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

    Neuronpedia

    INDEX
    Explanations

    the name "Col" followed by a number

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Roskov
    -0.77
    Jereo
    -0.73
    Ārējās
    -0.70
    zzard
    -0.68
     */;
    -0.68
    @[+][
    -0.67
     parseFrom
    -0.66
    aarrggbb
    -0.64
    mgren
    -0.63
    basicConfig
    -0.63
    POSITIVE LOGITS
     Col
    4.00
    Col
    3.84
     col
    3.78
    col
    3.45
     COL
    3.07
    COL
    2.99
     COLL
    2.19
     cols
    2.18
    Cols
    2.02
     kol
    1.99
    Act Density 0.051%

    No Known Activations