TOP ACTIVATIONS
MAX = 3.102

Del ayed Until At Le ast March Of 2014
support the mission of New Advent and get the full contents
) g ave the movement its vitality .
Up dates g ave a special interview to I
that Israel g ave back land in the Oslo
C aj un Bo il | C aj un Kitchen
download . Includes the Catholic Encyclopedia , Church Fathers , Sum
the gruesome deaths and mut il ations suffered by the winners
comments . High lights of this new release ,
offensive behavior , which sp anned a history of homophobic ,
into reality was beyond ir ks ome for me . Judging
Any ways , at le ast things are moving along .
CPUs and memory ( Intel VT - x , AMD -
governing the set - back distance from sidewalks and parking requirements
: C aj un Bo il | C aj un Kitchen
trial ). F iled Under : c bp ,
ox . rar and un pack the Data into your Skyrim
misdemeanor . . @ dev on ms ayers reports
real estate map accurately show distance ? Does it leave off
Advertisement # ad # They d usted

MIN ACTIVATIONS
MIN = -3.785

2002 United States 3 472 Posts # 11 On September 20
2012 United States 3 240 Posts # 10 Happy it worked
2011 United States 228 65 Posts # 13 On September 20
2010 United States 10 53 Posts # 15 honestly if we
2011 United States 6 12 Posts # 17 Good to hear
2012 United States 5 667 Posts # 12 I 'm glad
2010 United States 6 83 Posts Last Edited : 2013 -
June 2012 Canada 16 10 Posts # 14 On September 20
6 , 2010 Subject : R iff Tra x
15 , 2010 Subject : Que er magnet ?
June 2009 Germany 247 34 Posts # 20 Nice , happy
9 , 2010 Subject : R ipe for M
TL AD T 235 21 Posts # 18 Good stuff !
2010 United States 21 50 Posts # 16 Glad to hear
United States 3 240 Posts # 10 Happy it worked out
13 , 2010 Subject : boys beware This film
4 , 2010 Subject : User reviews are a
5 , 2009 Subject : Que ers are Here
United States 10 53 Posts # 15 honestly if we just
07 : 44 Se eker wrote : Cl arity

INTERVAL 1.380 - 3.102
CONTAINS 0.355%

Our Seas Foundation 's D ' Ar ros Research Centre .
. <|endoftext|> The Wild B unch would use 239 rifles ,
. <|endoftext|> This article is about the payment medium . For
Atlantic and North Pacific O ceans , is now
mess seriously Article Continued Below

INTERVAL -0.341 - 1.380
CONTAINS 80.033%

Uh oh , that 's no good ! The
15 th among running backs ) Finding an under
you aren t familiar , the Wiz Kids Open
4 * UT ( commit ) Levi Jones LB 6 '
Haw aii has several good legislators who understand this

INTERVAL -2.063 - -0.341
CONTAINS 19.586%

bear - feeding , David killed it . Thank you ,
China has about 12 nuclear - powered submarines ( 6
2 3 4 5 6 7 8 void vert ( in
- based artist Clark S ore ns en , and called
institute in Film city , on the outskirts of Mumbai .

INTERVAL -3.785 - -2.063
CONTAINS 0.026%

Grove , California . Hide Caption 15 of 15
20 , 2015 . Hide Caption 8 of 15 Photos :
Commando Rear med [/ b ][/ color ] - Normal ,
the day . They 've got a big bath tub full
Women in politics . Hide Caption 7 of 15 Photos :
Token Del
Token ID4216
Feature activation+9.27e-02

Pos logit contributions
phalt+1.032
 Antar+0.945
ustomed+0.798
nen+0.761
ּ+0.751
Neg logit contributions
estern-0.835
ostics-0.796
itans-0.782
/>-0.769
bris-0.747
Tokenayed
Token ID16548
Feature activation+1.48e+00

Pos logit contributions
phalt+0.078
 Antar+0.071
ustomed+0.061
nen+0.059
ּ+0.058
Neg logit contributions
estern-0.059
ostics-0.056
itans-0.055
/>-0.054
bris-0.052
Token Until
Token ID14303
Feature activation+2.23e-01

Pos logit contributions
phalt+1.152
 Antar+1.046
ustomed+0.879
nen+0.830
ּ+0.823
Neg logit contributions
estern-1.047
ostics-1.003
itans-0.987
/>-0.973
bris-0.946
Token At
Token ID1629
Feature activation+8.08e-01

Pos logit contributions
phalt+0.189
 Antar+0.173
ustomed+0.150
ּ+0.141
nen+0.140
Neg logit contributions
estern-0.141
ostics-0.135
itans-0.132
/>-0.131
bris-0.126
Token Le
Token ID1004
Feature activation+6.02e-01

Pos logit contributions
phalt+0.731
 Antar+0.672
ustomed+0.584
nen+0.554
ּ+0.552
Neg logit contributions
estern-0.468
ostics-0.444
itans-0.434
/>-0.429
bris-0.413
Tokenast
Token ID459
Feature activation+3.10e+00

Pos logit contributions
phalt+0.587
 Antar+0.537
ustomed+0.474
nen+0.459
ּ+0.447
Neg logit contributions
estern-0.300
ostics-0.288
itans-0.280
/>-0.269
bris-0.258
Token March
Token ID2805
Feature activation+9.22e-02

Pos logit contributions
phalt+2.589
 Antar+2.378
ustomed+1.995
nen+1.926
 Ud+1.899
Neg logit contributions
estern-2.005
ostics-1.902
itans-1.879
/>-1.824
bris-1.784
Token Of
Token ID3226
Feature activation+1.21e+00

Pos logit contributions
phalt+0.078
 Antar+0.072
ustomed+0.062
nen+0.058
ּ+0.058
Neg logit contributions
estern-0.058
ostics-0.056
itans-0.055
/>-0.054
bris-0.052
Token 2014
Token ID1946
Feature activation+3.50e-01

Pos logit contributions
phalt+0.983
 Antar+0.897
ustomed+0.764
nen+0.719
ּ+0.716
Neg logit contributions
estern-0.815
ostics-0.776
itans-0.765
/>-0.755
bris-0.733
Token
Token ID198
Feature activation+4.72e-01

Pos logit contributions
phalt+0.266
 Antar+0.241
ustomed+0.203
nen+0.189
ּ+0.189
Neg logit contributions
estern-0.254
ostics-0.243
itans-0.239
/>-0.237
bris-0.230
Token
Token ID198
Feature activation+3.59e-01

Pos logit contributions
phalt+0.345
 Antar+0.309
ustomed+0.260
nen+0.244
ּ+0.242
Neg logit contributions
estern-0.354
ostics-0.338
itans-0.333
/>-0.328
bris-0.321
Token support
Token ID1104
Feature activation-7.14e-01

Pos logit contributions
estern+0.183
ostics+0.169
/>+0.163
itans+0.162
bris+0.147
Neg logit contributions
phalt-0.635
 Antar-0.595
ustomed-0.539
ּ-0.515
nen-0.510
Token the
Token ID262
Feature activation-1.44e-01

Pos logit contributions
estern+0.472
ostics+0.450
itans+0.443
/>+0.439
bris+0.424
Neg logit contributions
phalt-0.587
 Antar-0.535
ustomed-0.461
ּ-0.431
nen-0.428
Token mission
Token ID4365
Feature activation+4.35e-01

Pos logit contributions
estern+0.091
ostics+0.087
itans+0.085
/>+0.084
bris+0.081
Neg logit contributions
phalt-0.123
 Antar-0.113
ustomed-0.097
nen-0.092
ּ-0.091
Token of
Token ID286
Feature activation-7.96e-02

Pos logit contributions
phalt+0.360
 Antar+0.329
ustomed+0.282
nen+0.268
ּ+0.265
Neg logit contributions
estern-0.284
ostics-0.269
itans-0.267
/>-0.260
bris-0.253
Token New
Token ID968
Feature activation+6.50e-01

Pos logit contributions
estern+0.047
ostics+0.044
itans+0.044
/>+0.043
bris+0.041
Neg logit contributions
phalt-0.071
 Antar-0.066
ustomed-0.057
ּ-0.054
nen-0.053
Token Advent
Token ID33732
Feature activation+3.08e+00

Pos logit contributions
phalt+0.378
 Antar+0.323
ustomed+0.242
ּ+0.222
nen+0.215
Neg logit contributions
estern-0.592
ostics-0.585
itans-0.577
/>-0.566
bris-0.556
Token and
Token ID290
Feature activation-1.88e-01

Pos logit contributions
phalt+2.880
 Antar+2.618
ustomed+2.312
ּ+2.189
nen+2.170
Neg logit contributions
estern-1.657
ostics-1.580
itans-1.542
/>-1.491
bris-1.440
Token get
Token ID651
Feature activation+4.55e-01

Pos logit contributions
estern+0.087
ostics+0.083
/>+0.082
itans+0.081
bris+0.075
Neg logit contributions
phalt-0.190
 Antar-0.176
ustomed-0.155
nen-0.147
ּ-0.147
Token the
Token ID262
Feature activation+5.76e-01

Pos logit contributions
phalt+0.390
 Antar+0.363
ustomed+0.310
ּ+0.288
nen+0.284
Neg logit contributions
estern-0.283
ostics-0.272
itans-0.263
/>-0.263
bris-0.253
Token full
Token ID1336
Feature activation-7.32e-01

Pos logit contributions
phalt+0.497
 Antar+0.455
ustomed+0.386
ּ+0.363
nen+0.360
Neg logit contributions
estern-0.354
ostics-0.345
itans-0.338
/>-0.332
bris-0.325
Token contents
Token ID10154
Feature activation+6.27e-01

Pos logit contributions
estern+0.412
ostics+0.391
itans+0.383
/>+0.377
bris+0.363
Neg logit contributions
phalt-0.674
 Antar-0.620
ustomed-0.541
ּ-0.513
nen-0.511
Token
Token ID247
Feature activation-3.99e-02

Pos logit contributions
phalt+0.002
 Antar+0.001
ustomed+0.001
ּ+0.001
nen+0.001
Neg logit contributions
estern-0.001
ostics-0.001
itans-0.001
/>-0.001
bris-0.001
Token)
Token ID8
Feature activation-3.10e-01

Pos logit contributions
estern+0.024
ostics+0.023
itans+0.023
/>+0.022
bris+0.022
Neg logit contributions
phalt-0.035
 Antar-0.032
ustomed-0.028
nen-0.026
ּ-0.026
Token
Token ID198
Feature activation-1.38e-02

Pos logit contributions
estern+0.168
ostics+0.158
itans+0.155
/>+0.153
bris+0.147
Neg logit contributions
phalt-0.292
 Antar-0.270
ustomed-0.236
nen-0.224
ּ-0.224
Token
Token ID198
Feature activation-2.82e-02

Pos logit contributions
estern+0.010
ostics+0.010
itans+0.010
/>+0.009
bris+0.009
Neg logit contributions
phalt-0.010
 Antar-0.009
ustomed-0.008
nen-0.007
ּ-0.007
Tokeng
Token ID70
Feature activation+3.10e-01

Pos logit contributions
estern+0.017
ostics+0.016
itans+0.016
/>+0.015
bris+0.015
Neg logit contributions
phalt-0.025
 Antar-0.023
ustomed-0.020
nen-0.019
ּ-0.019
Tokenave
Token ID1015
Feature activation+2.94e+00

Pos logit contributions
phalt+0.268
 Antar+0.243
ustomed+0.213
nen+0.199
ּ+0.198
Neg logit contributions
estern-0.191
ostics-0.182
itans-0.178
/>-0.177
bris-0.170
Token the
Token ID262
Feature activation+1.93e-01

Pos logit contributions
phalt+2.741
 Antar+2.538
ustomed+2.227
nen+2.119
ּ+2.117
Neg logit contributions
estern-1.601
ostics-1.501
itans-1.464
/>-1.443
bris-1.382
Token movement
Token ID3356
Feature activation+9.42e-02

Pos logit contributions
phalt+0.172
 Antar+0.159
ustomed+0.138
nen+0.130
ּ+0.130
Neg logit contributions
estern-0.113
ostics-0.107
itans-0.105
/>-0.104
bris-0.100
Token its
Token ID663
Feature activation-4.53e-01

Pos logit contributions
phalt+0.085
 Antar+0.078
ustomed+0.068
nen+0.064
ּ+0.064
Neg logit contributions
estern-0.055
ostics-0.052
itans-0.051
/>-0.051
bris-0.049
Token vitality
Token ID41687
Feature activation+6.56e-01

Pos logit contributions
estern+0.270
ostics+0.256
itans+0.251
/>+0.248
bris+0.239
Neg logit contributions
phalt-0.402
 Antar-0.370
ustomed-0.321
nen-0.303
ּ-0.303
Token.
Token ID13
Feature activation-2.32e-02

Pos logit contributions
phalt+0.546
 Antar+0.500
ustomed+0.430
ּ+0.405
nen+0.404
Neg logit contributions
estern-0.427
ostics-0.406
itans-0.400
/>-0.393
bris-0.383
TokenUp
Token ID4933
Feature activation+2.49e-01

Pos logit contributions
phalt+0.244
 Antar+0.224
ustomed+0.196
nen+0.186
ּ+0.186
Neg logit contributions
estern-0.147
ostics-0.139
itans-0.136
/>-0.134
bris-0.129
Tokendates
Token ID19581
Feature activation+6.12e-01

Pos logit contributions
phalt+0.234
 Antar+0.216
ustomed+0.189
nen+0.180
ּ+0.179
Neg logit contributions
estern-0.136
ostics-0.128
itans-0.125
/>-0.124
bris-0.119
Token
Token ID198
Feature activation-1.33e-01

Pos logit contributions
phalt+0.544
 Antar+0.500
ustomed+0.434
nen+0.410
ּ+0.409
Neg logit contributions
estern-0.364
ostics-0.345
itans-0.338
/>-0.332
bris-0.322
Token
Token ID198
Feature activation-1.38e-01

Pos logit contributions
estern+0.097
ostics+0.093
itans+0.092
/>+0.091
bris+0.088
Neg logit contributions
phalt-0.100
 Antar-0.090
ustomed-0.076
nen-0.071
ּ-0.071
Tokeng
Token ID70
Feature activation+6.28e-01

Pos logit contributions
estern+0.080
ostics+0.075
itans+0.074
/>+0.073
bris+0.070
Neg logit contributions
phalt-0.125
 Antar-0.115
ustomed-0.101
nen-0.095
ּ-0.095
Tokenave
Token ID1015
Feature activation+2.89e+00

Pos logit contributions
phalt+0.548
 Antar+0.499
ustomed+0.433
nen+0.409
ּ+0.408
Neg logit contributions
estern-0.384
ostics-0.365
itans-0.358
/>-0.354
bris-0.342
Token a
Token ID257
Feature activation+1.30e-01

Pos logit contributions
phalt+2.495
 Antar+2.273
ustomed+1.972
nen+1.881
ּ+1.859
Neg logit contributions
estern-1.783
ostics-1.664
itans-1.644
/>-1.614
bris-1.565
Token special
Token ID2041
Feature activation+2.70e-01

Pos logit contributions
phalt+0.114
 Antar+0.105
ustomed+0.091
ּ+0.085
nen+0.085
Neg logit contributions
estern-0.079
ostics-0.075
itans-0.073
/>-0.072
bris-0.070
Token interview
Token ID2720
Feature activation-5.20e-01

Pos logit contributions
phalt+0.237
 Antar+0.217
ustomed+0.188
ּ+0.178
nen+0.177
Neg logit contributions
estern-0.164
ostics-0.156
itans-0.153
/>-0.152
bris-0.146
Token to
Token ID284
Feature activation-1.08e-01

Pos logit contributions
estern+0.305
ostics+0.289
itans+0.283
/>+0.281
bris+0.269
Neg logit contributions
phalt-0.466
 Antar-0.428
ustomed-0.372
ּ-0.352
nen-0.351
Token I
Token ID314
Feature activation+1.94e-01

Pos logit contributions
estern+0.072
ostics+0.069
itans+0.068
/>+0.067
bris+0.065
Neg logit contributions
phalt-0.088
 Antar-0.081
ustomed-0.069
ּ-0.065
nen-0.065
Token that
Token ID326
Feature activation+3.84e-01

Pos logit contributions
estern+0.109
ostics+0.103
itans+0.101
/>+0.100
bris+0.096
Neg logit contributions
phalt-0.160
 Antar-0.146
ustomed-0.127
ּ-0.121
nen-0.120
Token Israel
Token ID2692
Feature activation-5.49e-01

Pos logit contributions
phalt+0.329
 Antar+0.302
ustomed+0.260
ּ+0.245
nen+0.245
Neg logit contributions
estern-0.240
ostics-0.228
itans-0.224
/>-0.221
bris-0.213
Token
Token ID564
Feature activation-3.39e-02

Pos logit contributions
estern+0.287
ostics+0.271
itans+0.263
/>+0.260
bris+0.250
Neg logit contributions
phalt-0.528
 Antar-0.488
ustomed-0.429
ּ-0.409
nen-0.408
Token
Token ID250
Feature activation+1.23e-01

Pos logit contributions
estern+0.017
ostics+0.016
itans+0.016
/>+0.015
bris+0.015
Neg logit contributions
phalt-0.033
 Antar-0.030
ustomed-0.027
ּ-0.026
nen-0.025
Tokeng
Token ID70
Feature activation+9.03e-01

Pos logit contributions
phalt+0.104
 Antar+0.095
ustomed+0.082
ּ+0.077
nen+0.077
Neg logit contributions
estern-0.079
ostics-0.076
itans-0.074
/>-0.073
bris-0.071
Tokenave
Token ID1015
Feature activation+2.79e+00

Pos logit contributions
phalt+0.687
 Antar+0.614
ustomed+0.527
ּ+0.491
nen+0.483
Neg logit contributions
estern-0.647
ostics-0.619
itans-0.608
/>-0.606
bris-0.586
Token back
Token ID736
Feature activation-4.80e-02

Pos logit contributions
phalt+2.344
 Antar+2.184
ustomed+1.859
ּ+1.808
 Ud+1.744
Neg logit contributions
estern-1.745
ostics-1.676
itans-1.643
/>-1.596
bris-1.548
Token land
Token ID1956
Feature activation+4.20e-01

Pos logit contributions
estern+0.029
ostics+0.028
itans+0.027
/>+0.027
bris+0.026
Neg logit contributions
phalt-0.042
 Antar-0.039
ustomed-0.034
ּ-0.032
nen-0.032
Token in
Token ID287
Feature activation-6.52e-02

Pos logit contributions
phalt+0.379
 Antar+0.350
ustomed+0.303
ּ+0.291
nen+0.286
Neg logit contributions
estern-0.244
ostics-0.232
itans-0.225
/>-0.222
bris-0.215
Token the
Token ID262
Feature activation-2.59e-01

Pos logit contributions
estern+0.042
ostics+0.040
itans+0.040
/>+0.039
bris+0.038
Neg logit contributions
phalt-0.054
 Antar-0.050
ustomed-0.043
ּ-0.040
nen-0.040
Token Oslo
Token ID39636
Feature activation-6.08e-01

Pos logit contributions
estern+0.161
ostics+0.154
itans+0.151
/>+0.149
bris+0.144
Neg logit contributions
phalt-0.223
 Antar-0.204
ustomed-0.176
ּ-0.166
nen-0.166
Token
Token ID198
Feature activation+1.32e-01

Pos logit contributions
phalt+0.101
 Antar+0.091
ustomed+0.076
nen+0.071
ּ+0.071
Neg logit contributions
estern-0.100
ostics-0.096
itans-0.094
/>-0.093
bris-0.091
TokenC
Token ID34
Feature activation+1.43e-01

Pos logit contributions
phalt+0.115
 Antar+0.105
ustomed+0.091
nen+0.086
ּ+0.086
Neg logit contributions
estern-0.082
ostics-0.078
itans-0.076
/>-0.075
bris-0.073
Tokenaj
Token ID1228
Feature activation-5.57e-01

Pos logit contributions
phalt+0.115
 Antar+0.105
ustomed+0.089
ּ+0.084
nen+0.084
Neg logit contributions
estern-0.097
ostics-0.093
itans-0.092
/>-0.091
bris-0.088
Tokenun
Token ID403
Feature activation-2.12e-01

Pos logit contributions
estern+0.385
ostics+0.369
itans+0.363
/>+0.359
bris+0.348
Neg logit contributions
phalt-0.441
 Antar-0.401
ustomed-0.339
ּ-0.319
nen-0.318
Token Bo
Token ID3248
Feature activation+4.53e-01

Pos logit contributions
estern+0.140
ostics+0.134
itans+0.132
/>+0.130
bris+0.126
Neg logit contributions
phalt-0.173
 Antar-0.158
ustomed-0.135
nen-0.127
ּ-0.127
Tokenil
Token ID346
Feature activation+2.69e+00

Pos logit contributions
phalt+0.408
 Antar+0.376
ustomed+0.326
nen+0.309
ּ+0.307
Neg logit contributions
estern-0.263
ostics-0.249
itans-0.245
/>-0.243
bris-0.232
Token |
Token ID930
Feature activation+8.84e-01

Pos logit contributions
phalt+2.232
 Antar+2.033
ustomed+1.729
nen+1.638
ּ+1.624
Neg logit contributions
estern-1.743
ostics-1.667
itans-1.637
/>-1.612
bris-1.567
Token C
Token ID327
Feature activation+1.83e-01

Pos logit contributions
phalt+0.700
 Antar+0.637
ustomed+0.540
nen+0.506
ּ+0.504
Neg logit contributions
estern-0.613
ostics-0.586
itans-0.576
/>-0.570
bris-0.552
Tokenaj
Token ID1228
Feature activation-5.56e-01

Pos logit contributions
phalt+0.116
 Antar+0.102
ustomed+0.083
nen+0.076
ּ+0.076
Neg logit contributions
estern-0.155
ostics-0.149
itans-0.147
/>-0.146
bris-0.142
Tokenun
Token ID403
Feature activation-3.77e-01

Pos logit contributions
estern+0.396
ostics+0.379
itans+0.373
/>+0.369
bris+0.358
Neg logit contributions
phalt-0.429
 Antar-0.389
ustomed-0.328
ּ-0.307
nen-0.307
Token Kitchen
Token ID22541
Feature activation+7.44e-01

Pos logit contributions
estern+0.255
ostics+0.244
itans+0.240
/>+0.237
bris+0.230
Neg logit contributions
phalt-0.304
 Antar-0.277
ustomed-0.236
nen-0.222
ּ-0.221
Token download
Token ID4321
Feature activation+2.65e-01

Pos logit contributions
phalt+0.140
 Antar+0.129
ustomed+0.110
nen+0.104
ּ+0.103
Neg logit contributions
estern-0.109
ostics-0.105
itans-0.101
/>-0.100
bris-0.098
Token.
Token ID13
Feature activation+9.35e-02

Pos logit contributions
phalt+0.197
 Antar+0.179
ustomed+0.150
ּ+0.140
nen+0.138
Neg logit contributions
estern-0.195
ostics-0.187
itans-0.185
/>-0.184
bris-0.177
Token Includes
Token ID29581
Feature activation+6.49e-01

Pos logit contributions
phalt+0.074
 Antar+0.069
ustomed+0.058
nen+0.055
ּ+0.054
Neg logit contributions
estern-0.064
ostics-0.060
itans-0.060
/>-0.059
bris-0.058
Token the
Token ID262
Feature activation-8.12e-02

Pos logit contributions
phalt+0.512
 Antar+0.463
ustomed+0.393
nen+0.369
ּ+0.368
Neg logit contributions
estern-0.450
ostics-0.433
itans-0.427
/>-0.420
bris-0.408
Token Catholic
Token ID7835
Feature activation+9.01e-01

Pos logit contributions
estern+0.049
ostics+0.046
itans+0.045
/>+0.045
bris+0.043
Neg logit contributions
phalt-0.072
 Antar-0.066
ustomed-0.057
nen-0.054
ּ-0.054
Token Encyclopedia
Token ID36732
Feature activation+2.67e+00

Pos logit contributions
phalt+0.948
 Antar+0.879
ustomed+0.777
ּ+0.742
nen+0.740
Neg logit contributions
estern-0.395
ostics-0.374
itans-0.365
/>-0.365
bris-0.336
Token,
Token ID11
Feature activation+1.52e-03

Pos logit contributions
phalt+2.143
 Antar+1.955
ustomed+1.687
nen+1.579
 Ud+1.567
Neg logit contributions
estern-1.781
ostics-1.690
itans-1.675
/>-1.656
���-1.616
Token Church
Token ID4564
Feature activation+5.31e-01

Pos logit contributions
phalt+0.001
 Antar+0.001
ustomed+0.001
nen+0.001
ּ+0.001
Neg logit contributions
estern-0.001
ostics-0.001
itans-0.001
/>-0.001
bris-0.001
Token Fathers
Token ID30969
Feature activation+1.47e+00

Pos logit contributions
phalt+0.357
 Antar+0.320
ustomed+0.264
ּ+0.246
+0.243
Neg logit contributions
estern-0.428
ostics-0.420
/>-0.410
bris-0.409
itans-0.404
Token,
Token ID11
Feature activation+3.93e-01

Pos logit contributions
phalt+1.368
 Antar+1.265
ustomed+1.110
ּ+1.051
nen+1.034
Neg logit contributions
estern-0.819
ostics-0.778
itans-0.759
/>-0.743
bris-0.724
Token Sum
Token ID5060
Feature activation+8.25e-02

Pos logit contributions
phalt+0.259
 Antar+0.231
ustomed+0.188
nen+0.173
ּ+0.173
Neg logit contributions
estern-0.323
ostics-0.311
itans-0.307
/>-0.304
bris-0.297
Token the
Token ID262
Feature activation+2.93e-01

Pos logit contributions
estern+0.068
ostics+0.065
itans+0.064
/>+0.063
bris+0.061
Neg logit contributions
phalt-0.085
 Antar-0.077
ustomed-0.066
nen-0.062
ּ-0.062
Token gruesome
Token ID34557
Feature activation+1.77e-01

Pos logit contributions
phalt+0.254
 Antar+0.234
ustomed+0.202
nen+0.190
ּ+0.190
Neg logit contributions
estern-0.180
ostics-0.171
itans-0.168
/>-0.166
bris-0.160
Token deaths
Token ID7040
Feature activation+3.68e-01

Pos logit contributions
phalt+0.157
 Antar+0.145
ustomed+0.125
nen+0.118
ּ+0.118
Neg logit contributions
estern-0.106
ostics-0.100
itans-0.098
/>-0.097
bris-0.094
Token and
Token ID290
Feature activation+1.13e-01

Pos logit contributions
phalt+0.326
 Antar+0.299
ustomed+0.260
nen+0.245
ּ+0.245
Neg logit contributions
estern-0.219
ostics-0.209
itans-0.205
/>-0.202
bris-0.195
Token mut
Token ID4517
Feature activation+1.14e+00

Pos logit contributions
phalt+0.101
 Antar+0.093
ustomed+0.080
nen+0.076
ּ+0.076
Neg logit contributions
estern-0.067
ostics-0.064
itans-0.063
/>-0.062
bris-0.060
Tokenil
Token ID346
Feature activation+2.66e+00

Pos logit contributions
phalt+1.012
 Antar+0.920
ustomed+0.810
nen+0.765
ּ+0.757
Neg logit contributions
estern-0.670
ostics-0.639
/>-0.615
itans-0.612
bris-0.600
Tokenations
Token ID602
Feature activation+1.15e-01

Pos logit contributions
phalt+2.131
 Antar+1.929
ustomed+1.658
nen+1.544
ּ+1.511
Neg logit contributions
estern-1.794
ostics-1.720
/>-1.662
itans-1.648
bris-1.623
Token suffered
Token ID6989
Feature activation+3.01e-01

Pos logit contributions
phalt+0.102
 Antar+0.094
ustomed+0.081
nen+0.077
ּ+0.077
Neg logit contributions
estern-0.068
ostics-0.065
itans-0.064
/>-0.063
bris-0.061
Token by
Token ID416
Feature activation+4.09e-01

Pos logit contributions
phalt+0.246
 Antar+0.224
ustomed+0.192
nen+0.180
ּ+0.180
Neg logit contributions
estern-0.200
ostics-0.191
itans-0.188
/>-0.186
bris-0.180
Token the
Token ID262
Feature activation+3.83e-03

Pos logit contributions
phalt+0.336
 Antar+0.308
ustomed+0.263
ּ+0.247
nen+0.247
Neg logit contributions
estern-0.270
ostics-0.257
itans-0.253
/>-0.250
bris-0.242
Token winners
Token ID14591
Feature activation+3.43e-01

Pos logit contributions
phalt+0.003
 Antar+0.003
ustomed+0.002
nen+0.002
ּ+0.002
Neg logit contributions
estern-0.003
ostics-0.002
itans-0.002
/>-0.002
bris-0.002
Token comments
Token ID3651
Feature activation-1.49e-01

Pos logit contributions
phalt+0.071
 Antar+0.066
ustomed+0.057
nen+0.054
ּ+0.054
Neg logit contributions
estern-0.045
ostics-0.042
itans-0.041
/>-0.041
bris-0.039
Token.
Token ID13
Feature activation+1.57e-01

Pos logit contributions
estern+0.098
ostics+0.094
itans+0.092
/>+0.091
bris+0.088
Neg logit contributions
phalt-0.122
 Antar-0.112
ustomed-0.095
nen-0.090
ּ-0.090
Token
Token ID198
Feature activation+1.67e-02

Pos logit contributions
phalt+0.124
 Antar+0.113
ustomed+0.096
nen+0.090
ּ+0.090
Neg logit contributions
estern-0.109
ostics-0.104
itans-0.103
/>-0.101
bris-0.098
Token
Token ID198
Feature activation-1.85e-01

Pos logit contributions
phalt+0.012
 Antar+0.011
ustomed+0.009
nen+0.009
ּ+0.009
Neg logit contributions
estern-0.012
ostics-0.012
itans-0.012
/>-0.012
bris-0.011
TokenHigh
Token ID11922
Feature activation-3.90e-01

Pos logit contributions
estern+0.114
ostics+0.108
itans+0.106
/>+0.105
bris+0.101
Neg logit contributions
phalt-0.161
 Antar-0.147
ustomed-0.128
nen-0.121
ּ-0.120
Tokenlights
Token ID8091
Feature activation+2.57e+00

Pos logit contributions
estern+0.240
ostics+0.226
itans+0.222
/>+0.218
bris+0.211
Neg logit contributions
phalt-0.341
 Antar-0.312
ustomed-0.270
nen-0.256
ּ-0.254
Token of
Token ID286
Feature activation-4.77e-01

Pos logit contributions
phalt+2.041
 Antar+1.852
ustomed+1.566
ּ+1.473
nen+1.472
Neg logit contributions
estern-1.769
ostics-1.689
itans-1.670
/>-1.620
bris-1.601
Token this
Token ID428
Feature activation-2.80e-01

Pos logit contributions
estern+0.305
ostics+0.290
itans+0.285
/>+0.282
bris+0.272
Neg logit contributions
phalt-0.403
 Antar-0.368
ustomed-0.317
nen-0.298
ּ-0.298
Token new
Token ID649
Feature activation-7.79e-02

Pos logit contributions
estern+0.156
ostics+0.147
itans+0.144
/>+0.141
bris+0.137
Neg logit contributions
phalt-0.260
 Antar-0.240
ustomed-0.209
nen-0.199
ּ-0.198
Token release
Token ID2650
Feature activation-1.07e+00

Pos logit contributions
estern+0.044
ostics+0.041
itans+0.040
/>+0.040
bris+0.038
Neg logit contributions
phalt-0.072
 Antar-0.066
ustomed-0.058
nen-0.055
ּ-0.055
Token,
Token ID11
Feature activation-3.33e-01

Pos logit contributions
estern+0.688
ostics+0.656
itans+0.644
/>+0.638
bris+0.615
Neg logit contributions
phalt-0.903
 Antar-0.826
ustomed-0.711
nen-0.669
ּ-0.668
Token offensive
Token ID5859
Feature activation+5.91e-01

Pos logit contributions
phalt+0.229
 Antar+0.211
ustomed+0.183
ּ+0.174
nen+0.174
Neg logit contributions
estern-0.147
ostics-0.139
itans-0.136
/>-0.134
bris-0.130
Token behavior
Token ID4069
Feature activation-1.27e-01

Pos logit contributions
phalt+0.558
 Antar+0.518
ustomed+0.451
nen+0.431
ּ+0.431
Neg logit contributions
estern-0.318
ostics-0.301
itans-0.295
/>-0.286
bris-0.278
Token,
Token ID11
Feature activation-5.26e-03

Pos logit contributions
estern+0.090
ostics+0.087
itans+0.085
/>+0.084
bris+0.082
Neg logit contributions
phalt-0.097
 Antar-0.088
ustomed-0.075
nen-0.070
ּ-0.070
Token which
Token ID543
Feature activation+2.74e-01

Pos logit contributions
estern+0.003
ostics+0.003
itans+0.003
/>+0.003
bris+0.003
Neg logit contributions
phalt-0.005
 Antar-0.005
ustomed-0.004
ּ-0.004
nen-0.004
Token sp
Token ID599
Feature activation+7.55e-01

Pos logit contributions
phalt+0.249
 Antar+0.229
ustomed+0.199
nen+0.189
ּ+0.188
Neg logit contributions
estern-0.158
ostics-0.150
itans-0.147
/>-0.145
bris-0.140
Tokenanned
Token ID3577
Feature activation+2.57e+00

Pos logit contributions
phalt+0.517
 Antar+0.460
ustomed+0.382
nen+0.352
ּ+0.351
Neg logit contributions
estern-0.603
ostics-0.580
itans-0.571
/>-0.566
bris-0.551
Token a
Token ID257
Feature activation+3.32e-01

Pos logit contributions
phalt+2.304
 Antar+2.129
ustomed+1.840
ּ+1.746
nen+1.743
Neg logit contributions
estern-1.494
ostics-1.430
itans-1.399
/>-1.370
bris-1.318
Token history
Token ID2106
Feature activation-2.37e-01

Pos logit contributions
phalt+0.284
 Antar+0.260
ustomed+0.224
nen+0.211
ּ+0.211
Neg logit contributions
estern-0.208
ostics-0.198
itans-0.195
/>-0.193
bris-0.186
Token of
Token ID286
Feature activation+1.01e-01

Pos logit contributions
estern+0.145
ostics+0.137
itans+0.135
/>+0.134
bris+0.129
Neg logit contributions
phalt-0.206
 Antar-0.189
ustomed-0.163
nen-0.154
ּ-0.154
Token homophobic
Token ID36034
Feature activation-8.44e-01

Pos logit contributions
phalt+0.089
 Antar+0.082
ustomed+0.071
ּ+0.067
nen+0.067
Neg logit contributions
estern-0.061
ostics-0.058
itans-0.056
/>-0.056
bris-0.054
Token,
Token ID11
Feature activation-1.99e-01

Pos logit contributions
estern+0.462
ostics+0.436
itans+0.427
/>+0.422
bris+0.404
Neg logit contributions
phalt-0.790
 Antar-0.728
ustomed-0.638
nen-0.605
ּ-0.604
Token into
Token ID656
Feature activation-3.12e-01

Pos logit contributions
phalt+0.798
 Antar+0.727
ustomed+0.622
nen+0.584
ּ+0.583
Neg logit contributions
estern-0.648
ostics-0.618
itans-0.608
/>-0.601
bris-0.582
Token reality
Token ID3950
Feature activation+5.31e-01

Pos logit contributions
estern+0.189
ostics+0.180
itans+0.176
/>+0.174
bris+0.168
Neg logit contributions
phalt-0.274
 Antar-0.252
ustomed-0.218
nen-0.206
ּ-0.206
Token was
Token ID373
Feature activation-5.74e-01

Pos logit contributions
phalt+0.481
 Antar+0.442
ustomed+0.386
nen+0.365
ּ+0.364
Neg logit contributions
estern-0.307
ostics-0.289
itans-0.284
/>-0.279
bris-0.269
Token beyond
Token ID3675
Feature activation-2.06e-02

Pos logit contributions
estern+0.339
ostics+0.320
itans+0.315
/>+0.313
bris+0.299
Neg logit contributions
phalt-0.512
 Antar-0.471
ustomed-0.410
ּ-0.387
nen-0.384
Token ir
Token ID4173
Feature activation+8.17e-01

Pos logit contributions
estern+0.013
ostics+0.012
itans+0.012
/>+0.012
bris+0.012
Neg logit contributions
phalt-0.018
 Antar-0.016
ustomed-0.014
nen-0.013
ּ-0.013
Tokenks
Token ID591
Feature activation+2.54e+00

Pos logit contributions
phalt+0.596
 Antar+0.540
ustomed+0.449
nen+0.417
ּ+0.417
Neg logit contributions
estern-0.616
ostics-0.593
itans-0.583
/>-0.577
bris-0.560
Tokenome
Token ID462
Feature activation+5.35e-01

Pos logit contributions
phalt+2.130
 Antar+1.937
ustomed+1.670
nen+1.580
ּ+1.571
Neg logit contributions
estern-1.629
ostics-1.555
itans-1.530
/>-1.508
bris-1.470
Token for
Token ID329
Feature activation-9.22e-02

Pos logit contributions
phalt+0.435
 Antar+0.397
ustomed+0.339
nen+0.319
ּ+0.318
Neg logit contributions
estern-0.358
ostics-0.342
itans-0.336
/>-0.332
bris-0.322
Token me
Token ID502
Feature activation-6.63e-02

Pos logit contributions
estern+0.065
ostics+0.062
itans+0.061
/>+0.061
bris+0.059
Neg logit contributions
phalt-0.072
 Antar-0.065
ustomed-0.055
ּ-0.052
nen-0.052
Token.
Token ID13
Feature activation+5.88e-01

Pos logit contributions
estern+0.045
ostics+0.043
itans+0.043
/>+0.042
bris+0.041
Neg logit contributions
phalt-0.053
 Antar-0.048
ustomed-0.041
nen-0.038
ּ-0.038
Token Judging
Token ID47024
Feature activation-2.02e-01

Pos logit contributions
phalt+0.465
 Antar+0.422
ustomed+0.360
nen+0.336
ּ+0.336
Neg logit contributions
estern-0.406
ostics-0.389
itans-0.383
/>-0.380
bris-0.366
TokenAny
Token ID7149
Feature activation+1.48e-02

Pos logit contributions
estern+0.353
ostics+0.336
itans+0.330
/>+0.327
bris+0.316
Neg logit contributions
phalt-0.469
 Antar-0.429
ustomed-0.369
nen-0.347
ּ-0.347
Tokenways
Token ID1322
Feature activation-4.58e-01

Pos logit contributions
phalt+0.013
 Antar+0.012
ustomed+0.010
nen+0.010
ּ+0.010
Neg logit contributions
estern-0.009
ostics-0.009
itans-0.008
/>-0.008
bris-0.008
Token,
Token ID11
Feature activation-2.45e-01

Pos logit contributions
estern+0.290
ostics+0.276
itans+0.272
/>+0.268
bris+0.259
Neg logit contributions
phalt-0.388
 Antar-0.355
ustomed-0.306
nen-0.288
ּ-0.288
Token at
Token ID379
Feature activation-2.07e-01

Pos logit contributions
estern+0.161
ostics+0.153
itans+0.150
/>+0.148
bris+0.144
Neg logit contributions
phalt-0.203
 Antar-0.186
ustomed-0.159
nen-0.150
ּ-0.149
Tokenle
Token ID293
Feature activation-5.02e-02

Pos logit contributions
estern+0.126
ostics+0.120
itans+0.118
/>+0.116
bris+0.112
Neg logit contributions
phalt-0.181
 Antar-0.166
ustomed-0.144
nen-0.136
ּ-0.136
Tokenast
Token ID459
Feature activation+2.53e+00

Pos logit contributions
estern+0.023
ostics+0.022
itans+0.021
/>+0.021
bris+0.020
Neg logit contributions
phalt-0.051
 Antar-0.047
ustomed-0.042
nen-0.040
ּ-0.040
Token things
Token ID1243
Feature activation-2.93e-01

Pos logit contributions
phalt+2.115
 Antar+1.942
ustomed+1.647
nen+1.567
 Ud+1.541
Neg logit contributions
estern-1.643
ostics-1.558
itans-1.526
/>-1.492
bris-1.454
Token are
Token ID389
Feature activation-1.42e-01

Pos logit contributions
estern+0.160
ostics+0.151
itans+0.148
/>+0.146
bris+0.140
Neg logit contributions
phalt-0.275
 Antar-0.254
ustomed-0.222
nen-0.210
ּ-0.210
Token moving
Token ID3867
Feature activation-9.05e-01

Pos logit contributions
estern+0.091
ostics+0.087
itans+0.085
/>+0.084
bris+0.082
Neg logit contributions
phalt-0.120
 Antar-0.109
ustomed-0.094
nen-0.089
ּ-0.088
Token along
Token ID1863
Feature activation+2.85e-01

Pos logit contributions
estern+0.536
ostics+0.508
itans+0.499
/>+0.497
bris+0.476
Neg logit contributions
phalt-0.805
 Antar-0.739
ustomed-0.646
ּ-0.609
nen-0.608
Token.
Token ID13
Feature activation-4.99e-01

Pos logit contributions
phalt+0.241
 Antar+0.220
ustomed+0.189
nen+0.178
ּ+0.178
Neg logit contributions
estern-0.183
ostics-0.174
itans-0.171
/>-0.168
bris-0.163
Token CPUs
Token ID32340
Feature activation+8.47e-01

Pos logit contributions
estern+0.253
ostics+0.241
itans+0.236
/>+0.234
bris+0.226
Neg logit contributions
phalt-0.339
 Antar-0.311
ustomed-0.268
nen-0.252
ּ-0.252
Token and
Token ID290
Feature activation-1.09e-01

Pos logit contributions
phalt+0.774
 Antar+0.712
ustomed+0.624
nen+0.590
ּ+0.589
Neg logit contributions
estern-0.483
ostics-0.454
itans-0.444
/>-0.437
bris-0.422
Token memory
Token ID4088
Feature activation-3.39e-01

Pos logit contributions
estern+0.066
ostics+0.063
itans+0.062
/>+0.061
bris+0.059
Neg logit contributions
phalt-0.096
 Antar-0.088
ustomed-0.076
nen-0.072
ּ-0.072
Token (
Token ID357
Feature activation-7.51e-02

Pos logit contributions
estern+0.205
ostics+0.195
itans+0.191
/>+0.189
bris+0.182
Neg logit contributions
phalt-0.298
 Antar-0.273
ustomed-0.237
nen-0.223
ּ-0.223
TokenIntel
Token ID24123
Feature activation+1.02e+00

Pos logit contributions
estern+0.050
ostics+0.048
itans+0.047
/>+0.047
bris+0.045
Neg logit contributions
phalt-0.061
 Antar-0.055
ustomed-0.047
nen-0.044
ּ-0.044
Token VT
Token ID32751
Feature activation+2.53e+00

Pos logit contributions
phalt+0.871
 Antar+0.797
ustomed+0.687
nen+0.648
ּ+0.647
Neg logit contributions
estern-0.639
ostics-0.607
itans-0.596
/>-0.588
bris-0.569
Token-
Token ID12
Feature activation-7.59e-02

Pos logit contributions
phalt+2.320
 Antar+2.146
ustomed+1.922
 Ud+1.814
nen+1.811
Neg logit contributions
estern-1.359
ostics-1.258
itans-1.220
bris-1.193
redo-1.179
Tokenx
Token ID87
Feature activation+2.76e-01

Pos logit contributions
estern+0.045
ostics+0.042
/>+0.041
itans+0.041
bris+0.040
Neg logit contributions
phalt-0.067
 Antar-0.061
ustomed-0.053
nen-0.052
ּ-0.050
Token,
Token ID11
Feature activation+5.01e-01

Pos logit contributions
phalt+0.232
 Antar+0.212
ustomed+0.182
nen+0.171
ּ+0.171
Neg logit contributions
estern-0.178
ostics-0.169
itans-0.166
/>-0.165
bris-0.159
Token AMD
Token ID10324
Feature activation+3.18e-01

Pos logit contributions
phalt+0.406
 Antar+0.370
ustomed+0.316
ּ+0.296
nen+0.294
Neg logit contributions
estern-0.339
ostics-0.322
itans-0.317
/>-0.312
bris-0.304
Token-
Token ID12
Feature activation+2.73e-01

Pos logit contributions
phalt+0.252
 Antar+0.229
ustomed+0.195
ּ+0.183
nen+0.182
Neg logit contributions
estern-0.219
ostics-0.210
itans-0.206
/>-0.204
bris-0.198
Token governing
Token ID15030
Feature activation+1.07e-01

Pos logit contributions
estern+0.187
ostics+0.177
itans+0.174
/>+0.172
bris+0.166
Neg logit contributions
phalt-0.281
 Antar-0.259
ustomed-0.225
nen-0.212
ּ-0.212
Token the
Token ID262
Feature activation+4.73e-01

Pos logit contributions
phalt+0.092
 Antar+0.084
ustomed+0.073
nen+0.069
ּ+0.069
Neg logit contributions
estern-0.066
ostics-0.063
itans-0.062
/>-0.061
bris-0.059
Token set
Token ID900
Feature activation+4.64e-01

Pos logit contributions
phalt+0.405
 Antar+0.371
ustomed+0.319
nen+0.302
ּ+0.301
Neg logit contributions
estern-0.297
ostics-0.282
itans-0.277
/>-0.273
bris-0.264
Token-
Token ID12
Feature activation+4.88e-01

Pos logit contributions
phalt+0.404
 Antar+0.370
ustomed+0.319
nen+0.302
ּ+0.301
Neg logit contributions
estern-0.285
ostics-0.271
itans-0.266
/>-0.262
bris-0.253
Tokenback
Token ID1891
Feature activation+1.17e+00

Pos logit contributions
phalt+0.414
 Antar+0.379
ustomed+0.326
nen+0.307
ּ+0.307
Neg logit contributions
estern-0.309
ostics-0.294
itans-0.289
/>-0.286
bris-0.276
Token distance
Token ID5253
Feature activation+2.52e+00

Pos logit contributions
phalt+1.043
 Antar+0.953
ustomed+0.827
nen+0.782
ּ+0.781
Neg logit contributions
estern-0.701
ostics-0.661
itans-0.654
/>-0.640
bris-0.622
Token from
Token ID422
Feature activation+2.46e-01

Pos logit contributions
phalt+1.981
 Antar+1.788
ustomed+1.512
ּ+1.414
nen+1.413
Neg logit contributions
estern-1.771
ostics-1.686
itans-1.668
/>-1.650
bris-1.595
Token sidewalks
Token ID38282
Feature activation+1.85e-01

Pos logit contributions
phalt+0.208
 Antar+0.190
ustomed+0.163
nen+0.153
ּ+0.153
Neg logit contributions
estern-0.159
ostics-0.150
itans-0.148
/>-0.146
bris-0.140
Token and
Token ID290
Feature activation+8.00e-02

Pos logit contributions
phalt+0.167
 Antar+0.153
ustomed+0.134
ּ+0.126
nen+0.126
Neg logit contributions
estern-0.108
ostics-0.102
itans-0.100
/>-0.099
bris-0.095
Token parking
Token ID7647
Feature activation+3.91e-01

Pos logit contributions
phalt+0.068
 Antar+0.063
ustomed+0.054
nen+0.051
ּ+0.051
Neg logit contributions
estern-0.051
ostics-0.048
itans-0.047
/>-0.046
bris-0.045
Token requirements
Token ID5359
Feature activation+2.81e-01

Pos logit contributions
phalt+0.336
 Antar+0.308
ustomed+0.266
ּ+0.250
nen+0.250
Neg logit contributions
estern-0.245
ostics-0.231
itans-0.226
/>-0.224
bris-0.217
Token:
Token ID25
Feature activation+4.42e-01

Pos logit contributions
phalt+0.623
 Antar+0.569
ustomed+0.487
nen+0.458
ּ+0.458
Neg logit contributions
estern-0.492
ostics-0.469
itans-0.461
/>-0.456
bris-0.441
Token C
Token ID327
Feature activation+9.14e-02

Pos logit contributions
phalt+0.326
 Antar+0.294
ustomed+0.247
nen+0.229
ּ+0.229
Neg logit contributions
estern-0.329
ostics-0.316
itans-0.311
/>-0.309
bris-0.300
Tokenaj
Token ID1228
Feature activation-6.27e-01

Pos logit contributions
phalt+0.060
 Antar+0.054
ustomed+0.044
nen+0.040
ּ+0.040
Neg logit contributions
estern-0.075
ostics-0.072
itans-0.071
/>-0.071
bris-0.069
Tokenun
Token ID403
Feature activation-2.28e-01

Pos logit contributions
estern+0.445
ostics+0.426
itans+0.420
/>+0.416
bris+0.403
Neg logit contributions
phalt-0.485
 Antar-0.444
ustomed-0.372
ּ-0.351
nen-0.347
Token Bo
Token ID3248
Feature activation+2.87e-01

Pos logit contributions
estern+0.156
ostics+0.149
itans+0.147
/>+0.145
bris+0.141
Neg logit contributions
phalt-0.182
 Antar-0.165
ustomed-0.141
nen-0.132
ּ-0.132
Tokenil
Token ID346
Feature activation+2.50e+00

Pos logit contributions
phalt+0.263
 Antar+0.240
ustomed+0.211
nen+0.199
ּ+0.198
Neg logit contributions
estern-0.163
ostics-0.155
itans-0.152
/>-0.150
bris-0.143
Token |
Token ID930
Feature activation+3.82e-01

Pos logit contributions
phalt+1.976
 Antar+1.796
ustomed+1.516
nen+1.427
ּ+1.425
Neg logit contributions
estern-1.739
ostics-1.657
itans-1.629
/>-1.607
bris-1.559
Token C
Token ID327
Feature activation-5.78e-02

Pos logit contributions
phalt+0.276
 Antar+0.248
ustomed+0.207
nen+0.192
ּ+0.192
Neg logit contributions
estern-0.291
ostics-0.279
itans-0.275
/>-0.273
bris-0.265
Tokenaj
Token ID1228
Feature activation-2.96e-01

Pos logit contributions
estern+0.049
ostics+0.048
itans+0.047
/>+0.047
bris+0.046
Neg logit contributions
phalt-0.036
 Antar-0.032
ustomed-0.026
nen-0.024
ּ-0.024
Tokenun
Token ID403
Feature activation-3.18e-01

Pos logit contributions
estern+0.209
ostics+0.200
itans+0.198
/>+0.196
bris+0.190
Neg logit contributions
phalt-0.231
 Antar-0.213
ustomed-0.176
ּ-0.167
nen-0.164
Token Kitchen
Token ID22541
Feature activation+3.20e-01

Pos logit contributions
estern+0.278
ostics+0.268
itans+0.265
/>+0.263
bris+0.256
Neg logit contributions
phalt-0.193
 Antar-0.170
ustomed-0.136
nen-0.124
ּ-0.123
Token trial
Token ID4473
Feature activation+5.43e-01

Pos logit contributions
estern+0.166
ostics+0.156
itans+0.153
/>+0.150
bris+0.144
Neg logit contributions
phalt-0.303
 Antar-0.281
ustomed-0.246
nen-0.235
ּ-0.234
Token).
Token ID737
Feature activation+3.49e-02

Pos logit contributions
phalt+0.460
 Antar+0.421
ustomed+0.361
nen+0.342
ּ+0.341
Neg logit contributions
estern-0.346
ostics-0.328
itans-0.323
/>-0.317
bris-0.308
Token
Token ID198
Feature activation-6.04e-01

Pos logit contributions
phalt+0.028
 Antar+0.026
ustomed+0.022
nen+0.021
ּ+0.021
Neg logit contributions
estern-0.023
ostics-0.022
itans-0.022
/>-0.022
bris-0.021
Token
Token ID198
Feature activation-3.61e-01

Pos logit contributions
estern+0.431
ostics+0.413
itans+0.407
/>+0.406
bris+0.390
Neg logit contributions
phalt-0.465
 Antar-0.424
ustomed-0.356
ּ-0.330
nen-0.330
TokenF
Token ID37
Feature activation-1.45e-01

Pos logit contributions
estern+0.225
ostics+0.215
itans+0.211
/>+0.209
bris+0.201
Neg logit contributions
phalt-0.311
 Antar-0.286
ustomed-0.246
nen-0.231
ּ-0.231
Tokeniled
Token ID3902
Feature activation+2.50e+00

Pos logit contributions
estern+0.082
ostics+0.077
itans+0.075
/>+0.074
bris+0.072
Neg logit contributions
phalt-0.134
 Antar-0.123
ustomed-0.108
nen-0.102
ּ-0.102
Token Under
Token ID4698
Feature activation+5.95e-01

Pos logit contributions
phalt+2.000
 Antar+1.833
ustomed+1.545
nen+1.473
ּ+1.459
Neg logit contributions
estern-1.698
ostics-1.609
itans-1.585
/>-1.545
bris-1.498
Token:
Token ID25
Feature activation+1.05e-01

Pos logit contributions
phalt+0.525
 Antar+0.482
ustomed+0.419
nen+0.395
ּ+0.394
Neg logit contributions
estern-0.358
ostics-0.340
itans-0.333
/>-0.329
bris-0.317
Token c
Token ID269
Feature activation-4.16e-01

Pos logit contributions
phalt+0.082
 Antar+0.074
ustomed+0.064
ּ+0.059
nen+0.059
Neg logit contributions
estern-0.074
ostics-0.070
itans-0.069
/>-0.068
bris-0.066
Tokenbp
Token ID46583
Feature activation+8.04e-01

Pos logit contributions
estern+0.254
ostics+0.242
itans+0.237
/>+0.234
bris+0.226
Neg logit contributions
phalt-0.364
 Antar-0.333
ustomed-0.289
nen-0.273
ּ-0.272
Token,
Token ID11
Feature activation+1.94e-02

Pos logit contributions
phalt+0.651
 Antar+0.593
ustomed+0.506
nen+0.475
ּ+0.474
Neg logit contributions
estern-0.542
ostics-0.517
itans-0.509
/>-0.503
bris-0.488
Tokenox
Token ID1140
Feature activation+8.32e-01

Pos logit contributions
phalt+0.773
 Antar+0.697
ustomed+0.607
nen+0.575
ּ+0.568
Neg logit contributions
estern-0.566
ostics-0.536
itans-0.527
/>-0.517
bris-0.503
Token.
Token ID13
Feature activation-2.07e-01

Pos logit contributions
phalt+0.683
 Antar+0.623
ustomed+0.533
ּ+0.503
nen+0.502
Neg logit contributions
estern-0.552
ostics-0.526
itans-0.517
/>-0.508
bris-0.494
Tokenrar
Token ID20040
Feature activation+5.00e-02

Pos logit contributions
estern+0.122
ostics+0.115
itans+0.113
/>+0.112
bris+0.107
Neg logit contributions
phalt-0.185
 Antar-0.170
ustomed-0.148
nen-0.140
ּ-0.140
Token and
Token ID290
Feature activation+7.32e-02

Pos logit contributions
phalt+0.045
 Antar+0.042
ustomed+0.036
ּ+0.034
nen+0.034
Neg logit contributions
estern-0.029
ostics-0.028
itans-0.027
/>-0.026
bris-0.026
Token un
Token ID555
Feature activation+8.20e-02

Pos logit contributions
phalt+0.065
 Antar+0.059
ustomed+0.052
nen+0.049
ּ+0.049
Neg logit contributions
estern-0.044
ostics-0.042
itans-0.041
/>-0.041
bris-0.039
Tokenpack
Token ID8002
Feature activation+2.49e+00

Pos logit contributions
phalt+0.063
 Antar+0.057
ustomed+0.048
nen+0.045
ּ+0.045
Neg logit contributions
estern-0.059
ostics-0.056
itans-0.055
/>-0.055
bris-0.053
Token the
Token ID262
Feature activation+1.42e-01

Pos logit contributions
phalt+2.051
 Antar+1.868
ustomed+1.580
ּ+1.523
nen+1.506
Neg logit contributions
estern-1.655
ostics-1.570
itans-1.546
/>-1.523
bris-1.453
Token Data
Token ID6060
Feature activation+1.00e+00

Pos logit contributions
phalt+0.128
 Antar+0.118
ustomed+0.102
ּ+0.097
nen+0.097
Neg logit contributions
estern-0.083
ostics-0.079
itans-0.077
/>-0.076
bris-0.073
Token into
Token ID656
Feature activation-7.60e-02

Pos logit contributions
phalt+0.952
 Antar+0.876
ustomed+0.769
ּ+0.739
nen+0.731
Neg logit contributions
estern-0.536
ostics-0.502
itans-0.495
/>-0.477
bris-0.462
Token your
Token ID534
Feature activation-3.77e-01

Pos logit contributions
estern+0.044
ostics+0.042
itans+0.041
/>+0.041
bris+0.039
Neg logit contributions
phalt-0.068
 Antar-0.063
ustomed-0.055
nen-0.052
ּ-0.052
Token Skyrim
Token ID21789
Feature activation+4.85e-01

Pos logit contributions
estern+0.219
ostics+0.207
itans+0.203
/>+0.201
bris+0.194
Neg logit contributions
phalt-0.341
 Antar-0.314
ustomed-0.273
nen-0.258
ּ-0.258
Token misdemeanor
Token ID22403
Feature activation+2.69e-01

Pos logit contributions
estern+0.169
ostics+0.160
itans+0.157
/>+0.154
bris+0.148
Neg logit contributions
phalt-0.276
 Antar-0.255
ustomed-0.222
nen-0.211
ּ-0.210
Token.
Token ID13
Feature activation-5.32e-01

Pos logit contributions
phalt+0.244
 Antar+0.225
ustomed+0.195
nen+0.186
ּ+0.184
Neg logit contributions
estern-0.156
ostics-0.147
itans-0.144
/>-0.141
bris-0.137
Token
Token ID198
Feature activation-3.12e-01

Pos logit contributions
estern+0.381
ostics+0.365
itans+0.359
/>+0.355
bris+0.345
Neg logit contributions
phalt-0.408
 Antar-0.370
ustomed-0.312
nen-0.292
ּ-0.292
Token
Token ID198
Feature activation-2.59e-01

Pos logit contributions
estern+0.229
ostics+0.220
itans+0.216
/>+0.214
bris+0.208
Neg logit contributions
phalt-0.233
 Antar-0.210
ustomed-0.177
nen-0.165
ּ-0.165
Token.
Token ID13
Feature activation+5.13e-01

Pos logit contributions
estern+0.159
ostics+0.151
itans+0.148
/>+0.145
bris+0.141
Neg logit contributions
phalt-0.226
 Antar-0.206
ustomed-0.179
nen-0.170
ּ-0.169
Token@
Token ID31
Feature activation+2.48e+00

Pos logit contributions
phalt+0.518
 Antar+0.481
ustomed+0.424
nen+0.405
ּ+0.405
Neg logit contributions
estern-0.244
ostics-0.229
itans-0.222
/>-0.217
bris-0.208
Tokendev
Token ID7959
Feature activation+4.65e-01

Pos logit contributions
phalt+2.050
 Antar+1.856
ustomed+1.585
nen+1.526
ּ+1.508
Neg logit contributions
estern-1.605
ostics-1.551
itans-1.516
/>-1.488
bris-1.421
Tokenon
Token ID261
Feature activation-7.98e-01

Pos logit contributions
phalt+0.397
 Antar+0.365
ustomed+0.314
ּ+0.295
nen+0.295
Neg logit contributions
estern-0.293
ostics-0.279
itans-0.273
/>-0.270
bris-0.261
Tokenms
Token ID907
Feature activation+5.95e-01

Pos logit contributions
estern+0.516
ostics+0.491
itans+0.482
/>+0.477
bris+0.462
Neg logit contributions
phalt-0.668
 Antar-0.612
ustomed-0.525
ּ-0.493
nen-0.493
Tokenayers
Token ID6962
Feature activation+3.28e-03

Pos logit contributions
phalt+0.513
 Antar+0.469
ustomed+0.405
nen+0.383
ּ+0.382
Neg logit contributions
estern-0.370
ostics-0.353
itans-0.345
/>-0.341
bris-0.329
Token reports
Token ID3136
Feature activation+2.71e-01

Pos logit contributions
phalt+0.003
 Antar+0.003
ustomed+0.002
nen+0.002
ּ+0.002
Neg logit contributions
estern-0.002
ostics-0.002
itans-0.002
/>-0.002
bris-0.002
Token real
Token ID1103
Feature activation-5.59e-01

Pos logit contributions
phalt+0.306
 Antar+0.280
ustomed+0.241
nen+0.228
ּ+0.227
Neg logit contributions
estern-0.223
ostics-0.212
itans-0.207
/>-0.204
bris-0.199
Token estate
Token ID7964
Feature activation+4.21e-01

Pos logit contributions
estern+0.328
ostics+0.311
itans+0.305
/>+0.301
bris+0.290
Neg logit contributions
phalt-0.501
 Antar-0.461
ustomed-0.401
nen-0.379
ּ-0.378
Token map
Token ID3975
Feature activation+3.96e-01

Pos logit contributions
phalt+0.371
 Antar+0.340
ustomed+0.292
ּ+0.279
nen+0.277
Neg logit contributions
estern-0.255
ostics-0.243
itans-0.237
/>-0.232
bris-0.227
Token accurately
Token ID14351
Feature activation-1.17e-01

Pos logit contributions
phalt+0.354
 Antar+0.326
ustomed+0.282
ּ+0.267
nen+0.267
Neg logit contributions
estern-0.235
ostics-0.222
itans-0.217
/>-0.214
bris-0.207
Token show
Token ID905
Feature activation-8.37e-01

Pos logit contributions
estern+0.068
ostics+0.065
itans+0.063
/>+0.062
bris+0.060
Neg logit contributions
phalt-0.105
 Antar-0.097
ustomed-0.084
nen-0.080
ּ-0.080
Token distance
Token ID5253
Feature activation+2.43e+00

Pos logit contributions
estern+0.526
ostics+0.501
itans+0.491
/>+0.487
bris+0.470
Neg logit contributions
phalt-0.714
 Antar-0.653
ustomed-0.565
nen-0.532
ּ-0.531
Token?
Token ID30
Feature activation-4.51e-01

Pos logit contributions
phalt+1.939
 Antar+1.757
ustomed+1.486
ּ+1.407
nen+1.401
Neg logit contributions
estern-1.674
ostics-1.607
itans-1.571
/>-1.555
bris-1.513
Token Does
Token ID8314
Feature activation+2.23e-01

Pos logit contributions
estern+0.281
ostics+0.267
itans+0.262
/>+0.259
bris+0.250
Neg logit contributions
phalt-0.389
 Antar-0.356
ustomed-0.308
nen-0.290
ּ-0.290
Token it
Token ID340
Feature activation-9.63e-02

Pos logit contributions
phalt+0.190
 Antar+0.174
ustomed+0.150
nen+0.141
ּ+0.141
Neg logit contributions
estern-0.141
ostics-0.135
itans-0.132
/>-0.130
bris-0.126
Token leave
Token ID2666
Feature activation+7.15e-01

Pos logit contributions
estern+0.053
ostics+0.050
itans+0.049
/>+0.048
bris+0.046
Neg logit contributions
phalt-0.090
 Antar-0.083
ustomed-0.073
nen-0.069
ּ-0.069
Token off
Token ID572
Feature activation+1.75e-01

Pos logit contributions
phalt+0.625
 Antar+0.573
ustomed+0.494
nen+0.467
ּ+0.467
Neg logit contributions
estern-0.437
ostics-0.415
itans-0.406
/>-0.400
bris-0.387
Token
Token ID198
Feature activation+3.92e-01

Pos logit contributions
phalt+1.064
 Antar+0.960
ustomed+0.805
nen+0.752
ּ+0.749
Neg logit contributions
estern-1.058
ostics-1.009
itans-0.998
/>-0.984
bris-0.963
Token
Token ID198
Feature activation+3.76e-01

Pos logit contributions
phalt+0.293
 Antar+0.264
ustomed+0.222
nen+0.207
ּ+0.207
Neg logit contributions
estern-0.289
ostics-0.277
itans-0.272
/>-0.269
bris-0.262
TokenAdvertisement
Token ID4723
Feature activation+1.13e+00

Pos logit contributions
phalt+0.304
 Antar+0.277
ustomed+0.236
nen+0.221
ּ+0.220
Neg logit contributions
estern-0.254
ostics-0.243
itans-0.239
/>-0.238
bris-0.229
Token
Token ID198
Feature activation+3.65e-01

Pos logit contributions
phalt+0.838
 Antar+0.754
ustomed+0.635
nen+0.594
ּ+0.591
Neg logit contributions
estern-0.837
ostics-0.801
itans-0.790
/>-0.778
bris-0.761
Token
Token ID198
Feature activation+3.82e-01

Pos logit contributions
phalt+0.272
 Antar+0.245
ustomed+0.207
nen+0.193
ּ+0.192
Neg logit contributions
estern-0.269
ostics-0.257
itans-0.253
/>-0.250
bris-0.244
Token#
Token ID2
Feature activation+2.40e+00

Pos logit contributions
phalt+0.318
 Antar+0.291
ustomed+0.249
nen+0.234
ּ+0.233
Neg logit contributions
estern-0.249
ostics-0.238
itans-0.234
/>-0.232
bris-0.224
Tokenad
Token ID324
Feature activation+1.62e+00

Pos logit contributions
phalt+1.728
 Antar+1.552
ustomed+1.303
nen+1.218
ּ+1.196
Neg logit contributions
estern-1.830
ostics-1.753
itans-1.732
/>-1.687
bris-1.641
Token#
Token ID2
Feature activation+1.53e+00

Pos logit contributions
phalt+1.567
 Antar+1.441
ustomed+1.268
nen+1.205
 Ud+1.192
Neg logit contributions
estern-0.842
ostics-0.778
itans-0.761
/>-0.730
bris-0.718
TokenThey
Token ID2990
Feature activation-1.03e-01

Pos logit contributions
phalt+1.296
 Antar+1.184
ustomed+1.021
nen+0.963
ּ+0.962
Neg logit contributions
estern-0.978
ostics-0.928
itans-0.914
/>-0.898
bris-0.872
Token d
Token ID288
Feature activation-2.66e-01

Pos logit contributions
estern+0.053
ostics+0.050
itans+0.049
/>+0.048
bris+0.046
Neg logit contributions
phalt-0.100
 Antar-0.092
ustomed-0.081
nen-0.077
ּ-0.077
Tokenusted
Token ID8459
Feature activation+8.90e-01

Pos logit contributions
estern+0.150
ostics+0.142
itans+0.139
/>+0.137
bris+0.132
Neg logit contributions
phalt-0.245
 Antar-0.225
ustomed-0.197
nen-0.186
ּ-0.186
Token 2002
Token ID6244
Feature activation+5.11e-02

Pos logit contributions
phalt+0.991
 Antar+0.913
ustomed+0.766
ּ+0.729
nen+0.720
Neg logit contributions
estern-0.879
ostics-0.833
itans-0.815
/>-0.801
bris-0.781
Token United
Token ID1578
Feature activation-1.03e+00

Pos logit contributions
phalt+0.040
 Antar+0.036
ustomed+0.031
ּ+0.029
nen+0.029
Neg logit contributions
estern-0.036
ostics-0.035
itans-0.034
/>-0.033
bris-0.033
Token States
Token ID1829
Feature activation-8.65e-01

Pos logit contributions
estern+0.626
ostics+0.594
itans+0.585
/>+0.578
bris+0.556
Neg logit contributions
phalt-0.894
 Antar-0.824
ustomed-0.710
nen-0.669
ּ-0.668
Token 3
Token ID513
Feature activation+3.76e-01

Pos logit contributions
estern+0.415
ostics+0.389
itans+0.380
/>+0.374
bris+0.357
Neg logit contributions
phalt-0.868
 Antar-0.806
ustomed-0.712
nen-0.679
ּ-0.678
Token472
Token ID37856
Feature activation+1.55e+00

Pos logit contributions
phalt+0.325
 Antar+0.298
ustomed+0.257
ּ+0.244
nen+0.244
Neg logit contributions
estern-0.233
ostics-0.221
itans-0.216
/>-0.213
bris-0.207
Token Posts
Token ID12043
Feature activation-3.78e+00

Pos logit contributions
phalt+1.125
 Antar+1.004
ustomed+0.844
nen+0.798
ּ+0.789
Neg logit contributions
estern-1.173
ostics-1.123
itans-1.102
/>-1.067
���-1.063
Token #
Token ID1303
Feature activation-2.95e+00

Pos logit contributions
estern+2.101
ostics+1.980
/>+1.941
itans+1.939
bris+1.854
Neg logit contributions
phalt-3.480
 Antar-3.208
ustomed-2.808
ּ-2.673
nen-2.671
Token11
Token ID1157
Feature activation-4.10e-01

Pos logit contributions
estern+1.413
ostics+1.386
/>+1.352
itans+1.337
bris+1.268
Neg logit contributions
phalt-2.907
 Antar-2.765
ustomed-2.370
ּ-2.255
nen-2.222
Token On
Token ID1550
Feature activation-1.49e+00

Pos logit contributions
estern+0.280
ostics+0.267
itans+0.263
/>+0.260
bris+0.252
Neg logit contributions
phalt-0.329
 Antar-0.300
ustomed-0.255
nen-0.239
ּ-0.238
Token September
Token ID2693
Feature activation+5.88e-01

Pos logit contributions
estern+0.989
ostics+0.944
itans+0.928
/>+0.918
bris+0.889
Neg logit contributions
phalt-1.220
 Antar-1.113
ustomed-0.953
nen-0.894
ּ-0.893
Token 20
Token ID1160
Feature activation-1.13e-01

Pos logit contributions
phalt+0.569
 Antar+0.528
ustomed+0.464
nen+0.442
ּ+0.441
Neg logit contributions
estern-0.303
ostics-0.284
itans-0.278
/>-0.272
bris-0.262
Token 2012
Token ID2321
Feature activation-5.60e-02

Pos logit contributions
phalt+0.392
 Antar+0.359
ustomed+0.306
nen+0.289
ּ+0.289
Neg logit contributions
estern-0.316
ostics-0.300
itans-0.294
/>-0.290
bris-0.281
Token United
Token ID1578
Feature activation-9.61e-01

Pos logit contributions
estern+0.038
ostics+0.037
itans+0.036
/>+0.035
bris+0.034
Neg logit contributions
phalt-0.045
 Antar-0.041
ustomed-0.035
ּ-0.033
nen-0.033
Token States
Token ID1829
Feature activation-1.14e+00

Pos logit contributions
estern+0.590
ostics+0.560
itans+0.553
/>+0.544
bris+0.524
Neg logit contributions
phalt-0.833
 Antar-0.768
ustomed-0.659
nen-0.623
ּ-0.622
Token 3
Token ID513
Feature activation+4.20e-01

Pos logit contributions
estern+0.538
ostics+0.503
itans+0.491
/>+0.485
bris+0.461
Neg logit contributions
phalt-1.152
 Antar-1.068
ustomed-0.947
nen-0.902
ּ-0.900
Token240
Token ID16102
Feature activation+6.23e-01

Pos logit contributions
phalt+0.336
 Antar+0.305
ustomed+0.260
nen+0.245
ּ+0.245
Neg logit contributions
estern-0.288
ostics-0.276
itans-0.270
/>-0.265
bris-0.259
Token Posts
Token ID12043
Feature activation-3.73e+00

Pos logit contributions
phalt+0.461
 Antar+0.415
ustomed+0.350
ּ+0.326
nen+0.326
Neg logit contributions
estern-0.464
ostics-0.446
itans-0.438
/>-0.429
bris-0.420
Token #
Token ID1303
Feature activation-3.24e+00

Pos logit contributions
estern+2.228
ostics+2.102
/>+2.073
itans+2.068
bris+1.979
Neg logit contributions
phalt-3.281
 Antar-3.024
ustomed-2.621
ּ-2.489
nen-2.483
Token10
Token ID940
Feature activation-4.00e-01

Pos logit contributions
estern+1.804
ostics+1.733
/>+1.717
itans+1.710
bris+1.599
Neg logit contributions
phalt-2.957
 Antar-2.765
ustomed-2.383
nen-2.209
ּ-2.195
Token Happy
Token ID14628
Feature activation-8.95e-01

Pos logit contributions
estern+0.276
ostics+0.264
itans+0.259
/>+0.256
bris+0.249
Neg logit contributions
phalt-0.318
 Antar-0.289
ustomed-0.245
nen-0.230
ּ-0.230
Token it
Token ID340
Feature activation-9.41e-01

Pos logit contributions
estern+0.543
ostics+0.516
itans+0.506
/>+0.500
bris+0.483
Neg logit contributions
phalt-0.785
 Antar-0.720
ustomed-0.623
nen-0.589
ּ-0.588
Token worked
Token ID3111
Feature activation+6.51e-01

Pos logit contributions
estern+0.603
ostics+0.574
itans+0.564
/>+0.558
bris+0.539
Neg logit contributions
phalt-0.793
 Antar-0.725
ustomed-0.623
nen-0.587
ּ-0.586
Token 2011
Token ID2813
Feature activation-2.28e-01

Pos logit contributions
phalt+0.672
 Antar+0.617
ustomed+0.523
nen+0.494
ּ+0.494
Neg logit contributions
estern-0.558
ostics-0.530
itans-0.520
/>-0.512
bris-0.499
Token United
Token ID1578
Feature activation-9.07e-01

Pos logit contributions
estern+0.157
ostics+0.150
itans+0.147
/>+0.145
bris+0.141
Neg logit contributions
phalt-0.181
 Antar-0.166
ustomed-0.140
ּ-0.132
nen-0.132
Token States
Token ID1829
Feature activation-7.07e-01

Pos logit contributions
estern+0.554
ostics+0.526
itans+0.518
/>+0.512
bris+0.492
Neg logit contributions
phalt-0.790
 Antar-0.728
ustomed-0.627
nen-0.592
ּ-0.591
Token 228
Token ID29041
Feature activation+5.17e-01

Pos logit contributions
estern+0.342
ostics+0.320
itans+0.312
/>+0.307
bris+0.294
Neg logit contributions
phalt-0.708
 Antar-0.657
ustomed-0.581
nen-0.553
ּ-0.553
Token65
Token ID2996
Feature activation+2.30e-01

Pos logit contributions
phalt+0.443
 Antar+0.406
ustomed+0.349
ּ+0.330
nen+0.330
Neg logit contributions
estern-0.325
ostics-0.309
itans-0.303
/>-0.298
bris-0.289
Token Posts
Token ID12043
Feature activation-3.64e+00

Pos logit contributions
phalt+0.174
 Antar+0.156
ustomed+0.132
nen+0.124
ּ+0.123
Neg logit contributions
estern-0.168
ostics-0.161
itans-0.158
/>-0.155
bris-0.152
Token #
Token ID1303
Feature activation-3.02e+00

Pos logit contributions
estern+2.023
ostics+1.902
/>+1.864
itans+1.861
bris+1.779
Neg logit contributions
phalt-3.351
 Antar-3.089
ustomed-2.701
nen-2.575
ּ-2.574
Token13
Token ID1485
Feature activation-3.72e-01

Pos logit contributions
estern+1.587
ostics+1.524
/>+1.492
itans+1.487
bris+1.408
Neg logit contributions
phalt-2.885
 Antar-2.718
ustomed-2.328
nen-2.171
ּ-2.170
Token On
Token ID1550
Feature activation-1.37e+00

Pos logit contributions
estern+0.260
ostics+0.249
itans+0.244
/>+0.241
bris+0.235
Neg logit contributions
phalt-0.292
 Antar-0.265
ustomed-0.224
nen-0.210
ּ-0.209
Token September
Token ID2693
Feature activation+3.82e-01

Pos logit contributions
estern+0.876
ostics+0.835
itans+0.820
/>+0.811
bris+0.784
Neg logit contributions
phalt-1.149
 Antar-1.052
ustomed-0.904
ּ-0.850
nen-0.849
Token 20
Token ID1160
Feature activation-3.86e-01

Pos logit contributions
phalt+0.364
 Antar+0.338
ustomed+0.298
nen+0.281
ּ+0.280
Neg logit contributions
estern-0.201
ostics-0.189
itans-0.185
/>-0.182
bris-0.174
Token 2010
Token ID3050
Feature activation-2.30e-01

Pos logit contributions
phalt+0.494
 Antar+0.454
ustomed+0.385
ּ+0.365
nen+0.364
Neg logit contributions
estern-0.413
ostics-0.391
itans-0.384
/>-0.377
bris-0.367
Token United
Token ID1578
Feature activation-9.70e-01

Pos logit contributions
estern+0.157
ostics+0.149
itans+0.147
/>+0.145
bris+0.141
Neg logit contributions
phalt-0.185
 Antar-0.170
ustomed-0.144
ּ-0.136
nen-0.135
Token States
Token ID1829
Feature activation-9.71e-01

Pos logit contributions
estern+0.590
ostics+0.560
itans+0.552
/>+0.544
bris+0.525
Neg logit contributions
phalt-0.847
 Antar-0.780
ustomed-0.673
nen-0.635
ּ-0.634
Token 10
Token ID838
Feature activation+2.99e-01

Pos logit contributions
estern+0.462
ostics+0.432
itans+0.422
/>+0.416
bris+0.396
Neg logit contributions
phalt-0.978
 Antar-0.908
ustomed-0.804
nen-0.765
ּ-0.764
Token53
Token ID4310
Feature activation+2.32e-01

Pos logit contributions
phalt+0.255
 Antar+0.234
ustomed+0.201
ּ+0.191
nen+0.190
Neg logit contributions
estern-0.188
ostics-0.179
itans-0.175
/>-0.172
bris-0.168
Token Posts
Token ID12043
Feature activation-3.52e+00

Pos logit contributions
phalt+0.176
 Antar+0.158
ustomed+0.134
nen+0.126
ּ+0.125
Neg logit contributions
estern-0.169
ostics-0.162
itans-0.159
/>-0.157
bris-0.153
Token #
Token ID1303
Feature activation-3.11e+00

Pos logit contributions
estern+1.997
ostics+1.884
/>+1.846
itans+1.845
bris+1.765
Neg logit contributions
phalt-3.191
 Antar-2.945
ustomed-2.564
ּ-2.442
nen-2.440
Token15
Token ID1314
Feature activation-2.45e-01

Pos logit contributions
estern+1.715
ostics+1.634
itans+1.633
/>+1.613
bris+1.536
Neg logit contributions
phalt-2.892
 Antar-2.748
ustomed-2.314
ּ-2.192
nen-2.180
Token honestly
Token ID12698
Feature activation-3.68e-01

Pos logit contributions
estern+0.173
ostics+0.165
itans+0.162
/>+0.160
bris+0.156
Neg logit contributions
phalt-0.191
 Antar-0.174
ustomed-0.147
nen-0.138
ּ-0.137
Token if
Token ID611
Feature activation-3.92e-01

Pos logit contributions
estern+0.233
ostics+0.221
itans+0.218
/>+0.215
bris+0.208
Neg logit contributions
phalt-0.314
 Antar-0.287
ustomed-0.247
nen-0.233
ּ-0.233
Token we
Token ID356
Feature activation-6.51e-02

Pos logit contributions
estern+0.261
ostics+0.249
itans+0.245
/>+0.243
bris+0.235
Neg logit contributions
phalt-0.321
 Antar-0.292
ustomed-0.251
ּ-0.235
nen-0.235
Token 2011
Token ID2813
Feature activation+2.50e-02

Pos logit contributions
phalt+0.422
 Antar+0.387
ustomed+0.328
nen+0.311
ּ+0.310
Neg logit contributions
estern-0.348
ostics-0.331
itans-0.324
/>-0.320
bris-0.311
Token United
Token ID1578
Feature activation-7.99e-01

Pos logit contributions
phalt+0.020
 Antar+0.018
ustomed+0.015
ּ+0.014
nen+0.014
Neg logit contributions
estern-0.017
ostics-0.017
itans-0.016
/>-0.016
bris-0.016
Token States
Token ID1829
Feature activation-7.37e-01

Pos logit contributions
estern+0.489
ostics+0.465
itans+0.458
/>+0.452
bris+0.435
Neg logit contributions
phalt-0.693
 Antar-0.639
ustomed-0.550
nen-0.519
ּ-0.518
Token 6
Token ID718
Feature activation+9.70e-02

Pos logit contributions
estern+0.356
ostics+0.333
itans+0.325
/>+0.320
bris+0.306
Neg logit contributions
phalt-0.737
 Antar-0.684
ustomed-0.605
nen-0.576
ּ-0.575
Token12
Token ID1065
Feature activation+9.41e-03

Pos logit contributions
phalt+0.083
 Antar+0.076
ustomed+0.066
nen+0.062
ּ+0.062
Neg logit contributions
estern-0.061
ostics-0.058
itans-0.057
/>-0.056
bris-0.054
Token Posts
Token ID12043
Feature activation-3.51e+00

Pos logit contributions
phalt+0.007
 Antar+0.007
ustomed+0.006
nen+0.005
ּ+0.005
Neg logit contributions
estern-0.007
ostics-0.006
itans-0.006
/>-0.006
bris-0.006
Token #
Token ID1303
Feature activation-2.79e+00

Pos logit contributions
estern+1.897
ostics+1.787
itans+1.747
/>+1.745
bris+1.666
Neg logit contributions
phalt-3.278
 Antar-3.030
ustomed-2.650
ּ-2.530
nen-2.528
Token17
Token ID1558
Feature activation-3.92e-01

Pos logit contributions
estern+1.593
ostics+1.535
/>+1.528
itans+1.506
bris+1.450
Neg logit contributions
phalt-2.547
 Antar-2.393
ustomed-1.984
nen-1.879
ּ-1.862
Token Good
Token ID4599
Feature activation-2.50e-01

Pos logit contributions
estern+0.272
ostics+0.260
itans+0.255
/>+0.252
bris+0.245
Neg logit contributions
phalt-0.310
 Antar-0.282
ustomed-0.238
nen-0.224
ּ-0.222
Token to
Token ID284
Feature activation+2.02e-01

Pos logit contributions
estern+0.147
ostics+0.140
itans+0.137
/>+0.135
bris+0.130
Neg logit contributions
phalt-0.224
 Antar-0.206
ustomed-0.178
nen-0.169
ּ-0.169
Token hear
Token ID3285
Feature activation-1.81e-01

Pos logit contributions
phalt+0.167
 Antar+0.153
ustomed+0.131
nen+0.123
ּ+0.123
Neg logit contributions
estern-0.132
ostics-0.126
itans-0.124
/>-0.122
bris-0.118
Token 2012
Token ID2321
Feature activation+7.52e-03

Pos logit contributions
phalt+0.090
 Antar+0.082
ustomed+0.070
nen+0.066
ּ+0.066
Neg logit contributions
estern-0.073
ostics-0.070
itans-0.068
/>-0.067
bris-0.065
Token United
Token ID1578
Feature activation-9.18e-01

Pos logit contributions
phalt+0.006
 Antar+0.005
ustomed+0.004
ּ+0.004
nen+0.004
Neg logit contributions
estern-0.005
ostics-0.005
itans-0.005
/>-0.005
bris-0.005
Token States
Token ID1829
Feature activation-8.43e-01

Pos logit contributions
estern+0.561
ostics+0.533
itans+0.525
/>+0.518
bris+0.499
Neg logit contributions
phalt-0.798
 Antar-0.735
ustomed-0.633
nen-0.597
ּ-0.596
Token 5
Token ID642
Feature activation+2.23e-01

Pos logit contributions
estern+0.406
ostics+0.380
itans+0.371
/>+0.365
bris+0.348
Neg logit contributions
phalt-0.845
 Antar-0.785
ustomed-0.694
nen-0.661
ּ-0.660
Token667
Token ID28933
Feature activation+9.21e-01

Pos logit contributions
phalt+0.192
 Antar+0.176
ustomed+0.152
ּ+0.143
nen+0.143
Neg logit contributions
estern-0.139
ostics-0.132
itans-0.129
/>-0.128
bris-0.124
Token Posts
Token ID12043
Feature activation-3.49e+00

Pos logit contributions
phalt+0.683
 Antar+0.614
ustomed+0.515
nen+0.487
ּ+0.484
Neg logit contributions
estern-0.686
ostics-0.655
itans-0.644
/>-0.629
bris-0.621
Token #
Token ID1303
Feature activation-2.82e+00

Pos logit contributions
estern+1.986
ostics+1.874
itans+1.836
/>+1.832
bris+1.753
Neg logit contributions
phalt-3.177
 Antar-2.928
ustomed-2.552
ּ-2.428
nen-2.426
Token12
Token ID1065
Feature activation-6.29e-01

Pos logit contributions
estern+1.640
ostics+1.605
/>+1.595
itans+1.560
flo+1.521
Neg logit contributions
phalt-2.517
 Antar-2.346
ustomed-1.982
nen-1.841
 Ud-1.803
Token I
Token ID314
Feature activation-1.79e+00

Pos logit contributions
estern+0.439
ostics+0.420
itans+0.413
/>+0.408
bris+0.397
Neg logit contributions
phalt-0.494
 Antar-0.450
ustomed-0.381
nen-0.357
ּ-0.355
Token'm
Token ID1101
Feature activation-7.60e-01

Pos logit contributions
estern+0.925
ostics+0.871
itans+0.857
/>+0.844
bris+0.811
Neg logit contributions
phalt-1.728
 Antar-1.593
ustomed-1.405
ּ-1.332
nen-1.331
Token glad
Token ID9675
Feature activation-9.25e-01

Pos logit contributions
estern+0.409
ostics+0.385
itans+0.377
/>+0.373
bris+0.358
Neg logit contributions
phalt-0.718
 Antar-0.664
ustomed-0.582
ּ-0.552
nen-0.552
Token 2010
Token ID3050
Feature activation-1.73e-01

Pos logit contributions
phalt+0.468
 Antar+0.430
ustomed+0.365
ּ+0.346
nen+0.345
Neg logit contributions
estern-0.378
ostics-0.359
itans-0.352
/>-0.347
bris-0.338
Token United
Token ID1578
Feature activation-6.33e-01

Pos logit contributions
estern+0.118
ostics+0.113
itans+0.111
/>+0.110
bris+0.106
Neg logit contributions
phalt-0.138
 Antar-0.126
ustomed-0.107
ּ-0.101
nen-0.100
Token States
Token ID1829
Feature activation-7.97e-01

Pos logit contributions
estern+0.387
ostics+0.367
itans+0.361
/>+0.356
bris+0.344
Neg logit contributions
phalt-0.551
 Antar-0.507
ustomed-0.436
nen-0.414
ּ-0.412
Token 6
Token ID718
Feature activation-2.11e-01

Pos logit contributions
estern+0.381
ostics+0.357
itans+0.348
/>+0.343
bris+0.327
Neg logit contributions
phalt-0.801
 Antar-0.743
ustomed-0.658
nen-0.626
ּ-0.626
Token83
Token ID5999
Feature activation+7.76e-01

Pos logit contributions
estern+0.130
ostics+0.123
itans+0.121
/>+0.120
bris+0.115
Neg logit contributions
phalt-0.183
 Antar-0.167
ustomed-0.145
nen-0.136
ּ-0.136
Token Posts
Token ID12043
Feature activation-3.45e+00

Pos logit contributions
phalt+0.583
 Antar+0.525
ustomed+0.441
nen+0.416
ּ+0.414
Neg logit contributions
estern-0.570
ostics-0.546
itans-0.536
/>-0.526
bris-0.516
Token Last
Token ID4586
Feature activation-1.36e+00

Pos logit contributions
estern+1.885
ostics+1.778
itans+1.736
/>+1.735
bris+1.659
Neg logit contributions
phalt-3.200
 Antar-2.955
ustomed-2.582
ּ-2.468
nen-2.464
Token Edited
Token ID34212
Feature activation-1.88e+00

Pos logit contributions
estern+1.034
ostics+0.992
itans+0.976
/>+0.962
bris+0.940
Neg logit contributions
phalt-0.980
 Antar-0.877
ustomed-0.735
nen-0.684
ּ-0.682
Token:
Token ID25
Feature activation-1.48e+00

Pos logit contributions
estern+1.139
ostics+1.080
itans+1.059
/>+1.045
bris+1.010
Neg logit contributions
phalt-1.657
 Antar-1.520
ustomed-1.318
nen-1.245
ּ-1.244
Token 2013
Token ID2211
Feature activation-8.64e-01

Pos logit contributions
estern+0.940
ostics+0.894
itans+0.879
/>+0.865
bris+0.840
Neg logit contributions
phalt-1.249
 Antar-1.143
ustomed-0.983
nen-0.929
ּ-0.926
Token-
Token ID12
Feature activation-6.63e-01

Pos logit contributions
estern+0.409
ostics+0.380
itans+0.372
/>+0.358
bris+0.350
Neg logit contributions
phalt-0.872
 Antar-0.808
ustomed-0.718
nen-0.688
ּ-0.686
Token June
Token ID2795
Feature activation+1.51e-01

Pos logit contributions
estern+0.566
ostics+0.542
itans+0.535
/>+0.531
bris+0.514
Neg logit contributions
phalt-0.633
 Antar-0.573
ustomed-0.488
ּ-0.456
nen-0.454
Token 2012
Token ID2321
Feature activation-1.17e-01

Pos logit contributions
phalt+0.125
 Antar+0.115
ustomed+0.098
nen+0.092
ּ+0.092
Neg logit contributions
estern-0.100
ostics-0.095
itans-0.093
/>-0.092
bris-0.089
Token Canada
Token ID3340
Feature activation-1.11e+00

Pos logit contributions
estern+0.082
ostics+0.079
itans+0.077
/>+0.076
bris+0.074
Neg logit contributions
phalt-0.091
 Antar-0.084
ustomed-0.070
ּ-0.066
nen-0.066
Token 16
Token ID1467
Feature activation-1.76e-01

Pos logit contributions
estern+0.522
ostics+0.490
itans+0.478
/>+0.474
bris+0.448
Neg logit contributions
phalt-1.123
 Antar-1.040
ustomed-0.923
nen-0.878
ּ-0.877
Token10
Token ID940
Feature activation-9.12e-02

Pos logit contributions
estern+0.108
ostics+0.103
itans+0.101
/>+0.099
bris+0.096
Neg logit contributions
phalt-0.153
 Antar-0.141
ustomed-0.121
ּ-0.115
nen-0.115
Token Posts
Token ID12043
Feature activation-3.35e+00

Pos logit contributions
estern+0.065
ostics+0.062
itans+0.061
/>+0.060
bris+0.058
Neg logit contributions
phalt-0.071
 Antar-0.064
ustomed-0.054
nen-0.051
ּ-0.051
Token #
Token ID1303
Feature activation-3.01e+00

Pos logit contributions
estern+1.878
ostics+1.771
itans+1.732
/>+1.730
bris+1.656
Neg logit contributions
phalt-3.068
 Antar-2.830
ustomed-2.470
ּ-2.353
nen-2.352
Token14
Token ID1415
Feature activation-4.26e-01

Pos logit contributions
estern+1.669
ostics+1.629
/>+1.624
itans+1.620
flo+1.551
Neg logit contributions
phalt-2.764
 Antar-2.636
ustomed-2.175
nen-2.043
ּ-2.023
Token On
Token ID1550
Feature activation-1.48e+00

Pos logit contributions
estern+0.300
ostics+0.286
itans+0.282
/>+0.278
bris+0.271
Neg logit contributions
phalt-0.332
 Antar-0.302
ustomed-0.255
nen-0.239
ּ-0.238
Token September
Token ID2693
Feature activation+4.36e-01

Pos logit contributions
estern+0.946
ostics+0.902
itans+0.885
/>+0.877
bris+0.847
Neg logit contributions
phalt-1.253
 Antar-1.148
ustomed-0.987
ּ-0.929
nen-0.927
Token 20
Token ID1160
Feature activation-4.97e-01

Pos logit contributions
phalt+0.419
 Antar+0.388
ustomed+0.343
nen+0.324
ּ+0.322
Neg logit contributions
estern-0.226
ostics-0.214
itans-0.209
/>-0.206
bris-0.196
Token 6
Token ID718
Feature activation-7.95e-02

Pos logit contributions
phalt+0.059
 Antar+0.055
ustomed+0.048
nen+0.046
ּ+0.046
Neg logit contributions
estern-0.029
ostics-0.027
itans-0.027
/>-0.026
bris-0.025
Token,
Token ID11
Feature activation+1.28e-01

Pos logit contributions
estern+0.049
ostics+0.047
itans+0.046
/>+0.045
bris+0.044
Neg logit contributions
phalt-0.068
 Antar-0.062
ustomed-0.054
nen-0.051
ּ-0.051
Token 2010
Token ID3050
Feature activation-2.96e-01

Pos logit contributions
phalt+0.105
 Antar+0.095
ustomed+0.082
nen+0.077
ּ+0.077
Neg logit contributions
estern-0.086
ostics-0.082
itans-0.080
/>-0.079
bris-0.077
Token
Token ID198
Feature activation-7.49e-01

Pos logit contributions
estern+0.215
ostics+0.206
itans+0.203
/>+0.201
bris+0.195
Neg logit contributions
phalt-0.225
 Antar-0.204
ustomed-0.171
nen-0.159
ּ-0.159
Token
Token ID198
Feature activation-7.07e-01

Pos logit contributions
estern+0.541
ostics+0.519
itans+0.511
/>+0.508
bris+0.491
Neg logit contributions
phalt-0.570
 Antar-0.517
ustomed-0.435
ּ-0.404
nen-0.404
TokenSubject
Token ID19776
Feature activation-3.33e+00

Pos logit contributions
estern+0.593
ostics+0.574
itans+0.566
/>+0.565
bris+0.548
Neg logit contributions
phalt-0.454
 Antar-0.406
ustomed-0.325
nen-0.296
ּ-0.296
Token:
Token ID25
Feature activation-7.17e-01

Pos logit contributions
estern+1.799
ostics+1.723
/>+1.701
itans+1.684
bris+1.584
Neg logit contributions
phalt-3.129
 Antar-2.932
ustomed-2.520
ּ-2.372
nen-2.352
Token R
Token ID371
Feature activation+6.66e-01

Pos logit contributions
estern+0.462
ostics+0.440
itans+0.433
/>+0.428
bris+0.414
Neg logit contributions
phalt-0.602
 Antar-0.549
ustomed-0.473
nen-0.445
ּ-0.444
Tokeniff
Token ID733
Feature activation+1.07e+00

Pos logit contributions
phalt+0.589
 Antar+0.540
ustomed+0.469
nen+0.444
ּ+0.442
Neg logit contributions
estern-0.397
ostics-0.378
itans-0.369
/>-0.365
bris-0.353
TokenTra
Token ID15721
Feature activation+5.27e-01

Pos logit contributions
phalt+0.965
 Antar+0.891
ustomed+0.772
nen+0.736
ּ+0.731
Neg logit contributions
estern-0.606
ostics-0.582
itans-0.566
/>-0.555
bris-0.533
Tokenx
Token ID87
Feature activation-1.69e-01

Pos logit contributions
phalt+0.505
 Antar+0.467
ustomed+0.410
nen+0.391
ּ+0.390
Neg logit contributions
estern-0.276
ostics-0.259
itans-0.253
/>-0.250
bris-0.239
Token 15
Token ID1315
Feature activation+1.49e-01

Pos logit contributions
estern+0.224
ostics+0.211
itans+0.206
/>+0.203
bris+0.193
Neg logit contributions
phalt-0.472
 Antar-0.438
ustomed-0.387
ּ-0.369
nen-0.368
Token,
Token ID11
Feature activation-1.12e-01

Pos logit contributions
phalt+0.128
 Antar+0.117
ustomed+0.101
nen+0.096
ּ+0.096
Neg logit contributions
estern-0.093
ostics-0.088
itans-0.086
/>-0.085
bris-0.082
Token 2010
Token ID3050
Feature activation+1.92e-02

Pos logit contributions
estern+0.075
ostics+0.071
itans+0.070
/>+0.069
bris+0.067
Neg logit contributions
phalt-0.092
 Antar-0.084
ustomed-0.072
nen-0.067
ּ-0.067
Token
Token ID198
Feature activation-7.35e-01

Pos logit contributions
phalt+0.015
 Antar+0.013
ustomed+0.011
nen+0.010
ּ+0.010
Neg logit contributions
estern-0.014
ostics-0.013
itans-0.013
/>-0.013
bris-0.013
Token
Token ID198
Feature activation-7.57e-01

Pos logit contributions
estern+0.530
ostics+0.509
itans+0.501
/>+0.498
bris+0.481
Neg logit contributions
phalt-0.560
 Antar-0.508
ustomed-0.427
ּ-0.398
nen-0.397
TokenSubject
Token ID19776
Feature activation-3.31e+00

Pos logit contributions
estern+0.640
ostics+0.620
itans+0.611
/>+0.609
bris+0.591
Neg logit contributions
phalt-0.482
 Antar-0.430
ustomed-0.344
nen-0.313
ּ-0.313
Token:
Token ID25
Feature activation-6.99e-01

Pos logit contributions
estern+1.800
ostics+1.722
/>+1.698
itans+1.684
bris+1.585
Neg logit contributions
phalt-3.097
 Antar-2.898
ustomed-2.492
ּ-2.341
nen-2.326
Token Que
Token ID4670
Feature activation-6.72e-01

Pos logit contributions
estern+0.454
ostics+0.433
itans+0.425
/>+0.420
bris+0.407
Neg logit contributions
phalt-0.583
 Antar-0.533
ustomed-0.458
nen-0.430
ּ-0.430
Tokener
Token ID263
Feature activation-1.27e+00

Pos logit contributions
estern+0.431
ostics+0.411
itans+0.404
/>+0.399
bris+0.386
Neg logit contributions
phalt-0.565
 Antar-0.517
ustomed-0.444
nen-0.418
ּ-0.417
Token magnet
Token ID19972
Feature activation-4.91e-01

Pos logit contributions
estern+0.787
ostics+0.749
itans+0.735
/>+0.727
bris+0.702
Neg logit contributions
phalt-1.089
 Antar-0.997
ustomed-0.863
ּ-0.812
nen-0.812
Token?
Token ID30
Feature activation-4.25e-01

Pos logit contributions
estern+0.314
ostics+0.299
itans+0.294
/>+0.290
bris+0.280
Neg logit contributions
phalt-0.414
 Antar-0.379
ustomed-0.326
nen-0.307
ּ-0.307
Token June
Token ID2795
Feature activation+3.95e-01

Pos logit contributions
estern+0.230
ostics+0.220
itans+0.217
/>+0.215
bris+0.208
Neg logit contributions
phalt-0.247
 Antar-0.224
ustomed-0.189
ּ-0.177
nen-0.177
Token 2009
Token ID3717
Feature activation-2.81e-01

Pos logit contributions
phalt+0.327
 Antar+0.300
ustomed+0.256
nen+0.242
ּ+0.241
Neg logit contributions
estern-0.259
ostics-0.246
itans-0.242
/>-0.239
bris-0.231
Token Germany
Token ID4486
Feature activation-8.05e-01

Pos logit contributions
estern+0.213
ostics+0.203
itans+0.200
/>+0.198
bris+0.193
Neg logit contributions
phalt-0.205
 Antar-0.186
ustomed-0.154
ּ-0.144
nen-0.144
Token 247
Token ID30179
Feature activation+5.17e-01

Pos logit contributions
estern+0.391
ostics+0.366
itans+0.357
/>+0.351
bris+0.336
Neg logit contributions
phalt-0.803
 Antar-0.746
ustomed-0.658
nen-0.628
ּ-0.627
Token34
Token ID2682
Feature activation+5.26e-02

Pos logit contributions
phalt+0.423
 Antar+0.386
ustomed+0.330
ּ+0.311
nen+0.311
Neg logit contributions
estern-0.344
ostics-0.328
itans-0.322
/>-0.317
bris-0.309
Token Posts
Token ID12043
Feature activation-3.29e+00

Pos logit contributions
phalt+0.039
 Antar+0.035
ustomed+0.030
nen+0.028
ּ+0.028
Neg logit contributions
estern-0.039
ostics-0.037
itans-0.036
/>-0.036
bris-0.035
Token #
Token ID1303
Feature activation-2.85e+00

Pos logit contributions
estern+1.809
ostics+1.702
/>+1.667
itans+1.666
bris+1.591
Neg logit contributions
phalt-3.043
 Antar-2.812
ustomed-2.456
ּ-2.341
nen-2.339
Token20
Token ID1238
Feature activation-6.86e-01

Pos logit contributions
estern+1.590
/>+1.524
ostics+1.511
itans+1.493
flo+1.417
Neg logit contributions
phalt-2.596
 Antar-2.493
ustomed-2.067
ּ-1.964
nen-1.954
Token Nice
Token ID18460
Feature activation-8.21e-01

Pos logit contributions
estern+0.465
ostics+0.443
itans+0.436
/>+0.431
bris+0.418
Neg logit contributions
phalt-0.553
 Antar-0.504
ustomed-0.429
nen-0.403
ּ-0.402
Token,
Token ID11
Feature activation-4.31e-01

Pos logit contributions
estern+0.468
ostics+0.443
itans+0.434
/>+0.429
bris+0.413
Neg logit contributions
phalt-0.750
 Antar-0.691
ustomed-0.603
nen-0.570
ּ-0.570
Token happy
Token ID3772
Feature activation-2.03e-01

Pos logit contributions
estern+0.272
ostics+0.259
itans+0.254
/>+0.251
bris+0.243
Neg logit contributions
phalt-0.367
 Antar-0.336
ustomed-0.289
nen-0.273
ּ-0.272
Token 9
Token ID860
Feature activation+2.06e-01

Pos logit contributions
phalt+0.042
 Antar+0.039
ustomed+0.034
nen+0.032
ּ+0.032
Neg logit contributions
estern-0.020
ostics-0.019
itans-0.018
/>-0.018
bris-0.017
Token,
Token ID11
Feature activation+3.18e-01

Pos logit contributions
phalt+0.176
 Antar+0.160
ustomed+0.139
nen+0.132
ּ+0.131
Neg logit contributions
estern-0.130
ostics-0.123
itans-0.121
/>-0.118
bris-0.116
Token 2010
Token ID3050
Feature activation+6.66e-02

Pos logit contributions
phalt+0.257
 Antar+0.234
ustomed+0.201
nen+0.188
ּ+0.188
Neg logit contributions
estern-0.214
ostics-0.204
itans-0.201
/>-0.198
bris-0.193
Token
Token ID198
Feature activation-3.99e-01

Pos logit contributions
phalt+0.050
 Antar+0.045
ustomed+0.038
nen+0.036
ּ+0.036
Neg logit contributions
estern-0.049
ostics-0.047
itans-0.046
/>-0.045
bris-0.044
Token
Token ID198
Feature activation-4.86e-01

Pos logit contributions
estern+0.292
ostics+0.280
itans+0.275
/>+0.273
bris+0.265
Neg logit contributions
phalt-0.300
 Antar-0.271
ustomed-0.228
nen-0.213
ּ-0.212
TokenSubject
Token ID19776
Feature activation-3.26e+00

Pos logit contributions
estern+0.412
ostics+0.399
itans+0.393
/>+0.392
bris+0.381
Neg logit contributions
phalt-0.308
 Antar-0.274
ustomed-0.220
nen-0.200
ּ-0.200
Token:
Token ID25
Feature activation-6.54e-01

Pos logit contributions
estern+1.774
ostics+1.697
/>+1.674
itans+1.659
bris+1.562
Neg logit contributions
phalt-3.050
 Antar-2.857
ustomed-2.456
ּ-2.309
nen-2.292
Token R
Token ID371
Feature activation+4.49e-01

Pos logit contributions
estern+0.423
ostics+0.403
itans+0.396
/>+0.392
bris+0.379
Neg logit contributions
phalt-0.547
 Antar-0.500
ustomed-0.430
nen-0.404
ּ-0.404
Tokenipe
Token ID3757
Feature activation+5.43e-01

Pos logit contributions
phalt+0.411
 Antar+0.377
ustomed+0.330
nen+0.314
ּ+0.312
Neg logit contributions
estern-0.253
ostics-0.241
itans-0.235
/>-0.232
bris-0.224
Token for
Token ID329
Feature activation-7.97e-02

Pos logit contributions
phalt+0.463
 Antar+0.425
ustomed+0.365
nen+0.344
ּ+0.342
Neg logit contributions
estern-0.342
ostics-0.326
itans-0.320
/>-0.315
bris-0.304
Token M
Token ID337
Feature activation-2.80e-01

Pos logit contributions
estern+0.051
ostics+0.048
itans+0.047
/>+0.047
bris+0.045
Neg logit contributions
phalt-0.068
 Antar-0.062
ustomed-0.053
nen-0.050
ּ-0.050
Token TL
Token ID24811
Feature activation-4.38e-01

Pos logit contributions
phalt+0.000
 Antar+0.000
ustomed+0.000
ּ+0.000
nen+0.000
Neg logit contributions
estern-0.000
ostics-0.000
itans-0.000
/>-0.000
bris-0.000
TokenAD
Token ID2885
Feature activation+8.39e-01

Pos logit contributions
estern+0.290
ostics+0.277
itans+0.272
/>+0.269
bris+0.261
Neg logit contributions
phalt-0.358
 Antar-0.327
ustomed-0.280
nen-0.263
ּ-0.262
TokenT
Token ID51
Feature activation+3.21e-01

Pos logit contributions
phalt+0.709
 Antar+0.649
ustomed+0.560
nen+0.526
ּ+0.524
Neg logit contributions
estern-0.535
ostics-0.510
itans-0.497
/>-0.490
bris-0.476
Token 235
Token ID28878
Feature activation+8.17e-02

Pos logit contributions
phalt+0.306
 Antar+0.285
ustomed+0.249
ּ+0.237
nen+0.236
Neg logit contributions
estern-0.169
ostics-0.160
itans-0.154
/>-0.152
bris-0.147
Token21
Token ID2481
Feature activation-4.04e-01

Pos logit contributions
phalt+0.070
 Antar+0.064
ustomed+0.055
ּ+0.052
nen+0.052
Neg logit contributions
estern-0.051
ostics-0.049
itans-0.048
/>-0.047
bris-0.046
Token Posts
Token ID12043
Feature activation-3.25e+00

Pos logit contributions
estern+0.285
ostics+0.272
itans+0.268
/>+0.266
bris+0.257
Neg logit contributions
phalt-0.315
 Antar-0.286
ustomed-0.242
nen-0.226
ּ-0.226
Token #
Token ID1303
Feature activation-2.66e+00

Pos logit contributions
estern+1.757
ostics+1.654
/>+1.617
itans+1.616
bris+1.545
Neg logit contributions
phalt-3.041
 Antar-2.811
ustomed-2.460
ּ-2.346
nen-2.346
Token18
Token ID1507
Feature activation-2.43e-01

Pos logit contributions
estern+1.793
/>+1.765
ostics+1.750
itans+1.723
flo+1.680
Neg logit contributions
phalt-2.113
 Antar-1.989
ustomed-1.566
nen-1.495
 Ud-1.451
Token Good
Token ID4599
Feature activation-3.38e-01

Pos logit contributions
estern+0.168
ostics+0.160
itans+0.158
/>+0.155
bris+0.151
Neg logit contributions
phalt-0.193
 Antar-0.176
ustomed-0.149
nen-0.140
ּ-0.139
Token stuff
Token ID3404
Feature activation+5.32e-01

Pos logit contributions
estern+0.207
ostics+0.196
itans+0.193
/>+0.190
bris+0.183
Neg logit contributions
phalt-0.296
 Antar-0.271
ustomed-0.234
nen-0.222
ּ-0.221
Token!
Token ID0
Feature activation-1.01e-01

Pos logit contributions
phalt+0.447
 Antar+0.409
ustomed+0.351
nen+0.331
ּ+0.330
Neg logit contributions
estern-0.342
ostics-0.326
itans-0.320
/>-0.316
bris-0.306
Token 2010
Token ID3050
Feature activation-1.67e-01

Pos logit contributions
phalt+0.800
 Antar+0.736
ustomed+0.619
ּ+0.588
nen+0.586
Neg logit contributions
estern-0.689
ostics-0.652
itans-0.639
/>-0.629
bris-0.615
Token United
Token ID1578
Feature activation-9.90e-01

Pos logit contributions
estern+0.119
ostics+0.114
itans+0.112
/>+0.111
bris+0.108
Neg logit contributions
phalt-0.129
 Antar-0.118
ustomed-0.099
ּ-0.093
nen-0.093
Token States
Token ID1829
Feature activation-7.84e-01

Pos logit contributions
estern+0.602
ostics+0.572
itans+0.563
/>+0.556
bris+0.536
Neg logit contributions
phalt-0.864
 Antar-0.796
ustomed-0.686
nen-0.648
ּ-0.647
Token 21
Token ID2310
Feature activation-4.62e-01

Pos logit contributions
estern+0.375
ostics+0.351
itans+0.343
/>+0.338
bris+0.322
Neg logit contributions
phalt-0.787
 Antar-0.731
ustomed-0.646
nen-0.616
ּ-0.615
Token50
Token ID1120
Feature activation-2.69e-01

Pos logit contributions
estern+0.298
ostics+0.284
itans+0.279
/>+0.275
bris+0.267
Neg logit contributions
phalt-0.387
 Antar-0.354
ustomed-0.304
nen-0.286
ּ-0.286
Token Posts
Token ID12043
Feature activation-3.25e+00

Pos logit contributions
estern+0.193
ostics+0.184
itans+0.181
/>+0.179
bris+0.174
Neg logit contributions
phalt-0.206
 Antar-0.187
ustomed-0.158
nen-0.148
ּ-0.147
Token #
Token ID1303
Feature activation-2.86e+00

Pos logit contributions
estern+1.800
ostics+1.695
itans+1.659
/>+1.659
bris+1.585
Neg logit contributions
phalt-3.000
 Antar-2.771
ustomed-2.419
nen-2.304
ּ-2.302
Token16
Token ID1433
Feature activation-5.58e-01

Pos logit contributions
estern+1.429
/>+1.390
itans+1.389
ostics+1.378
flo+1.307
Neg logit contributions
phalt-2.752
 Antar-2.644
ustomed-2.210
nen-2.087
ּ-2.081
Token Glad
Token ID28442
Feature activation-9.69e-01

Pos logit contributions
estern+0.393
ostics+0.376
itans+0.370
/>+0.365
bris+0.355
Neg logit contributions
phalt-0.435
 Antar-0.395
ustomed-0.334
nen-0.313
ּ-0.311
Token to
Token ID284
Feature activation+1.96e-01

Pos logit contributions
estern+0.612
ostics+0.583
itans+0.575
/>+0.570
bris+0.549
Neg logit contributions
phalt-0.823
 Antar-0.753
ustomed-0.652
ּ-0.612
nen-0.608
Token hear
Token ID3285
Feature activation-3.92e-01

Pos logit contributions
phalt+0.163
 Antar+0.149
ustomed+0.128
nen+0.120
ּ+0.120
Neg logit contributions
estern-0.128
ostics-0.122
itans-0.120
/>-0.118
bris-0.114
Token United
Token ID1578
Feature activation-9.61e-01

Pos logit contributions
estern+0.038
ostics+0.037
itans+0.036
/>+0.035
bris+0.034
Neg logit contributions
phalt-0.045
 Antar-0.041
ustomed-0.035
ּ-0.033
nen-0.033
Token States
Token ID1829
Feature activation-1.14e+00

Pos logit contributions
estern+0.590
ostics+0.560
itans+0.553
/>+0.544
bris+0.524
Neg logit contributions
phalt-0.833
 Antar-0.768
ustomed-0.659
nen-0.623
ּ-0.622
Token 3
Token ID513
Feature activation+4.20e-01

Pos logit contributions
estern+0.538
ostics+0.503
itans+0.491
/>+0.485
bris+0.461
Neg logit contributions
phalt-1.152
 Antar-1.068
ustomed-0.947
nen-0.902
ּ-0.900
Token240
Token ID16102
Feature activation+6.23e-01

Pos logit contributions
phalt+0.336
 Antar+0.305
ustomed+0.260
nen+0.245
ּ+0.245
Neg logit contributions
estern-0.288
ostics-0.276
itans-0.270
/>-0.265
bris-0.259
Token Posts
Token ID12043
Feature activation-3.73e+00

Pos logit contributions
phalt+0.461
 Antar+0.415
ustomed+0.350
ּ+0.326
nen+0.326
Neg logit contributions
estern-0.464
ostics-0.446
itans-0.438
/>-0.429
bris-0.420
Token #
Token ID1303
Feature activation-3.24e+00

Pos logit contributions
estern+2.228
ostics+2.102
/>+2.073
itans+2.068
bris+1.979
Neg logit contributions
phalt-3.281
 Antar-3.024
ustomed-2.621
ּ-2.489
nen-2.483
Token10
Token ID940
Feature activation-4.00e-01

Pos logit contributions
estern+1.804
ostics+1.733
/>+1.717
itans+1.710
bris+1.599
Neg logit contributions
phalt-2.957
 Antar-2.765
ustomed-2.383
nen-2.209
ּ-2.195
Token Happy
Token ID14628
Feature activation-8.95e-01

Pos logit contributions
estern+0.276
ostics+0.264
itans+0.259
/>+0.256
bris+0.249
Neg logit contributions
phalt-0.318
 Antar-0.289
ustomed-0.245
nen-0.230
ּ-0.230
Token it
Token ID340
Feature activation-9.41e-01

Pos logit contributions
estern+0.543
ostics+0.516
itans+0.506
/>+0.500
bris+0.483
Neg logit contributions
phalt-0.785
 Antar-0.720
ustomed-0.623
nen-0.589
ּ-0.588
Token worked
Token ID3111
Feature activation+6.51e-01

Pos logit contributions
estern+0.603
ostics+0.574
itans+0.564
/>+0.558
bris+0.539
Neg logit contributions
phalt-0.793
 Antar-0.725
ustomed-0.623
nen-0.587
ּ-0.586
Token out
Token ID503
Feature activation-1.16e-01

Pos logit contributions
phalt+0.578
 Antar+0.531
ustomed+0.459
nen+0.435
ּ+0.434
Neg logit contributions
estern-0.387
ostics-0.367
itans-0.360
/>-0.355
bris-0.343
Token 13
Token ID1511
Feature activation+1.37e-01

Pos logit contributions
phalt+0.236
 Antar+0.219
ustomed+0.193
nen+0.184
ּ+0.184
Neg logit contributions
estern-0.120
ostics-0.112
itans-0.109
/>-0.107
bris-0.103
Token,
Token ID11
Feature activation+2.36e-01

Pos logit contributions
phalt+0.115
 Antar+0.105
ustomed+0.091
nen+0.086
ּ+0.086
Neg logit contributions
estern-0.088
ostics-0.083
itans-0.081
/>-0.080
bris-0.078
Token 2010
Token ID3050
Feature activation-2.24e-01

Pos logit contributions
phalt+0.197
 Antar+0.180
ustomed+0.155
nen+0.145
ּ+0.145
Neg logit contributions
estern-0.153
ostics-0.146
itans-0.143
/>-0.142
bris-0.137
Token
Token ID198
Feature activation-7.72e-01

Pos logit contributions
estern+0.163
ostics+0.156
itans+0.153
/>+0.152
bris+0.148
Neg logit contributions
phalt-0.170
 Antar-0.154
ustomed-0.130
nen-0.121
ּ-0.121
Token
Token ID198
Feature activation-6.10e-01

Pos logit contributions
estern+0.553
ostics+0.531
itans+0.523
/>+0.521
bris+0.502
Neg logit contributions
phalt-0.592
 Antar-0.539
ustomed-0.453
ּ-0.422
nen-0.421
TokenSubject
Token ID19776
Feature activation-3.23e+00

Pos logit contributions
estern+0.525
ostics+0.507
itans+0.500
/>+0.496
bris+0.484
Neg logit contributions
phalt-0.380
 Antar-0.336
ustomed-0.270
nen-0.246
ּ-0.246
Token:
Token ID25
Feature activation-6.65e-01

Pos logit contributions
estern+1.755
ostics+1.686
/>+1.657
itans+1.644
bris+1.555
Neg logit contributions
phalt-3.020
 Antar-2.814
ustomed-2.429
ּ-2.295
nen-2.273
Token boys
Token ID6510
Feature activation-1.32e-03

Pos logit contributions
estern+0.432
ostics+0.411
itans+0.404
/>+0.400
bris+0.387
Neg logit contributions
phalt-0.555
 Antar-0.507
ustomed-0.435
nen-0.409
ּ-0.409
Token beware
Token ID40600
Feature activation+3.57e-01

Pos logit contributions
estern+0.001
ostics+0.001
itans+0.001
/>+0.001
bris+0.001
Neg logit contributions
phalt-0.001
 Antar-0.001
ustomed-0.001
nen-0.001
ּ-0.001
Token This
Token ID770
Feature activation+1.22e-01

Pos logit contributions
phalt+0.307
 Antar+0.282
ustomed+0.243
nen+0.229
ּ+0.229
Neg logit contributions
estern-0.223
ostics-0.212
itans-0.208
/>-0.205
bris-0.198
Token film
Token ID2646
Feature activation+5.68e-01

Pos logit contributions
phalt+0.116
 Antar+0.108
ustomed+0.094
nen+0.090
ּ+0.090
Neg logit contributions
estern-0.064
ostics-0.060
itans-0.059
/>-0.058
bris-0.056
Token 4
Token ID604
Feature activation-3.80e-02

Pos logit contributions
estern+0.211
ostics+0.198
itans+0.193
/>+0.191
bris+0.181
Neg logit contributions
phalt-0.473
 Antar-0.440
ustomed-0.390
ּ-0.371
nen-0.371
Token,
Token ID11
Feature activation-1.17e-01

Pos logit contributions
estern+0.024
ostics+0.022
itans+0.022
/>+0.022
bris+0.021
Neg logit contributions
phalt-0.033
 Antar-0.030
ustomed-0.026
nen-0.025
ּ-0.024
Token 2010
Token ID3050
Feature activation-1.17e-01

Pos logit contributions
estern+0.078
ostics+0.074
itans+0.073
/>+0.072
bris+0.070
Neg logit contributions
phalt-0.096
 Antar-0.088
ustomed-0.075
nen-0.071
ּ-0.071
Token
Token ID198
Feature activation-6.76e-01

Pos logit contributions
estern+0.084
ostics+0.081
itans+0.079
/>+0.079
bris+0.076
Neg logit contributions
phalt-0.089
 Antar-0.080
ustomed-0.068
ּ-0.063
nen-0.063
Token
Token ID198
Feature activation-6.86e-01

Pos logit contributions
estern+0.489
ostics+0.469
itans+0.462
/>+0.458
bris+0.443
Neg logit contributions
phalt-0.513
 Antar-0.465
ustomed-0.392
nen-0.364
ּ-0.364
TokenSubject
Token ID19776
Feature activation-3.19e+00

Pos logit contributions
estern+0.590
ostics+0.570
itans+0.562
/>+0.559
bris+0.544
Neg logit contributions
phalt-0.428
 Antar-0.379
ustomed-0.304
nen-0.277
ּ-0.276
Token:
Token ID25
Feature activation-8.28e-01

Pos logit contributions
estern+1.735
ostics+1.661
/>+1.639
itans+1.624
bris+1.529
Neg logit contributions
phalt-2.986
 Antar-2.795
ustomed-2.404
ּ-2.256
nen-2.242
Token User
Token ID11787
Feature activation+4.67e-02

Pos logit contributions
estern+0.538
ostics+0.512
itans+0.503
/>+0.498
bris+0.482
Neg logit contributions
phalt-0.690
 Antar-0.630
ustomed-0.541
nen-0.509
ּ-0.508
Token reviews
Token ID8088
Feature activation-7.21e-01

Pos logit contributions
phalt+0.041
 Antar+0.037
ustomed+0.032
nen+0.030
ּ+0.030
Neg logit contributions
estern-0.029
ostics-0.027
itans-0.027
/>-0.026
bris-0.025
Token are
Token ID389
Feature activation+1.71e-01

Pos logit contributions
estern+0.452
ostics+0.430
itans+0.422
/>+0.418
bris+0.403
Neg logit contributions
phalt-0.617
 Antar-0.565
ustomed-0.488
nen-0.459
ּ-0.459
Token a
Token ID257
Feature activation-2.45e-02

Pos logit contributions
phalt+0.154
 Antar+0.142
ustomed+0.123
nen+0.117
ּ+0.116
Neg logit contributions
estern-0.100
ostics-0.094
itans-0.092
/>-0.091
bris-0.088
Token 5
Token ID642
Feature activation-1.58e-02

Pos logit contributions
estern+0.042
ostics+0.039
itans+0.038
/>+0.038
bris+0.036
Neg logit contributions
phalt-0.087
 Antar-0.081
ustomed-0.071
ּ-0.068
nen-0.068
Token,
Token ID11
Feature activation+2.30e-01

Pos logit contributions
estern+0.010
ostics+0.009
itans+0.009
/>+0.009
bris+0.009
Neg logit contributions
phalt-0.014
 Antar-0.012
ustomed-0.011
nen-0.010
ּ-0.010
Token 2009
Token ID3717
Feature activation-4.40e-01

Pos logit contributions
phalt+0.184
 Antar+0.168
ustomed+0.143
nen+0.134
ּ+0.134
Neg logit contributions
estern-0.158
ostics-0.151
itans-0.148
/>-0.146
bris-0.142
Token
Token ID198
Feature activation-7.25e-01

Pos logit contributions
estern+0.315
ostics+0.302
itans+0.297
/>+0.296
bris+0.286
Neg logit contributions
phalt-0.338
 Antar-0.307
ustomed-0.258
ּ-0.240
nen-0.240
Token
Token ID198
Feature activation-7.28e-01

Pos logit contributions
estern+0.523
ostics+0.502
itans+0.494
/>+0.491
bris+0.474
Neg logit contributions
phalt-0.553
 Antar-0.502
ustomed-0.422
ּ-0.393
nen-0.393
TokenSubject
Token ID19776
Feature activation-3.19e+00

Pos logit contributions
estern+0.622
ostics+0.602
itans+0.593
/>+0.590
bris+0.574
Neg logit contributions
phalt-0.457
 Antar-0.406
ustomed-0.325
nen-0.296
ּ-0.295
Token:
Token ID25
Feature activation-7.60e-01

Pos logit contributions
estern+1.735
ostics+1.661
/>+1.642
itans+1.625
bris+1.530
Neg logit contributions
phalt-2.984
 Antar-2.795
ustomed-2.402
ּ-2.251
nen-2.240
Token Que
Token ID4670
Feature activation-9.37e-01

Pos logit contributions
estern+0.496
ostics+0.473
itans+0.465
/>+0.460
bris+0.445
Neg logit contributions
phalt-0.631
 Antar-0.576
ustomed-0.494
nen-0.464
ּ-0.464
Tokeners
Token ID364
Feature activation-7.87e-01

Pos logit contributions
estern+0.603
ostics+0.574
itans+0.565
/>+0.558
bris+0.540
Neg logit contributions
phalt-0.786
 Antar-0.718
ustomed-0.617
nen-0.581
ּ-0.580
Token are
Token ID389
Feature activation-4.95e-02

Pos logit contributions
estern+0.461
ostics+0.437
itans+0.428
/>+0.422
bris+0.408
Neg logit contributions
phalt-0.707
 Antar-0.650
ustomed-0.565
nen-0.534
ּ-0.533
Token Here
Token ID3423
Feature activation-5.92e-02

Pos logit contributions
estern+0.029
ostics+0.028
itans+0.027
/>+0.027
bris+0.026
Neg logit contributions
phalt-0.044
 Antar-0.041
ustomed-0.035
nen-0.033
ּ-0.033
Token United
Token ID1578
Feature activation-9.70e-01

Pos logit contributions
estern+0.157
ostics+0.149
itans+0.147
/>+0.145
bris+0.141
Neg logit contributions
phalt-0.185
 Antar-0.170
ustomed-0.144
ּ-0.136
nen-0.135
Token States
Token ID1829
Feature activation-9.71e-01

Pos logit contributions
estern+0.590
ostics+0.560
itans+0.552
/>+0.544
bris+0.525
Neg logit contributions
phalt-0.847
 Antar-0.780
ustomed-0.673
nen-0.635
ּ-0.634
Token 10
Token ID838
Feature activation+2.99e-01

Pos logit contributions
estern+0.462
ostics+0.432
itans+0.422
/>+0.416
bris+0.396
Neg logit contributions
phalt-0.978
 Antar-0.908
ustomed-0.804
nen-0.765
ּ-0.764
Token53
Token ID4310
Feature activation+2.32e-01

Pos logit contributions
phalt+0.255
 Antar+0.234
ustomed+0.201
ּ+0.191
nen+0.190
Neg logit contributions
estern-0.188
ostics-0.179
itans-0.175
/>-0.172
bris-0.168
Token Posts
Token ID12043
Feature activation-3.52e+00

Pos logit contributions
phalt+0.176
 Antar+0.158
ustomed+0.134
nen+0.126
ּ+0.125
Neg logit contributions
estern-0.169
ostics-0.162
itans-0.159
/>-0.157
bris-0.153
Token #
Token ID1303
Feature activation-3.11e+00

Pos logit contributions
estern+1.997
ostics+1.884
/>+1.846
itans+1.845
bris+1.765
Neg logit contributions
phalt-3.191
 Antar-2.945
ustomed-2.564
ּ-2.442
nen-2.440
Token15
Token ID1314
Feature activation-2.45e-01

Pos logit contributions
estern+1.715
ostics+1.634
itans+1.633
/>+1.613
bris+1.536
Neg logit contributions
phalt-2.892
 Antar-2.748
ustomed-2.314
ּ-2.192
nen-2.180
Token honestly
Token ID12698
Feature activation-3.68e-01

Pos logit contributions
estern+0.173
ostics+0.165
itans+0.162
/>+0.160
bris+0.156
Neg logit contributions
phalt-0.191
 Antar-0.174
ustomed-0.147
nen-0.138
ּ-0.137
Token if
Token ID611
Feature activation-3.92e-01

Pos logit contributions
estern+0.233
ostics+0.221
itans+0.218
/>+0.215
bris+0.208
Neg logit contributions
phalt-0.314
 Antar-0.287
ustomed-0.247
nen-0.233
ּ-0.233
Token we
Token ID356
Feature activation-6.51e-02

Pos logit contributions
estern+0.261
ostics+0.249
itans+0.245
/>+0.243
bris+0.235
Neg logit contributions
phalt-0.321
 Antar-0.292
ustomed-0.251
ּ-0.235
nen-0.235
Token just
Token ID655
Feature activation+6.33e-01

Pos logit contributions
estern+0.034
ostics+0.032
itans+0.031
/>+0.031
bris+0.030
Neg logit contributions
phalt-0.062
 Antar-0.058
ustomed-0.051
nen-0.048
ּ-0.048
Token 07
Token ID8753
Feature activation-4.59e-01

Pos logit contributions
phalt+0.042
 Antar+0.039
ustomed+0.035
nen+0.033
ּ+0.033
Neg logit contributions
estern-0.022
ostics-0.020
itans-0.020
/>-0.019
bris-0.018
Token:
Token ID25
Feature activation-3.97e-01

Pos logit contributions
estern+0.281
ostics+0.266
itans+0.261
/>+0.257
bris+0.249
Neg logit contributions
phalt-0.400
 Antar-0.365
ustomed-0.318
nen-0.301
ּ-0.300
Token44
Token ID2598
Feature activation+5.30e-01

Pos logit contributions
estern+0.242
ostics+0.230
itans+0.225
/>+0.223
bris+0.215
Neg logit contributions
phalt-0.347
 Antar-0.318
ustomed-0.275
nen-0.260
ּ-0.260
Token Se
Token ID1001
Feature activation-3.50e-01

Pos logit contributions
phalt+0.354
 Antar+0.317
ustomed+0.258
nen+0.239
ּ+0.238
Neg logit contributions
estern-0.432
ostics-0.416
itans-0.410
/>-0.406
bris-0.396
Tokeneker
Token ID28233
Feature activation+3.01e-01

Pos logit contributions
estern+0.124
ostics+0.114
itans+0.110
/>+0.107
bris+0.100
Neg logit contributions
phalt-0.394
 Antar-0.368
ustomed-0.331
nen-0.318
ּ-0.317
Token wrote
Token ID2630
Feature activation-3.09e+00

Pos logit contributions
phalt+0.292
 Antar+0.268
ustomed+0.238
nen+0.227
ּ+0.225
Neg logit contributions
estern-0.155
ostics-0.146
itans-0.143
/>-0.139
bris-0.134
Token:
Token ID25
Feature activation-1.24e+00

Pos logit contributions
estern+1.695
ostics+1.622
/>+1.609
itans+1.592
bris+1.501
Neg logit contributions
phalt-2.885
 Antar-2.697
ustomed-2.312
ּ-2.171
nen-2.161
Token
Token ID198
Feature activation-1.63e+00

Pos logit contributions
estern+0.888
ostics+0.853
itans+0.839
/>+0.836
bris+0.806
Neg logit contributions
phalt-0.954
 Antar-0.869
ustomed-0.730
ּ-0.681
nen-0.678
Token
Token ID198
Feature activation-1.67e+00

Pos logit contributions
estern+1.160
ostics+1.113
itans+1.095
/>+1.094
bris+1.052
Neg logit contributions
phalt-1.259
 Antar-1.150
ustomed-0.965
ּ-0.899
nen-0.895
TokenCl
Token ID2601
Feature activation-8.86e-01

Pos logit contributions
estern+1.112
ostics+1.058
itans+1.041
/>+1.023
bris+0.992
Neg logit contributions
phalt-1.368
 Antar-1.240
ustomed-1.067
nen-1.003
ּ-0.999
Tokenarity
Token ID6806
Feature activation-5.09e-02

Pos logit contributions
estern+0.427
ostics+0.400
itans+0.390
/>+0.384
bris+0.367
Neg logit contributions
phalt-0.887
 Antar-0.821
ustomed-0.728
nen-0.694
ּ-0.691
Token Our
Token ID3954
Feature activation+7.97e-01

Pos logit contributions
phalt+0.560
 Antar+0.511
ustomed+0.434
nen+0.408
ּ+0.406
Neg logit contributions
estern-0.470
ostics-0.450
itans-0.443
/>-0.438
bris-0.423
Token Seas
Token ID32306
Feature activation+4.53e-01

Pos logit contributions
phalt+0.650
 Antar+0.595
ustomed+0.503
nen+0.475
ּ+0.471
Neg logit contributions
estern-0.531
ostics-0.508
itans-0.498
/>-0.495
bris-0.477
Token Foundation
Token ID5693
Feature activation+1.17e-01

Pos logit contributions
phalt+0.420
 Antar+0.388
ustomed+0.337
nen+0.321
ּ+0.319
Neg logit contributions
estern-0.253
ostics-0.238
itans-0.233
/>-0.230
bris-0.220
Token's
Token ID338
Feature activation-8.17e-02

Pos logit contributions
phalt+0.096
 Antar+0.087
ustomed+0.075
nen+0.070
ּ+0.070
Neg logit contributions
estern-0.078
ostics-0.075
itans-0.073
/>-0.073
bris-0.070
Token D
Token ID360
Feature activation+4.70e-01

Pos logit contributions
estern+0.053
ostics+0.050
itans+0.049
/>+0.049
bris+0.047
Neg logit contributions
phalt-0.068
 Antar-0.063
ustomed-0.054
nen-0.051
ּ-0.050
Token'
Token ID6
Feature activation+1.76e+00

Pos logit contributions
phalt+0.397
 Antar+0.363
ustomed+0.313
nen+0.295
ּ+0.294
Neg logit contributions
estern-0.299
ostics-0.285
itans-0.280
/>-0.277
bris-0.267
TokenAr
Token ID3163
Feature activation-5.09e-02

Pos logit contributions
phalt+1.474
 Antar+1.345
ustomed+1.156
nen+1.096
ּ+1.081
Neg logit contributions
estern-1.126
ostics-1.065
itans-1.048
/>-1.035
bris-0.999
Tokenros
Token ID4951
Feature activation+8.40e-02

Pos logit contributions
estern+0.032
ostics+0.030
itans+0.029
/>+0.029
bris+0.028
Neg logit contributions
phalt-0.044
 Antar-0.040
ustomed-0.035
nen-0.033
ּ-0.033
Token Research
Token ID4992
Feature activation+5.80e-01

Pos logit contributions
phalt+0.074
 Antar+0.068
ustomed+0.059
nen+0.056
ּ+0.055
Neg logit contributions
estern-0.051
ostics-0.048
itans-0.047
/>-0.047
bris-0.045
Token Centre
Token ID9072
Feature activation-2.66e-01

Pos logit contributions
phalt+0.455
 Antar+0.415
ustomed+0.349
nen+0.328
ּ+0.326
Neg logit contributions
estern-0.406
ostics-0.386
itans-0.381
/>-0.376
bris-0.366
Token.
Token ID13
Feature activation+2.93e-01

Pos logit contributions
estern+0.177
ostics+0.169
itans+0.166
/>+0.164
bris+0.159
Neg logit contributions
phalt-0.218
 Antar-0.199
ustomed-0.170
ּ-0.160
nen-0.160
Token.
Token ID13
Feature activation+1.38e-01

Pos logit contributions
phalt+0.859
 Antar+0.787
ustomed+0.680
nen+0.641
ּ+0.640
Neg logit contributions
estern-0.609
ostics-0.580
itans-0.568
/>-0.562
bris-0.542
Token<|endoftext|>
Token ID50256
Feature activation+1.04e-01

Pos logit contributions
phalt+0.096
 Antar+0.086
ustomed+0.071
nen+0.066
ּ+0.066
Neg logit contributions
estern-0.109
ostics-0.104
itans-0.103
/>-0.102
bris-0.099
TokenThe
Token ID464
Feature activation-1.94e-01

Pos logit contributions
phalt+0.087
 Antar+0.079
ustomed+0.068
nen+0.064
ּ+0.064
Neg logit contributions
estern-0.067
ostics-0.064
itans-0.063
/>-0.062
bris-0.060
Token Wild
Token ID6183
Feature activation-8.04e-01

Pos logit contributions
estern+0.126
ostics+0.120
itans+0.118
/>+0.117
bris+0.113
Neg logit contributions
phalt-0.162
 Antar-0.148
ustomed-0.127
nen-0.120
ּ-0.119
Token B
Token ID347
Feature activation-2.95e-01

Pos logit contributions
estern+0.487
ostics+0.463
itans+0.454
/>+0.449
bris+0.433
Neg logit contributions
phalt-0.705
 Antar-0.647
ustomed-0.560
nen-0.529
ּ-0.528
Tokenunch
Token ID3316
Feature activation+1.93e+00

Pos logit contributions
estern+0.179
ostics+0.170
itans+0.167
/>+0.165
bris+0.159
Neg logit contributions
phalt-0.258
 Antar-0.237
ustomed-0.205
nen-0.193
ּ-0.193
Token would
Token ID561
Feature activation-2.21e-01

Pos logit contributions
phalt+1.699
 Antar+1.562
ustomed+1.350
nen+1.283
ּ+1.269
Neg logit contributions
estern-1.156
ostics-1.106
itans-1.078
/>-1.063
bris-1.030
Token use
Token ID779
Feature activation-2.12e-01

Pos logit contributions
estern+0.138
ostics+0.131
itans+0.128
/>+0.127
bris+0.122
Neg logit contributions
phalt-0.191
 Antar-0.175
ustomed-0.151
nen-0.143
ּ-0.142
Token 239
Token ID32817
Feature activation+6.56e-01

Pos logit contributions
estern+0.130
ostics+0.124
itans+0.122
/>+0.120
bris+0.116
Neg logit contributions
phalt-0.184
 Antar-0.168
ustomed-0.146
nen-0.137
ּ-0.137
Token rifles
Token ID18469
Feature activation-1.03e+00

Pos logit contributions
phalt+0.568
 Antar+0.520
ustomed+0.450
nen+0.425
ּ+0.424
Neg logit contributions
estern-0.406
ostics-0.386
itans-0.379
/>-0.374
bris-0.361
Token,
Token ID11
Feature activation-6.80e-01

Pos logit contributions
estern+0.588
ostics+0.555
itans+0.547
/>+0.541
bris+0.520
Neg logit contributions
phalt-0.937
 Antar-0.863
ustomed-0.751
ּ-0.711
nen-0.709
Token.
Token ID13
Feature activation-2.71e-02

Pos logit contributions
estern+0.201
ostics+0.192
itans+0.190
/>+0.189
bris+0.181
Neg logit contributions
phalt-0.238
 Antar-0.216
ustomed-0.185
ּ-0.173
nen-0.173
Token<|endoftext|>
Token ID50256
Feature activation-5.39e-02

Pos logit contributions
estern+0.021
ostics+0.020
itans+0.020
/>+0.020
bris+0.019
Neg logit contributions
phalt-0.019
 Antar-0.017
ustomed-0.014
nen-0.013
ּ-0.013
TokenThis
Token ID1212
Feature activation-5.64e-01

Pos logit contributions
estern+0.035
ostics+0.033
itans+0.033
/>+0.032
bris+0.031
Neg logit contributions
phalt-0.045
 Antar-0.041
ustomed-0.035
nen-0.033
ּ-0.033
Token article
Token ID2708
Feature activation-5.08e-01

Pos logit contributions
estern+0.315
ostics+0.298
itans+0.292
/>+0.288
bris+0.277
Neg logit contributions
phalt-0.522
 Antar-0.482
ustomed-0.421
nen-0.398
ּ-0.398
Token is
Token ID318
Feature activation+4.56e-02

Pos logit contributions
estern+0.260
ostics+0.244
itans+0.237
/>+0.233
bris+0.225
Neg logit contributions
phalt-0.494
 Antar-0.457
ustomed-0.403
nen-0.383
ּ-0.381
Token about
Token ID546
Feature activation+1.39e+00

Pos logit contributions
phalt+0.038
 Antar+0.035
ustomed+0.030
nen+0.028
ּ+0.028
Neg logit contributions
estern-0.029
ostics-0.028
itans-0.027
/>-0.027
bris-0.026
Token the
Token ID262
Feature activation-2.43e-01

Pos logit contributions
phalt+1.150
 Antar+1.053
ustomed+0.901
nen+0.847
ּ+0.847
Neg logit contributions
estern-0.901
ostics-0.859
itans-0.847
/>-0.835
bris-0.809
Token payment
Token ID6074
Feature activation+3.63e-02

Pos logit contributions
estern+0.153
ostics+0.146
itans+0.143
/>+0.142
bris+0.137
Neg logit contributions
phalt-0.207
 Antar-0.189
ustomed-0.164
ּ-0.154
nen-0.154
Token medium
Token ID7090
Feature activation+6.91e-01

Pos logit contributions
phalt+0.034
 Antar+0.031
ustomed+0.027
nen+0.026
ּ+0.026
Neg logit contributions
estern-0.020
ostics-0.019
itans-0.019
/>-0.019
bris-0.018
Token.
Token ID13
Feature activation-2.31e-01

Pos logit contributions
phalt+0.567
 Antar+0.515
ustomed+0.443
nen+0.415
ּ+0.414
Neg logit contributions
estern-0.458
ostics-0.437
itans-0.431
/>-0.426
bris-0.412
Token For
Token ID1114
Feature activation+5.16e-01

Pos logit contributions
estern+0.168
ostics+0.161
itans+0.159
/>+0.157
bris+0.152
Neg logit contributions
phalt-0.175
 Antar-0.158
ustomed-0.133
nen-0.124
ּ-0.124
Token Atlantic
Token ID10596
Feature activation+3.36e-01

Pos logit contributions
phalt+0.161
 Antar+0.147
ustomed+0.123
nen+0.115
ּ+0.115
Neg logit contributions
estern-0.153
ostics-0.146
itans-0.144
/>-0.143
bris-0.139
Token and
Token ID290
Feature activation+3.35e-03

Pos logit contributions
phalt+0.306
 Antar+0.281
ustomed+0.245
nen+0.232
ּ+0.232
Neg logit contributions
estern-0.193
ostics-0.182
itans-0.179
/>-0.177
bris-0.169
Token North
Token ID2258
Feature activation+5.98e-02

Pos logit contributions
phalt+0.003
 Antar+0.003
ustomed+0.002
nen+0.002
ּ+0.002
Neg logit contributions
estern-0.002
ostics-0.002
itans-0.002
/>-0.002
bris-0.002
Token Pacific
Token ID8211
Feature activation+7.46e-01

Pos logit contributions
phalt+0.052
 Antar+0.048
ustomed+0.042
nen+0.039
ּ+0.039
Neg logit contributions
estern-0.036
ostics-0.034
itans-0.034
/>-0.033
bris-0.032
Token O
Token ID440
Feature activation+8.06e-01

Pos logit contributions
phalt+0.567
 Antar+0.512
ustomed+0.432
nen+0.403
ּ+0.402
Neg logit contributions
estern-0.540
ostics-0.518
itans-0.509
/>-0.505
bris-0.489
Tokenceans
Token ID19961
Feature activation+1.79e+00

Pos logit contributions
phalt+0.653
 Antar+0.594
ustomed+0.508
nen+0.477
ּ+0.475
Neg logit contributions
estern-0.542
ostics-0.518
itans-0.509
/>-0.503
bris-0.488
Token,
Token ID11
Feature activation+4.15e-02

Pos logit contributions
phalt+1.508
 Antar+1.382
ustomed+1.188
ּ+1.122
nen+1.120
Neg logit contributions
estern-1.137
ostics-1.089
itans-1.067
/>-1.055
bris-1.019
Token
Token ID447
Feature activation+2.97e-01

Pos logit contributions
phalt+0.041
 Antar+0.038
ustomed+0.034
ּ+0.032
nen+0.032
Neg logit contributions
estern-0.020
ostics-0.019
itans-0.019
/>-0.018
bris-0.018
Token
Token ID251
Feature activation-4.68e-03

Pos logit contributions
phalt+0.276
 Antar+0.253
ustomed+0.221
ּ+0.211
nen+0.209
Neg logit contributions
estern-0.167
ostics-0.156
itans-0.154
/>-0.150
bris-0.145
Token is
Token ID318
Feature activation-9.10e-04

Pos logit contributions
estern+0.004
ostics+0.003
itans+0.003
/>+0.003
bris+0.003
Neg logit contributions
phalt-0.003
 Antar-0.003
ustomed-0.003
nen-0.002
ּ-0.002
Token now
Token ID783
Feature activation-1.04e-01

Pos logit contributions
estern+0.001
ostics+0.001
itans+0.001
/>+0.001
bris+0.001
Neg logit contributions
phalt-0.001
 Antar-0.001
ustomed-0.001
nen-0.001
ּ-0.001
Token mess
Token ID2085
Feature activation-3.07e-01

Pos logit contributions
phalt+0.089
 Antar+0.082
ustomed+0.071
nen+0.067
ּ+0.067
Neg logit contributions
estern-0.061
ostics-0.058
itans-0.057
/>-0.056
bris-0.054
Token seriously
Token ID6411
Feature activation-8.19e-01

Pos logit contributions
estern+0.143
ostics+0.133
itans+0.130
/>+0.128
bris+0.121
Neg logit contributions
phalt-0.313
 Antar-0.290
ustomed-0.259
nen-0.245
ּ-0.245
Token
Token ID198
Feature activation-4.25e-02

Pos logit contributions
estern+0.565
ostics+0.540
itans+0.531
/>+0.527
bris+0.509
Neg logit contributions
phalt-0.650
 Antar-0.589
ustomed-0.503
nen-0.470
ּ-0.470
Token
Token ID198
Feature activation+1.30e-02

Pos logit contributions
estern+0.031
ostics+0.030
itans+0.030
/>+0.029
bris+0.029
Neg logit contributions
phalt-0.032
 Antar-0.029
ustomed-0.024
nen-0.022
ּ-0.022
TokenArticle
Token ID14906
Feature activation-3.51e-02

Pos logit contributions
phalt+0.009
 Antar+0.008
ustomed+0.006
nen+0.006
ּ+0.006
Neg logit contributions
estern-0.011
ostics-0.010
itans-0.010
/>-0.010
bris-0.010
Token Continued
Token ID22168
Feature activation+1.54e+00

Pos logit contributions
estern+0.026
ostics+0.025
itans+0.025
/>+0.024
bris+0.024
Neg logit contributions
phalt-0.026
 Antar-0.023
ustomed-0.020
nen-0.018
ּ-0.018
Token Below
Token ID10383
Feature activation+2.08e+00

Pos logit contributions
phalt+1.157
 Antar+1.052
ustomed+0.884
nen+0.833
ּ+0.833
Neg logit contributions
estern-1.125
ostics-1.074
itans-1.057
/>-1.031
bris-1.020
Token
Token ID198
Feature activation+1.75e-01

Pos logit contributions
phalt+1.514
 Antar+1.355
ustomed+1.136
nen+1.068
ּ+1.057
Neg logit contributions
estern-1.573
ostics-1.504
itans-1.482
/>-1.455
bris-1.433
Token
Token ID198
Feature activation+2.58e-01

Pos logit contributions
phalt+0.131
 Antar+0.118
ustomed+0.100
nen+0.093
ּ+0.093
Neg logit contributions
estern-0.129
ostics-0.123
itans-0.121
/>-0.120
bris-0.117
Token
Token ID447
Feature activation+1.03e+00

Pos logit contributions
phalt+0.217
 Antar+0.198
ustomed+0.171
nen+0.161
ּ+0.161
Neg logit contributions
estern-0.165
ostics-0.157
itans-0.154
/>-0.152
bris-0.147
Token
Token ID250
Feature activation+6.78e-01

Pos logit contributions
phalt+0.853
 Antar+0.777
ustomed+0.667
ּ+0.630
nen+0.626
Neg logit contributions
estern-0.678
ostics-0.645
itans-0.635
/>-0.624
bris-0.605
Token
Token ID198
Feature activation-8.69e-01

Pos logit contributions
estern+0.585
ostics+0.559
itans+0.549
/>+0.545
bris+0.527
Neg logit contributions
phalt-0.696
 Antar-0.633
ustomed-0.541
nen-0.508
ּ-0.507
Token
Token ID198
Feature activation-9.14e-01

Pos logit contributions
estern+0.625
ostics+0.599
itans+0.590
/>+0.587
bris+0.567
Neg logit contributions
phalt-0.665
 Antar-0.605
ustomed-0.508
ּ-0.473
nen-0.472
TokenUh
Token ID34653
Feature activation-4.63e-01

Pos logit contributions
estern+0.553
ostics+0.527
itans+0.517
/>+0.512
bris+0.493
Neg logit contributions
phalt-0.801
 Antar-0.737
ustomed-0.637
ּ-0.601
nen-0.600
Token oh
Token ID11752
Feature activation-5.56e-01

Pos logit contributions
estern+0.276
ostics+0.262
itans+0.257
/>+0.254
bris+0.245
Neg logit contributions
phalt-0.410
 Antar-0.377
ustomed-0.327
nen-0.309
ּ-0.309
Token,
Token ID11
Feature activation-2.14e-01

Pos logit contributions
estern+0.375
ostics+0.358
itans+0.352
/>+0.348
bris+0.337
Neg logit contributions
phalt-0.449
 Antar-0.409
ustomed-0.349
nen-0.328
ּ-0.327
Token that
Token ID326
Feature activation+2.09e-01

Pos logit contributions
estern+0.129
ostics+0.122
itans+0.120
/>+0.118
bris+0.114
Neg logit contributions
phalt-0.189
 Antar-0.174
ustomed-0.150
nen-0.142
ּ-0.141
Token's
Token ID338
Feature activation-2.43e-01

Pos logit contributions
phalt+0.173
 Antar+0.159
ustomed+0.135
nen+0.127
ּ+0.127
Neg logit contributions
estern-0.138
ostics-0.131
itans-0.129
/>-0.127
bris-0.123
Token no
Token ID645
Feature activation+3.05e-01

Pos logit contributions
estern+0.143
ostics+0.135
itans+0.133
/>+0.131
bris+0.126
Neg logit contributions
phalt-0.218
 Antar-0.200
ustomed-0.174
nen-0.165
ּ-0.164
Token good
Token ID922
Feature activation+4.25e-01

Pos logit contributions
phalt+0.253
 Antar+0.231
ustomed+0.197
nen+0.186
ּ+0.185
Neg logit contributions
estern-0.200
ostics-0.190
itans-0.187
/>-0.185
bris-0.179
Token!
Token ID0
Feature activation+6.21e-01

Pos logit contributions
phalt+0.332
 Antar+0.303
ustomed+0.255
nen+0.240
ּ+0.239
Neg logit contributions
estern-0.299
ostics-0.284
itans-0.280
/>-0.277
bris-0.269
Token The
Token ID383
Feature activation-1.12e-01

Pos logit contributions
phalt+0.493
 Antar+0.451
ustomed+0.381
nen+0.358
ּ+0.356
Neg logit contributions
estern-0.429
ostics-0.407
itans-0.401
/>-0.396
bris-0.385
Token15
Token ID1314
Feature activation+1.99e-02

Pos logit contributions
estern+0.184
ostics+0.175
itans+0.172
/>+0.170
bris+0.164
Neg logit contributions
phalt-0.254
 Antar-0.233
ustomed-0.201
nen-0.190
ּ-0.189
Tokenth
Token ID400
Feature activation+8.20e-01

Pos logit contributions
phalt+0.018
 Antar+0.017
ustomed+0.015
nen+0.014
ּ+0.014
Neg logit contributions
estern-0.011
ostics-0.011
itans-0.010
/>-0.010
bris-0.010
Token among
Token ID1871
Feature activation-1.20e+00

Pos logit contributions
phalt+0.625
 Antar+0.567
ustomed+0.477
ּ+0.445
nen+0.444
Neg logit contributions
estern-0.591
ostics-0.566
itans-0.554
/>-0.550
bris-0.538
Token running
Token ID2491
Feature activation-6.92e-02

Pos logit contributions
estern+0.818
ostics+0.783
itans+0.771
/>+0.762
bris+0.737
Neg logit contributions
phalt-0.963
 Antar-0.875
ustomed-0.746
nen-0.699
ּ-0.698
Token backs
Token ID12983
Feature activation+3.99e-01

Pos logit contributions
estern+0.027
ostics+0.024
itans+0.023
/>+0.023
bris+0.022
Neg logit contributions
phalt-0.076
 Antar-0.071
ustomed-0.064
nen-0.061
ּ-0.061
Token)
Token ID8
Feature activation-1.64e-01

Pos logit contributions
phalt+0.326
 Antar+0.297
ustomed+0.255
nen+0.240
ּ+0.239
Neg logit contributions
estern-0.264
ostics-0.254
itans-0.247
/>-0.245
bris-0.239
Token
Token ID198
Feature activation-2.38e-01

Pos logit contributions
estern+0.121
ostics+0.116
itans+0.114
/>+0.113
bris+0.110
Neg logit contributions
phalt-0.122
 Antar-0.110
ustomed-0.093
nen-0.086
ּ-0.086
Token
Token ID198
Feature activation-3.70e-01

Pos logit contributions
estern+0.177
ostics+0.169
itans+0.166
/>+0.164
bris+0.160
Neg logit contributions
phalt-0.176
 Antar-0.158
ustomed-0.133
nen-0.124
ּ-0.124
TokenFinding
Token ID36276
Feature activation-6.48e-01

Pos logit contributions
estern+0.248
ostics+0.237
itans+0.233
/>+0.230
bris+0.223
Neg logit contributions
phalt-0.301
 Antar-0.274
ustomed-0.234
nen-0.220
ּ-0.220
Token an
Token ID281
Feature activation+1.11e-01

Pos logit contributions
estern+0.389
ostics+0.369
itans+0.362
/>+0.357
bris+0.344
Neg logit contributions
phalt-0.572
 Antar-0.526
ustomed-0.456
nen-0.431
ּ-0.430
Token under
Token ID739
Feature activation-2.93e-02

Pos logit contributions
phalt+0.100
 Antar+0.092
ustomed+0.080
ּ+0.076
nen+0.075
Neg logit contributions
estern-0.065
ostics-0.062
itans-0.060
/>-0.060
bris-0.058
Token you
Token ID345
Feature activation+1.41e-01

Pos logit contributions
estern+0.339
ostics+0.324
itans+0.319
/>+0.316
bris+0.304
Neg logit contributions
phalt-0.445
 Antar-0.406
ustomed-0.349
nen-0.328
ּ-0.327
Token aren
Token ID3588
Feature activation+3.69e-02

Pos logit contributions
phalt+0.146
 Antar+0.136
ustomed+0.120
ּ+0.116
nen+0.115
Neg logit contributions
estern-0.063
ostics-0.058
itans-0.057
/>-0.056
bris-0.053
Token
Token ID447
Feature activation-3.87e-01

Pos logit contributions
phalt+0.035
 Antar+0.032
ustomed+0.028
nen+0.027
ּ+0.027
Neg logit contributions
estern-0.020
ostics-0.019
itans-0.018
/>-0.018
bris-0.017
Token
Token ID247
Feature activation-3.82e-02

Pos logit contributions
estern+0.247
ostics+0.236
itans+0.233
/>+0.232
bris+0.223
Neg logit contributions
phalt-0.326
 Antar-0.300
ustomed-0.256
nen-0.241
ּ-0.238
Tokent
Token ID83
Feature activation-1.10e-01

Pos logit contributions
estern+0.024
ostics+0.023
itans+0.023
/>+0.022
bris+0.022
Neg logit contributions
phalt-0.032
 Antar-0.029
ustomed-0.026
nen-0.024
ּ-0.024
Token familiar
Token ID5385
Feature activation+2.61e-01

Pos logit contributions
estern+0.056
ostics+0.053
itans+0.052
/>+0.051
bris+0.049
Neg logit contributions
phalt-0.108
 Antar-0.100
ustomed-0.088
nen-0.084
ּ-0.083
Token,
Token ID11
Feature activation+8.34e-02

Pos logit contributions
phalt+0.240
 Antar+0.221
ustomed+0.193
ּ+0.183
nen+0.183
Neg logit contributions
estern-0.147
ostics-0.139
itans-0.136
/>-0.135
bris-0.130
Token the
Token ID262
Feature activation+2.43e-01

Pos logit contributions
phalt+0.068
 Antar+0.062
ustomed+0.054
nen+0.050
ּ+0.050
Neg logit contributions
estern-0.055
ostics-0.053
itans-0.052
/>-0.051
bris-0.050
Token Wiz
Token ID41122
Feature activation+6.61e-02

Pos logit contributions
phalt+0.221
 Antar+0.203
ustomed+0.177
nen+0.168
ּ+0.167
Neg logit contributions
estern-0.140
ostics-0.132
itans-0.129
/>-0.128
bris-0.123
TokenKids
Token ID40229
Feature activation+2.63e-01

Pos logit contributions
phalt+0.058
 Antar+0.053
ustomed+0.046
nen+0.044
ּ+0.044
Neg logit contributions
estern-0.040
ostics-0.038
itans-0.037
/>-0.037
bris-0.035
Token Open
Token ID4946
Feature activation+5.57e-02

Pos logit contributions
phalt+0.192
 Antar+0.173
ustomed+0.144
ּ+0.135
nen+0.134
Neg logit contributions
estern-0.198
ostics-0.190
itans-0.187
/>-0.185
bris-0.181
Token 4
Token ID604
Feature activation-9.14e-01

Pos logit contributions
estern+0.244
ostics+0.229
itans+0.223
/>+0.219
bris+0.210
Neg logit contributions
phalt-0.498
 Antar-0.463
ustomed-0.408
nen-0.389
ּ-0.388
Token*
Token ID9
Feature activation-5.20e-01

Pos logit contributions
estern+0.322
ostics+0.295
itans+0.285
/>+0.281
bris+0.260
Neg logit contributions
phalt-1.033
 Antar-0.969
ustomed-0.869
nen-0.831
ּ-0.831
Token UT
Token ID19255
Feature activation+8.08e-01

Pos logit contributions
estern+0.333
ostics+0.318
itans+0.312
/>+0.310
bris+0.298
Neg logit contributions
phalt-0.437
 Antar-0.399
ustomed-0.344
ּ-0.323
nen-0.323
Token (
Token ID357
Feature activation-8.55e-02

Pos logit contributions
phalt+0.658
 Antar+0.600
ustomed+0.513
nen+0.481
ּ+0.481
Neg logit contributions
estern-0.540
ostics-0.515
itans-0.506
/>-0.501
bris-0.485
Tokencommit
Token ID41509
Feature activation+8.20e-01

Pos logit contributions
estern+0.055
ostics+0.052
itans+0.051
/>+0.051
bris+0.049
Neg logit contributions
phalt-0.072
 Antar-0.065
ustomed-0.056
nen-0.053
ּ-0.053
Token)
Token ID8
Feature activation-1.96e-01

Pos logit contributions
phalt+0.663
 Antar+0.604
ustomed+0.515
nen+0.487
ּ+0.484
Neg logit contributions
estern-0.549
ostics-0.525
itans-0.514
/>-0.505
bris-0.495
Token Levi
Token ID20196
Feature activation+5.11e-01

Pos logit contributions
estern+0.147
ostics+0.141
itans+0.139
/>+0.138
bris+0.134
Neg logit contributions
phalt-0.144
 Antar-0.130
ustomed-0.109
ּ-0.101
nen-0.101
Token Jones
Token ID5437
Feature activation+2.90e-01

Pos logit contributions
phalt+0.403
 Antar+0.367
ustomed+0.312
nen+0.292
ּ+0.290
Neg logit contributions
estern-0.354
ostics-0.338
itans-0.332
/>-0.329
bris-0.320
Token LB
Token ID22199
Feature activation-4.77e-02

Pos logit contributions
phalt+0.238
 Antar+0.217
ustomed+0.186
nen+0.175
ּ+0.174
Neg logit contributions
estern-0.192
ostics-0.183
itans-0.180
/>-0.178
bris-0.172
Token 6
Token ID718
Feature activation+2.13e-02

Pos logit contributions
estern+0.021
ostics+0.019
itans+0.019
/>+0.018
bris+0.018
Neg logit contributions
phalt-0.050
 Antar-0.047
ustomed-0.041
nen-0.040
ּ-0.040
Token'
Token ID6
Feature activation+8.49e-01

Pos logit contributions
phalt+0.020
 Antar+0.019
ustomed+0.017
ּ+0.016
nen+0.016
Neg logit contributions
estern-0.011
ostics-0.011
itans-0.010
/>-0.010
bris-0.010
Token
Token ID447
Feature activation+1.27e+00

Pos logit contributions
phalt+0.005
 Antar+0.005
ustomed+0.004
nen+0.004
ּ+0.004
Neg logit contributions
estern-0.004
ostics-0.004
itans-0.004
/>-0.004
bris-0.003
Token
Token ID250
Feature activation+3.35e-01

Pos logit contributions
phalt+1.156
 Antar+1.061
ustomed+0.919
ּ+0.878
nen+0.874
Neg logit contributions
estern-0.733
ostics-0.695
itans-0.684
/>-0.666
bris-0.649
TokenHaw
Token ID33055
Feature activation-4.05e-01

Pos logit contributions
phalt+0.274
 Antar+0.250
ustomed+0.214
nen+0.201
ּ+0.201
Neg logit contributions
estern-0.222
ostics-0.212
itans-0.208
/>-0.206
bris-0.200
Tokenaii
Token ID42648
Feature activation+5.41e-01

Pos logit contributions
estern+0.191
ostics+0.178
itans+0.174
/>+0.171
bris+0.163
Neg logit contributions
phalt-0.409
 Antar-0.380
ustomed-0.336
nen-0.321
ּ-0.320
Token has
Token ID468
Feature activation-1.63e-01

Pos logit contributions
phalt+0.414
 Antar+0.375
ustomed+0.316
nen+0.295
ּ+0.294
Neg logit contributions
estern-0.390
ostics-0.373
itans-0.367
/>-0.363
bris-0.353
Token several
Token ID1811
Feature activation-2.15e-01

Pos logit contributions
estern+0.097
ostics+0.092
itans+0.090
/>+0.089
bris+0.086
Neg logit contributions
phalt-0.145
 Antar-0.134
ustomed-0.116
nen-0.110
ּ-0.109
Token good
Token ID922
Feature activation-2.77e-01

Pos logit contributions
estern+0.122
ostics+0.115
itans+0.113
/>+0.111
bris+0.107
Neg logit contributions
phalt-0.198
 Antar-0.182
ustomed-0.159
nen-0.151
ּ-0.151
Token legislators
Token ID19964
Feature activation-6.54e-01

Pos logit contributions
estern+0.146
ostics+0.137
itans+0.134
/>+0.132
bris+0.127
Neg logit contributions
phalt-0.266
 Antar-0.246
ustomed-0.215
nen-0.205
ּ-0.205
Token who
Token ID508
Feature activation-7.80e-02

Pos logit contributions
estern+0.368
ostics+0.349
itans+0.341
/>+0.339
bris+0.324
Neg logit contributions
phalt-0.601
 Antar-0.553
ustomed-0.483
ּ-0.457
nen-0.456
Token understand
Token ID1833
Feature activation-2.01e-01

Pos logit contributions
estern+0.041
ostics+0.038
itans+0.038
/>+0.037
bris+0.036
Neg logit contributions
phalt-0.075
 Antar-0.069
ustomed-0.061
nen-0.058
ּ-0.058
Token this
Token ID428
Feature activation+8.16e-01

Pos logit contributions
estern+0.120
ostics+0.114
itans+0.112
/>+0.110
bris+0.106
Neg logit contributions
phalt-0.178
 Antar-0.164
ustomed-0.142
ּ-0.134
nen-0.134
Token bear
Token ID6842
Feature activation+9.76e-01

Pos logit contributions
phalt+0.058
 Antar+0.054
ustomed+0.046
nen+0.044
ּ+0.044
Neg logit contributions
estern-0.041
ostics-0.039
itans-0.038
/>-0.038
bris-0.036
Token-
Token ID12
Feature activation+2.83e-01

Pos logit contributions
phalt+0.876
 Antar+0.808
ustomed+0.699
nen+0.664
ּ+0.660
Neg logit contributions
estern-0.570
ostics-0.541
itans-0.530
/>-0.520
bris-0.503
Tokenfeeding
Token ID22824
Feature activation-1.93e-01

Pos logit contributions
phalt+0.243
 Antar+0.223
ustomed+0.192
nen+0.181
ּ+0.181
Neg logit contributions
estern-0.177
ostics-0.168
itans-0.165
/>-0.163
bris-0.158
Token,
Token ID11
Feature activation-5.17e-02

Pos logit contributions
estern+0.118
ostics+0.112
itans+0.110
/>+0.109
bris+0.105
Neg logit contributions
phalt-0.168
 Antar-0.154
ustomed-0.133
nen-0.126
ּ-0.126
Token David
Token ID3271
Feature activation-7.79e-01

Pos logit contributions
estern+0.034
ostics+0.032
itans+0.031
/>+0.031
bris+0.030
Neg logit contributions
phalt-0.043
 Antar-0.040
ustomed-0.034
nen-0.032
ּ-0.032
Token killed
Token ID2923
Feature activation-6.50e-01

Pos logit contributions
estern+0.436
ostics+0.413
itans+0.403
/>+0.397
bris+0.382
Neg logit contributions
phalt-0.720
 Antar-0.665
ustomed-0.579
nen-0.550
ּ-0.549
Token it
Token ID340
Feature activation-3.34e-01

Pos logit contributions
estern+0.380
ostics+0.361
itans+0.353
/>+0.348
bris+0.336
Neg logit contributions
phalt-0.583
 Antar-0.538
ustomed-0.466
nen-0.442
ּ-0.441
Token.
Token ID13
Feature activation-6.21e-01

Pos logit contributions
estern+0.219
ostics+0.209
itans+0.205
/>+0.203
bris+0.196
Neg logit contributions
phalt-0.276
 Antar-0.252
ustomed-0.216
nen-0.203
ּ-0.202
Token Thank
Token ID6952
Feature activation-4.09e-01

Pos logit contributions
estern+0.420
ostics+0.401
itans+0.394
/>+0.390
bris+0.378
Neg logit contributions
phalt-0.501
 Antar-0.456
ustomed-0.389
nen-0.365
ּ-0.365
Token you
Token ID345
Feature activation-6.30e-01

Pos logit contributions
estern+0.260
ostics+0.248
itans+0.243
/>+0.241
bris+0.232
Neg logit contributions
phalt-0.347
 Antar-0.318
ustomed-0.274
nen-0.257
ּ-0.257
Token,
Token ID11
Feature activation-6.16e-01

Pos logit contributions
estern+0.395
ostics+0.376
itans+0.369
/>+0.365
bris+0.353
Neg logit contributions
phalt-0.539
 Antar-0.493
ustomed-0.426
nen-0.401
ּ-0.400
Token
Token ID198
Feature activation-2.69e-01

Pos logit contributions
estern+0.092
ostics+0.088
itans+0.087
/>+0.086
bris+0.084
Neg logit contributions
phalt-0.095
 Antar-0.086
ustomed-0.072
nen-0.067
ּ-0.067
TokenChina
Token ID14581
Feature activation-5.53e-01

Pos logit contributions
estern+0.173
ostics+0.165
itans+0.162
/>+0.161
bris+0.155
Neg logit contributions
phalt-0.226
 Antar-0.206
ustomed-0.177
nen-0.167
ּ-0.166
Token has
Token ID468
Feature activation+9.78e-02

Pos logit contributions
estern+0.320
ostics+0.303
itans+0.297
/>+0.293
bris+0.282
Neg logit contributions
phalt-0.501
 Antar-0.461
ustomed-0.401
nen-0.380
ּ-0.379
Token about
Token ID546
Feature activation+4.16e-02

Pos logit contributions
phalt+0.090
 Antar+0.083
ustomed+0.072
nen+0.068
ּ+0.068
Neg logit contributions
estern-0.056
ostics-0.053
itans-0.052
/>-0.050
bris-0.049
Token 12
Token ID1105
Feature activation-6.44e-01

Pos logit contributions
phalt+0.041
 Antar+0.038
ustomed+0.033
nen+0.032
ּ+0.031
Neg logit contributions
estern-0.021
ostics-0.020
itans-0.019
/>-0.019
bris-0.018
Token nuclear
Token ID4523
Feature activation-1.06e+00

Pos logit contributions
estern+0.330
ostics+0.311
itans+0.303
/>+0.298
bris+0.286
Neg logit contributions
phalt-0.626
 Antar-0.579
ustomed-0.508
nen-0.485
ּ-0.483
Token-
Token ID12
Feature activation+1.98e-01

Pos logit contributions
estern+0.476
ostics+0.443
itans+0.431
/>+0.423
bris+0.404
Neg logit contributions
phalt-1.099
 Antar-1.021
ustomed-0.908
nen-0.866
ּ-0.865
Tokenpowered
Token ID12293
Feature activation-1.64e-01

Pos logit contributions
phalt+0.169
 Antar+0.152
ustomed+0.135
nen+0.126
ּ+0.125
Neg logit contributions
estern-0.123
ostics-0.117
itans-0.114
/>-0.112
bris-0.110
Token submarines
Token ID34031
Feature activation-4.48e-02

Pos logit contributions
estern+0.092
ostics+0.087
itans+0.085
/>+0.083
bris+0.080
Neg logit contributions
phalt-0.152
 Antar-0.140
ustomed-0.122
nen-0.116
ּ-0.115
Token (
Token ID357
Feature activation-3.53e-01

Pos logit contributions
estern+0.028
ostics+0.026
itans+0.026
/>+0.025
bris+0.025
Neg logit contributions
phalt-0.039
 Antar-0.035
ustomed-0.031
nen-0.029
ּ-0.029
Token6
Token ID21
Feature activation-3.17e-01

Pos logit contributions
estern+0.230
ostics+0.219
itans+0.216
/>+0.213
bris+0.206
Neg logit contributions
phalt-0.293
 Antar-0.268
ustomed-0.230
nen-0.216
ּ-0.216
Token 2
Token ID362
Feature activation-1.33e+00

Pos logit contributions
estern+0.434
ostics+0.413
itans+0.405
/>+0.404
bris+0.385
Neg logit contributions
phalt-0.666
 Antar-0.613
ustomed-0.533
ּ-0.505
nen-0.504
Token 3
Token ID513
Feature activation-1.23e+00

Pos logit contributions
estern+0.677
ostics+0.634
itans+0.619
/>+0.608
bris+0.584
Neg logit contributions
phalt-1.303
 Antar-1.205
ustomed-1.062
nen-1.010
ּ-1.006
Token 4
Token ID604
Feature activation-1.69e+00

Pos logit contributions
estern+0.615
ostics+0.578
itans+0.565
/>+0.557
bris+0.532
Neg logit contributions
phalt-1.206
 Antar-1.117
ustomed-0.985
nen-0.937
ּ-0.936
Token 5
Token ID642
Feature activation-1.08e+00

Pos logit contributions
estern+0.736
ostics+0.685
itans+0.667
/>+0.656
bris+0.622
Neg logit contributions
phalt-1.765
 Antar-1.644
ustomed-1.462
nen-1.396
ּ-1.394
Token 6
Token ID718
Feature activation-1.21e+00

Pos logit contributions
estern+0.457
ostics+0.424
itans+0.412
/>+0.405
bris+0.384
Neg logit contributions
phalt-1.143
 Antar-1.065
ustomed-0.949
nen-0.907
ּ-0.906
Token 7
Token ID767
Feature activation-1.05e+00

Pos logit contributions
estern+0.493
ostics+0.455
itans+0.442
/>+0.432
bris+0.410
Neg logit contributions
phalt-1.305
 Antar-1.217
ustomed-1.087
nen-1.038
ּ-1.036
Token 8
Token ID807
Feature activation-8.50e-01

Pos logit contributions
estern+0.476
ostics+0.447
itans+0.435
/>+0.433
bris+0.405
Neg logit contributions
phalt-1.080
 Antar-1.002
ustomed-0.888
nen-0.854
ּ-0.849
Token void
Token ID7951
Feature activation+3.26e-01

Pos logit contributions
estern+0.398
ostics+0.371
itans+0.362
/>+0.356
bris+0.340
Neg logit contributions
phalt-0.863
 Antar-0.802
ustomed-0.711
nen-0.676
ּ-0.675
Token vert
Token ID9421
Feature activation-9.65e-02

Pos logit contributions
phalt+0.243
 Antar+0.217
ustomed+0.183
nen+0.172
ּ+0.168
Neg logit contributions
estern-0.241
ostics-0.232
itans-0.226
/>-0.224
bris-0.219
Token (
Token ID357
Feature activation-4.19e-02

Pos logit contributions
estern+0.052
ostics+0.050
itans+0.049
/>+0.048
bris+0.046
Neg logit contributions
phalt-0.091
 Antar-0.084
ustomed-0.073
nen-0.070
ּ-0.069
Token in
Token ID287
Feature activation+7.67e-01

Pos logit contributions
estern+0.026
ostics+0.025
itans+0.024
/>+0.024
bris+0.023
Neg logit contributions
phalt-0.036
 Antar-0.033
ustomed-0.029
nen-0.027
ּ-0.027
Token-
Token ID12
Feature activation-1.65e-01

Pos logit contributions
phalt+0.006
 Antar+0.005
ustomed+0.005
ּ+0.004
nen+0.004
Neg logit contributions
estern-0.004
ostics-0.004
itans-0.004
/>-0.004
bris-0.003
Tokenbased
Token ID3106
Feature activation+1.23e-01

Pos logit contributions
estern+0.132
ostics+0.127
itans+0.126
/>+0.125
bris+0.121
Neg logit contributions
phalt-0.112
 Antar-0.100
ustomed-0.082
nen-0.076
ּ-0.076
Token artist
Token ID6802
Feature activation-3.96e-01

Pos logit contributions
phalt+0.100
 Antar+0.092
ustomed+0.078
nen+0.073
ּ+0.073
Neg logit contributions
estern-0.082
ostics-0.078
itans-0.077
/>-0.076
bris-0.074
Token Clark
Token ID11264
Feature activation-2.02e-02

Pos logit contributions
estern+0.291
ostics+0.279
itans+0.276
/>+0.273
bris+0.265
Neg logit contributions
phalt-0.295
 Antar-0.266
ustomed-0.225
ּ-0.209
nen-0.209
Token S
Token ID311
Feature activation-4.00e-01

Pos logit contributions
estern+0.014
ostics+0.013
itans+0.013
/>+0.013
bris+0.012
Neg logit contributions
phalt-0.016
 Antar-0.015
ustomed-0.013
ּ-0.012
nen-0.012
Tokenore
Token ID382
Feature activation-1.42e+00

Pos logit contributions
estern+0.246
ostics+0.233
itans+0.229
/>+0.226
bris+0.219
Neg logit contributions
phalt-0.348
 Antar-0.319
ustomed-0.276
nen-0.260
ּ-0.260
Tokenns
Token ID5907
Feature activation-5.75e-01

Pos logit contributions
estern+0.631
ostics+0.590
itans+0.574
/>+0.561
bris+0.540
Neg logit contributions
phalt-1.466
 Antar-1.370
ustomed-1.216
ּ-1.157
nen-1.148
Tokenen
Token ID268
Feature activation-3.07e-01

Pos logit contributions
estern+0.377
ostics+0.360
itans+0.354
/>+0.352
bris+0.340
Neg logit contributions
phalt-0.475
 Antar-0.436
ustomed-0.372
ּ-0.350
nen-0.348
Token,
Token ID11
Feature activation+5.21e-02

Pos logit contributions
estern+0.212
ostics+0.204
itans+0.201
/>+0.199
bris+0.193
Neg logit contributions
phalt-0.241
 Antar-0.220
ustomed-0.188
ּ-0.175
nen-0.174
Token and
Token ID290
Feature activation+2.24e-01

Pos logit contributions
phalt+0.049
 Antar+0.045
ustomed+0.040
nen+0.038
ּ+0.038
Neg logit contributions
estern-0.028
ostics-0.027
itans-0.026
/>-0.026
bris-0.025
Token called
Token ID1444
Feature activation-4.66e-02

Pos logit contributions
phalt+0.206
 Antar+0.189
ustomed+0.165
nen+0.157
ּ+0.156
Neg logit contributions
estern-0.127
ostics-0.120
itans-0.118
/>-0.116
bris-0.112
Token institute
Token ID24224
Feature activation-1.69e-01

Pos logit contributions
estern+0.048
ostics+0.046
itans+0.045
/>+0.044
bris+0.043
Neg logit contributions
phalt-0.066
 Antar-0.060
ustomed-0.052
nen-0.049
ּ-0.049
Token in
Token ID287
Feature activation-2.48e-01

Pos logit contributions
estern+0.108
ostics+0.103
itans+0.101
/>+0.101
bris+0.097
Neg logit contributions
phalt-0.141
 Antar-0.128
ustomed-0.111
nen-0.105
ּ-0.104
Token Film
Token ID13741
Feature activation-1.88e-01

Pos logit contributions
estern+0.168
ostics+0.161
itans+0.158
/>+0.157
bris+0.152
Neg logit contributions
phalt-0.200
 Antar-0.182
ustomed-0.155
nen-0.145
ּ-0.145
Tokencity
Token ID19205
Feature activation-4.33e-01

Pos logit contributions
estern+0.127
ostics+0.121
itans+0.119
/>+0.118
bris+0.114
Neg logit contributions
phalt-0.152
 Antar-0.138
ustomed-0.118
nen-0.111
ּ-0.110
Token,
Token ID11
Feature activation-6.50e-02

Pos logit contributions
estern+0.279
ostics+0.267
itans+0.262
/>+0.260
bris+0.251
Neg logit contributions
phalt-0.363
 Antar-0.330
ustomed-0.285
ּ-0.267
nen-0.267
Token on
Token ID319
Feature activation-3.46e-01

Pos logit contributions
estern+0.040
ostics+0.038
itans+0.037
/>+0.037
bris+0.036
Neg logit contributions
phalt-0.056
 Antar-0.052
ustomed-0.045
nen-0.042
ּ-0.042
Token the
Token ID262
Feature activation-6.51e-02

Pos logit contributions
estern+0.213
ostics+0.202
itans+0.199
/>+0.196
bris+0.189
Neg logit contributions
phalt-0.300
 Antar-0.275
ustomed-0.238
nen-0.225
ּ-0.224
Token outskirts
Token ID30140
Feature activation-3.24e-01

Pos logit contributions
estern+0.033
ostics+0.030
itans+0.030
/>+0.029
bris+0.028
Neg logit contributions
phalt-0.064
 Antar-0.060
ustomed-0.052
nen-0.050
ּ-0.050
Token of
Token ID286
Feature activation-3.78e-01

Pos logit contributions
estern+0.197
ostics+0.188
itans+0.184
/>+0.182
bris+0.176
Neg logit contributions
phalt-0.283
 Antar-0.260
ustomed-0.225
ּ-0.212
nen-0.212
Token Mumbai
Token ID22917
Feature activation-3.44e-01

Pos logit contributions
estern+0.252
ostics+0.240
itans+0.236
/>+0.234
bris+0.227
Neg logit contributions
phalt-0.309
 Antar-0.281
ustomed-0.241
ּ-0.226
nen-0.226
Token.
Token ID13
Feature activation-4.37e-01

Pos logit contributions
estern+0.240
ostics+0.231
itans+0.227
/>+0.226
bris+0.218
Neg logit contributions
phalt-0.270
 Antar-0.244
ustomed-0.207
nen-0.194
ּ-0.193
Token Grove
Token ID24144
Feature activation+1.53e-01

Pos logit contributions
phalt+0.426
 Antar+0.385
ustomed+0.321
nen+0.302
ּ+0.297
Neg logit contributions
estern-0.441
ostics-0.423
itans-0.418
/>-0.414
bris-0.400
Token,
Token ID11
Feature activation+6.70e-04

Pos logit contributions
phalt+0.132
 Antar+0.121
ustomed+0.104
nen+0.098
ּ+0.098
Neg logit contributions
estern-0.095
ostics-0.090
itans-0.089
/>-0.088
bris-0.085
Token California
Token ID3442
Feature activation+2.44e-01

Pos logit contributions
phalt+0.000
 Antar+0.000
ustomed+0.000
nen+0.000
ּ+0.000
Neg logit contributions
estern-0.001
ostics-0.000
itans-0.000
/>-0.000
bris-0.000
Token.
Token ID13
Feature activation-6.90e-01

Pos logit contributions
phalt+0.177
 Antar+0.159
ustomed+0.133
nen+0.124
ּ+0.123
Neg logit contributions
estern-0.186
ostics-0.178
itans-0.176
/>-0.174
bris-0.169
Token Hide
Token ID10415
Feature activation-1.02e+00

Pos logit contributions
estern+0.507
ostics+0.485
itans+0.477
/>+0.471
bris+0.459
Neg logit contributions
phalt-0.517
 Antar-0.468
ustomed-0.392
nen-0.367
ּ-0.365
Token Caption
Token ID11260
Feature activation-2.38e+00

Pos logit contributions
estern+0.597
ostics+0.571
itans+0.562
/>+0.560
bris+0.534
Neg logit contributions
phalt-0.913
 Antar-0.845
ustomed-0.733
ּ-0.690
nen-0.688
Token 15
Token ID1315
Feature activation-2.86e-01

Pos logit contributions
estern+1.012
ostics+0.947
itans+0.926
/>+0.913
bris+0.855
Neg logit contributions
phalt-2.522
 Antar-2.355
ustomed-2.087
ּ-1.995
nen-1.985
Token of
Token ID286
Feature activation-4.65e-01

Pos logit contributions
estern+0.179
ostics+0.169
itans+0.167
/>+0.164
bris+0.159
Neg logit contributions
phalt-0.245
 Antar-0.224
ustomed-0.193
nen-0.183
ּ-0.183
Token 15
Token ID1315
Feature activation-1.13e+00

Pos logit contributions
estern+0.214
ostics+0.200
itans+0.195
/>+0.191
bris+0.182
Neg logit contributions
phalt-0.476
 Antar-0.442
ustomed-0.392
nen-0.374
ּ-0.373
Token
Token ID198
Feature activation-1.94e+00

Pos logit contributions
estern+0.770
ostics+0.747
itans+0.736
/>+0.732
bris+0.698
Neg logit contributions
phalt-0.898
 Antar-0.827
ustomed-0.707
ּ-0.658
nen-0.642
Token
Token ID198
Feature activation-1.79e+00

Pos logit contributions
estern+1.325
ostics+1.282
/>+1.271
itans+1.258
bris+1.203
Neg logit contributions
phalt-1.549
 Antar-1.432
ustomed-1.196
ּ-1.111
nen-1.105
Token 20
Token ID1160
Feature activation-4.87e-01

Pos logit contributions
phalt+0.490
 Antar+0.454
ustomed+0.401
nen+0.382
ּ+0.381
Neg logit contributions
estern-0.247
ostics-0.232
itans-0.226
/>-0.222
bris-0.213
Token,
Token ID11
Feature activation+2.88e-01

Pos logit contributions
estern+0.293
ostics+0.279
itans+0.274
/>+0.272
bris+0.261
Neg logit contributions
phalt-0.428
 Antar-0.394
ustomed-0.341
ּ-0.321
nen-0.320
Token 2015
Token ID1853
Feature activation+3.99e-01

Pos logit contributions
phalt+0.260
 Antar+0.239
ustomed+0.208
nen+0.197
ּ+0.196
Neg logit contributions
estern-0.167
ostics-0.158
itans-0.155
/>-0.153
bris-0.147
Token.
Token ID13
Feature activation-3.39e-01

Pos logit contributions
phalt+0.292
 Antar+0.263
ustomed+0.220
nen+0.204
ּ+0.204
Neg logit contributions
estern-0.301
ostics-0.288
itans-0.284
/>-0.281
bris-0.274
Token Hide
Token ID10415
Feature activation-9.47e-01

Pos logit contributions
estern+0.259
ostics+0.248
itans+0.244
/>+0.241
bris+0.236
Neg logit contributions
phalt-0.243
 Antar-0.219
ustomed-0.182
nen-0.170
ּ-0.169
Token Caption
Token ID11260
Feature activation-2.43e+00

Pos logit contributions
estern+0.556
ostics+0.530
itans+0.522
/>+0.520
bris+0.497
Neg logit contributions
phalt-0.845
 Antar-0.782
ustomed-0.678
ּ-0.639
nen-0.637
Token 8
Token ID807
Feature activation-4.92e-01

Pos logit contributions
estern+0.949
ostics+0.904
/>+0.899
itans+0.868
flo+0.800
Neg logit contributions
phalt-2.655
 Antar-2.466
ustomed-2.179
nen-2.081
ּ-2.062
Token of
Token ID286
Feature activation-2.82e-01

Pos logit contributions
estern+0.308
ostics+0.292
itans+0.287
/>+0.282
bris+0.275
Neg logit contributions
phalt-0.421
 Antar-0.384
ustomed-0.333
nen-0.315
ּ-0.314
Token 15
Token ID1315
Feature activation-7.12e-01

Pos logit contributions
estern+0.132
ostics+0.123
itans+0.120
/>+0.118
bris+0.113
Neg logit contributions
phalt-0.286
 Antar-0.265
ustomed-0.235
nen-0.225
ּ-0.224
Token Photos
Token ID9434
Feature activation-1.43e+00

Pos logit contributions
estern+0.512
ostics+0.492
itans+0.485
/>+0.483
bris+0.465
Neg logit contributions
phalt-0.543
 Antar-0.495
ustomed-0.416
ּ-0.387
nen-0.385
Token:
Token ID25
Feature activation-1.22e+00

Pos logit contributions
estern+0.839
ostics+0.797
itans+0.782
/>+0.777
bris+0.744
Neg logit contributions
phalt-1.281
 Antar-1.181
ustomed-1.023
nen-0.963
ּ-0.962
Token Commando
Token ID47150
Feature activation-3.57e-01

Pos logit contributions
phalt+0.047
 Antar+0.042
ustomed+0.035
nen+0.033
ּ+0.033
Neg logit contributions
estern-0.047
ostics-0.045
itans-0.045
/>-0.044
bris-0.043
Token Rear
Token ID30144
Feature activation+8.97e-01

Pos logit contributions
estern+0.195
ostics+0.185
itans+0.180
/>+0.178
bris+0.171
Neg logit contributions
phalt-0.334
 Antar-0.308
ustomed-0.269
nen-0.256
ּ-0.255
Tokenmed
Token ID1150
Feature activation-3.41e-01

Pos logit contributions
phalt+0.738
 Antar+0.672
ustomed+0.573
nen+0.542
ּ+0.539
Neg logit contributions
estern-0.595
ostics-0.566
itans-0.554
/>-0.548
bris-0.532
Token[/
Token ID13412
Feature activation-2.03e+00

Pos logit contributions
estern+0.190
ostics+0.179
itans+0.176
/>+0.174
bris+0.167
Neg logit contributions
phalt-0.316
 Antar-0.291
ustomed-0.255
nen-0.241
ּ-0.241
Tokenb
Token ID65
Feature activation-8.50e-01

Pos logit contributions
estern+1.066
ostics+1.004
/>+0.986
itans+0.979
bris+0.945
Neg logit contributions
phalt-1.929
 Antar-1.806
ustomed-1.574
ּ-1.493
nen-1.485
Token][/
Token ID44926
Feature activation-2.40e+00

Pos logit contributions
estern+0.406
ostics+0.380
itans+0.371
/>+0.366
bris+0.349
Neg logit contributions
phalt-0.854
 Antar-0.793
ustomed-0.701
nen-0.668
ּ-0.667
Tokencolor
Token ID8043
Feature activation-1.17e+00

Pos logit contributions
estern+1.052
ostics+0.981
/>+0.960
itans+0.952
bris+0.907
Neg logit contributions
phalt-2.479
 Antar-2.346
ustomed-2.063
ּ-1.971
nen-1.948
Token]
Token ID60
Feature activation-6.20e-01

Pos logit contributions
estern+0.603
ostics+0.568
itans+0.557
/>+0.552
bris+0.524
Neg logit contributions
phalt-1.130
 Antar-1.048
ustomed-0.922
nen-0.873
ּ-0.873
Token -
Token ID532
Feature activation+8.55e-02

Pos logit contributions
estern+0.396
ostics+0.378
itans+0.372
/>+0.368
bris+0.354
Neg logit contributions
phalt-0.521
 Antar-0.478
ustomed-0.412
nen-0.386
ּ-0.386
Token Normal
Token ID14435
Feature activation+5.12e-01

Pos logit contributions
phalt+0.071
 Antar+0.065
ustomed+0.055
nen+0.052
ּ+0.052
Neg logit contributions
estern-0.056
ostics-0.053
itans-0.053
/>-0.052
bris-0.050
Token,
Token ID11
Feature activation-1.32e-01

Pos logit contributions
phalt+0.443
 Antar+0.404
ustomed+0.349
nen+0.331
ּ+0.329
Neg logit contributions
estern-0.318
ostics-0.302
itans-0.296
/>-0.292
bris-0.283
Token the
Token ID262
Feature activation+5.52e-02

Pos logit contributions
phalt+0.153
 Antar+0.139
ustomed+0.120
nen+0.113
ּ+0.113
Neg logit contributions
estern-0.118
ostics-0.113
itans-0.111
/>-0.110
bris-0.106
Token day
Token ID1110
Feature activation-8.92e-02

Pos logit contributions
phalt+0.049
 Antar+0.045
ustomed+0.039
nen+0.037
ּ+0.037
Neg logit contributions
estern-0.033
ostics-0.031
itans-0.031
/>-0.030
bris-0.029
Token.
Token ID13
Feature activation+9.81e-02

Pos logit contributions
estern+0.056
ostics+0.054
itans+0.053
/>+0.052
bris+0.050
Neg logit contributions
phalt-0.076
 Antar-0.070
ustomed-0.060
nen-0.057
ּ-0.056
Token They
Token ID1119
Feature activation+1.66e-01

Pos logit contributions
phalt+0.077
 Antar+0.070
ustomed+0.060
nen+0.056
ּ+0.056
Neg logit contributions
estern-0.068
ostics-0.065
itans-0.064
/>-0.064
bris-0.061
Token've
Token ID1053
Feature activation-4.66e-01

Pos logit contributions
phalt+0.151
 Antar+0.139
ustomed+0.122
nen+0.115
ּ+0.115
Neg logit contributions
estern-0.095
ostics-0.090
itans-0.088
/>-0.086
bris-0.084
Token got
Token ID1392
Feature activation-2.19e+00

Pos logit contributions
estern+0.256
ostics+0.241
itans+0.236
/>+0.232
bris+0.224
Neg logit contributions
phalt-0.437
 Antar-0.403
ustomed-0.353
nen-0.335
ּ-0.334
Token a
Token ID257
Feature activation-7.84e-02

Pos logit contributions
estern+1.253
ostics+1.187
itans+1.167
/>+1.161
bris+1.112
Neg logit contributions
phalt-1.992
 Antar-1.830
ustomed-1.594
ּ-1.517
nen-1.506
Token big
Token ID1263
Feature activation-9.65e-01

Pos logit contributions
estern+0.045
ostics+0.043
itans+0.042
/>+0.042
bris+0.040
Neg logit contributions
phalt-0.071
 Antar-0.065
ustomed-0.057
nen-0.054
ּ-0.054
Token bath
Token ID7837
Feature activation+4.03e-01

Pos logit contributions
estern+0.565
ostics+0.536
itans+0.526
/>+0.522
bris+0.502
Neg logit contributions
phalt-0.864
 Antar-0.795
ustomed-0.690
ּ-0.653
nen-0.652
Tokentub
Token ID37995
Feature activation+7.13e-01

Pos logit contributions
phalt+0.339
 Antar+0.310
ustomed+0.267
nen+0.251
ּ+0.251
Neg logit contributions
estern-0.259
ostics-0.247
itans-0.242
/>-0.239
bris-0.231
Token full
Token ID1336
Feature activation-1.01e+00

Pos logit contributions
phalt+0.614
 Antar+0.563
ustomed+0.486
nen+0.459
ּ+0.457
Neg logit contributions
estern-0.444
ostics-0.423
itans-0.414
/>-0.407
bris-0.395
Token Women
Token ID6926
Feature activation-5.10e-01

Pos logit contributions
estern+0.223
ostics+0.212
itans+0.209
/>+0.206
bris+0.199
Neg logit contributions
phalt-0.299
 Antar-0.274
ustomed-0.235
nen-0.222
ּ-0.221
Token in
Token ID287
Feature activation-2.13e-01

Pos logit contributions
estern+0.313
ostics+0.298
itans+0.292
/>+0.291
bris+0.279
Neg logit contributions
phalt-0.444
 Antar-0.405
ustomed-0.351
ּ-0.331
nen-0.330
Token politics
Token ID4819
Feature activation-7.56e-01

Pos logit contributions
estern+0.133
ostics+0.126
itans+0.123
/>+0.121
bris+0.118
Neg logit contributions
phalt-0.184
 Antar-0.169
ustomed-0.145
nen-0.138
ּ-0.136
Token.
Token ID13
Feature activation-5.71e-01

Pos logit contributions
estern+0.490
ostics+0.467
itans+0.459
/>+0.457
bris+0.440
Neg logit contributions
phalt-0.630
 Antar-0.574
ustomed-0.494
ּ-0.463
nen-0.463
Token Hide
Token ID10415
Feature activation-1.11e+00

Pos logit contributions
estern+0.430
ostics+0.412
itans+0.406
/>+0.401
bris+0.391
Neg logit contributions
phalt-0.418
 Antar-0.377
ustomed-0.315
nen-0.293
ּ-0.292
Token Caption
Token ID11260
Feature activation-2.87e+00

Pos logit contributions
estern+0.647
ostics+0.617
itans+0.607
/>+0.606
bris+0.579
Neg logit contributions
phalt-0.989
 Antar-0.914
ustomed-0.793
ּ-0.746
nen-0.745
Token 7
Token ID767
Feature activation-4.68e-01

Pos logit contributions
estern+1.008
ostics+0.932
/>+0.906
itans+0.891
bris+0.819
Neg logit contributions
phalt-3.248
 Antar-3.049
ustomed-2.727
ּ-2.611
nen-2.595
Token of
Token ID286
Feature activation-2.02e-01

Pos logit contributions
estern+0.294
ostics+0.279
itans+0.274
/>+0.269
bris+0.262
Neg logit contributions
phalt-0.400
 Antar-0.364
ustomed-0.315
nen-0.299
ּ-0.298
Token 15
Token ID1315
Feature activation-7.48e-01

Pos logit contributions
estern+0.095
ostics+0.088
itans+0.086
/>+0.084
bris+0.081
Neg logit contributions
phalt-0.205
 Antar-0.190
ustomed-0.169
nen-0.162
ּ-0.161
Token Photos
Token ID9434
Feature activation-1.58e+00

Pos logit contributions
estern+0.537
ostics+0.517
itans+0.509
/>+0.507
bris+0.488
Neg logit contributions
phalt-0.570
 Antar-0.520
ustomed-0.437
ּ-0.406
nen-0.405
Token:
Token ID25
Feature activation-1.33e+00

Pos logit contributions
estern+0.921
ostics+0.876
itans+0.860
/>+0.856
bris+0.817
Neg logit contributions
phalt-1.420
 Antar-1.311
ustomed-1.134
nen-1.067
ּ-1.067