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

    Neuronpedia

    INDEX
    Explanations

    phrases that express disbelief or surprise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     any
    -0.54
     Larsson
    -0.52
     Familienname
    -0.51
     humain
    -0.51
    Ũ
    -0.50
    Planck
    -0.49
    냅
    -0.48
    λέον
    -0.48
    dyr
    -0.47
    icoot
    -0.47
    POSITIVE LOGITS
    ScopeManager
    0.85
    Personendaten
    0.79
    <bos>
    0.77
    CloseOperation
    0.76
     snippetHide
    0.73
     HttpNotFound
    0.71
    клопе
    0.69
     doInBackground
    0.69
    styleType
    0.69
    __(/*!
    0.66
    Act Density 0.125%

    No Known Activations