INDEX
Explanations
references to San Francisco and its related areas
New Auto-Interp
Negative Logits
itſelf
-0.85
myſelf
-0.78
Platon
-0.78
Hege
-0.75
ZDF
-0.75
يتيمه
-0.75
theſe
-0.73
Jefus
-0.73
reft
-0.73
nozze
-0.72
POSITIVE LOGITS
Francisco
2.74
Francisco
2.18
FRANCISCO
2.12
francisco
1.77
Fran
1.20
Frans
1.20
Francis
1.13
fran
1.01
Frans
0.99
Fran
0.96
Activations Density 0.057%