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

    Neuronpedia

    INDEX
    Explanations

    terms related to selection and emission in programming or scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Мексичка
    -0.50
    :✨
    -0.46
    EndContext
    -0.46
    WriteLiteral
    -0.43
    TemporalType
    -0.41
     Übers
    -0.41
    WindowConstants
    -0.41
    Erst
    -0.39
    Nevertheless
    -0.38
    mord
    -0.38
    POSITIVE LOGITS
     Emission
    0.72
    sel
    0.71
     emission
    0.63
    /**
    0.62
    Emission
    0.61
     drag
    0.58
     Emissions
    0.57
     Sed
    0.56
    Emissions
    0.56
    Sed
    0.56
    Act Density 0.399%

    No Known Activations