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

    Neuronpedia

    INDEX
    Explanations

    technical measurements and specifications

    oai_token-act-pair · gpt-3.5-turbo

    references to quantitative measurements and specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ozy
    -0.79
    oyal
    -0.70
    ovie
    -0.67
    NetMessage
    -0.65
    arious
    -0.64
    geries
    -0.64
    jab
    -0.63
    EY
    -0.62
    pora
    -0.62
    odon
    -0.62
    POSITIVE LOGITS
     calculation
    1.06
     varies
    1.04
     estimation
    0.98
     ranges
    0.98
     slider
    0.98
     Calculator
    0.97
     calculator
    0.95
     difference
    0.91
     measurement
    0.90
     exceeded
    0.90
    Act Density 0.295%

    No Known Activations