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

    Neuronpedia

    INDEX
    Explanations

    occurrences of variable or parameter references in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rsiniz
    -0.84
    circledR
    -0.82
    LookAnd
    -0.78
    *{-
    -0.69
    -0.68
    Kaieteur
    -0.68
     Luch
    -0.67
     waitFor
    -0.66
    eror
    -0.65
    ertor
    -0.65
    POSITIVE LOGITS
    params
    2.23
     params
    2.05
    Params
    1.62
     Params
    1.45
    getParams
    1.23
    PARAMS
    1.20
     useParams
    0.98
    LayoutParams
    0.97
     Niklas
    0.85
     häm
    0.83
    Act Density 0.047%

    No Known Activations