INDEX
Explanations
The neuron is looking for text related to clicking a box or link on a website
occurrences of the word "click" and its variations in the context of online interactions
New Auto-Interp
Negative Logits
Yard
-0.67
egal
-0.64
adium
-0.64
venge
-0.63
firsthand
-0.61
Ministers
-0.59
Variety
-0.59
ministers
-0.57
istg
-0.57
Concent
-0.55
POSITIVE LOGITS
lish
0.97
through
0.86
dress
0.79
wheel
0.77
pad
0.77
prints
0.75
antry
0.74
urable
0.74
kered
0.72
ety
0.72
Activations Density 0.027%