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

    Neuronpedia

    INDEX
    Explanations

    questions asking for clarification or explanations about a particular subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     EconPapers
    -0.84
    :✨
    -0.63
    ThroughAttribute
    -0.62
    errHandler
    -0.61
     sisa
    -0.60
    DoubleQuotes
    -0.59
    Datuak
    -0.59
    Билгалдахарш
    -0.57
    galus
    -0.57
     secret
    -0.56
    POSITIVE LOGITS
     does
    0.97
    Does
    0.73
    does
    0.72
     Does
    0.70
    Timber
    0.67
    doses
    0.64
    adecimal
    0.61
     Theſe
    0.61
    timber
    0.61
     Perſ
    0.60
    Act Density 0.193%

    No Known Activations