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

    Neuronpedia

    INDEX
    Explanations

    expressions of surprise or disappointment

    oai_token-act-pair · gpt-3.5-turbo

    expressions of surprise or desire for favorable circumstances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acca
    -0.69
    ership
    -0.61
    internal
    -0.60
    iencies
    -0.58
     disinfect
    -0.58
    onut
    -0.58
    pread
    -0.57
    ench
    -0.57
     defect
    -0.56
    ilon
    -0.56
    POSITIVE LOGITS
     Flan
    0.68
     sooner
    0.68
    aeda
    0.65
     Blizz
    0.64
     someday
    0.64
     TAMADRA
    0.64
    SPONSORED
    0.63
    Ire
    0.62
     Hirosh
    0.60
     if
    0.60
    Act Density 0.351%

    No Known Activations