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

    Neuronpedia

    INDEX
    Explanations

    quantifiable metrics or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    :✨
    -0.69
     Audiodateien
    -0.63
    parsedMessage
    -0.62
     ModelExpression
    -0.62
    TargetException
    -0.59
    matchCondition
    -0.59
    posedge
    -0.59
    żesz
    -0.56
     sessionFactory
    -0.56
    bidities
    -0.56
    POSITIVE LOGITS
    Referencie
    0.64
     popoli
    0.63
    Odkazy
    0.60
     plegable
    0.55
     ©️
    0.55
    ьаж
    0.55
     humain
    0.54
     same
    0.54
     Same
    0.53
     gomma
    0.53
    Act Density 0.406%

    No Known Activations