-03

Pos logit contributions
��+0.158
haar+0.122
isphere+0.114
+0.111
yrus+0.103
Neg logit contributions
Rated-0.145
 whisper-0.141
Marginal-0.130
 Minutes-0.128
arella-0.128
Token streets
Token ID6483
Feature activation-1.55e-01

Pos logit contributions
��+0.006
haar+0.005
isphere+0.005
+0.005
yrus+0.004
Neg logit contributions
Rated-0.003
 whisper-0.003
Marginal-0.003
arella-0.003
 Minutes-0.003
Token a
Token ID257
Feature activation+1.46e-01

Pos logit contributions
��+0.426
haar+0.341
isphere+0.324
+0.307
yrus+0.290
Neg logit contributions
Rated-0.279
 whisper-0.261
Marginal-0.244
arella-0.241
 Minutes-0.239
Token bit
Token ID1643
Feature activation+2.13e+00

Pos logit contributions
Rated+0.253
 whisper+0.239
Marginal+0.217
 Minutes+0.216
arella+0.215
Neg logit contributions
��-0.416
haar-0.338
isphere-0.317
-0.309
yrus-0.293
Token more
Token ID517
Feature activation-5.73e-01

Pos logit contributions
Rated+3.427
 whisper+3.372
Marginal+2.943
 Minutes+2.914
 nearer+2.891
Neg logit contributions
��-6.264
haar-5.108
isphere-4.865
-4.785
yrus-4.531
Token difficult
Token ID2408
Feature activation+1.94e-01

Pos logit contributions
��+1.501
haar+1.198
isphere+1.130
+1.071
 Tinder+1.029
Neg logit contributions
Rated-1.097
 whisper-1.010
arella-0.954
Marginal-0.945
 Minutes-0.933
Token.
Token ID13
Feature activation+8.05e-02

Pos logit contributions
Rated+0.334
 whisper+0.324
Marginal+0.288
 Minutes+0.285
arella+0.281
Neg logit contributions
��-0.553
haar-0.448
isphere-0.424
-0.415
yrus-0.393
Token
Token ID198
Feature activation-7.90e-02

Pos logit contributions
Rated+0.154
 whisper+0.151
Marginal+0.134
arella+0.132
uries+0.132
Neg logit contributions
��-0.213
haar-0.170
isphere-0.158
-0.157
yrus-0.145
Token
Token ID198
Feature activation-2.78e-02

Pos logit contributions
��+0.209
haar+0.172
isphere+0.159
+0.157
yrus+0.149
Neg logit contributions
Rated-0.143
 whisper-0.141
Marginal-0.125
arella-0.125
uries-0.124
Token the
Token ID262
Feature activation+2.55e-02

Pos logit contributions
��+1.342
haar+1.039
isphere+0.963
+0.945
yrus+0.887
Neg logit contributions
Rated-1.099
 whisper-1.073
 Minutes-0.970
Marginal-0.964
arella-0.958
Token Conservative
Token ID11132
Feature activation-9.69e-03

Pos logit contributions
Rated+0.049
 whisper+0.047
Marginal+0.042
 Minutes+0.042
arella+0.042
Neg logit contributions
��-0.068
haar-0.054
isphere-0.050
-0.049
yrus-0.047
Token government
Token ID1230
Feature activation+6.61e-01

Pos logit contributions
��+0.024
haar+0.018
isphere+0.017
+0.017
yrus+0.016
Neg logit contributions
Rated-0.021
 whisper-0.020
 Minutes-0.018
Marginal-0.018
arella-0.018
Token is
Token ID318
Feature activation+2.05e-01

Pos logit contributions
Rated+1.207
 whisper+1.175
Marginal+1.049
 Minutes+1.040
arella+1.029
Neg logit contributions
��-1.821
haar-1.461
isphere-1.383
-1.352
yrus-1.276
Token a
Token ID257
Feature activation+2.09e-01

Pos logit contributions
Rated+0.410
 whisper+0.402
 Minutes+0.365
arella+0.364
Marginal+0.361
Neg logit contributions
��-0.525
haar-0.409
isphere-0.385
-0.373
yrus-0.350
Token bit
Token ID1643
Feature activation+2.12e+00

Pos logit contributions
Rated+0.418
 whisper+0.402
 Minutes+0.369
arella+0.364
Marginal+0.363
Neg logit contributions
��-0.538
haar-0.427
isphere-0.395
-0.390
yrus-0.364
Token like
Token ID588
Feature activation-3.63e-01

Pos logit contributions
Rated+3.980
 whisper+3.926
Marginal+3.538
 nearer+3.442
 Minutes+3.419
Neg logit contributions
��-5.655
haar-4.506
isphere-4.261
-4.172
yrus-3.963
Token a
Token ID257
Feature activation-9.42e-02

Pos logit contributions
��+0.902
haar+0.701
isphere+0.656
+0.641
yrus+0.593
Neg logit contributions
Rated-0.758
 whisper-0.728
arella-0.667
Marginal-0.667
 Minutes-0.665
Token boat
Token ID8848
Feature activation-1.03e-01

Pos logit contributions
��+0.251
haar+0.202
isphere+0.189
+0.185
yrus+0.174
Neg logit contributions
Rated-0.179
 whisper-0.168
arella-0.155
Marginal-0.154
 Minutes-0.154
Token without
Token ID1231
Feature activation-4.24e-01

Pos logit contributions
��+0.275
haar+0.219
isphere+0.208
+0.204
yrus+0.191
Neg logit contributions
Rated-0.194
 whisper-0.185
Marginal-0.168
 Minutes-0.168
arella-0.167
Token a
Token ID257
Feature activation+1.41e-01

Pos logit contributions
��+1.041
haar+0.816
isphere+0.774
+0.745
yrus+0.698
Neg logit contributions
Rated-0.880
 whisper-0.843
Marginal-0.780
arella-0.775
 Minutes-0.773
Token where
Token ID810
Feature activation-3.17e-02

Pos logit contributions
Rated+0.653
 whisper+0.631
Marginal+0.559
 Minutes+0.555
arella+0.550
Neg logit contributions
��-1.101
haar-0.893
isphere-0.849
-0.829
yrus-0.784
Token they
Token ID484
Feature activation+1.63e-01

Pos logit contributions
��+0.080
haar+0.063
isphere+0.059
+0.057
yrus+0.054
Neg logit contributions
Rated-0.065
 whisper-0.063
Marginal-0.058
arella-0.057
 Minutes-0.056
Token were
Token ID547
Feature activation-1.54e-01

Pos logit contributions
Rated+0.296
 whisper+0.279
Marginal+0.260
 Minutes+0.255
arella+0.252
Neg logit contributions
��-0.446
haar-0.362
isphere-0.343
-0.327
yrus-0.316
Token in
Token ID287
Feature activation+1.18e-01

Pos logit contributions
��+0.392
haar+0.310
isphere+0.292
+0.279
yrus+0.267
Neg logit contributions
Rated-0.308
 whisper-0.293
Marginal-0.274
 Minutes-0.269
uries-0.269
Token a
Token ID257
Feature activation-2.42e-03

Pos logit contributions
Rated+0.238
 whisper+0.230
Marginal+0.211
 Minutes+0.207
arella+0.206
Neg logit contributions
��-0.300
haar-0.238
isphere-0.222
-0.217
yrus-0.204
Token bit
Token ID1643
Feature activation+2.08e+00

Pos logit contributions
��+0.006
haar+0.005
isphere+0.005
+0.005
yrus+0.004
Neg logit contributions
Rated-0.005
 whisper-0.004
Marginal-0.004
arella-0.004
 Minutes-0.004
Token of
Token ID286
Feature activation-2.34e-01

Pos logit contributions
 whisper+3.196
Rated+3.178
Marginal+2.756
 nearer+2.733
 Minutes+2.690
Neg logit contributions
��-6.211
haar-5.064
isphere-4.810
-4.727
yrus-4.453
Token a
Token ID257
Feature activation-2.04e-02

Pos logit contributions
��+0.570
haar+0.446
isphere+0.419
+0.406
yrus+0.383
Neg logit contributions
Rated-0.499
 whisper-0.470
Marginal-0.440
arella-0.436
 Minutes-0.432
Token familiar
Token ID5385
Feature activation-1.43e-01

Pos logit contributions
��+0.054
haar+0.044
isphere+0.041
+0.040
yrus+0.038
Neg logit contributions
Rated-0.039
 whisper-0.036
Marginal-0.033
 Minutes-0.033
arella-0.033
Token pattern
Token ID3912
Feature activation-7.02e-02

Pos logit contributions
��+0.362
haar+0.287
isphere+0.272
+0.263
yrus+0.247
Neg logit contributions
Rated-0.287
 whisper-0.273
 Minutes-0.252
Marginal-0.252
wives-0.250
Token?
Token ID30
Feature activation-3.50e-01

Pos logit contributions
��+0.184
haar+0.148
isphere+0.140
+0.134
yrus+0.128
Neg logit contributions
Rated-0.137
 whisper-0.131
Marginal-0.118
 Minutes-0.118
uries-0.117
Token that
Token ID326
Feature activation+8.45e-02

Pos logit contributions
��+0.787
haar+0.628
isphere+0.612
+0.580
yrus+0.550
Neg logit contributions
Rated-0.575
 whisper-0.545
Marginal-0.499
 Minutes-0.488
wives-0.483
Token would
Token ID561
Feature activation+6.50e-02

Pos logit contributions
Rated+0.162
 whisper+0.155
Marginal+0.141
 Minutes+0.138
arella+0.138
Neg logit contributions
��-0.225
haar-0.179
isphere-0.170
-0.164
yrus-0.156
Token govern
Token ID1089
Feature activation+7.04e-01

Pos logit contributions
Rated+0.125
 whisper+0.118
Marginal+0.109
 Minutes+0.108
arella+0.107
Neg logit contributions
��-0.172
haar-0.137
isphere-0.130
-0.126
yrus-0.120
Token what
Token ID644
Feature activation+2.87e-01

Pos logit contributions
Rated+1.467
 whisper+1.421
Marginal+1.297
 Minutes+1.285
arella+1.273
Neg logit contributions
��-1.755
haar-1.380
isphere-1.294
-1.257
yrus-1.180
Token it
Token ID340
Feature activation+1.80e-01

Pos logit contributions
Rated+0.649
 whisper+0.623
Marginal+0.578
arella+0.573
 Minutes+0.569
Neg logit contributions
��-0.654
haar-0.510
isphere-0.481
-0.458
yrus-0.428
Token calls
Token ID3848
Feature activation+2.03e+00

Pos logit contributions
Rated+0.330
 whisper+0.310
Marginal+0.289
 Minutes+0.285
uries+0.277
Neg logit contributions
��-0.486
haar-0.396
isphere-0.381
-0.369
yrus-0.344
Token Ro
Token ID5564
Feature activation-3.22e-01

Pos logit contributions
Rated+3.864
 whisper+3.799
Marginal+3.380
 Minutes+3.379
 nearer+3.344
Neg logit contributions
��-5.388
haar-4.274
isphere-4.041
-3.936
yrus-3.692
Tokenjava
Token ID12355
Feature activation-4.31e-02

Pos logit contributions
��+0.794
haar+0.625
isphere+0.594
+0.567
yrus+0.562
Neg logit contributions
Rated-0.660
 whisper-0.641
Marginal-0.594
 Minutes-0.586
arella-0.575
Token -
Token ID532
Feature activation+2.31e-01

Pos logit contributions
��+0.117
haar+0.094
isphere+0.088
+0.086
yrus+0.082
Neg logit contributions
Rated-0.080
 whisper-0.077
Marginal-0.070
arella-0.068
 Minutes-0.068
Token the
Token ID262
Feature activation-6.07e-02

Pos logit contributions
Rated+0.485
 whisper+0.474
Marginal+0.434
 Minutes+0.429
arella+0.427
Neg logit contributions
��-0.570
haar-0.442
isphere-0.414
-0.408
yrus-0.378
Token Kurdish
Token ID14845
Feature activation+5.19e-01

Pos logit contributions
��+0.157
haar+0.124
isphere+0.116
+0.114
yrus+0.107
Neg logit contributions
Rated-0.121
 whisper-0.115
Marginal-0.106
arella-0.105
uries-0.105
Token towel
Token ID24808
Feature activation+3.76e-01

Pos logit contributions
Rated+2.114
 whisper+2.072
Marginal+1.913
 Minutes+1.901
arella+1.888
Neg logit contributions
��-1.741
haar-1.284
isphere-1.183
-1.144
yrus-1.045
Token-
Token ID12
Feature activation+1.69e-01

Pos logit contributions
Rated+0.680
 whisper+0.662
Marginal+0.595
 Minutes+0.589
arella+0.581
Neg logit contributions
��-1.032
haar-0.829
isphere-0.787
-0.764
yrus-0.725
Tokenlined
Token ID10837
Feature activation+9.09e-01

Pos logit contributions
Rated+0.241
 whisper+0.236
Marginal+0.204
 Minutes+0.202
arella+0.197
Neg logit contributions
��-0.526
haar-0.437
isphere-0.417
-0.408
yrus-0.391
Token plate
Token ID7480
Feature activation-2.58e-01

Pos logit contributions
Rated+1.852
 whisper+1.806
Marginal+1.638
 Minutes+1.625
arella+1.612
Neg logit contributions
��-2.306
haar-1.809
isphere-1.702
-1.659
yrus-1.555
Token.
Token ID13
Feature activation+1.59e-01

Pos logit contributions
��+0.709
haar+0.569
isphere+0.536
+0.522
yrus+0.497
Neg logit contributions
Rated-0.465
 whisper-0.454
Marginal-0.409
 Minutes-0.404
arella-0.401
Token Serve
Token ID35557
Feature activation+2.01e+00

Pos logit contributions
Rated+0.289
 whisper+0.283
Marginal+0.253
arella+0.247
 nearer+0.247
Neg logit contributions
��-0.437
haar-0.349
isphere-0.329
-0.322
yrus-0.304
Token hot
Token ID3024
Feature activation+2.27e-01

Pos logit contributions
Rated+3.468
 whisper+3.448
 Minutes+2.975
 nearer+2.958
arella+2.955
Neg logit contributions
��-5.617
haar-4.556
isphere-4.336
-4.251
yrus-3.991
Token!
Token ID0
Feature activation+1.72e-03

Pos logit contributions
Rated+0.399
 whisper+0.388
Marginal+0.352
 Minutes+0.346
arella+0.337
Neg logit contributions
��-0.638
haar-0.514
isphere-0.485
-0.476
yrus-0.452
Token
Token ID198
Feature activation+2.13e-01

Pos logit contributions
Rated+0.003
 whisper+0.003
Marginal+0.003
 Minutes+0.003
arella+0.003
Neg logit contributions
��-0.005
haar-0.004
isphere-0.004
-0.004
yrus-0.003
Token
Token ID198
Feature activation+2.72e-01

Pos logit contributions
Rated+0.377
 whisper+0.374
Marginal+0.331
arella+0.329
uries+0.327
Neg logit contributions
��-0.573
haar-0.471
isphere-0.439
-0.433
yrus-0.409
Token1
Token ID16
Feature activation+7.17e-01

Pos logit contributions
Rated+0.521
 whisper+0.513
 Minutes+0.459
Marginal+0.457
arella+0.454
Neg logit contributions
��-0.722
haar-0.573
isphere-0.542
-0.529
yrus-0.496
Token
Token ID198
Feature activation-2.03e-01

Pos logit contributions
��+0.789
haar+0.642
+0.604
isphere+0.591
yrus+0.545
Neg logit contributions
 whisper-0.560
Rated-0.539
arella-0.494
uries-0.491
ktop-0.488
TokenThe
Token ID464
Feature activation+2.96e-01

Pos logit contributions
��+0.487
haar+0.378
+0.354
isphere+0.353
yrus+0.319
Neg logit contributions
 whisper-0.433
Rated-0.421
 Minutes-0.390
arella-0.389
 nearer-0.385
Token film
Token ID2646
Feature activation-6.74e-01

Pos logit contributions
Rated+0.571
 whisper+0.549
Marginal+0.504
arella+0.495
 Minutes+0.493
Neg logit contributions
��-0.784
haar-0.620
isphere-0.585
-0.571
yrus-0.540
Token seemed
Token ID3947
Feature activation-6.84e-02

Pos logit contributions
��+1.817
haar+1.440
isphere+1.393
+1.338
yrus+1.277
Neg logit contributions
Rated-1.237
 whisper-1.197
Marginal-1.090
arella-1.075
 Minutes-1.071
Token every
Token ID790
Feature activation+4.05e-01

Pos logit contributions
��+0.185
haar+0.148
isphere+0.141
+0.136
yrus+0.128
Neg logit contributions
Rated-0.128
 whisper-0.122
Marginal-0.111
 Minutes-0.110
arella-0.110
Token bit
Token ID1643
Feature activation+1.98e+00

Pos logit contributions
Rated+0.631
 whisper+0.596
Marginal+0.538
arella+0.530
 Minutes+0.529
Neg logit contributions
��-1.216
haar-1.003
isphere-0.951
-0.929
yrus-0.879
Token as
Token ID355
Feature activation-1.53e-01

Pos logit contributions
Rated+2.977
 whisper+2.936
Marginal+2.516
 Minutes+2.507
 nearer+2.462
Neg logit contributions
��-6.026
haar-4.958
isphere-4.714
-4.615
yrus-4.424
Token sensational
Token ID31826
Feature activation-3.12e-01

Pos logit contributions
��+0.391
haar+0.310
isphere+0.292
+0.281
yrus+0.265
Neg logit contributions
Rated-0.308
 whisper-0.293
Marginal-0.270
 Minutes-0.269
arella-0.268
Tokenistic
Token ID2569
Feature activation-1.17e-01

Pos logit contributions
��+0.908
haar+0.742
isphere+0.713
+0.694
yrus+0.656
Neg logit contributions
Rated-0.511
 whisper-0.485
Marginal-0.434
 Minutes-0.432
wives-0.419
Token as
Token ID355
Feature activation+5.75e-03

Pos logit contributions
��+0.345
haar+0.283
isphere+0.270
+0.264
yrus+0.249
Neg logit contributions
Rated-0.190
 whisper-0.181
Marginal-0.162
 Minutes-0.160
arella-0.157
Token its
Token ID663
Feature activation+1.56e-01

Pos logit contributions
Rated+0.012
 whisper+0.011
Marginal+0.010
 Minutes+0.010
arella+0.010
Neg logit contributions
��-0.015
haar-0.012
isphere-0.011
-0.011
yrus-0.010
Token 121
Token ID20416
Feature activation+6.85e-01

Pos logit contributions
��+2.299
haar+1.862
isphere+1.753
+1.686
yrus+1.621
Neg logit contributions
Rated-1.688
 whisper-1.652
Marginal-1.496
arella-1.462
wives-1.446
Token 24
Token ID1987
Feature activation+2.46e-01

Pos logit contributions
Rated+1.336
 whisper+1.310
Marginal+1.162
arella+1.159
wives+1.138
Neg logit contributions
��-1.802
haar-1.431
isphere-1.341
-1.320
yrus-1.235
Token
Token ID198
Feature activation+9.16e-01

Pos logit contributions
Rated+0.479
 whisper+0.474
arella+0.419
Marginal+0.417
uries+0.412
Neg logit contributions
��-0.639
haar-0.509
isphere-0.471
-0.470
yrus-0.436
Token
Token ID198
Feature activation+8.45e-01

Pos logit contributions
Rated+1.566
 whisper+1.530
Marginal+1.348
arella+1.335
 Minutes+1.334
Neg logit contributions
��-2.592
haar-2.120
isphere-1.998
-1.964
yrus-1.854
TokenInternational
Token ID24274
Feature activation+4.72e-01

Pos logit contributions
Rated+1.662
 whisper+1.650
 Minutes+1.468
Marginal+1.459
arella+1.459
Neg logit contributions
��-2.189
haar-1.735
isphere-1.637
-1.601
yrus-1.492
Token goals
Token ID4661
Feature activation+1.98e+00

Pos logit contributions
Rated+0.855
 whisper+0.833
Marginal+0.744
arella+0.731
 Minutes+0.723
Neg logit contributions
��-1.306
haar-1.048
isphere-0.998
-0.971
yrus-0.914
Token
Token ID198
Feature activation+4.01e-01

Pos logit contributions
Rated+3.496
 whisper+3.414
 Minutes+3.056
Marginal+3.042
arella+2.987
Neg logit contributions
��-5.525
haar-4.421
isphere-4.175
-4.111
yrus-3.863
Token
Token ID198
Feature activation+3.92e-01

Pos logit contributions
Rated+0.718
 whisper+0.706
Marginal+0.623
arella+0.623
uries+0.620
Neg logit contributions
��-1.076
haar-0.886
isphere-0.827
-0.815
yrus-0.767
TokenAs
Token ID1722
Feature activation+5.93e-02

Pos logit contributions
 whisper+0.761
Rated+0.753
 Minutes+0.668
arella+0.666
 nearer+0.662
Neg logit contributions
��-1.020
haar-0.815
isphere-0.771
-0.756
yrus-0.699
Token of
Token ID286
Feature activation+1.94e-01

Pos logit contributions
Rated+0.110
 whisper+0.108
Marginal+0.096
 Minutes+0.095
arella+0.093
Neg logit contributions
��-0.161
haar-0.130
isphere-0.123
-0.119
yrus-0.112
Token 12
Token ID1105
Feature activation+2.77e-01

Pos logit contributions
Rated+0.351
 whisper+0.335
Marginal+0.304
arella+0.299
uries+0.296
Neg logit contributions
��-0.533
haar-0.431
isphere-0.407
-0.396
yrus-0.376
Token ours
Token ID16903
Feature activation-2.84e-01

Pos logit contributions
��+0.014
haar+0.010
isphere+0.010
+0.009
yrus+0.009
Neg logit contributions
Rated-0.013
 whisper-0.012
Marginal-0.011
arella-0.011
 Minutes-0.011
Token that
Token ID326
Feature activation+1.36e-01

Pos logit contributions
��+0.774
haar+0.620
isphere+0.593
+0.575
yrus+0.545
Neg logit contributions
Rated-0.521
 whisper-0.504
Marginal-0.450
 Minutes-0.449
arella-0.443
Token everybody
Token ID7288
Feature activation+3.90e-01

Pos logit contributions
Rated+0.298
 whisper+0.289
Marginal+0.264
arella+0.263
 Minutes+0.262
Neg logit contributions
��-0.323
haar-0.246
isphere-0.233
-0.224
yrus-0.214
Token offers
Token ID4394
Feature activation+2.58e-01

Pos logit contributions
Rated+0.715
 whisper+0.673
Marginal+0.620
 Minutes+0.604
arella+0.604
Neg logit contributions
��-1.066
haar-0.860
isphere-0.820
-0.791
yrus-0.756
Token a
Token ID257
Feature activation+1.84e-01

Pos logit contributions
Rated+0.531
 whisper+0.508
Marginal+0.469
arella+0.463
 Minutes+0.459
Neg logit contributions
��-0.648
haar-0.513
isphere-0.481
-0.464
yrus-0.440
Token bit
Token ID1643
Feature activation+1.97e+00

Pos logit contributions
Rated+0.374
 whisper+0.353
Marginal+0.331
 Minutes+0.325
arella+0.324
Neg logit contributions
��-0.463
haar-0.372
isphere-0.346
-0.332
yrus-0.317
Token of
Token ID286
Feature activation-1.98e-01

Pos logit contributions
 whisper+2.929
Rated+2.917
Marginal+2.507
 Minutes+2.482
 nearer+2.479
Neg logit contributions
��-6.019
haar-4.896
isphere-4.642
-4.598
yrus-4.362
Token leadership
Token ID5531
Feature activation+5.32e-01

Pos logit contributions
��+0.498
haar+0.395
isphere+0.371
+0.357
yrus+0.338
Neg logit contributions
Rated-0.403
 whisper-0.379
Marginal-0.356
arella-0.350
wives-0.349
Token here
Token ID994
Feature activation+5.97e-01

Pos logit contributions
Rated+0.971
 whisper+0.932
Marginal+0.838
 Minutes+0.833
arella+0.827
Neg logit contributions
��-1.467
haar-1.175
isphere-1.116
-1.088
yrus-1.028
Token and
Token ID290
Feature activation+2.86e-01

Pos logit contributions
Rated+1.064
 whisper+1.031
Marginal+0.919
 Minutes+0.912
arella+0.901
Neg logit contributions
��-1.669
haar-1.345
isphere-1.277
-1.246
yrus-1.179
Token there
Token ID612
Feature activation-1.09e-01

Pos logit contributions
Rated+0.589
 whisper+0.563
Marginal+0.520
 Minutes+0.514
arella+0.513
Neg logit contributions
��-0.723
haar-0.563
isphere-0.535
-0.514
yrus-0.490
Token,
Token ID11
Feature activation+2.37e-01

Pos logit contributions
��+0.896
haar+0.727
isphere+0.693
+0.673
yrus+0.638
Neg logit contributions
Rated-0.578
 whisper-0.553
Marginal-0.498
 Minutes-0.493
arella-0.489
Token because
Token ID780
Feature activation+6.46e-01

Pos logit contributions
Rated+0.472
 whisper+0.453
Marginal+0.415
 Minutes+0.413
arella+0.411
Neg logit contributions
��-0.610
haar-0.480
isphere-0.452
-0.436
yrus-0.414
Token you
Token ID345
Feature activation+5.30e-01

Pos logit contributions
Rated+1.340
 whisper+1.280
Marginal+1.187
arella+1.170
 Minutes+1.166
Neg logit contributions
��-1.625
haar-1.264
isphere-1.194
-1.143
yrus-1.092
Token do
Token ID466
Feature activation+3.03e-02

Pos logit contributions
Rated+1.073
 whisper+1.026
Marginal+0.948
 Minutes+0.945
arella+0.926
Neg logit contributions
��-1.349
haar-1.065
isphere-1.002
-0.970
yrus-0.913
Token,'
Token ID4032
Feature activation+4.82e-01

Pos logit contributions
Rated+0.054
 whisper+0.052
Marginal+0.046
 Minutes+0.046
arella+0.046
Neg logit contributions
��-0.085
haar-0.068
isphere-0.065
-0.063
yrus-0.060
Token Mrs
Token ID9074
Feature activation+1.97e+00

Pos logit contributions
Rated+0.938
 whisper+0.912
Marginal+0.824
 Minutes+0.815
arella+0.810
Neg logit contributions
��-1.270
haar-1.004
isphere-0.945
-0.922
yrus-0.870
Token.
Token ID13
Feature activation+1.15e+00

Pos logit contributions
Rated+3.225
 whisper+3.119
Marginal+2.752
 Minutes+2.744
arella+2.702
Neg logit contributions
��-5.793
haar-4.706
isphere-4.482
-4.390
yrus-4.149
Token Obama
Token ID2486
Feature activation+1.01e+00

Pos logit contributions
Rated+2.392
 whisper+2.328
Marginal+2.125
 Minutes+2.085
arella+2.078
Neg logit contributions
��-2.861
haar-2.243
isphere-2.104
-2.032
yrus-1.916
Token said
Token ID531
Feature activation+1.24e-01

Pos logit contributions
Rated+1.791
 whisper+1.730
Marginal+1.555
 Minutes+1.537
arella+1.515
Neg logit contributions
��-2.834
haar-2.285
isphere-2.167
-2.112
yrus-2.003
Token.
Token ID13
Feature activation+6.21e-01

Pos logit contributions
Rated+0.222
 whisper+0.212
Marginal+0.193
 Minutes+0.189
arella+0.186
Neg logit contributions
��-0.343
haar-0.277
isphere-0.262
-0.255
yrus-0.242
Token '
Token ID705
Feature activation-1.95e-01

Pos logit contributions
Rated+0.930
 whisper+0.898
 Minutes+0.799
arella+0.783
Marginal+0.781
Neg logit contributions
��-1.919
haar-1.566
isphere-1.516
-1.482
yrus-1.401
Token a
Token ID257
Feature activation-2.72e-01

Pos logit contributions
Rated+0.237
 whisper+0.229
Marginal+0.210
 Minutes+0.206
arella+0.205
Neg logit contributions
��-0.297
haar-0.236
isphere-0.220
-0.216
yrus-0.202
Token critic
Token ID4014
Feature activation+3.15e-01

Pos logit contributions
��+0.746
haar+0.601
isphere+0.560
+0.556
yrus+0.525
Neg logit contributions
Rated-0.490
 whisper-0.456
Marginal-0.428
uries-0.417
arella-0.415
Token of
Token ID286
Feature activation+2.85e-01

Pos logit contributions
Rated+0.490
 whisper+0.478
Marginal+0.417
 Minutes+0.409
arella+0.406
Neg logit contributions
��-0.953
haar-0.782
isphere-0.743
-0.726
yrus-0.693
Token what
Token ID644
Feature activation+1.33e-01

Pos logit contributions
Rated+0.611
 whisper+0.594
Marginal+0.543
 Minutes+0.538
arella+0.534
Neg logit contributions
��-0.694
haar-0.539
isphere-0.504
-0.491
yrus-0.458
Token he
Token ID339
Feature activation+3.76e-02

Pos logit contributions
Rated+0.308
 whisper+0.300
Marginal+0.278
arella+0.275
 Minutes+0.272
Neg logit contributions
��-0.298
haar-0.227
isphere-0.209
-0.206
yrus-0.189
Token called
Token ID1444
Feature activation+1.97e+00

Pos logit contributions
Rated+0.066
 whisper+0.063
Marginal+0.057
 Minutes+0.056
arella+0.055
Neg logit contributions
��-0.106
haar-0.086
isphere-0.082
-0.080
yrus-0.074
Token perceived
Token ID11067
Feature activation+8.58e-01

Pos logit contributions
Rated+3.703
 whisper+3.653
Marginal+3.247
 Minutes+3.231
 Speaker+3.187
Neg logit contributions
��-5.199
haar-4.149
isphere-3.927
-3.800
yrus-3.599
Token integration
Token ID11812
Feature activation+5.56e-01

Pos logit contributions
Rated+1.631
 whisper+1.578
Marginal+1.420
 Minutes+1.414
arella+1.404
Neg logit contributions
��-2.295
haar-1.830
isphere-1.733
-1.694
yrus-1.587
Token problems
Token ID2761
Feature activation-3.90e-01

Pos logit contributions
Rated+0.991
 whisper+0.958
Marginal+0.862
 Minutes+0.847
arella+0.846
Neg logit contributions
��-1.553
haar-1.251
isphere-1.180
-1.172
yrus-1.103
Token among
Token ID1871
Feature activation+5.06e-01

Pos logit contributions
��+1.080
haar+0.871
isphere+0.822
+0.811
yrus+0.770
Neg logit contributions
Rated-0.691
 whisper-0.668
Marginal-0.609
 Minutes-0.593
arella-0.588
Token immigrants
Token ID7971
Feature activation+1.61e-01

Pos logit contributions
Rated+1.033
 whisper+0.996
Marginal+0.913
arella+0.902
 Minutes+0.899
Neg logit contributions
��-1.278
haar-1.013
isphere-0.943
-0.922
yrus-0.864
Token Fiorina
Token ID49028
Feature activation+5.15e-01

Pos logit contributions
Rated+0.450
 whisper+0.442
Marginal+0.387
arella+0.381
 nearer+0.378
Neg logit contributions
��-0.740
haar-0.600
isphere-0.562
-0.556
yrus-0.521
Token spoke
Token ID5158
Feature activation-4.20e-01

Pos logit contributions
Rated+0.914
 whisper+0.881
Marginal+0.802
 Minutes+0.782
arella+0.777
Neg logit contributions
��-1.440
haar-1.160
isphere-1.103
-1.069
yrus-1.017
Token about
Token ID546
Feature activation+6.05e-02

Pos logit contributions
��+1.135
haar+0.909
isphere+0.883
+0.844
yrus+0.807
Neg logit contributions
Rated-0.753
 whisper-0.717
Marginal-0.663
uries-0.649
wives-0.645
Token what
Token ID644
Feature activation+1.35e-01

Pos logit contributions
Rated+0.116
 whisper+0.113
Marginal+0.103
 Minutes+0.101
arella+0.101
Neg logit contributions
��-0.160
haar-0.127
isphere-0.120
-0.116
yrus-0.109
Token she
Token ID673
Feature activation+6.03e-01

Pos logit contributions
Rated+0.277
 whisper+0.268
Marginal+0.246
arella+0.244
 Minutes+0.241
Neg logit contributions
��-0.338
haar-0.265
isphere-0.249
-0.240
yrus-0.227
Token calls
Token ID3848
Feature activation+1.96e+00

Pos logit contributions
Rated+1.054
 whisper+1.009
Marginal+0.928
 Minutes+0.909
arella+0.895
Neg logit contributions
��-1.695
haar-1.368
isphere-1.316
-1.269
yrus-1.197
Token the
Token ID262
Feature activation+1.16e-01

Pos logit contributions
Rated+3.613
 whisper+3.511
Marginal+3.136
 Speaker+3.119
 Minutes+3.119
Neg logit contributions
��-5.293
haar-4.269
isphere-4.057
-3.961
yrus-3.722
Token War
Token ID1810
Feature activation+5.56e-01

Pos logit contributions
Rated+0.215
 whisper+0.206
Marginal+0.188
 Minutes+0.186
arella+0.185
Neg logit contributions
��-0.312
haar-0.250
isphere-0.234
-0.227
yrus-0.217
Token on
Token ID319
Feature activation-2.03e-01

Pos logit contributions
Rated+0.814
 whisper+0.783
Marginal+0.682
 Minutes+0.667
arella+0.662
Neg logit contributions
��-1.729
haar-1.430
isphere-1.374
-1.338
yrus-1.281
Token Women
Token ID6926
Feature activation+9.68e-01

Pos logit contributions
��+0.649
haar+0.541
isphere+0.513
+0.507
yrus+0.487
Neg logit contributions
Rated-0.264
 whisper-0.258
Marginal-0.220
arella-0.218
EngineDebug-0.213
Token in
Token ID287
Feature activation-2.71e-01

Pos logit contributions
Rated+1.723
 whisper+1.663
Marginal+1.490
arella+1.458
 Minutes+1.452
Neg logit contributions
��-2.714
haar-2.183
isphere-2.073
-2.031
yrus-1.918
Token Haas
Token ID50090
Feature activation-3.78e-01

Pos logit contributions
��+1.782
haar+1.446
isphere+1.330
+1.301
yrus+1.216
Neg logit contributions
Rated-1.309
 whisper-1.266
Marginal-1.151
uries-1.132
wives-1.132
Tokenan
Token ID272
Feature activation-7.37e-01

Pos logit contributions
��+0.994
haar+0.796
isphere+0.736
+0.721
yrus+0.676
Neg logit contributions
Rated-0.738
 whisper-0.719
Marginal-0.649
 Minutes-0.636
arella-0.633
Token
Token ID447
Feature activation-4.61e-01

Pos logit contributions
��+1.985
haar+1.610
isphere+1.501
+1.449
yrus+1.368
Neg logit contributions
Rated-1.386
 whisper-1.328
Marginal-1.218
arella-1.172
uries-1.170
Token
Token ID247
Feature activation-2.22e-01

Pos logit contributions
��+1.093
haar+0.835
isphere+0.743
+0.738
yrus+0.671
Neg logit contributions
 whisper-1.033
Rated-1.032
Marginal-0.929
 Minutes-0.927
uries-0.918
Tokens
Token ID82
Feature activation-1.85e-01

Pos logit contributions
��+0.582
haar+0.466
isphere+0.433
+0.430
yrus+0.398
Neg logit contributions
Rated-0.430
 whisper-0.422
Marginal-0.378
arella-0.373
 Minutes-0.373
Token Vish
Token ID36900
Feature activation-2.64e+00

Pos logit contributions
��+0.499
haar+0.404
isphere+0.375
+0.369
yrus+0.346
Neg logit contributions
Rated-0.348
 whisper-0.332
Marginal-0.303
arella-0.297
 Minutes-0.295
Tokenwar
Token ID5767
Feature activation-1.27e+00

Pos logit contributions
��+6.353
haar+5.266
isphere+4.693
+4.503
yrus+4.388
Neg logit contributions
 whisper-5.228
Rated-5.185
Marginal-4.688
 Minutes-4.628
EngineDebug-4.589
Tokenoop
Token ID11224
Feature activation-7.57e-01

Pos logit contributions
��+3.145
haar+2.516
isphere+2.299
+2.277
yrus+2.138
Neg logit contributions
Rated-2.562
 whisper-2.516
Marginal-2.309
 nearer-2.250
ktop-2.240
Tokenam
Token ID321
Feature activation-9.61e-01

Pos logit contributions
��+1.861
haar+1.480
isphere+1.364
+1.326
yrus+1.244
Neg logit contributions
Rated-1.596
 whisper-1.555
Marginal-1.418
 Minutes-1.382
arella-1.377
Token (
Token ID357
Feature activation-5.56e-01

Pos logit contributions
��+2.532
haar+2.060
isphere+1.909
+1.890
yrus+1.763
Neg logit contributions
Rated-1.809
 whisper-1.765
Marginal-1.588
arella-1.567
ktop-1.550
Token2013
Token ID6390
Feature activation+3.08e-01

Pos logit contributions
��+1.455
haar+1.164
+1.092
isphere+1.081
yrus+0.996
Neg logit contributions
Rated-1.062
 whisper-1.056
 Minutes-0.937
arella-0.933
Marginal-0.931
Token the
Token ID262
Feature activation+1.78e-01

Pos logit contributions
��+0.127
haar+0.099
isphere+0.093
+0.090
yrus+0.084
Neg logit contributions
Rated-0.107
 whisper-0.105
Marginal-0.096
 Minutes-0.094
arella-0.094
Token temple
Token ID12505
Feature activation-4.05e-01

Pos logit contributions
Rated+0.337
 whisper+0.324
Marginal+0.295
arella+0.290
 Minutes+0.290
Neg logit contributions
��-0.480
haar-0.384
isphere-0.360
-0.352
yrus-0.331
Token dedicated
Token ID7256
Feature activation+1.70e-02

Pos logit contributions
��+1.105
haar+0.888
isphere+0.854
+0.823
yrus+0.778
Neg logit contributions
Rated-0.741
 whisper-0.706
Marginal-0.648
arella-0.639
 Minutes-0.632
Token to
Token ID284
Feature activation+3.67e-03

Pos logit contributions
Rated+0.028
 whisper+0.028
Marginal+0.024
 Minutes+0.024
arella+0.024
Neg logit contributions
��-0.050
haar-0.040
isphere-0.038
-0.038
yrus-0.036
Token Lord
Token ID4453
Feature activation-3.43e-01

Pos logit contributions
Rated+0.008
 whisper+0.007
Marginal+0.007
 Minutes+0.007
arella+0.007
Neg logit contributions
��-0.009
haar-0.007
isphere-0.007
-0.007
yrus-0.006
Token Vish
Token ID36900
Feature activation-2.37e+00

Pos logit contributions
��+0.833
haar+0.659
isphere+0.612
+0.595
yrus+0.553
Neg logit contributions
Rated-0.737
 whisper-0.712
Marginal-0.653
arella-0.641
 Minutes-0.635
Tokennu
Token ID28803
Feature activation-4.95e-02

Pos logit contributions
��+3.942
haar+2.934
isphere+2.525
+2.335
yrus+2.246
Neg logit contributions
Rated-6.418
 whisper-6.374
Marginal-6.038
EngineDebug-6.028
 Minutes-5.877
Token,
Token ID11
Feature activation-1.12e-01

Pos logit contributions
��+0.134
haar+0.108
isphere+0.102
+0.099
yrus+0.093
Neg logit contributions
Rated-0.092
 whisper-0.089
Marginal-0.081
arella-0.079
 Minutes-0.079
Token here
Token ID994
Feature activation+7.63e-01

Pos logit contributions
��+0.283
haar+0.224
isphere+0.210
+0.206
yrus+0.192
Neg logit contributions
Rated-0.227
 whisper-0.218
Marginal-0.203
arella-0.197
 Minutes-0.197
Token known
Token ID1900
Feature activation+9.79e-01

Pos logit contributions
Rated+1.425
 whisper+1.382
Marginal+1.250
 Minutes+1.232
arella+1.225
Neg logit contributions
��-2.069
haar-1.655
isphere-1.566
-1.529
yrus-1.438
Token as
Token ID355
Feature activation+4.03e-01

Pos logit contributions
Rated+1.350
 whisper+1.307
Marginal+1.109
 Minutes+1.104
arella+1.096
Neg logit contributions
��-3.128
haar-2.595
isphere-2.476
-2.420
yrus-2.319
Token Standing
Token ID22493
Feature activation-1.44e-01

Pos logit contributions
��+0.344
haar+0.274
isphere+0.255
+0.252
yrus+0.235
Neg logit contributions
Rated-0.258
 whisper-0.253
Marginal-0.230
arella-0.225
uries-0.222
Token Lord
Token ID4453
Feature activation-2.37e-01

Pos logit contributions
��+0.402
haar+0.325
isphere+0.309
+0.301
yrus+0.286
Neg logit contributions
Rated-0.256
 whisper-0.241
Marginal-0.226
arella-0.219
 Minutes-0.215
Token Gan
Token ID23207
Feature activation-4.48e-01

Pos logit contributions
��+0.545
haar+0.424
isphere+0.394
+0.383
yrus+0.353
Neg logit contributions
Rated-0.537
 whisper-0.517
Marginal-0.485
arella-0.473
 Minutes-0.471
Tokenesh
Token ID5069
Feature activation-3.01e-01

Pos logit contributions
��+0.868
haar+0.655
isphere+0.600
+0.552
yrus+0.533
Neg logit contributions
Rated-1.173
 whisper-1.144
Marginal-1.066
 Minutes-1.052
wives-1.037
Token and
Token ID290
Feature activation-3.21e-02

Pos logit contributions
��+0.815
haar+0.663
isphere+0.623
+0.609
yrus+0.576
Neg logit contributions
Rated-0.558
 whisper-0.533
Marginal-0.497
 Minutes-0.479
arella-0.477
Token Vish
Token ID36900
Feature activation-2.20e+00

Pos logit contributions
��+0.082
haar+0.065
isphere+0.061
+0.060
yrus+0.056
Neg logit contributions
Rated-0.065
 whisper-0.062
Marginal-0.058
arella-0.057
 Minutes-0.056
Tokennu
Token ID28803
Feature activation+5.39e-02

Pos logit contributions
��+3.987
haar+2.969
isphere+2.681
+2.476
yrus+2.348
Neg logit contributions
Rated-5.789
 whisper-5.672
Marginal-5.325
 Minutes-5.309
EngineDebug-5.213
Token D
Token ID360
Feature activation-8.23e-03

Pos logit contributions
Rated+0.101
 whisper+0.095
Marginal+0.089
arella+0.086
 Minutes+0.086
Neg logit contributions
��-0.146
haar-0.118
isphere-0.111
-0.109
yrus-0.102
Tokenurga
Token ID45098
Feature activation-4.87e-01

Pos logit contributions
��+0.020
haar+0.016
isphere+0.015
+0.014
yrus+0.014
Neg logit contributions
Rated-0.018
 whisper-0.017
Marginal-0.016
 Minutes-0.015
 nearer-0.015
Token also
Token ID635
Feature activation-3.59e-01

Pos logit contributions
��+1.322
haar+1.071
isphere+1.010
+0.987
yrus+0.934
Neg logit contributions
Rated-0.900
 whisper-0.844
Marginal-0.798
arella-0.769
 Minutes-0.761
Token have
Token ID423
Feature activation+9.35e-03

Pos logit contributions
��+0.986
haar+0.803
isphere+0.763
+0.741
yrus+0.705
Neg logit contributions
Rated-0.642
 whisper-0.596
Marginal-0.569
arella-0.548
 Minutes-0.548
Token by
Token ID416
Feature activation-9.10e-02

Pos logit contributions
Rated+0.313
 whisper+0.304
Marginal+0.272
arella+0.269
 Minutes+0.267
Neg logit contributions
��-0.451
haar-0.364
isphere-0.340
-0.334
yrus-0.314
Token blocking
Token ID12013
Feature activation-3.87e-01

Pos logit contributions
��+0.234
haar+0.185
isphere+0.172
+0.170
yrus+0.160
Neg logit contributions
Rated-0.183
 whisper-0.175
arella-0.160
Marginal-0.160
 Minutes-0.157
Token national
Token ID2260
Feature activation+4.15e-01

Pos logit contributions
��+1.055
haar+0.847
isphere+0.798
+0.785
yrus+0.734
Neg logit contributions
Rated-0.713
 whisper-0.691
Marginal-0.620
arella-0.616
 Minutes-0.615
Token highway
Token ID12763
Feature activation-1.06e-01

Pos logit contributions
Rated+0.811
 whisper+0.788
Marginal+0.712
 Minutes+0.704
arella+0.703
Neg logit contributions
��-1.092
haar-0.869
isphere-0.818
-0.802
yrus-0.748
Token connecting
Token ID14320
Feature activation+2.59e-01

Pos logit contributions
��+0.284
haar+0.229
isphere+0.215
+0.212
yrus+0.198
Neg logit contributions
Rated-0.199
 whisper-0.192
Marginal-0.173
arella-0.170
 Minutes-0.169
Token Roh
Token ID32694
Feature activation-2.09e+00

Pos logit contributions
Rated+0.521
 whisper+0.506
Marginal+0.459
arella+0.453
 Minutes+0.453
Neg logit contributions
��-0.663
haar-0.525
isphere-0.493
-0.482
yrus-0.450
Tokent
Token ID83
Feature activation-4.92e-01

Pos logit contributions
��+3.753
haar+2.919
isphere+2.637
+2.364
yrus+2.236
Neg logit contributions
Rated-5.512
 whisper-5.463
Marginal-5.057
 Minutes-4.958
EngineDebug-4.953
Tokenak
Token ID461
Feature activation-9.11e-02

Pos logit contributions
��+0.994
haar+0.810
isphere+0.740
+0.668
yrus+0.652
Neg logit contributions
Rated-1.207
 whisper-1.183
Marginal-1.103
 Minutes-1.080
-1.067
Token to
Token ID284
Feature activation-1.57e-01

Pos logit contributions
��+0.254
haar+0.206
isphere+0.194
+0.191
yrus+0.178
Neg logit contributions
Rated-0.162
 whisper-0.158
Marginal-0.141
arella-0.138
 Minutes-0.137
Token Delhi
Token ID12517
Feature activation-6.93e-01

Pos logit contributions
��+0.408
haar+0.326
isphere+0.303
+0.299
yrus+0.277
Neg logit contributions
Rated-0.312
 whisper-0.301
Marginal-0.274
arella-0.271
 Minutes-0.267
Token.
Token ID13
Feature activation+4.11e-01

Pos logit contributions
��+1.843
haar+1.475
isphere+1.378
+1.367
yrus+1.262
Neg logit contributions
Rated-1.307
 whisper-1.282
Marginal-1.147
arella-1.129
 Minutes-1.115
Token16
Token ID1433
Feature activation+5.07e-01

Pos logit contributions
��+0.471
haar+0.390
+0.366
isphere+0.359
yrus+0.331
Neg logit contributions
Rated-0.303
 whisper-0.300
arella-0.261
Marginal-0.260
uries-0.259
Token,
Token ID11
Feature activation-2.69e-01

Pos logit contributions
Rated+0.942
 whisper+0.913
Marginal+0.819
 Minutes+0.809
arella+0.807
Neg logit contributions
��-1.383
haar-1.109
isphere-1.044
-1.025
yrus-0.963
Token violence
Token ID3685
Feature activation-3.40e-01

Pos logit contributions
��+0.664
haar+0.523
isphere+0.484
+0.478
yrus+0.448
Neg logit contributions
Rated-0.562
 whisper-0.540
arella-0.496
Marginal-0.496
 Minutes-0.483
Token erupted
Token ID23681
Feature activation-3.66e-01

Pos logit contributions
��+0.929
haar+0.742
isphere+0.699
+0.683
yrus+0.647
Neg logit contributions
Rated-0.618
 whisper-0.600
Marginal-0.552
 Minutes-0.539
arella-0.536
Token in
Token ID287
Feature activation-3.55e-02

Pos logit contributions
��+1.010
haar+0.810
isphere+0.762
+0.745
yrus+0.713
Neg logit contributions
Rated-0.655
 whisper-0.631
Marginal-0.579
 Minutes-0.561
arella-0.559
Token Roh
Token ID32694
Feature activation-2.07e+00

Pos logit contributions
��+0.091
haar+0.072
isphere+0.067
+0.066
yrus+0.062
Neg logit contributions
Rated-0.071
 whisper-0.069
Marginal-0.063
arella-0.063
 Minutes-0.061
Tokent
Token ID83
Feature activation-3.19e-01

Pos logit contributions
��+3.697
haar+2.847
isphere+2.574
+2.315
yrus+2.171
Neg logit contributions
Rated-5.461
 whisper-5.388
Marginal-5.012
 Minutes-4.927
wives-4.919
Tokenak
Token ID461
Feature activation+1.83e-01

Pos logit contributions
��+0.645
haar+0.520
isphere+0.473
+0.437
yrus+0.420
Neg logit contributions
Rated-0.782
 whisper-0.766
Marginal-0.714
 Minutes-0.700
-0.692
Token city
Token ID1748
Feature activation-6.53e-02

Pos logit contributions
Rated+0.333
 whisper+0.323
Marginal+0.289
arella+0.288
 Minutes+0.282
Neg logit contributions
��-0.504
haar-0.406
isphere-0.385
-0.376
yrus-0.354
Token which
Token ID543
Feature activation-5.97e-03

Pos logit contributions
��+0.179
haar+0.144
isphere+0.137
+0.135
yrus+0.126
Neg logit contributions
Rated-0.118
 whisper-0.114
Marginal-0.103
arella-0.102
 Minutes-0.100
Token continued
Token ID3767
Feature activation-1.95e-01

Pos logit contributions
��+0.016
haar+0.013
isphere+0.012
+0.012
yrus+0.011
Neg logit contributions
Rated-0.011
 whisper-0.011
Marginal-0.010
arella-0.009
 Minutes-0.009
Token,
Token ID11
Feature activation+4.29e-02

Pos logit contributions
��+1.181
haar+0.944
isphere+0.896
+0.875
yrus+0.827
Neg logit contributions
Rated-0.808
 whisper-0.783
Marginal-0.700
 Minutes-0.694
arella-0.689
Token including
Token ID1390
Feature activation-1.43e-01

Pos logit contributions
Rated+0.085
 whisper+0.082
Marginal+0.074
 Minutes+0.074
arella+0.074
Neg logit contributions
��-0.111
haar-0.088
isphere-0.083
-0.081
yrus-0.076
Token paraly
Token ID26901
Feature activation-1.81e-01

Pos logit contributions
��+0.360
haar+0.274
isphere+0.266
+0.256
yrus+0.239
Neg logit contributions
Rated-0.300
 whisper-0.286
arella-0.263
Marginal-0.263
 Minutes-0.262
Tokentic
Token ID13370
Feature activation+2.75e-01

Pos logit contributions
��+0.443
haar+0.346
isphere+0.323
+0.313
yrus+0.295
Neg logit contributions
Rated-0.386
 whisper-0.375
Marginal-0.343
 Minutes-0.340
arella-0.339
Token and
Token ID290
Feature activation+2.07e-02

Pos logit contributions
Rated+0.544
 whisper+0.524
Marginal+0.477
 Minutes+0.473
arella+0.470
Neg logit contributions
��-0.718
haar-0.565
isphere-0.534
-0.522
yrus-0.490
Token diarr
Token ID30409
Feature activation-2.07e+00

Pos logit contributions
Rated+0.042
 whisper+0.040
arella+0.036
 Minutes+0.036
Marginal+0.036
Neg logit contributions
��-0.054
haar-0.041
isphere-0.040
-0.038
yrus-0.036
Tokenhetic
Token ID6587
Feature activation+2.76e-02

Pos logit contributions
��+3.065
haar+2.133
isphere+1.856
+1.567
stra+1.509
Neg logit contributions
Rated-6.098
 whisper-5.904
Marginal-5.665
 Minutes-5.585
arella-5.533
Token shell
Token ID7582
Feature activation-1.13e+00

Pos logit contributions
Rated+0.054
 whisper+0.052
Marginal+0.047
 Minutes+0.047
arella+0.047
Neg logit contributions
��-0.072
haar-0.057
isphere-0.054
-0.053
yrus-0.050
Tokenfish
Token ID11084
Feature activation-6.79e-01

Pos logit contributions
��+2.246
haar+1.622
isphere+1.495
+1.472
yrus+1.344
Neg logit contributions
Rated-2.932
 whisper-2.767
Marginal-2.597
arella-2.592
 Minutes-2.571
Token poisoning
Token ID22475
Feature activation-1.97e-01

Pos logit contributions
��+1.724
haar+1.321
isphere+1.269
+1.249
yrus+1.168
Neg logit contributions
Rated-1.393
 whisper-1.315
 Minutes-1.211
Marginal-1.201
arella-1.192
Token in
Token ID287
Feature activation-5.71e-02

Pos logit contributions
��+0.542
haar+0.433
isphere+0.411
+0.404
yrus+0.381
Neg logit contributions
Rated-0.359
 whisper-0.347
Marginal-0.311
 Minutes-0.308
arella-0.305
Token The
Token ID383
Feature activation-1.39e-01

Pos logit contributions
Rated+0.286
 whisper+0.280
Marginal+0.256
 Minutes+0.251
arella+0.251
Neg logit contributions
��-0.309
haar-0.238
isphere-0.224
-0.218
yrus-0.202
Token Chronicle
Token ID14160
Feature activation-5.77e-01

Pos logit contributions
��+0.372
haar+0.298
isphere+0.281
+0.275
yrus+0.257
Neg logit contributions
Rated-0.262
 whisper-0.254
Marginal-0.229
arella-0.223
uries-0.223
Token 2
Token ID362
Feature activation+1.04e-01

Pos logit contributions
��+1.688
haar+1.386
isphere+1.304
+1.288
yrus+1.219
Neg logit contributions
Rated-0.944
 whisper-0.905
Marginal-0.810
uries-0.784
 Minutes-0.780
Token of
Token ID286
Feature activation-3.02e-01

Pos logit contributions
Rated+0.177
 whisper+0.170
Marginal+0.155
uries+0.149
ktop+0.149
Neg logit contributions
��-0.295
haar-0.239
isphere-0.229
-0.227
yrus-0.213
Token 15
Token ID1315
Feature activation+6.26e-02

Pos logit contributions
��+0.796
haar+0.640
isphere+0.606
+0.598
yrus+0.555
Neg logit contributions
Rated-0.571
 whisper-0.553
Marginal-0.501
uries-0.493
 Minutes-0.487
Token Photo
Token ID5555
Feature activation-2.07e+00

Pos logit contributions
Rated+0.139
 whisper+0.134
Marginal+0.123
arella+0.122
 Minutes+0.121
Neg logit contributions
��-0.148
haar-0.114
isphere-0.106
-0.104
yrus-0.097
Token:
Token ID25
Feature activation-4.90e-01

Pos logit contributions
��+4.022
haar+3.196
isphere+2.976
+2.969
yrus+2.549
Neg logit contributions
 whisper-4.757
Rated-4.697
arella-4.416
ktop-4.406
Marginal-4.338
Token Le
Token ID1004
Feature activation-1.36e-01

Pos logit contributions
��+1.464
haar+1.206
isphere+1.148
+1.131
yrus+1.069
Neg logit contributions
Rated-0.762
 whisper-0.736
Marginal-0.652
arella-0.629
 Minutes-0.628
Tokena
Token ID64
Feature activation-1.20e-01

Pos logit contributions
��+0.280
haar+0.217
isphere+0.194
+0.188
yrus+0.177
Neg logit contributions
Rated-0.334
 whisper-0.328
Marginal-0.304
 Minutes-0.299
 nearer-0.295
Token Suzuki
Token ID35807
Feature activation+3.30e-02

Pos logit contributions
��+0.286
haar+0.223
isphere+0.208
+0.205
yrus+0.193
Neg logit contributions
Rated-0.255
 whisper-0.249
Marginal-0.230
arella-0.226
wives-0.223
Token,
Token ID11
Feature activation+2.27e-01

Pos logit contributions
Rated+0.063
 whisper+0.063
Marginal+0.056
arella+0.056
uries+0.055
Neg logit contributions
��-0.085
haar-0.069
isphere-0.064
-0.063
yrus-0.059
Token and
Token ID290
Feature activation-5.09e-02

Pos logit contributions
��+3.755
haar+2.995
isphere+2.846
+2.814
yrus+2.644
Neg logit contributions
Rated-2.790
 whisper-2.605
Marginal-2.484
 Minutes-2.404
uries-2.385
Token normally
Token ID7685
Feature activation-3.89e-01

Pos logit contributions
��+0.131
haar+0.103
isphere+0.098
+0.095
yrus+0.090
Neg logit contributions
Rated-0.102
 whisper-0.097
Marginal-0.091
arella-0.089
 Minutes-0.088
Token none
Token ID4844
Feature activation-9.18e-02

Pos logit contributions
��+1.030
haar+0.817
isphere+0.781
+0.756
yrus+0.717
Neg logit contributions
Rated-0.754
 whisper-0.710
Marginal-0.670
arella-0.651
 Minutes-0.646
Token of
Token ID286
Feature activation+3.56e-01

Pos logit contributions
��+0.260
haar+0.212
isphere+0.200
+0.195
yrus+0.185
Neg logit contributions
Rated-0.160
 whisper-0.153
Marginal-0.138
 Minutes-0.136
arella-0.135
Token the
Token ID262
Feature activation+1.93e-01

Pos logit contributions
Rated+0.795
 whisper+0.770
Marginal+0.711
 Minutes+0.703
arella+0.698
Neg logit contributions
��-0.840
haar-0.649
isphere-0.603
-0.587
yrus-0.546
Token Vish
Token ID36900
Feature activation-2.06e+00

Pos logit contributions
Rated+0.385
 whisper+0.365
Marginal+0.342
arella+0.333
 Minutes+0.330
Neg logit contributions
��-0.501
haar-0.401
isphere-0.373
-0.366
yrus-0.345
Tokennu
Token ID28803
Feature activation-4.75e-03

Pos logit contributions
��+3.621
haar+2.727
isphere+2.413
+2.233
yrus+2.162
Neg logit contributions
Rated-5.493
 whisper-5.380
Marginal-5.078
 Minutes-5.030
EngineDebug-4.969
Token temple
Token ID12505
Feature activation-7.33e-01

Pos logit contributions
��+0.012
haar+0.010
isphere+0.009
+0.009
yrus+0.008
Neg logit contributions
Rated-0.010
 whisper-0.009
Marginal-0.009
arella-0.008
 Minutes-0.008
Token have
Token ID423
Feature activation+1.96e-01

Pos logit contributions
��+1.912
haar+1.548
isphere+1.464
+1.422
yrus+1.352
Neg logit contributions
Rated-1.414
 whisper-1.329
Marginal-1.269
arella-1.222
 Minutes-1.207
Token a
Token ID257
Feature activation-1.16e-01

Pos logit contributions
Rated+0.399
 whisper+0.384
Marginal+0.355
arella+0.347
 Minutes+0.346
Neg logit contributions
��-0.498
haar-0.394
isphere-0.371
-0.359
yrus-0.339
Token shrine
Token ID29981
Feature activation-5.98e-01

Pos logit contributions
��+0.267
haar+0.207
isphere+0.191
+0.186
yrus+0.174
Neg logit contributions
Rated-0.265
 whisper-0.253
Marginal-0.239
 Minutes-0.233
arella-0.233
TokenSync
Token ID28985
Feature activation+4.45e-01

Pos logit contributions
��+0.298
haar+0.215
isphere+0.193
+0.183
yrus+0.169
Neg logit contributions
 whisper-0.457
Rated-0.454
arella-0.424
Marginal-0.422
wives-0.421
Token is
Token ID318
Feature activation+1.28e-01

Pos logit contributions
Rated+0.834
 whisper+0.806
Marginal+0.738
arella+0.720
wives+0.719
Neg logit contributions
��-1.192
haar-0.956
isphere-0.906
-0.877
yrus-0.841
Token turned
Token ID2900
Feature activation-8.24e-02

Pos logit contributions
Rated+0.264
 whisper+0.255
Marginal+0.237
arella+0.235
wives+0.233
Neg logit contributions
��-0.321
haar-0.250
isphere-0.235
-0.227
yrus-0.217
Token off
Token ID572
Feature activation-7.64e-01

Pos logit contributions
��+0.226
haar+0.181
isphere+0.172
+0.166
yrus+0.160
Neg logit contributions
Rated-0.148
 whisper-0.142
Marginal-0.131
arella-0.129
wives-0.128
Token by
Token ID416
Feature activation-9.47e-02

Pos logit contributions
��+2.073
haar+1.697
isphere+1.615
+1.539
yrus+1.517
Neg logit contributions
Rated-1.330
 whisper-1.261
Marginal-1.184
wives-1.145
uries-1.137
Token default
Token ID4277
Feature activation-2.03e+00

Pos logit contributions
��+0.220
haar+0.168
isphere+0.157
+0.153
yrus+0.144
Neg logit contributions
Rated-0.208
 whisper-0.202
Marginal-0.193
wives-0.185
arella-0.185
Token and
Token ID290
Feature activation-1.12e-01

Pos logit contributions
��+5.056
haar+4.126
isphere+3.866
+3.739
yrus+3.707
Neg logit contributions
Rated-3.719
 whisper-3.552
Marginal-3.350
wives-3.280
uries-3.196
Token has
Token ID468
Feature activation+6.94e-02

Pos logit contributions
��+0.287
haar+0.228
isphere+0.217
+0.205
yrus+0.200
Neg logit contributions
Rated-0.219
 whisper-0.211
Marginal-0.199
arella-0.193
wives-0.192
Token to
Token ID284
Feature activation-1.14e-01

Pos logit contributions
Rated+0.132
 whisper+0.127
Marginal+0.117
arella+0.115
wives+0.114
Neg logit contributions
��-0.184
haar-0.147
isphere-0.139
-0.133
yrus-0.128
Token be
Token ID307
Feature activation-1.07e-01

Pos logit contributions
��+0.292
haar+0.236
isphere+0.221
+0.208
yrus+0.204
Neg logit contributions
Rated-0.226
 whisper-0.214
Marginal-0.203
 Minutes-0.197
wives-0.197
Token enabled
Token ID9343
Feature activation-2.91e-01

Pos logit contributions
��+0.289
haar+0.232
isphere+0.221
+0.207
yrus+0.203
Neg logit contributions
Rated-0.198
 whisper-0.190
Marginal-0.178
wives-0.173
 Minutes-0.172
Token Hide
Token ID10415
Feature activation-1.07e+00

Pos logit contributions
Rated+0.229
 whisper+0.227
Marginal+0.201
arella+0.199
uries+0.198
Neg logit contributions
��-0.319
haar-0.255
isphere-0.237
-0.234
yrus-0.218
Token Caption
Token ID11260
Feature activation-3.62e-01

Pos logit contributions
��+2.809
haar+2.293
isphere+2.115
+2.077
yrus+2.004
Neg logit contributions
Rated-1.961
 whisper-1.897
Marginal-1.755
wives-1.705
ktop-1.687
Token 4
Token ID604
Feature activation-2.47e-01

Pos logit contributions
��+0.897
haar+0.702
isphere+0.650
+0.649
yrus+0.596
Neg logit contributions
Rated-0.727
 whisper-0.725
ktop-0.652
Marginal-0.648
arella-0.647
Token of
Token ID286
Feature activation-6.85e-01

Pos logit contributions
��+0.632
haar+0.519
+0.482
isphere+0.482
yrus+0.445
Neg logit contributions
 whisper-0.458
Rated-0.456
Marginal-0.405
ktop-0.404
uries-0.404
Token 15
Token ID1315
Feature activation-2.24e-01

Pos logit contributions
��+1.593
haar+1.249
+1.138
isphere+1.133
 Tinder+1.035
Neg logit contributions
Rated-1.462
 whisper-1.452
uries-1.317
ktop-1.315
arella-1.305
Token Photos
Token ID9434
Feature activation-2.02e+00

Pos logit contributions
��+0.563
haar+0.448
isphere+0.420
+0.407
yrus+0.384
Neg logit contributions
Rated-0.453
 whisper-0.444
Marginal-0.398
arella-0.394
 nearer-0.389
Token:
Token ID25
Feature activation-8.06e-01

Pos logit contributions
��+3.716
haar+2.993
isphere+2.680
+2.593
​​+2.327
Neg logit contributions
 whisper-4.725
Rated-4.660
arella-4.425
Marginal-4.423
ktop-4.397
Token Carly
Token ID35982
Feature activation-7.07e-02

Pos logit contributions
��+2.074
haar+1.615
isphere+1.523
+1.497
yrus+1.382
Neg logit contributions
Rated-1.590
 whisper-1.563
Marginal-1.391
arella-1.382
 nearer-1.367
Token Fiorina
Token ID49028
Feature activation+4.13e-01

Pos logit contributions
��+0.191
haar+0.153
isphere+0.144
+0.140
yrus+0.133
Neg logit contributions
Rated-0.133
 whisper-0.128
Marginal-0.116
arella-0.113
 Minutes-0.113
Token's
Token ID338
Feature activation+6.88e-03

Pos logit contributions
Rated+0.743
 whisper+0.712
Marginal+0.648
arella+0.631
 Minutes+0.629
Neg logit contributions
��-1.142
haar-0.919
isphere-0.873
-0.851
yrus-0.807
Token political
Token ID1964
Feature activation-6.01e-01

Pos logit contributions
Rated+0.013
 whisper+0.012
Marginal+0.011
arella+0.011
 Minutes+0.011
Neg logit contributions
��-0.018
haar-0.014
isphere-0.014
-0.013
yrus-0.013
Token is
Token ID318
Feature activation+7.32e-02

Pos logit contributions
Rated+1.201
 whisper+1.167
Marginal+1.046
 Minutes+1.034
arella+1.023
Neg logit contributions
��-1.835
haar-1.477
isphere-1.396
-1.363
yrus-1.291
Token that
Token ID326
Feature activation+8.36e-02

Pos logit contributions
Rated+0.139
 whisper+0.135
Marginal+0.123
 Minutes+0.122
arella+0.120
Neg logit contributions
��-0.195
haar-0.155
isphere-0.147
-0.143
yrus-0.136
Token it
Token ID340
Feature activation+1.14e-01

Pos logit contributions
Rated+0.194
 whisper+0.188
Marginal+0.174
 Minutes+0.173
arella+0.171
Neg logit contributions
��-0.189
haar-0.143
isphere-0.133
-0.129
yrus-0.121
Token can
Token ID460
Feature activation-2.93e-01

Pos logit contributions
Rated+0.233
 whisper+0.226
Marginal+0.206
 Minutes+0.205
arella+0.202
Neg logit contributions
��-0.289
haar-0.228
isphere-0.213
-0.209
yrus-0.197
Token skip
Token ID14267
Feature activation-6.26e-01

Pos logit contributions
��+0.767
haar+0.611
isphere+0.571
+0.562
yrus+0.533
Neg logit contributions
Rated-0.567
 whisper-0.546
 Minutes-0.499
Marginal-0.499
wives-0.489
Token default
Token ID4277
Feature activation-2.00e+00

Pos logit contributions
��+1.606
haar+1.267
isphere+1.183
+1.166
yrus+1.104
Neg logit contributions
Rated-1.247
 whisper-1.198
Marginal-1.101
 Minutes-1.092
wives-1.075
Token values
Token ID3815
Feature activation-1.84e-01

Pos logit contributions
��+5.023
haar+3.960
+3.652
isphere+3.651
yrus+3.524
Neg logit contributions
Rated-3.829
 whisper-3.637
wives-3.385
Marginal-3.382
 Minutes-3.358
Token.
Token ID13
Feature activation-3.81e-01

Pos logit contributions
��+0.503
haar+0.406
isphere+0.385
+0.377
yrus+0.357
Neg logit contributions
Rated-0.333
 whisper-0.323
Marginal-0.292
 Minutes-0.287
arella-0.285
Token In
Token ID554
Feature activation-3.60e-01

Pos logit contributions
��+0.922
haar+0.709
isphere+0.663
+0.647
yrus+0.611
Neg logit contributions
Rated-0.807
 whisper-0.781
Marginal-0.717
arella-0.714
wives-0.706
Token my
Token ID616
Feature activation+7.14e-02

Pos logit contributions
��+0.958
haar+0.757
isphere+0.703
+0.701
yrus+0.662
Neg logit contributions
Rated-0.686
 whisper-0.661
Marginal-0.604
arella-0.591
uries-0.590
Token comparison
Token ID7208
Feature activation-8.67e-01

Pos logit contributions
Rated+0.123
 whisper+0.119
Marginal+0.108
 Minutes+0.105
wives+0.105
Neg logit contributions
��-0.202
haar-0.164
isphere-0.154
-0.151
yrus-0.143
Token hur
Token ID6990
Feature activation-7.27e-01

Pos logit contributions
��+1.509
haar+1.187
isphere+1.108
+1.102
yrus+1.037
Neg logit contributions
Rated-1.169
 whisper-1.120
Marginal-1.029
uries-1.027
arella-1.015
Tokenrying
Token ID14992
Feature activation-2.98e-01

Pos logit contributions
��+1.547
haar+1.155
isphere+1.072
+1.023
yrus+0.947
Neg logit contributions
Rated-1.767
 whisper-1.739
Marginal-1.609
 Minutes-1.575
 nearer-1.568
Token back
Token ID736
Feature activation+2.34e-01

Pos logit contributions
��+0.807
haar+0.656
isphere+0.617
+0.608
yrus+0.577
Neg logit contributions
Rated-0.542
 whisper-0.515
Marginal-0.478
uries-0.464
 Minutes-0.460
Token to
Token ID284
Feature activation+6.23e-02

Pos logit contributions
Rated+0.407
 whisper+0.393
Marginal+0.355
 Minutes+0.346
arella+0.345
Neg logit contributions
��-0.662
haar-0.538
isphere-0.510
-0.502
yrus-0.475
Token where
Token ID810
Feature activation+2.65e-01

Pos logit contributions
Rated+0.135
 whisper+0.130
Marginal+0.121
arella+0.118
 Minutes+0.118
Neg logit contributions
��-0.151
haar-0.117
isphere-0.108
-0.107
yrus-0.099
Token Ruk
Token ID49037
Feature activation-2.00e+00

Pos logit contributions
Rated+0.580
 whisper+0.565
Marginal+0.517
 Minutes+0.512
arella+0.509
Neg logit contributions
��-0.634
haar-0.488
isphere-0.456
-0.445
yrus-0.414
Tokenia
Token ID544
Feature activation-4.58e-01

Pos logit contributions
��+4.761
haar+3.639
isphere+3.475
yrus+3.317
+3.268
Neg logit contributions
Rated-4.233
 whisper-3.991
Marginal-3.957
wives-3.824
 nearer-3.818
Token was
Token ID373
Feature activation+9.95e-02

Pos logit contributions
��+1.270
haar+1.018
isphere+0.966
+0.948
yrus+0.899
Neg logit contributions
Rated-0.816
 whisper-0.776
Marginal-0.720
arella-0.700
 Minutes-0.697
Token waiting
Token ID4953
Feature activation-1.38e-01

Pos logit contributions
Rated+0.189
 whisper+0.182
Marginal+0.165
 Minutes+0.164
arella+0.162
Neg logit contributions
��-0.267
haar-0.213
isphere-0.199
-0.196
yrus-0.185
Token.
Token ID13
Feature activation-3.47e-01

Pos logit contributions
��+0.390
haar+0.316
isphere+0.298
+0.292
yrus+0.277
Neg logit contributions
Rated-0.244
 whisper-0.232
Marginal-0.210
 Minutes-0.206
uries-0.204
Token When
Token ID1649
Feature activation-3.97e-01

Pos logit contributions
��+0.872
haar+0.676
+0.632
isphere+0.621
yrus+0.577
Neg logit contributions
Rated-0.712
 whisper-0.695
Marginal-0.629
arella-0.625
uries-0.618
Token of
Token ID286
Feature activation+1.49e-02

Pos logit contributions
Rated+0.431
 whisper+0.417
Marginal+0.371
 Minutes+0.368
arella+0.364
Neg logit contributions
��-0.686
haar-0.557
isphere-0.528
-0.515
yrus-0.487
Token the
Token ID262
Feature activation-2.22e-01

Pos logit contributions
Rated+0.033
 whisper+0.032
Marginal+0.030
 Minutes+0.029
arella+0.029
Neg logit contributions
��-0.035
haar-0.027
isphere-0.025
-0.024
yrus-0.023
Token study
Token ID2050
Feature activation-9.58e-01

Pos logit contributions
��+0.572
haar+0.454
isphere+0.425
+0.416
yrus+0.392
Neg logit contributions
Rated-0.445
 whisper-0.425
Marginal-0.388
 Minutes-0.383
wives-0.382
Token is
Token ID318
Feature activation-1.21e-02

Pos logit contributions
��+2.438
haar+1.987
isphere+1.863
+1.785
yrus+1.718
Neg logit contributions
Rated-1.894
 whisper-1.822
Marginal-1.648
 Minutes-1.622
arella-1.616
Token that
Token ID326
Feature activation+1.14e-01

Pos logit contributions
��+0.034
haar+0.027
isphere+0.026
+0.025
yrus+0.024
Neg logit contributions
Rated-0.022
 whisper-0.021
Marginal-0.019
 Minutes-0.019
arella-0.019
Token carbon
Token ID6588
Feature activation-1.95e+00

Pos logit contributions
Rated+0.235
 whisper+0.227
Marginal+0.207
 Minutes+0.205
arella+0.204
Neg logit contributions
��-0.286
haar-0.225
isphere-0.211
-0.205
yrus-0.193
Token emission
Token ID25592
Feature activation-1.27e+00

Pos logit contributions
��+4.983
haar+4.037
isphere+3.929
+3.896
yrus+3.582
Neg logit contributions
Rated-3.587
 whisper-3.386
 Minutes-3.132
Marginal-3.060
wives-3.030
Token and
Token ID290
Feature activation-1.46e-01

Pos logit contributions
��+3.074
haar+2.526
isphere+2.360
+2.354
yrus+2.209
Neg logit contributions
Rated-2.536
 whisper-2.437
Marginal-2.239
 Minutes-2.200
arella-2.182
Token climate
Token ID4258
Feature activation-3.52e-01

Pos logit contributions
��+0.371
haar+0.293
isphere+0.276
+0.266
yrus+0.251
Neg logit contributions
Rated-0.297
 whisper-0.283
Marginal-0.260
 Minutes-0.259
arella-0.257
Token change
Token ID1487
Feature activation-7.10e-01

Pos logit contributions
��+0.947
haar+0.777
isphere+0.731
+0.727
yrus+0.679
Neg logit contributions
Rated-0.645
 whisper-0.611
Marginal-0.559
 Minutes-0.555
wives-0.549
Token-
Token ID12
Feature activation-1.40e-01

Pos logit contributions
��+1.827
haar+1.494
isphere+1.393
+1.374
yrus+1.299
Neg logit contributions
Rated-1.375
 whisper-1.303
Marginal-1.199
 Minutes-1.179
wives-1.159
Token to
Token ID284
Feature activation-3.42e-02

Pos logit contributions
Rated+0.985
 whisper+0.955
Marginal+0.851
 Minutes+0.842
arella+0.835
Neg logit contributions
��-1.583
haar-1.280
isphere-1.214
-1.187
yrus-1.120
Token the
Token ID262
Feature activation+2.84e-03

Pos logit contributions
��+0.089
haar+0.071
isphere+0.067
+0.065
yrus+0.061
Neg logit contributions
Rated-0.067
 whisper-0.064
Marginal-0.059
arella-0.058
 Minutes-0.058
Token recent
Token ID2274
Feature activation+3.96e-01

Pos logit contributions
Rated+0.005
 whisper+0.005
Marginal+0.005
arella+0.005
 Minutes+0.005
Neg logit contributions
��-0.008
haar-0.006
isphere-0.006
-0.005
yrus-0.005
Token National
Token ID2351
Feature activation+7.18e-01

Pos logit contributions
Rated+0.756
 whisper+0.723
Marginal+0.663
arella+0.653
 Minutes+0.650
Neg logit contributions
��-1.056
haar-0.844
isphere-0.793
-0.770
yrus-0.731
Token Labor
Token ID7882
Feature activation-3.93e-02

Pos logit contributions
Rated+1.215
 whisper+1.171
Marginal+1.043
arella+1.025
 Minutes+1.015
Neg logit contributions
��-2.060
haar-1.687
isphere-1.598
-1.563
yrus-1.482
Token Relations
Token ID13883
Feature activation-1.94e+00

Pos logit contributions
��+0.091
haar+0.070
isphere+0.065
+0.064
yrus+0.058
Neg logit contributions
Rated-0.088
 whisper-0.086
Marginal-0.078
uries-0.077
ktop-0.077
Token Board
Token ID5926
Feature activation+2.18e-01

Pos logit contributions
��+5.283
haar+4.381
isphere+4.187
+4.014
yrus+3.783
Neg logit contributions
Rated-3.315
 whisper-3.031
Marginal-2.835
arella-2.769
ktop-2.729
Token attack
Token ID1368
Feature activation+7.41e-01

Pos logit contributions
Rated+0.375
 whisper+0.350
Marginal+0.322
arella+0.313
wives+0.309
Neg logit contributions
��-0.624
haar-0.505
isphere-0.481
-0.464
yrus-0.443
Token on
Token ID319
Feature activation-2.01e-01

Pos logit contributions
Rated+1.141
 whisper+1.094
Marginal+0.968
 Minutes+0.946
arella+0.939
Neg logit contributions
��-2.253
haar-1.849
isphere-1.764
-1.723
yrus-1.643
Token Boeing
Token ID17880
Feature activation-5.83e-01

Pos logit contributions
��+0.529
haar+0.422
isphere+0.393
+0.385
yrus+0.363
Neg logit contributions
Rated-0.384
 whisper-0.370
Marginal-0.342
arella-0.334
 Minutes-0.330
Token's
Token ID338
Feature activation-1.53e-01

Pos logit contributions
��+1.532
haar+1.216
isphere+1.147
+1.128
yrus+1.074
Neg logit contributions
Rated-1.103
 whisper-1.058
Marginal-0.983
arella-0.948
uries-0.944
Token The
Token ID383
Feature activation-1.30e-01

Pos logit contributions
Rated+0.559
 whisper+0.553
Marginal+0.509
arella+0.502
uries+0.500
Neg logit contributions
��-0.472
haar-0.351
isphere-0.322
-0.318
yrus-0.285
Token Chronicle
Token ID14160
Feature activation-5.81e-01

Pos logit contributions
��+0.344
haar+0.274
isphere+0.261
+0.254
yrus+0.238
Neg logit contributions
Rated-0.245
 whisper-0.239
Marginal-0.215
arella-0.212
uries-0.209
Token 3
Token ID513
Feature activation+3.67e-01

Pos logit contributions
��+1.667
haar+1.349
isphere+1.279
+1.253
yrus+1.183
Neg logit contributions
Rated-0.998
 whisper-0.969
Marginal-0.858
 Minutes-0.854
arella-0.844
Token of
Token ID286
Feature activation-2.35e-01

Pos logit contributions
Rated+0.665
 whisper+0.643
Marginal+0.581
 Minutes+0.571
arella+0.568
Neg logit contributions
��-0.991
haar-0.811
isphere-0.763
-0.748
yrus-0.701
Token 15
Token ID1315
Feature activation+1.89e-02

Pos logit contributions
��+0.624
haar+0.508
isphere+0.476
+0.469
yrus+0.436
Neg logit contributions
Rated-0.439
 whisper-0.425
Marginal-0.383
uries-0.375
 Minutes-0.374
Token Photo
Token ID5555
Feature activation-1.93e+00

Pos logit contributions
Rated+0.042
 whisper+0.041
Marginal+0.038
arella+0.037
 Minutes+0.037
Neg logit contributions
��-0.044
haar-0.034
isphere-0.032
-0.031
yrus-0.029
Token:
Token ID25
Feature activation-4.72e-01

Pos logit contributions
��+3.778
haar+3.008
isphere+2.795
+2.781
 Tinder+2.411
Neg logit contributions
 whisper-4.437
Rated-4.390
arella-4.121
ktop-4.104
uries-4.059
Token Le
Token ID1004
Feature activation-9.04e-02

Pos logit contributions
��+1.447
haar+1.196
isphere+1.141
+1.122
yrus+1.064
Neg logit contributions
Rated-0.701
 whisper-0.676
Marginal-0.594
 Minutes-0.573
arella-0.573
Tokena
Token ID64
Feature activation-7.24e-02

Pos logit contributions
��+0.186
haar+0.144
isphere+0.129
+0.125
yrus+0.118
Neg logit contributions
Rated-0.222
 whisper-0.218
Marginal-0.202
 Minutes-0.199
arella-0.197
Token Suzuki
Token ID35807
Feature activation+2.84e-02

Pos logit contributions
��+0.174
haar+0.136
isphere+0.126
+0.125
yrus+0.117
Neg logit contributions
Rated-0.153
 whisper-0.150
Marginal-0.138
arella-0.136
wives-0.134
Token,
Token ID11
Feature activation+2.40e-01

Pos logit contributions
Rated+0.055
 whisper+0.054
Marginal+0.048
arella+0.048
uries+0.048
Neg logit contributions
��-0.073
haar-0.059
isphere-0.054
-0.054
yrus-0.050
Token ign
Token ID3627
Feature activation+3.30e-01

Pos logit contributions
��+0.161
haar+0.129
isphere+0.123
+0.118
yrus+0.113
Neg logit contributions
Rated-0.113
 whisper-0.107
Marginal-0.099
 Minutes-0.097
arella-0.097
Tokeniting
Token ID1780
Feature activation-4.44e-01

Pos logit contributions
Rated+0.579
 whisper+0.562
Marginal+0.498
 Minutes+0.490
arella+0.482
Neg logit contributions
��-0.927
haar-0.755
isphere-0.719
-0.692
yrus-0.664
Token speculation
Token ID13367
Feature activation-1.64e-01

Pos logit contributions
��+1.123
haar+0.885
isphere+0.835
+0.804
yrus+0.757
Neg logit contributions
Rated-0.894
 whisper-0.854
arella-0.791
Marginal-0.789
 Minutes-0.780
Token about
Token ID546
Feature activation-5.53e-01

Pos logit contributions
��+0.447
haar+0.356
isphere+0.344
+0.331
yrus+0.313
Neg logit contributions
Rated-0.298
 whisper-0.285
Marginal-0.261
arella-0.256
 Minutes-0.253
Token secret
Token ID3200
Feature activation-3.76e-01

Pos logit contributions
��+1.398
haar+1.097
isphere+1.044
+1.004
yrus+0.947
Neg logit contributions
Rated-1.117
 whisper-1.072
Marginal-0.989
 Minutes-0.973
arella-0.972
Token Oval
Token ID25165
Feature activation-1.91e+00

Pos logit contributions
��+0.952
haar+0.747
isphere+0.713
+0.689
yrus+0.643
Neg logit contributions
Rated-0.755
 whisper-0.724
Marginal-0.670
 Minutes-0.651
 nearer-0.651
Token Office
Token ID4452
Feature activation-5.76e-01

Pos logit contributions
��+4.883
haar+3.860
isphere+3.616
+3.515
yrus+3.358
Neg logit contributions
Rated-3.751
 whisper-3.601
Marginal-3.357
 nearer-3.263
arella-3.230
Token recordings
Token ID18813
Feature activation+8.89e-02

Pos logit contributions
��+1.433
haar+1.126
isphere+1.064
+1.030
yrus+0.964
Neg logit contributions
Rated-1.191
 whisper-1.129
Marginal-1.051
arella-1.025
 nearer-1.019
Token is
Token ID318
Feature activation+6.32e-03

Pos logit contributions
Rated+0.164
 whisper+0.157
Marginal+0.143
arella+0.140
 Minutes+0.138
Neg logit contributions
��-0.240
haar-0.194
isphere-0.186
-0.178
yrus-0.169
Token like
Token ID588
Feature activation-4.08e-02

Pos logit contributions
Rated+0.013
 whisper+0.012
Marginal+0.011
 Minutes+0.011
arella+0.011
Neg logit contributions
��-0.016
haar-0.013
isphere-0.012
-0.012
yrus-0.011
Token a
Token ID257
Feature activation-1.28e-01

Pos logit contributions
��+0.102
haar+0.080
isphere+0.075
+0.073
yrus+0.068
Neg logit contributions
Rated-0.084
 whisper-0.082
Marginal-0.075
 Minutes-0.074
arella-0.074
Token 1941
Token ID23234
Feature activation-3.22e-01

Pos logit contributions
��+2.150
haar+1.728
isphere+1.631
+1.602
yrus+1.516
Neg logit contributions
Rated-1.430
 whisper-1.366
Marginal-1.252
arella-1.217
uries-1.204
Token,
Token ID11
Feature activation-3.96e-01

Pos logit contributions
��+0.889
haar+0.713
isphere+0.676
+0.661
yrus+0.622
Neg logit contributions
Rated-0.584
 whisper-0.567
Marginal-0.508
 Minutes-0.501
arella-0.498
Token Germany
Token ID4486
Feature activation-1.62e-01

Pos logit contributions
��+1.027
haar+0.805
isphere+0.767
+0.749
yrus+0.706
Neg logit contributions
Rated-0.780
 whisper-0.742
Marginal-0.693
arella-0.671
uries-0.660
Token launched
Token ID5611
Feature activation-2.04e-01

Pos logit contributions
��+0.420
haar+0.334
isphere+0.320
+0.305
yrus+0.292
Neg logit contributions
Rated-0.318
 whisper-0.306
Marginal-0.283
 Minutes-0.274
arella-0.274
Token Operation
Token ID14680
Feature activation-1.97e-01

Pos logit contributions
��+0.501
haar+0.388
isphere+0.360
+0.358
yrus+0.334
Neg logit contributions
Rated-0.432
 whisper-0.416
Marginal-0.383
arella-0.377
 Minutes-0.375
Token Barbar
Token ID45952
Feature activation-1.91e+00

Pos logit contributions
��+0.456
haar+0.348
isphere+0.325
+0.322
yrus+0.292
Neg logit contributions
Rated-0.440
 whisper-0.429
Marginal-0.394
arella-0.390
wives-0.387
Tokenoss
Token ID793
Feature activation+7.55e-02

Pos logit contributions
��+3.484
haar+2.595
+2.311
isphere+2.285
yrus+2.038
Neg logit contributions
Rated-4.888
 whisper-4.883
Marginal-4.658
 Minutes-4.552
wives-4.524
Tokena
Token ID64
Feature activation-7.96e-02

Pos logit contributions
Rated+0.183
 whisper+0.177
Marginal+0.164
 Minutes+0.163
arella+0.161
Neg logit contributions
��-0.165
haar-0.123
isphere-0.113
-0.110
yrus-0.102
Token,
Token ID11
Feature activation-3.60e-01

Pos logit contributions
��+0.218
haar+0.176
isphere+0.167
+0.163
yrus+0.154
Neg logit contributions
Rated-0.144
 whisper-0.141
Marginal-0.126
arella-0.123
 Minutes-0.122
Token an
Token ID281
Feature activation-1.34e-02

Pos logit contributions
��+0.855
haar+0.662
isphere+0.623
+0.616
yrus+0.571
Neg logit contributions
Rated-0.768
 whisper-0.753
Marginal-0.694
arella-0.684
 Minutes-0.679
Token invasion
Token ID11796
Feature activation+2.21e-01

Pos logit contributions
��+0.034
haar+0.026
isphere+0.025
+0.024
yrus+0.023
Neg logit contributions
Rated-0.028
 whisper-0.027
Marginal-0.025
arella-0.024
 Minutes-0.024
Token belt
Token ID10999
Feature activation-8.26e-01

Pos logit contributions
��+1.509
haar+1.231
isphere+1.140
+1.112
yrus+1.048
Neg logit contributions
Rated-1.084
 whisper-1.050
Marginal-0.951
arella-0.947
 Minutes-0.927
Token which
Token ID543
Feature activation-2.48e-01

Pos logit contributions
��+2.228
haar+1.823
isphere+1.723
+1.662
yrus+1.597
Neg logit contributions
Rated-1.499
 whisper-1.444
arella-1.302
Marginal-1.300
 Minutes-1.284
Token comprises
Token ID28800
Feature activation-2.11e-01

Pos logit contributions
��+0.674
haar+0.540
isphere+0.508
+0.497
yrus+0.471
Neg logit contributions
Rated-0.458
 whisper-0.445
Marginal-0.405
arella-0.398
 Minutes-0.394
Token parts
Token ID3354
Feature activation-6.71e-02

Pos logit contributions
��+0.539
haar+0.429
isphere+0.399
+0.390
yrus+0.366
Neg logit contributions
Rated-0.424
 whisper-0.409
Marginal-0.376
arella-0.373
 Minutes-0.368
Token of
Token ID286
Feature activation-2.38e-01

Pos logit contributions
��+0.200
haar+0.162
isphere+0.155
+0.152
yrus+0.144
Neg logit contributions
Rated-0.108
 whisper-0.105
Marginal-0.092
 Minutes-0.091
 nearer-0.089
Token Roh
Token ID32694
Feature activation-1.91e+00

Pos logit contributions
��+0.609
haar+0.485
isphere+0.449
+0.441
yrus+0.412
Neg logit contributions
Rated-0.478
 whisper-0.462
Marginal-0.423
arella-0.420
 Minutes-0.414
Tokent
Token ID83
Feature activation-3.56e-01

Pos logit contributions
��+3.137
haar+2.473
isphere+2.189
+1.933
yrus+1.836
Neg logit contributions
Rated-5.222
 whisper-5.160
Marginal-4.827
 Minutes-4.724
 nearer-4.702
Tokenak
Token ID461
Feature activation+9.80e-02

Pos logit contributions
��+0.735
haar+0.585
isphere+0.532
+0.500
yrus+0.472
Neg logit contributions
Rated-0.860
 whisper-0.845
Marginal-0.784
 Minutes-0.769
 nearer-0.757
Token,
Token ID11
Feature activation-5.91e-02

Pos logit contributions
Rated+0.181
 whisper+0.176
Marginal+0.158
 Minutes+0.156
arella+0.156
Neg logit contributions
��-0.267
haar-0.214
isphere-0.202
-0.198
yrus-0.186
Token J
Token ID449
Feature activation-3.62e-01

Pos logit contributions
��+0.155
haar+0.124
isphere+0.116
+0.114
yrus+0.106
Neg logit contributions
Rated-0.114
 whisper-0.111
Marginal-0.101
arella-0.100
 Minutes-0.098
Tokenind
Token ID521
Feature activation-7.59e-02

Pos logit contributions
��+0.779
haar+0.604
isphere+0.545
+0.520
yrus+0.492
Neg logit contributions
Rated-0.875
 whisper-0.860
Marginal-0.790
 Minutes-0.783
arella-0.772
Token.
Token ID13
Feature activation-5.33e-01

Pos logit contributions
Rated+0.295
 whisper+0.288
Marginal+0.258
 Minutes+0.254
wives+0.252
Neg logit contributions
��-0.457
haar-0.369
isphere-0.343
-0.340
yrus-0.320
TokenV
Token ID53
Feature activation-5.68e-01

Pos logit contributions
��+1.171
haar+0.921
+0.791
isphere+0.788
yrus+0.728
Neg logit contributions
Rated-1.227
 whisper-1.221
 nearer-1.103
arella-1.091
 Minutes-1.090
Token.
Token ID13
Feature activation-3.45e-01

Pos logit contributions
��+1.609
haar+1.303
isphere+1.241
+1.211
yrus+1.139
Neg logit contributions
Rated-0.985
 whisper-0.956
Marginal-0.851
 Minutes-0.845
arella-0.841
Token All
Token ID1439
Feature activation-4.40e-01

Pos logit contributions
��+0.922
haar+0.743
isphere+0.684
+0.682
yrus+0.635
Neg logit contributions
Rated-0.654
 whisper-0.637
Marginal-0.572
arella-0.560
 Minutes-0.558
Token rights
Token ID2489
Feature activation-8.99e-01

Pos logit contributions
��+1.108
haar+0.889
isphere+0.832
+0.804
yrus+0.765
Neg logit contributions
Rated-0.885
 whisper-0.851
arella-0.783
wives-0.771
Marginal-0.765
Token reserved
Token ID10395
Feature activation-1.88e+00

Pos logit contributions
��+2.208
haar+1.731
isphere+1.698
+1.586
yrus+1.551
Neg logit contributions
Rated-1.802
 whisper-1.700
uries-1.615
arella-1.610
-1.572
Token.
Token ID13
Feature activation-1.78e-01

Pos logit contributions
��+4.232
haar+3.480
+3.159
isphere+3.011
yrus+2.978
Neg logit contributions
Rated-3.843
 whisper-3.809
Marginal-3.532
wives-3.484
ktop-3.452
Token<|endoftext|>
Token ID50256
Feature activation-7.57e-04

Pos logit contributions
��+0.482
haar+0.392
isphere+0.367
+0.362
yrus+0.339
Neg logit contributions
Rated-0.327
 whisper-0.318
arella-0.282
Marginal-0.279
uries-0.277
TokenOn
Token ID2202
Feature activation+2.11e-01

Pos logit contributions
��+0.002
haar+0.002
isphere+0.001
+0.001
yrus+0.001
Neg logit contributions
 whisper-0.002
Rated-0.002
 Minutes-0.001
arella-0.001
 nearer-0.001
Token the
Token ID262
Feature activation-1.05e-01

Pos logit contributions
Rated+0.394
 whisper+0.383
Marginal+0.344
arella+0.339
 Minutes+0.336
Neg logit contributions
��-0.575
haar-0.457
isphere-0.434
-0.424
yrus-0.400
Token heels
Token ID18728
Feature activation-1.17e-02

Pos logit contributions
��+0.284
haar+0.226
isphere+0.214
+0.208
yrus+0.200
Neg logit contributions
Rated-0.193
 whisper-0.184
Marginal-0.169
arella-0.168
wives-0.163
Token23
Token ID1954
Feature activation-5.48e-03

Pos logit contributions
��+0.982
haar+0.788
+0.746
isphere+0.730
yrus+0.684
Neg logit contributions
Rated-0.650
 whisper-0.646
arella-0.567
Marginal-0.565
uries-0.562
Token22
Token ID1828
Feature activation-2.43e-01

Pos logit contributions
��+0.015
haar+0.012
+0.011
isphere+0.011
yrus+0.011
Neg logit contributions
Rated-0.010
 whisper-0.010
arella-0.008
Marginal-0.008
uries-0.008
Token62
Token ID5237
Feature activation-1.46e-01

Pos logit contributions
��+0.658
haar+0.534
+0.502
isphere+0.490
yrus+0.457
Neg logit contributions
Rated-0.439
 whisper-0.435
uries-0.386
arella-0.383
Marginal-0.378
Token13
Token ID1485
Feature activation+3.33e-01

Pos logit contributions
��+0.382
haar+0.305
+0.284
isphere+0.282
yrus+0.260
Neg logit contributions
Rated-0.281
 whisper-0.279
arella-0.246
Marginal-0.246
uries-0.246
Token (
Token ID357
Feature activation-3.27e-01

Pos logit contributions
Rated+0.648
 whisper+0.637
Marginal+0.572
arella+0.567
 Minutes+0.563
Neg logit contributions
��-0.866
haar-0.693
isphere-0.644
-0.638
yrus-0.592
TokenPhoto
Token ID6191
Feature activation-1.84e+00

Pos logit contributions
��+0.693
haar+0.520
isphere+0.482
+0.472
yrus+0.425
Neg logit contributions
Rated-0.784
 whisper-0.778
Marginal-0.710
arella-0.708
uries-0.708
Token11
Token ID1157
Feature activation+4.63e-01

Pos logit contributions
��+3.784
haar+2.831
isphere+2.739
+2.713
 Tinder+2.282
Neg logit contributions
Rated-4.328
 whisper-4.187
ktop-4.074
Marginal-4.005
uries-3.952
Token:
Token ID25
Feature activation-4.07e-01

Pos logit contributions
Rated+0.860
 whisper+0.836
Marginal+0.748
 Minutes+0.741
arella+0.735
Neg logit contributions
��-1.257
haar-1.006
isphere-0.951
-0.934
yrus-0.877
Token SA
Token ID14719
Feature activation-2.84e-01

Pos logit contributions
��+1.110
haar+0.904
isphere+0.850
+0.848
yrus+0.791
Neg logit contributions
Rated-0.725
 whisper-0.705
Marginal-0.627
uries-0.617
arella-0.615
TokenUL
Token ID6239
Feature activation+3.54e-01

Pos logit contributions
��+0.819
haar+0.665
isphere+0.632
+0.628
yrus+0.588
Neg logit contributions
Rated-0.471
 whisper-0.461
Marginal-0.411
 Minutes-0.406
arella-0.405
Token LO
Token ID17579
Feature activation+2.00e-01

Pos logit contributions
Rated+0.503
 whisper+0.491
Marginal+0.423
arella+0.420
uries+0.418
Neg logit contributions
��-1.115
haar-0.920
isphere-0.876
-0.862
yrus-0.815
Token over
Token ID625
Feature activation+6.95e-02

Pos logit contributions
Rated+0.195
 whisper+0.187
Marginal+0.175
+0.165
 Minutes+0.164
Neg logit contributions
��-0.294
haar-0.236
isphere-0.225
-0.216
yrus-0.209
Token several
Token ID1811
Feature activation+4.25e-01

Pos logit contributions
Rated+0.147
 whisper+0.142
Marginal+0.135
 Minutes+0.129
arella+0.129
Neg logit contributions
��-0.172
haar-0.132
isphere-0.123
-0.119
yrus-0.113
Token months
Token ID1933
Feature activation+1.45e-01

Pos logit contributions
Rated+0.763
 whisper+0.722
Marginal+0.677
arella+0.651
 Minutes+0.639
Neg logit contributions
��-1.176
haar-0.946
isphere-0.904
-0.870
yrus-0.829
Token.
Token ID13
Feature activation+2.71e-01

Pos logit contributions
Rated+0.268
 whisper+0.257
Marginal+0.237
 Minutes+0.229
wives+0.225
Neg logit contributions
��-0.395
haar-0.319
isphere-0.302
-0.292
yrus-0.279
Token<|endoftext|>
Token ID50256
Feature activation+1.62e-01

Pos logit contributions
Rated+0.448
 whisper+0.433
 Minutes+0.383
Marginal+0.382
arella+0.375
Neg logit contributions
��-0.796
haar-0.648
isphere-0.617
-0.604
yrus-0.572
TokenOutside
Token ID30815
Feature activation+1.47e+00

Pos logit contributions
 whisper+0.324
Rated+0.322
 Minutes+0.290
arella+0.289
 nearer+0.286
Neg logit contributions
��-0.410
haar-0.323
isphere-0.303
-0.299
yrus-0.277
Token linebacker
Token ID18961
Feature activation-2.48e-01

Pos logit contributions
Rated+2.847
 whisper+2.779
Marginal+2.497
 Minutes+2.482
arella+2.453
Neg logit contributions
��-3.865
haar-3.068
isphere-2.891
-2.826
yrus-2.654
Token Ryan
Token ID6047
Feature activation+2.04e-01

Pos logit contributions
��+0.624
haar+0.486
isphere+0.457
+0.444
yrus+0.421
Neg logit contributions
Rated-0.512
 whisper-0.495
Marginal-0.455
arella-0.445
 Minutes-0.444
Token Ker
Token ID17337
Feature activation+1.04e+00

Pos logit contributions
Rated+0.401
 whisper+0.388
Marginal+0.350
arella+0.341
uries+0.341
Neg logit contributions
��-0.538
haar-0.431
isphere-0.406
-0.389
yrus-0.370
Tokenrigan
Token ID35631
Feature activation+5.33e-02

Pos logit contributions
Rated+2.148
 whisper+2.101
Marginal+1.910
 Minutes+1.877
arella+1.852
Neg logit contributions
��-2.605
haar-2.074
isphere-1.939
-1.874
yrus-1.775
Token grabs
Token ID22378
Feature activation+5.37e-01

Pos logit contributions
Rated+0.096
 whisper+0.092
Marginal+0.085
uries+0.082
 Minutes+0.081
Neg logit contributions
��-0.147
haar-0.119
isphere-0.113
-0.109
yrus-0.104
Token slowed
Token ID20955
Feature activation-4.59e-01

Pos logit contributions
Rated+0.757
 whisper+0.734
Marginal+0.668
arella+0.663
 Minutes+0.655
Neg logit contributions
��-1.117
haar-0.886
isphere-0.843
-0.807
yrus-0.774
Token them
Token ID606
Feature activation-3.63e-01

Pos logit contributions
��+1.198
haar+0.930
isphere+0.896
+0.866
yrus+0.838
Neg logit contributions
Rated-0.902
 whisper-0.856
Marginal-0.781
arella-0.773
uries-0.769
Token down
Token ID866
Feature activation-2.94e-01

Pos logit contributions
��+1.032
haar+0.836
isphere+0.794
+0.774
yrus+0.740
Neg logit contributions
Rated-0.618
 whisper-0.590
Marginal-0.523
 Minutes-0.520
arella-0.519
Token a
Token ID257
Feature activation+2.70e-02

Pos logit contributions
��+0.785
haar+0.626
isphere+0.591
+0.575
yrus+0.547
Neg logit contributions
Rated-0.555
 whisper-0.536
Marginal-0.483
arella-0.476
 Minutes-0.476
Token little
Token ID1310
Feature activation+1.15e+00

Pos logit contributions
Rated+0.045
 whisper+0.043
Marginal+0.038
 Minutes+0.038
arella+0.038
Neg logit contributions
��-0.078
haar-0.064
isphere-0.060
-0.059
yrus-0.056
Token bit
Token ID1643
Feature activation+1.50e+00

Pos logit contributions
Rated+1.758
 whisper+1.704
Marginal+1.486
 Minutes+1.470
arella+1.451
Neg logit contributions
��-3.522
haar-2.894
isphere-2.758
-2.703
yrus-2.567
Token better
Token ID1365
Feature activation-4.41e-01

Pos logit contributions
Rated+2.668
 whisper+2.602
Marginal+2.323
 Minutes+2.301
arella+2.276
Neg logit contributions
��-4.171
haar-3.354
isphere-3.182
-3.111
yrus-2.928
Token than
Token ID621
Feature activation+9.11e-02

Pos logit contributions
��+1.184
haar+0.949
isphere+0.894
+0.870
yrus+0.832
Neg logit contributions
Rated-0.814
 whisper-0.791
Marginal-0.709
 Minutes-0.704
arella-0.698
Token we
Token ID356
Feature activation+2.08e-01

Pos logit contributions
Rated+0.199
 whisper+0.191
Marginal+0.178
arella+0.175
 Minutes+0.174
Neg logit contributions
��-0.219
haar-0.167
isphere-0.157
-0.150
yrus-0.143
Token could
Token ID714
Feature activation+1.64e-01

Pos logit contributions
Rated+0.383
 whisper+0.365
Marginal+0.337
 Minutes+0.332
arella+0.329
Neg logit contributions
��-0.569
haar-0.459
isphere-0.429
-0.420
yrus-0.398
Token.
Token ID13
Feature activation-1.87e-02

Pos logit contributions
Rated+0.297
 whisper+0.285
Marginal+0.257
 Minutes+0.257
arella+0.253
Neg logit contributions
��-0.450
haar-0.363
isphere-0.339
-0.336
yrus-0.318
Token to
Token ID284
Feature activation+2.88e-01

Pos logit contributions
Rated+0.450
 whisper+0.439
Marginal+0.400
 Minutes+0.397
arella+0.395
Neg logit contributions
��-0.505
haar-0.392
isphere-0.367
-0.358
yrus-0.334
Token use
Token ID779
Feature activation+4.26e-01

Pos logit contributions
Rated+0.507
 whisper+0.477
Marginal+0.439
 Minutes+0.431
arella+0.426
Neg logit contributions
��-0.809
haar-0.654
isphere-0.624
-0.607
yrus-0.580
Token or
Token ID393
Feature activation-3.90e-02

Pos logit contributions
Rated+0.750
 whisper+0.723
Marginal+0.649
 Minutes+0.642
arella+0.635
Neg logit contributions
��-1.195
haar-0.969
isphere-0.917
-0.897
yrus-0.849
Token how
Token ID703
Feature activation+7.38e-03

Pos logit contributions
��+0.098
haar+0.077
isphere+0.074
+0.071
yrus+0.068
Neg logit contributions
Rated-0.079
 whisper-0.076
Marginal-0.070
 Minutes-0.069
arella-0.069
Token to
Token ID284
Feature activation+2.91e-01

Pos logit contributions
Rated+0.015
 whisper+0.014
Marginal+0.013
 Minutes+0.013
arella+0.013
Neg logit contributions
��-0.019
haar-0.015
isphere-0.014
-0.014
yrus-0.013
Token call
Token ID869
Feature activation+1.45e+00

Pos logit contributions
Rated+0.514
 whisper+0.485
Marginal+0.444
 Minutes+0.440
uries+0.432
Neg logit contributions
��-0.815
haar-0.658
isphere-0.628
-0.609
yrus-0.586
Token another
Token ID1194
Feature activation-9.66e-03

Pos logit contributions
Rated+2.766
 whisper+2.696
Marginal+2.421
 Minutes+2.403
arella+2.380
Neg logit contributions
��-3.859
haar-3.073
isphere-2.901
-2.832
yrus-2.661
Token person
Token ID1048
Feature activation-9.92e-02

Pos logit contributions
��+0.025
haar+0.020
isphere+0.019
+0.019
yrus+0.018
Neg logit contributions
Rated-0.018
 whisper-0.018
Marginal-0.016
 Minutes-0.016
arella-0.016
Token out
Token ID503
Feature activation+5.60e-01

Pos logit contributions
��+0.269
haar+0.218
isphere+0.205
+0.200
yrus+0.191
Neg logit contributions
Rated-0.182
 whisper-0.174
Marginal-0.159
 Minutes-0.155
arella-0.154
Token.
Token ID13
Feature activation+2.88e-02

Pos logit contributions
Rated+0.962
 whisper+0.929
Marginal+0.829
 Minutes+0.821
arella+0.809
Neg logit contributions
��-1.602
haar-1.301
isphere-1.234
-1.205
yrus-1.142
Token He
Token ID679
Feature activation-4.43e-02

Pos logit contributions
Rated+0.058
 whisper+0.058
arella+0.051
uries+0.051
Marginal+0.051
Neg logit contributions
��-0.072
haar-0.057
-0.053
isphere-0.052
yrus-0.049
Tokenils
Token ID4487
Feature activation-3.90e-01

Pos logit contributions
Rated+0.737
 whisper+0.723
Marginal+0.610
 Minutes+0.605
 nearer+0.591
Neg logit contributions
��-1.620
haar-1.359
isphere-1.280
-1.252
yrus-1.212
Token ont
Token ID39585
Feature activation-2.30e-01

Pos logit contributions
��+1.076
haar+0.874
isphere+0.813
+0.797
yrus+0.765
Neg logit contributions
Rated-0.706
 whisper-0.665
Marginal-0.600
arella-0.597
wives-0.591
Token mont
Token ID40689
Feature activation-9.40e-03

Pos logit contributions
��+0.651
haar+0.529
isphere+0.495
+0.486
yrus+0.465
Neg logit contributions
Rated-0.400
 whisper-0.380
Marginal-0.340
arella-0.339
wives-0.336
Tokené
Token ID2634
Feature activation-1.06e-01

Pos logit contributions
��+0.024
haar+0.019
isphere+0.018
+0.017
yrus+0.017
Neg logit contributions
Rated-0.019
 whisper-0.018
Marginal-0.017
 Minutes-0.017
wives-0.016
Token une
Token ID17809
Feature activation-3.77e-02

Pos logit contributions
��+0.298
haar+0.242
isphere+0.227
+0.222
yrus+0.212
Neg logit contributions
Rated-0.188
 whisper-0.181
Marginal-0.160
 Minutes-0.160
arella-0.160
Token n
Token ID299
Feature activation+1.43e+00

Pos logit contributions
��+0.104
haar+0.084
isphere+0.079
+0.077
yrus+0.073
Neg logit contributions
Rated-0.068
 whisper-0.065
Marginal-0.059
arella-0.059
 Minutes-0.058
Tokenou
Token ID280
Feature activation+5.31e-01

Pos logit contributions
Rated+2.261
 whisper+2.189
Marginal+1.920
 Minutes+1.901
arella+1.878
Neg logit contributions
��-4.296
haar-3.517
isphere-3.347
-3.280
yrus-3.110
Tokenvel
Token ID626
Feature activation+2.63e-01

Pos logit contributions
Rated+1.156
 whisper+1.122
Marginal+1.029
 Minutes+1.019
arella+1.008
Neg logit contributions
��-1.279
haar-0.997
isphere-0.932
-0.904
yrus-0.848
Tokenle
Token ID293
Feature activation-1.11e-03

Pos logit contributions
Rated+0.660
 whisper+0.643
Marginal+0.593
 Minutes+0.589
arella+0.587
Neg logit contributions
��-0.550
haar-0.412
isphere-0.374
-0.360
yrus-0.332
Token organisation
Token ID12684
Feature activation-6.26e-02

Pos logit contributions
��+0.003
haar+0.003
isphere+0.002
+0.002
yrus+0.002
Neg logit contributions
Rated-0.002
 whisper-0.002
arella-0.002
Marginal-0.002
 Minutes-0.002
Token ind
Token ID773
Feature activation+3.53e-01

Pos logit contributions
��+0.178
haar+0.144
isphere+0.136
+0.132
yrus+0.128
Neg logit contributions
Rated-0.109
 whisper-0.103
arella-0.091
Marginal-0.091
wives-0.091
Token,
Token ID11
Feature activation-2.13e-01

Pos logit contributions
Rated+1.243
 whisper+1.211
Marginal+1.083
 Minutes+1.075
arella+1.063
Neg logit contributions
��-1.854
haar-1.486
isphere-1.406
-1.374
yrus-1.294
Token the
Token ID262
Feature activation-1.49e-01

Pos logit contributions
��+0.533
haar+0.419
isphere+0.394
+0.381
yrus+0.360
Neg logit contributions
Rated-0.443
 whisper-0.429
Marginal-0.390
arella-0.384
 Minutes-0.381
Token commission
Token ID5810
Feature activation+6.17e-01

Pos logit contributions
��+0.396
haar+0.315
isphere+0.298
+0.287
yrus+0.274
Neg logit contributions
Rated-0.286
 whisper-0.272
Marginal-0.248
arella-0.244
wives-0.241
Token of
Token ID286
Feature activation+2.26e-01

Pos logit contributions
Rated+1.056
 whisper+1.022
Marginal+0.904
 Minutes+0.897
arella+0.888
Neg logit contributions
��-1.771
haar-1.434
isphere-1.368
-1.328
yrus-1.264
Token inquiry
Token ID12069
Feature activation+5.82e-01

Pos logit contributions
Rated+0.376
 whisper+0.362
Marginal+0.323
 Minutes+0.316
arella+0.314
Neg logit contributions
��-0.659
haar-0.537
isphere-0.508
-0.496
yrus-0.472
Token treated
Token ID5716
Feature activation+1.40e+00

Pos logit contributions
Rated+0.978
 whisper+0.943
Marginal+0.836
arella+0.824
 Minutes+0.824
Neg logit contributions
��-1.688
haar-1.370
isphere-1.309
-1.267
yrus-1.215
Token the
Token ID262
Feature activation-2.29e-02

Pos logit contributions
Rated+2.811
 whisper+2.761
 Minutes+2.484
Marginal+2.480
arella+2.453
Neg logit contributions
��-3.549
haar-2.786
isphere-2.634
-2.577
yrus-2.389
Token two
Token ID734
Feature activation-1.58e-01

Pos logit contributions
��+0.061
haar+0.049
isphere+0.046
+0.044
yrus+0.042
Neg logit contributions
Rated-0.044
 whisper-0.042
Marginal-0.038
arella-0.037
 Minutes-0.037
Token parts
Token ID3354
Feature activation-5.81e-01

Pos logit contributions
��+0.387
haar+0.303
isphere+0.285
+0.271
yrus+0.259
Neg logit contributions
Rated-0.338
 whisper-0.323
Marginal-0.301
arella-0.292
 Minutes-0.290
Token as
Token ID355
Feature activation-3.13e-01

Pos logit contributions
��+1.627
haar+1.322
isphere+1.248
+1.218
yrus+1.153
Neg logit contributions
Rated-1.026
 whisper-0.989
Marginal-0.882
 Minutes-0.870
arella-0.866
Token a
Token ID257
Feature activation-1.92e-01

Pos logit contributions
��+0.807
haar+0.643
isphere+0.602
+0.585
yrus+0.554
Neg logit contributions
Rated-0.617
 whisper-0.595
Marginal-0.544
arella-0.538
 Minutes-0.535
Token no
Token ID645
Feature activation+4.72e-01

Pos logit contributions
Rated+1.340
 whisper+1.284
Marginal+1.173
 Minutes+1.150
arella+1.149
Neg logit contributions
��-1.909
haar-1.531
isphere-1.439
-1.404
yrus-1.330
Token mercy
Token ID17703
Feature activation+8.76e-01

Pos logit contributions
Rated+0.913
 whisper+0.866
Marginal+0.802
 Minutes+0.778
arella+0.776
Neg logit contributions
��-1.238
haar-0.992
isphere-0.928
-0.910
yrus-0.859
Token,
Token ID11
Feature activation+1.65e-01

Pos logit contributions
Rated+1.571
 whisper+1.515
Marginal+1.357
 Minutes+1.342
arella+1.335
Neg logit contributions
��-2.448
haar-1.974
isphere-1.870
-1.819
yrus-1.729
Token and
Token ID290
Feature activation+2.40e-01

Pos logit contributions
Rated+0.314
 whisper+0.299
Marginal+0.276
 Minutes+0.271
arella+0.271
Neg logit contributions
��-0.440
haar-0.351
isphere-0.329
-0.323
yrus-0.306
Token his
Token ID465
Feature activation+2.38e-01

Pos logit contributions
Rated+0.475
 whisper+0.450
Marginal+0.418
arella+0.413
 Minutes+0.410
Neg logit contributions
��-0.623
haar-0.490
isphere-0.463
-0.447
yrus-0.428
Token forces
Token ID3386
Feature activation+3.92e-01

Pos logit contributions
Rated+0.457
 whisper+0.428
Marginal+0.398
 Minutes+0.393
arella+0.391
Neg logit contributions
��-0.629
haar-0.508
isphere-0.476
-0.464
yrus-0.437
Token step
Token ID2239
Feature activation+1.90e-01

Pos logit contributions
Rated+0.733
 whisper+0.689
Marginal+0.642
 Minutes+0.627
arella+0.623
Neg logit contributions
��-1.058
haar-0.853
isphere-0.809
-0.784
yrus-0.746
Token up
Token ID510
Feature activation-2.06e-01

Pos logit contributions
Rated+0.352
 whisper+0.338
Marginal+0.309
 Minutes+0.304
arella+0.301
Neg logit contributions
��-0.512
haar-0.414
isphere-0.390
-0.382
yrus-0.363
Token their
Token ID511
Feature activation+4.37e-01

Pos logit contributions
��+0.534
haar+0.432
isphere+0.403
+0.397
yrus+0.374
Neg logit contributions
Rated-0.393
 whisper-0.374
Marginal-0.345
 Minutes-0.341
arella-0.339
Token assaults
Token ID21832
Feature activation+1.55e-01

Pos logit contributions
Rated+0.939
 whisper+0.900
Marginal+0.832
 Minutes+0.827
arella+0.819
Neg logit contributions
��-1.059
haar-0.827
isphere-0.770
-0.747
yrus-0.702
Token on
Token ID319
Feature activation+3.14e-02

Pos logit contributions
Rated+0.272
 whisper+0.260
Marginal+0.235
 Minutes+0.231
arella+0.227
Neg logit contributions
��-0.435
haar-0.356
isphere-0.335
-0.327
yrus-0.310
Token 65
Token ID6135
Feature activation-3.33e-01

Pos logit contributions
��+0.257
haar+0.198
isphere+0.181
+0.180
yrus+0.165
Neg logit contributions
Rated-0.259
 whisper-0.252
Marginal-0.235
arella-0.231
uries-0.229
Token 1
Token ID352
Feature activation+2.61e-01

Pos logit contributions
��+0.999
haar+0.810
isphere+0.776
+0.762
yrus+0.728
Neg logit contributions
Rated-0.524
 whisper-0.502
Marginal-0.449
arella-0.440
wives-0.430
Token/
Token ID14
Feature activation-5.45e-02

Pos logit contributions
Rated+0.535
 whisper+0.526
Marginal+0.477
arella+0.472
 Minutes+0.466
Neg logit contributions
��-0.639
haar-0.509
isphere-0.474
-0.467
yrus-0.434
Token3
Token ID18
Feature activation+2.07e-01

Pos logit contributions
��+0.156
haar+0.127
isphere+0.121
+0.119
yrus+0.112
Neg logit contributions
Rated-0.091
 whisper-0.090
arella-0.078
Marginal-0.078
 Minutes-0.077
Token IP
Token ID6101
Feature activation-1.21e+00

Pos logit contributions
Rated+0.383
 whisper+0.372
 Minutes+0.334
Marginal+0.331
arella+0.323
Neg logit contributions
��-0.566
haar-0.457
isphere-0.429
-0.420
yrus-0.396
Token
Token ID198
Feature activation+3.76e-01

Pos logit contributions
��+3.498
haar+2.824
isphere+2.689
+2.643
yrus+2.511
Neg logit contributions
Rated-2.035
 whisper-1.974
Marginal-1.754
 Minutes-1.733
arella-1.702
Token
Token ID198
Feature activation+3.63e-01

Pos logit contributions
Rated+0.662
 whisper+0.650
Marginal+0.576
arella+0.570
 Minutes+0.569
Neg logit contributions
��-1.029
haar-0.845
isphere-0.791
-0.778
yrus-0.736
TokenKevin
Token ID23865
Feature activation+2.33e-01

Pos logit contributions
Rated+0.745
 whisper+0.742
 Minutes+0.667
Marginal+0.662
arella+0.662
Neg logit contributions
��-0.905
haar-0.707
isphere-0.664
-0.655
yrus-0.608
Token Qu
Token ID2264
Feature activation+1.12e+00

Pos logit contributions
Rated+0.442
 whisper+0.429
Marginal+0.386
 Minutes+0.380
arella+0.378
Neg logit contributions
��-0.628
haar-0.500
isphere-0.472
-0.460
yrus-0.434
Tokenack
Token ID441
Feature activation+3.37e-01

Pos logit contributions
Rated+2.109
 whisper+2.053
Marginal+1.839
 Minutes+1.820
arella+1.791
Neg logit contributions
��-3.030
haar-2.435
isphere-2.306
-2.231
yrus-2.119
Tokenen
Token ID268
Feature activation+2.47e-01

Pos logit contributions
Rated+0.863
 whisper+0.846
Marginal+0.789
 Minutes+0.776
uries+0.769
Neg logit contributions
��-0.677
haar-0.505
isphere-0.459
-0.435
yrus-0.404
Token going
Token ID1016
Feature activation-2.20e-01

Pos logit contributions
��+0.602
haar+0.478
isphere+0.444
+0.440
yrus+0.413
Neg logit contributions
Rated-0.485
 whisper-0.471
Marginal-0.432
 Minutes-0.428
arella-0.424
Token to
Token ID284
Feature activation-5.67e-02

Pos logit contributions
��+0.643
haar+0.524
isphere+0.499
+0.486
yrus+0.461
Neg logit contributions
Rated-0.365
 whisper-0.356
Marginal-0.312
 Minutes-0.308
arella-0.305
Token go
Token ID467
Feature activation+6.42e-02

Pos logit contributions
��+0.154
haar+0.124
isphere+0.117
+0.115
yrus+0.110
Neg logit contributions
Rated-0.104
 whisper-0.098
Marginal-0.091
 Minutes-0.089
arella-0.089
Token all
Token ID477
Feature activation-1.96e-01

Pos logit contributions
Rated+0.117
 whisper+0.113
Marginal+0.104
 Minutes+0.102
arella+0.101
Neg logit contributions
��-0.174
haar-0.141
isphere-0.131
-0.130
yrus-0.123
Token 1984
Token ID12844
Feature activation-1.24e-02

Pos logit contributions
��+0.530
haar+0.422
isphere+0.399
+0.392
yrus+0.369
Neg logit contributions
Rated-0.365
 whisper-0.354
Marginal-0.318
 Minutes-0.317
arella-0.314
Token on
Token ID319
Feature activation+2.18e-01

Pos logit contributions
��+0.033
haar+0.026
isphere+0.025
+0.025
yrus+0.023
Neg logit contributions
Rated-0.024
 whisper-0.023
Marginal-0.021
 Minutes-0.020
arella-0.020
Token other
Token ID584
Feature activation+2.77e-01

Pos logit contributions
Rated+0.444
 whisper+0.429
Marginal+0.394
 Minutes+0.390
arella+0.389
Neg logit contributions
��-0.549
haar-0.431
isphere-0.403
-0.399
yrus-0.374
Token books
Token ID3835
Feature activation+1.21e-01

Pos logit contributions
Rated+0.498
 whisper+0.484
Marginal+0.435
arella+0.433
 Minutes+0.428
Neg logit contributions
��-0.764
haar-0.614
isphere-0.584
-0.573
yrus-0.545
Token in
Token ID287
Feature activation-2.04e-01

Pos logit contributions
Rated+0.237
 whisper+0.230
Marginal+0.208
 Minutes+0.207
arella+0.206
Neg logit contributions
��-0.316
haar-0.252
isphere-0.238
-0.232
yrus-0.219
Token your
Token ID534
Feature activation-1.75e-01

Pos logit contributions
��+0.481
haar+0.371
isphere+0.340
+0.336
yrus+0.316
Neg logit contributions
Rated-0.448
 whisper-0.434
Marginal-0.403
arella-0.398
wives-0.390
Token Kindle
Token ID27114
Feature activation+6.33e-02

Pos logit contributions
��+0.437
haar+0.346
isphere+0.322
+0.313
yrus+0.297
Neg logit contributions
Rated-0.356
 whisper-0.350
Marginal-0.322
arella-0.314
 Minutes-0.314
Token but
Token ID475
Feature activation+1.91e-01

Pos logit contributions
Rated+0.096
 whisper+0.093
Marginal+0.084
 Minutes+0.083
arella+0.082
Neg logit contributions
��-0.136
haar-0.109
isphere-0.103
-0.101
yrus-0.095
Token ask
Token ID1265
Feature activation+1.70e-01

Pos logit contributions
Rated+0.400
 whisper+0.385
Marginal+0.354
arella+0.349
 Minutes+0.347
Neg logit contributions
��-0.476
haar-0.372
isphere-0.351
-0.340
yrus-0.319
Token any
Token ID597
Feature activation+1.95e-01

Pos logit contributions
Rated+0.341
 whisper+0.329
Marginal+0.302
arella+0.296
 Minutes+0.295
Neg logit contributions
��-0.433
haar-0.340
isphere-0.323
-0.314
yrus-0.293
Token one
Token ID530
Feature activation-2.28e-01

Pos logit contributions
Rated+0.341
 whisper+0.327
Marginal+0.295
arella+0.292
 Minutes+0.291
Neg logit contributions
��-0.550
haar-0.441
isphere-0.424
-0.411
yrus-0.386
Token of
Token ID286
Feature activation-6.27e-03

Pos logit contributions
��+0.625
haar+0.496
isphere+0.476
+0.461
yrus+0.435
Neg logit contributions
Rated-0.413
 whisper-0.393
Marginal-0.359
arella-0.357
 Minutes-0.356
Token the
Token ID262
Feature activation+1.10e-01

Pos logit contributions
��+0.015
haar+0.012
isphere+0.011
+0.011
yrus+0.010
Neg logit contributions
Rated-0.014
 whisper-0.013
Marginal-0.012
 Minutes-0.012
arella-0.012
Token players
Token ID1938
Feature activation-1.53e-01

Pos logit contributions
Rated+0.208
 whisper+0.198
Marginal+0.182
 Minutes+0.178
arella+0.178
Neg logit contributions
��-0.295
haar-0.236
isphere-0.225
-0.217
yrus-0.205
Token who
Token ID508
Feature activation+2.80e-01

Pos logit contributions
��+0.413
haar+0.328
isphere+0.312
+0.305
yrus+0.287
Neg logit contributions
Rated-0.284
 whisper-0.272
Marginal-0.247
arella-0.246
 Minutes-0.245
Token has
Token ID468
Feature activation+6.76e-02

Pos logit contributions
Rated+0.515
 whisper+0.486
Marginal+0.454
 Minutes+0.439
arella+0.436
Neg logit contributions
��-0.763
haar-0.614
isphere-0.588
-0.560
yrus-0.541
Token don
Token ID836
Feature activation+1.93e-02

Pos logit contributions
Rated+0.125
 whisper+0.120
Marginal+0.110
arella+0.108
 Minutes+0.107
Neg logit contributions
��-0.184
haar-0.145
isphere-0.139
-0.133
yrus-0.128
Tokenned
Token ID2817
Feature activation+7.97e-01

Pos logit contributions
Rated+0.029
 whisper+0.028
Marginal+0.024
 Minutes+0.024
arella+0.024
Neg logit contributions
��-0.059
haar-0.049
isphere-0.047
-0.046
yrus-0.043
Token traff
Token ID11878
Feature activation+1.04e+00

Pos logit contributions
Rated+0.229
 whisper+0.222
 Minutes+0.204
arella+0.204
Marginal+0.203
Neg logit contributions
��-0.287
haar-0.225
isphere-0.212
-0.204
yrus-0.193
Tokenicked
Token ID9484
Feature activation+1.57e-01

Pos logit contributions
Rated+1.327
 whisper+1.281
 Minutes+1.094
Marginal+1.082
arella+1.053
Neg logit contributions
��-3.433
haar-2.878
isphere-2.773
-2.701
yrus-2.598
Token thorough
Token ID9321
Feature activation-6.20e-01

Pos logit contributions
Rated+0.313
 whisper+0.301
Marginal+0.278
 Minutes+0.273
arella+0.272
Neg logit contributions
��-0.407
haar-0.320
isphere-0.300
-0.292
yrus-0.278
Tokenf
Token ID69
Feature activation+2.15e-01

Pos logit contributions
��+1.606
haar+1.271
isphere+1.170
+1.140
yrus+1.106
Neg logit contributions
Rated-1.224
 whisper-1.191
Marginal-1.098
 Minutes-1.070
arella-1.058
Tokenares
Token ID3565
Feature activation+2.96e-01

Pos logit contributions
Rated+0.270
 whisper+0.250
Marginal+0.215
EngineDebug+0.207
 Minutes+0.205
Neg logit contributions
��-0.708
haar-0.598
isphere-0.574
yrus-0.554
-0.549
Token
Token ID960
Feature activation+3.90e-03

Pos logit contributions
Rated+0.540
 whisper+0.522
Marginal+0.474
 Minutes+0.464
arella+0.460
Neg logit contributions
��-0.818
haar-0.658
isphere-0.624
-0.606
yrus-0.575
Tokenwhich
Token ID4758
Feature activation-1.28e-02

Pos logit contributions
Rated+0.008
 whisper+0.008
Marginal+0.007
 Minutes+0.007
arella+0.007
Neg logit contributions
��-0.010
haar-0.008
isphere-0.007
-0.007
yrus-0.007
Token she
Token ID673
Feature activation+5.88e-02

Pos logit contributions
��+0.035
haar+0.028
isphere+0.026
+0.026
yrus+0.024
Neg logit contributions
Rated-0.024
 whisper-0.023
Marginal-0.021
arella-0.021
 Minutes-0.021
Token considers
Token ID14358
Feature activation+1.72e-01

Pos logit contributions
Rated+0.105
 whisper+0.102
Marginal+0.093
 Minutes+0.092
arella+0.091
Neg logit contributions
��-0.163
haar-0.132
isphere-0.124
-0.122
yrus-0.115
Token urban
Token ID7876
Feature activation+8.11e-01

Pos logit contributions
Rated+0.336
 whisper+0.326
Marginal+0.295
arella+0.294
 Minutes+0.293
Neg logit contributions
��-0.450
haar-0.355
isphere-0.334
-0.327
yrus-0.306
Token thru
Token ID33834
Feature activation-1.47e-01

Pos logit contributions
Rated+1.530
 whisper+1.485
Marginal+1.336
 Minutes+1.329
arella+1.311
Neg logit contributions
��-2.190
haar-1.743
isphere-1.652
-1.615
yrus-1.517
Token bear
Token ID6842
Feature activation+3.26e-01

Pos logit contributions
Rated+1.010
 whisper+0.945
Marginal+0.879
 Minutes+0.868
arella+0.856
Neg logit contributions
��-1.651
haar-1.342
isphere-1.266
-1.239
yrus-1.182
Token the
Token ID262
Feature activation+3.43e-01

Pos logit contributions
Rated+0.661
 whisper+0.628
Marginal+0.586
 Minutes+0.574
arella+0.573
Neg logit contributions
��-0.835
haar-0.658
isphere-0.614
-0.602
yrus-0.567
Token wh
Token ID348
Feature activation+5.54e-01

Pos logit contributions
Rated+0.708
 whisper+0.664
Marginal+0.628
 Minutes+0.615
arella+0.614
Neg logit contributions
��-0.870
haar-0.683
isphere-0.639
-0.623
yrus-0.582
Tokenips
Token ID2419
Feature activation+1.11e+00

Pos logit contributions
Rated+1.074
 whisper+1.038
Marginal+0.937
 Minutes+0.921
arella+0.909
Neg logit contributions
��-1.457
haar-1.178
isphere-1.121
-1.063
yrus-1.028
Token and
Token ID290
Feature activation-1.65e-02

Pos logit contributions
Rated+2.025
 whisper+1.950
Marginal+1.761
 Minutes+1.739
arella+1.719
Neg logit contributions
��-3.067
haar-2.485
isphere-2.345
-2.283
yrus-2.159
Token sc
Token ID629
Feature activation-3.69e-01

Pos logit contributions
��+0.044
haar+0.035
isphere+0.033
+0.032
yrus+0.030
Neg logit contributions
Rated-0.032
 whisper-0.030
Marginal-0.028
arella-0.027
 Minutes-0.027
Tokenorns
Token ID19942
Feature activation+2.02e-01

Pos logit contributions
��+0.780
haar+0.608
isphere+0.560
yrus+0.512
+0.506
Neg logit contributions
Rated-0.891
 whisper-0.875
Marginal-0.807
 Minutes-0.793
 nearer-0.782
Token of
Token ID286
Feature activation+2.96e-01

Pos logit contributions
Rated+0.378
 whisper+0.357
Marginal+0.330
 Minutes+0.323
arella+0.323
Neg logit contributions
��-0.544
haar-0.443
isphere-0.416
-0.404
yrus-0.382
Token time
Token ID640
Feature activation+7.40e-01

Pos logit contributions
Rated+0.595
 whisper+0.566
Marginal+0.524
arella+0.514
 Minutes+0.511
Neg logit contributions
��-0.766
haar-0.604
isphere-0.567
-0.552
yrus-0.522
Token,
Token ID11
Feature activation+1.04e-01

Pos logit contributions
Rated+1.470
 whisper+1.409
Marginal+1.294
 Minutes+1.272
arella+1.262
Neg logit contributions
��-1.924
haar-1.536
isphere-1.441
-1.401
yrus-1.322
Token
Token ID198
Feature activation+1.00e+00

Pos logit contributions
Rated+0.190
 whisper+0.177
Marginal+0.165
arella+0.160
 Minutes+0.160
Neg logit contributions
��-0.284
haar-0.229
isphere-0.218
-0.210
yrus-0.201
Token b
Token ID275
Feature activation+8.58e-01

Pos logit contributions
��+0.742
haar+0.591
isphere+0.563
+0.544
yrus+0.509
Neg logit contributions
Rated-0.519
 whisper-0.492
Marginal-0.465
arella-0.445
 Minutes-0.442
Tokenikers
Token ID24913
Feature activation-6.96e-01

Pos logit contributions
Rated+1.829
 whisper+1.796
Marginal+1.637
 Minutes+1.613
arella+1.589
Neg logit contributions
��-2.103
haar-1.642
isphere-1.539
-1.484
yrus-1.399
Token dislike
Token ID23109
Feature activation+4.79e-02

Pos logit contributions
��+1.803
haar+1.444
isphere+1.384
+1.316
yrus+1.268
Neg logit contributions
Rated-1.327
 whisper-1.236
Marginal-1.207
 Minutes-1.152
uries-1.139
Token the
Token ID262
Feature activation+2.98e-03

Pos logit contributions
Rated+0.101
 whisper+0.098
Marginal+0.090
 Minutes+0.089
arella+0.088
Neg logit contributions
��-0.118
haar-0.092
isphere-0.086
-0.084
yrus-0.078
Token st
Token ID336
Feature activation-1.98e-01

Pos logit contributions
Rated+0.006
 whisper+0.006
Marginal+0.005
 Minutes+0.005
arella+0.005
Neg logit contributions
��-0.008
haar-0.006
isphere-0.006
-0.006
yrus-0.005
Tokeneeper
Token ID41278
Feature activation-3.24e-01

Pos logit contributions
��+0.546
haar+0.446
isphere+0.428
+0.399
yrus+0.397
Neg logit contributions
Rated-0.352
 whisper-0.346
Marginal-0.312
 Minutes-0.302
 nearer-0.296
Token paths
Token ID13532
Feature activation+1.74e-02

Pos logit contributions
��+0.840
haar+0.662
isphere+0.623
+0.605
yrus+0.566
Neg logit contributions
Rated-0.635
 whisper-0.610
Marginal-0.566
 Minutes-0.557
arella-0.548
Token up
Token ID510
Feature activation-8.79e-02

Pos logit contributions
Rated+0.032
 whisper+0.031
Marginal+0.028
 Minutes+0.027
arella+0.027
Neg logit contributions
��-0.048
haar-0.038
isphere-0.036
-0.035
yrus-0.033
Token to
Token ID284
Feature activation-2.15e-01

Pos logit contributions
��+0.227
haar+0.179
isphere+0.168
+0.164
yrus+0.154
Neg logit contributions
Rated-0.175
 whisper-0.170
Marginal-0.155
 Minutes-0.153
arella-0.151
Token Lynd
Token ID33561
Feature activation-6.22e-02

Pos logit contributions
��+0.533
haar+0.414
isphere+0.386
+0.375
yrus+0.352
Neg logit contributions
Rated-0.453
 whisper-0.440
Marginal-0.407
 Minutes-0.397
arella-0.396
Tokenale
Token ID1000
Feature activation+2.53e-01

Pos logit contributions
��+0.176
haar+0.147
isphere+0.139
+0.133
yrus+0.129
Neg logit contributions
Rated-0.105
 whisper-0.102
Marginal-0.090
 Minutes-0.089
uries-0.087
Token get
Token ID651
Feature activation+3.74e-01

Pos logit contributions
��+0.813
haar+0.650
isphere+0.613
+0.584
yrus+0.569
Neg logit contributions
Rated-0.569
 whisper-0.536
Marginal-0.515
EngineDebug-0.495
 Minutes-0.494
Token the
Token ID262
Feature activation-1.17e-01

Pos logit contributions
Rated+0.804
 whisper+0.775
Marginal+0.721
arella+0.713
 Minutes+0.707
Neg logit contributions
��-0.912
haar-0.701
isphere-0.663
-0.638
yrus-0.598
Token impression
Token ID10647
Feature activation-4.34e-01

Pos logit contributions
��+0.286
haar+0.221
isphere+0.207
+0.200
yrus+0.189
Neg logit contributions
Rated-0.248
 whisper-0.237
Marginal-0.221
arella-0.218
 Minutes-0.217
Token that
Token ID326
Feature activation-1.23e-01

Pos logit contributions
��+1.156
haar+0.914
isphere+0.869
+0.840
yrus+0.797
Neg logit contributions
Rated-0.832
 whisper-0.800
Marginal-0.732
arella-0.722
 Minutes-0.714
Token the
Token ID262
Feature activation-2.44e-01

Pos logit contributions
��+0.294
haar+0.227
isphere+0.213
+0.204
yrus+0.193
Neg logit contributions
Rated-0.268
 whisper-0.259
Marginal-0.241
arella-0.237
 Minutes-0.235
Token house
Token ID2156
Feature activation-7.64e-02

Pos logit contributions
��+0.656
haar+0.521
isphere+0.494
+0.477
yrus+0.454
Neg logit contributions
Rated-0.459
 whisper-0.440
Marginal-0.405
arella-0.399
 Minutes-0.395
Token was
Token ID373
Feature activation-1.20e-01

Pos logit contributions
��+0.210
haar+0.168
isphere+0.160
+0.156
yrus+0.147
Neg logit contributions
Rated-0.139
 whisper-0.134
Marginal-0.122
 Minutes-0.120
arella-0.119
Token moved
Token ID3888
Feature activation+7.37e-02

Pos logit contributions
��+0.316
haar+0.250
isphere+0.238
+0.228
yrus+0.216
Neg logit contributions
Rated-0.232
 whisper-0.222
Marginal-0.206
arella-0.204
 Minutes-0.204
Token there
Token ID612
Feature activation-8.25e-02

Pos logit contributions
Rated+0.134
 whisper+0.128
Marginal+0.118
 Minutes+0.114
arella+0.113
Neg logit contributions
��-0.202
haar-0.163
isphere-0.155
-0.151
yrus-0.143
Token and
Token ID290
Feature activation+1.03e-01

Pos logit contributions
��+0.224
haar+0.181
isphere+0.171
+0.166
yrus+0.158
Neg logit contributions
Rated-0.151
 whisper-0.146
Marginal-0.134
 Minutes-0.129
arella-0.127
Token then
Token ID788
Feature activation-1.59e-01

Pos logit contributions
Rated+0.205
 whisper+0.198
Marginal+0.184
arella+0.181
 Minutes+0.179
Neg logit contributions
��-0.265
haar-0.207
isphere-0.196
-0.189
yrus-0.179
Token Ann
Token ID5506
Feature activation+5.43e-01

Pos logit contributions
��+0.369
haar+0.288
isphere+0.271
+0.267
yrus+0.251
Neg logit contributions
Rated-0.290
 whisper-0.276
Marginal-0.257
arella-0.251
 Minutes-0.249
Tokenal
Token ID282
Feature activation+9.93e-03

Pos logit contributions
Rated+0.931
 whisper+0.905
Marginal+0.808
 Minutes+0.799
uries+0.771
Neg logit contributions
��-1.544
haar-1.273
isphere-1.210
-1.164
yrus-1.122
Tokenise
Token ID786
Feature activation+4.00e-03

Pos logit contributions
Rated+0.021
 whisper+0.020
Marginal+0.019
 Minutes+0.019
 Speaker+0.018
Neg logit contributions
��-0.024
haar-0.019
isphere-0.018
-0.017
yrus-0.017
Token.
Token ID13
Feature activation-2.14e-02

Pos logit contributions
Rated+0.007
 whisper+0.007
Marginal+0.006
 Minutes+0.006
arella+0.006
Neg logit contributions
��-0.011
haar-0.009
isphere-0.008
-0.008
yrus-0.008
Token There
Token ID1318
Feature activation-1.53e-01

Pos logit contributions
��+0.053
haar+0.042
isphere+0.039
+0.038
 Tinder+0.035
Neg logit contributions
Rated-0.044
 whisper-0.043
Marginal-0.039
arella-0.038
uries-0.038
Token
Token ID447
Feature activation-2.96e-01

Pos logit contributions
��+0.386
haar+0.304
isphere+0.286
+0.277
yrus+0.261
Neg logit contributions
Rated-0.310
 whisper-0.301
Marginal-0.277
 Minutes-0.270
arella-0.270
Token
Token ID247
Feature activation-1.11e-01

Pos logit contributions
��+0.523
haar+0.349
isphere+0.305
+0.290
yrus+0.255
Neg logit contributions
Rated-0.842
 whisper-0.837
Marginal-0.786
 Minutes-0.777
arella-0.773
Tokens
Token ID82
Feature activation-7.50e-02

Pos logit contributions
��+0.291
haar+0.232
isphere+0.217
+0.212
yrus+0.200
Neg logit contributions
Rated-0.218
 whisper-0.213
Marginal-0.194
 Minutes-0.190
arella-0.187
Token a
Token ID257
Feature activation+2.32e-02

Pos logit contributions
��+0.194
haar+0.152
isphere+0.143
+0.138
yrus+0.132
Neg logit contributions
Rated-0.150
 whisper-0.142
Marginal-0.133
arella-0.130
 Minutes-0.128
Token huge
Token ID3236
Feature activation-1.44e-01

Pos logit contributions
Rated+0.047
 whisper+0.044
Marginal+0.041
 Minutes+0.041
arella+0.041
Neg logit contributions
��-0.059
haar-0.047
isphere-0.044
-0.042
yrus-0.040
Token assumption
Token ID13196
Feature activation+2.67e-01

Pos logit contributions
��+0.389
haar+0.310
isphere+0.291
+0.284
yrus+0.272
Neg logit contributions
Rated-0.270
 whisper-0.252
Marginal-0.235
 Minutes-0.231
arella-0.230
Token
Token ID198
Feature activation-5.02e-01

Pos logit contributions
��+0.600
haar+0.477
isphere+0.445
+0.438
yrus+0.411
Neg logit contributions
Rated-0.443
 whisper-0.436
Marginal-0.387
arella-0.383
uries-0.381
Token
Token ID198
Feature activation-5.07e-01

Pos logit contributions
��+1.243
haar+1.034
isphere+0.948
+0.939
yrus+0.878
Neg logit contributions
Rated-0.945
 whisper-0.941
uries-0.846
arella-0.846
Marginal-0.833
TokenMech
Token ID28452
Feature activation+3.73e-01

Pos logit contributions
��+1.340
haar+1.064
isphere+1.004
+0.992
yrus+0.920
Neg logit contributions
 whisper-0.958
Rated-0.951
 Minutes-0.851
arella-0.850
 nearer-0.840
Tokenan
Token ID272
Feature activation+5.74e-01

Pos logit contributions
Rated+0.695
 whisper+0.676
Marginal+0.605
 Minutes+0.600
arella+0.593
Neg logit contributions
��-1.012
haar-0.816
isphere-0.770
-0.748
yrus-0.709
Tokenically
Token ID1146
Feature activation-1.95e-01

Pos logit contributions
Rated+0.840
 whisper+0.812
Marginal+0.701
 Minutes+0.694
arella+0.679
Neg logit contributions
��-1.787
haar-1.481
isphere-1.423
-1.380
yrus-1.325
Token,
Token ID11
Feature activation-3.71e-02

Pos logit contributions
��+0.532
haar+0.427
isphere+0.403
+0.394
yrus+0.371
Neg logit contributions
Rated-0.359
 whisper-0.349
Marginal-0.312
 Minutes-0.310
arella-0.307
Token I
Token ID314
Feature activation-1.40e-01

Pos logit contributions
��+0.086
haar+0.066
isphere+0.062
+0.059
yrus+0.056
Neg logit contributions
Rated-0.084
 whisper-0.081
Marginal-0.075
 Minutes-0.074
arella-0.074
Token think
Token ID892
Feature activation-4.52e-01

Pos logit contributions
��+0.360
haar+0.286
isphere+0.269
+0.257
yrus+0.250
Neg logit contributions
Rated-0.276
 whisper-0.261
Marginal-0.248
 Minutes-0.241
EngineDebug-0.238
Token it
Token ID340
Feature activation-6.46e-03

Pos logit contributions
��+1.054
haar+0.798
isphere+0.749
+0.714
yrus+0.682
Neg logit contributions
Rated-1.026
 whisper-0.979
Marginal-0.914
 Minutes-0.900
arella-0.898
Token worked
Token ID3111
Feature activation-6.96e-01

Pos logit contributions
��+0.018
haar+0.014
isphere+0.014
+0.013
yrus+0.013
Neg logit contributions
Rated-0.012
 whisper-0.011
Marginal-0.010
 Minutes-0.010
arella-0.010
Token great
Token ID1049
Feature activation-2.34e-01

Pos logit contributions
��+1.806
haar+1.447
isphere+1.359
+1.316
yrus+1.269
Neg logit contributions
Rated-1.333
 whisper-1.273
Marginal-1.190
 Minutes-1.167
uries-1.152
Tokenor
Token ID273
Feature activation+6.48e-03

Pos logit contributions
Rated+0.805
 whisper+0.778
Marginal+0.713
 Minutes+0.698
arella+0.688
Neg logit contributions
��-1.008
haar-0.805
isphere-0.762
-0.731
yrus-0.693
Tokenail
Token ID603
Feature activation+2.66e-01

Pos logit contributions
Rated+0.008
 whisper+0.008
 Minutes+0.007
Marginal+0.007
arella+0.007
Neg logit contributions
��-0.021
haar-0.018
isphere-0.017
-0.016
yrus-0.016
Token
Token ID960
Feature activation-1.13e-02

Pos logit contributions
Rated+0.559
 whisper+0.536
Marginal+0.494
 Minutes+0.486
arella+0.482
Neg logit contributions
��-0.657
haar-0.519
isphere-0.490
-0.477
yrus-0.447
Tokenit
Token ID270
Feature activation-5.54e-02

Pos logit contributions
��+0.027
haar+0.022
isphere+0.020
+0.020
yrus+0.018
Neg logit contributions
Rated-0.024
 whisper-0.023
 Minutes-0.021
Marginal-0.021
arella-0.021
Token put
Token ID1234
Feature activation-8.31e-01

Pos logit contributions
��+0.135
haar+0.107
isphere+0.099
+0.097
yrus+0.091
Neg logit contributions
Rated-0.117
 whisper-0.114
Marginal-0.104
 Minutes-0.103
arella-0.102
Token Brock
Token ID20501
Feature activation-1.48e+00

Pos logit contributions
��+2.136
haar+1.675
isphere+1.591
+1.563
yrus+1.475
Neg logit contributions
Rated-1.621
 whisper-1.556
Marginal-1.443
arella-1.404
 Minutes-1.396
Tokenway
Token ID1014
Feature activation-5.73e-01

Pos logit contributions
��+3.727
haar+3.027
isphere+2.749
+2.715
yrus+2.536
Neg logit contributions
Rated-2.928
 whisper-2.820
Marginal-2.649
ktop-2.552
uries-2.542
Token,
Token ID11
Feature activation-2.16e-01

Pos logit contributions
��+1.570
haar+1.263
isphere+1.194
+1.176
yrus+1.102
Neg logit contributions
Rated-1.035
 whisper-0.994
Marginal-0.912
 Minutes-0.878
uries-0.878
Token Og
Token ID25686
Feature activation-5.75e-01

Pos logit contributions
��+0.548
haar+0.431
isphere+0.403
+0.393
yrus+0.370
Neg logit contributions
Rated-0.438
 whisper-0.424
Marginal-0.390
arella-0.383
 Minutes-0.380
Tokenden
Token ID6559
Feature activation-8.56e-01

Pos logit contributions
��+1.360
haar+1.082
isphere+1.019
+0.963
yrus+0.930
Neg logit contributions
Rated-1.252
 whisper-1.214
Marginal-1.107
 Minutes-1.094
wives-1.071
Tokenville
Token ID4244
Feature activation-2.26e-01

Pos logit contributions
��+2.302
haar+1.841
isphere+1.730
+1.694
yrus+1.598
Neg logit contributions
Rated-1.598
 whisper-1.549
Marginal-1.407
arella-1.381
 Minutes-1.371
Token an
Token ID281
Feature activation+4.38e-02

Pos logit contributions
��+0.626
haar+0.498
isphere+0.467
+0.456
yrus+0.430
Neg logit contributions
Rated-0.485
 whisper-0.466
Marginal-0.427
wives-0.418
arella-0.418
Token explanation
Token ID7468
Feature activation+7.35e-01

Pos logit contributions
Rated+0.085
 whisper+0.083
Marginal+0.075
wives+0.074
 Minutes+0.074
Neg logit contributions
��-0.114
haar-0.090
isphere-0.086
-0.082
yrus-0.079
Token Monday
Token ID3321
Feature activation-6.80e-01

Pos logit contributions
Rated+1.252
 whisper+1.211
Marginal+1.074
 Minutes+1.057
arella+1.053
Neg logit contributions
��-2.114
haar-1.716
isphere-1.637
-1.591
yrus-1.508
Token of
Token ID286
Feature activation-3.22e-02

Pos logit contributions
��+1.847
haar+1.492
isphere+1.427
+1.377
yrus+1.307
Neg logit contributions
Rated-1.233
 whisper-1.184
Marginal-1.069
arella-1.045
wives-1.044
Token the
Token ID262
Feature activation-2.78e-01

Pos logit contributions
��+0.076
haar+0.058
isphere+0.055
+0.053
yrus+0.050
Neg logit contributions
Rated-0.071
 whisper-0.069
Marginal-0.063
arella-0.063
 Minutes-0.063
Token unprecedented
Token ID13029
Feature activation-1.34e+00

Pos logit contributions
��+0.747
haar+0.598
isphere+0.568
+0.549
yrus+0.523
Neg logit contributions
Rated-0.523
 whisper-0.492
Marginal-0.452
arella-0.449
 Minutes-0.443
Token misc
Token ID12747
Feature activation+5.23e-01

Pos logit contributions
��+3.397
haar+2.697
isphere+2.588
+2.470
yrus+2.368
Neg logit contributions
Rated-2.606
 whisper-2.392
arella-2.266
Marginal-2.248
wives-2.248
Tokenue
Token ID518
Feature activation-3.06e-01

Pos logit contributions
Rated+0.932
 whisper+0.898
Marginal+0.799
 Minutes+0.779
wives+0.777
Neg logit contributions
��-1.467
haar-1.192
isphere-1.128
-1.089
yrus-1.047
Token,
Token ID11
Feature activation-3.12e-01

Pos logit contributions
��+0.823
haar+0.661
isphere+0.630
+0.612
yrus+0.579
Neg logit contributions
Rated-0.568
 whisper-0.548
Marginal-0.494
arella-0.486
 Minutes-0.481
Token along
Token ID1863
Feature activation+1.09e-01

Pos logit contributions
��+0.798
haar+0.630
isphere+0.601
+0.579
yrus+0.546
Neg logit contributions
Rated-0.617
 whisper-0.595
Marginal-0.546
arella-0.533
wives-0.532
Token with
Token ID351
Feature activation-1.18e-01

Pos logit contributions
Rated+0.179
 whisper+0.172
Marginal+0.153
 Minutes+0.151
uries+0.149
Neg logit contributions
��-0.318
haar-0.260
isphere-0.248
-0.239
yrus-0.227
Token
Token ID198
Feature activation-1.85e-01

Pos logit contributions
��+0.730
haar+0.605
isphere+0.558
+0.550
yrus+0.520
Neg logit contributions
Rated-0.527
 whisper-0.526
arella-0.468
uries-0.466
Marginal-0.464
TokenQ
Token ID48
Feature activation-4.68e-01

Pos logit contributions
��+0.556
haar+0.454
isphere+0.432
+0.427
yrus+0.401
Neg logit contributions
 whisper-0.285
Rated-0.280
 Minutes-0.246
arella-0.242
 nearer-0.242
Token:
Token ID25
Feature activation-4.47e-01

Pos logit contributions
��+1.034
haar+0.811
isphere+0.744
+0.740
yrus+0.672
Neg logit contributions
 whisper-1.036
Rated-1.022
arella-0.932
ktop-0.928
 nearer-0.926
TokenA
Token ID32
Feature activation-4.83e-01

Pos logit contributions
��+1.078
haar+0.849
isphere+0.781
+0.775
yrus+0.703
Neg logit contributions
 whisper-0.931
Rated-0.913
arella-0.837
 nearer-0.835
uries-0.830
Token human
Token ID1692
Feature activation+2.40e-02

Pos logit contributions
��+1.279
haar+1.016
isphere+0.946
+0.927
yrus+0.876
Neg logit contributions
Rated-0.913
 whisper-0.882
Marginal-0.821
 Minutes-0.801
arella-0.797
Token resource
Token ID8271
Feature activation-1.36e+00

Pos logit contributions
Rated+0.049
 whisper+0.047
Marginal+0.043
 Minutes+0.043
arella+0.042
Neg logit contributions
��-0.061
haar-0.048
isphere-0.046
-0.044
yrus-0.041
Token person
Token ID1048
Feature activation-5.03e-01

Pos logit contributions
��+3.263
haar+2.483
isphere+2.391
+2.288
yrus+2.164
Neg logit contributions
Rated-2.890
 whisper-2.698
arella-2.555
Marginal-2.536
 Minutes-2.493
Token could
Token ID714
Feature activation-1.86e-01

Pos logit contributions
��+1.325
haar+1.062
isphere+1.011
+0.972
yrus+0.928
Neg logit contributions
Rated-0.953
 whisper-0.910
Marginal-0.833
 Minutes-0.820
arella-0.808
Token work
Token ID670
Feature activation-5.64e-01

Pos logit contributions
��+0.509
haar+0.405
isphere+0.383
+0.369
yrus+0.358
Neg logit contributions
Rated-0.340
 whisper-0.318
Marginal-0.296
 Minutes-0.295
uries-0.291
Token for
Token ID329
Feature activation+3.41e-01

Pos logit contributions
��+1.560
haar+1.279
isphere+1.200
+1.154
yrus+1.113
Neg logit contributions
Rated-1.000
 whisper-0.939
Marginal-0.863
 Minutes-0.836
EngineDebug-0.825
Token every
Token ID790
Feature activation+2.63e-01

Pos logit contributions
Rated+0.697
 whisper+0.677
Marginal+0.616
arella+0.606
 Minutes+0.606
Neg logit contributions
��-0.865
haar-0.680
isphere-0.639
-0.619
yrus-0.584
Token don
Token ID836
Feature activation-5.36e-02

Pos logit contributions
��+0.383
haar+0.300
isphere+0.285
+0.271
yrus+0.260
Neg logit contributions
Rated-0.316
 whisper-0.297
Marginal-0.282
arella-0.275
 Minutes-0.270
Token't
Token ID470
Feature activation-3.44e-01

Pos logit contributions
��+0.100
haar+0.075
isphere+0.068
+0.065
yrus+0.059
Neg logit contributions
Rated-0.140
 whisper-0.138
Marginal-0.128
 Minutes-0.127
arella-0.127
Token mess
Token ID2085
Feature activation+3.12e-01

Pos logit contributions
��+0.934
haar+0.748
isphere+0.713
+0.678
yrus+0.662
Neg logit contributions
Rated-0.635
 whisper-0.576
Marginal-0.563
 Minutes-0.539
arella-0.538
Token with
Token ID351
Feature activation+4.79e-01

Pos logit contributions
Rated+0.552
 whisper+0.530
Marginal+0.486
 Minutes+0.475
arella+0.463
Neg logit contributions
��-0.874
haar-0.709
isphere-0.665
-0.656
yrus-0.621
Token '
Token ID705
Feature activation+1.08e+00

Pos logit contributions
Rated+0.969
 whisper+0.933
Marginal+0.859
arella+0.842
 Minutes+0.838
Neg logit contributions
��-1.222
haar-0.962
isphere-0.907
-0.885
yrus-0.832
Tokenem
Token ID368
Feature activation-1.33e+00

Pos logit contributions
Rated+2.602
 whisper+2.548
Marginal+2.346
 Minutes+2.330
arella+2.313
Neg logit contributions
��-2.330
haar-1.744
isphere-1.615
-1.564
yrus-1.438
Token!"
Token ID2474
Feature activation+9.16e-02

Pos logit contributions
��+3.546
haar+2.870
isphere+2.764
+2.699
yrus+2.558
Neg logit contributions
Rated-2.359
 whisper-2.215
Marginal-2.083
arella-2.003
 Minutes-1.977
Token At
Token ID1629
Feature activation-3.04e-01

Pos logit contributions
Rated+0.182
 whisper+0.176
Marginal+0.162
arella+0.159
uries+0.157
Neg logit contributions
��-0.236
haar-0.187
isphere-0.174
-0.170
yrus-0.160
Token that
Token ID326
Feature activation-4.08e-01

Pos logit contributions
��+0.722
haar+0.560
isphere+0.516
+0.501
yrus+0.473
Neg logit contributions
Rated-0.663
 whisper-0.634
Marginal-0.601
arella-0.582
uries-0.581
Token moment
Token ID2589
Feature activation-4.34e-01

Pos logit contributions
��+1.102
haar+0.882
isphere+0.834
+0.807
yrus+0.764
Neg logit contributions
Rated-0.752
 whisper-0.702
Marginal-0.662
arella-0.648
wives-0.642
Token,
Token ID11
Feature activation-2.28e-01

Pos logit contributions
��+1.092
haar+0.852
isphere+0.802
+0.772
yrus+0.732
Neg logit contributions
Rated-0.894
 whisper-0.854
Marginal-0.799
arella-0.781
 Minutes-0.768
Tokenman
Token ID805
Feature activation-1.08e-01

Pos logit contributions
Rated+0.752
 whisper+0.737
Marginal+0.675
 Minutes+0.668
arella+0.661
Neg logit contributions
��-0.762
haar-0.586
isphere-0.549
-0.527
yrus-0.492
Tokenovsky
Token ID29716
Feature activation+6.24e-01

Pos logit contributions
��+0.270
haar+0.215
isphere+0.203
+0.194
yrus+0.184
Neg logit contributions
Rated-0.223
 whisper-0.216
Marginal-0.198
 Minutes-0.195
arella-0.192
Token Museum
Token ID9594
Feature activation-2.11e-01

Pos logit contributions
Rated+1.246
 whisper+1.210
Marginal+1.100
 Minutes+1.082
arella+1.078
Neg logit contributions
��-1.611
haar-1.277
isphere-1.207
-1.173
yrus-1.105
Token in
Token ID287
Feature activation+1.83e-01

Pos logit contributions
��+0.578
haar+0.468
isphere+0.452
+0.434
yrus+0.416
Neg logit contributions
Rated-0.380
 whisper-0.368
Marginal-0.331
arella-0.321
 Minutes-0.316
Token northern
Token ID7840
Feature activation+4.62e-01

Pos logit contributions
Rated+0.388
 whisper+0.375
Marginal+0.348
arella+0.339
 Minutes+0.337
Neg logit contributions
��-0.447
haar-0.349
isphere-0.325
-0.318
yrus-0.298
Token Siber
Token ID28394
Feature activation-1.39e+00

Pos logit contributions
Rated+1.157
 whisper+1.122
Marginal+1.048
 Minutes+1.029
arella+1.028
Neg logit contributions
��-0.956
haar-0.707
isphere-0.657
-0.631
yrus-0.581
Tokena
Token ID64
Feature activation-1.83e-01

Pos logit contributions
��+3.442
haar+2.763
isphere+2.653
+2.506
yrus+2.420
Neg logit contributions
Rated-2.820
 whisper-2.738
Marginal-2.507
 Minutes-2.464
 nearer-2.397
Token and
Token ID290
Feature activation+1.26e-01

Pos logit contributions
��+0.484
haar+0.390
isphere+0.373
+0.357
yrus+0.343
Neg logit contributions
Rated-0.346
 whisper-0.333
Marginal-0.308
arella-0.295
 Minutes-0.294
Token named
Token ID3706
Feature activation+5.81e-01

Pos logit contributions
Rated+0.241
 whisper+0.234
Marginal+0.214
arella+0.210
 Minutes+0.208
Neg logit contributions
��-0.335
haar-0.268
isphere-0.253
-0.245
yrus-0.234
Token Ly
Token ID9334
Feature activation+1.98e-01

Pos logit contributions
Rated+1.039
 whisper+1.009
Marginal+0.903
 Minutes+0.889
arella+0.883
Neg logit contributions
��-1.622
haar-1.306
isphere-1.236
-1.211
yrus-1.144
Tokenuba
Token ID22013
Feature activation-1.22e-01

Pos logit contributions
Rated+0.377
 whisper+0.373
Marginal+0.332
 Minutes+0.327
arella+0.323
Neg logit contributions
��-0.528
haar-0.427
isphere-0.399
-0.389
yrus-0.372