INDEX
Explanations
The neuron seems to be looking for terms related to craftsmanship and brinksmanship
references to craftsmanship and related skills
New Auto-Interp
Negative Logits
loc
-0.71
cell
-0.63
core
-0.62
ob
-0.61
Summer
-0.60
Core
-0.59
bus
-0.58
beta
-0.58
FB
-0.57
subway
-0.57
POSITIVE LOGITS
manship
5.52
smanship
2.07
worthiness
1.44
men
1.40
anship
1.28
liness
1.27
lihood
1.22
afety
1.18
hip
1.14
woman
1.12
Activations Density 0.011%