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

    Neuronpedia

    INDEX
    Explanations

    references to participation in surveys or polls

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.05
    1:0.02
    2:0.07
    3:0.03
    4:0.06
    5:0.02
    6:0.26
    7:0.04
    8:0.07
    9:0.26
    10:0.02
    11:0.03
    Negative Logits
    apter
    -4.08
     cannibal
    -3.95
     Bapt
    -3.91
     cannabin
    -3.83
     Amar
    -3.81
     bapt
    -3.81
     contrace
    -3.59
    Bird
    -3.58
    ufact
    -3.58
     fragrance
    -3.56
    POSITIVE LOGITS
     Lew
    11.70
    Lew
    11.14
    Chel
    4.92
     Levy
    4.65
     Ell
    4.46
     Chel
    4.45
     Nev
    4.34
     Lange
    4.34
     Ross
    4.30
     Hill
    4.24
    Act Density 0.003%

    No Known Activations