Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    parenthetical statements or references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.20
    1:0.09
    2:0.04
    3:0.06
    4:0.06
    5:0.03
    6:0.13
    7:0.10
    8:0.04
    9:0.05
    10:0.10
    11:0.05
    Negative Logits
     Cast
    -3.07
     Hispan
    -3.01
     simulator
    -3.01
    Cast
    -2.99
     Mog
    -2.89
    ••
    -2.88
     Inquisitor
    -2.85
     Crimson
    -2.82
     Tobias
    -2.82
     Cobb
    -2.81
    POSITIVE LOGITS
     Patty
    7.51
     iodine
    4.66
     Burger
    3.80
     burgers
    3.46
     Redmond
    3.35
     Meow
    3.34
     burger
    3.28
    Murray
    3.25
     Pats
    3.25
    PK
    3.21
    Act Density 0.000%

    No Known Activations