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

    Neuronpedia

    INDEX
    Explanations

    numerical values and measurements in a scientific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    曖昧さ回避
    -0.88
    Hentet
    -0.83
    complexContent
    -0.82
     ModelExpression
    -0.81
    NamedQueries
    -0.78
    تقاوى
    -0.77
    apimachinery
    -0.69
    featureID
    -0.69
     calendriers
    -0.68
    :✨
    -0.68
    POSITIVE LOGITS
     viceversa
    0.54
     XNUMX
    0.52
    Ours
    0.52
     Theſe
    0.48
    何より
    0.47
     Hift
    0.47
    😂
    0.45
    صاد
    0.45
     fevere
    0.44
     preſent
    0.44
    Act Density 0.022%

    No Known Activations