INDEX
Explanations
words related to sympathy and empathy
New Auto-Interp
Negative Logits
bang
-0.70
consolidation
-0.66
put
-0.60
carpet
-0.59
consolidated
-0.58
odder
-0.57
reditary
-0.56
elight
-0.56
indicator
-0.55
establishment
-0.54
POSITIVE LOGITS
with
0.85
ationally
0.78
withd
0.76
bly
0.75
lihood
0.73
against
0.72
between
0.72
SHIP
0.71
WITH
0.71
ially
0.70
Activations Density 0.049%