INDEX
Explanations
contact information and requests for communication
New Auto-Interp
Negative Logits
reon
-0.16
itto
-0.15
eldorf
-0.15
ise
-0.14
roe
-0.14
FIG
-0.14
ism
-0.14
robat
-0.14
.
-0.14
.
-0.14
POSITIVE LOGITS
tel
0.36
phone
0.34
telephone
0.33
toll
0.32
tel
0.30
phone
0.30
Phone
0.29
ç͵è¯Ŀ
0.29
Phone
0.28
Tel
0.28
Activations Density 0.120%