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

    Neuronpedia

    INDEX
    Explanations

    mentions of a specific country or organization

    oai_token-act-pair · gpt-3.5-turbo

    instances of the acronym "SA" associated with various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ships
    -0.77
    ysis
    -0.71
    naires
    -0.66
    tons
    -0.65
    naire
    -0.65
     MacArthur
    -0.64
    hang
    -0.63
    estine
    -0.61
    ship
    -0.60
     ubiqu
    -0.60
    POSITIVE LOGITS
    VE
    1.12
    ven
    1.02
    plings
    0.95
    vant
    0.92
    ULT
    0.91
    ccess
    0.90
    pling
    0.89
    GE
    0.88
    FE
    0.86
    BILITIES
    0.84
    Act Density 0.067%

    No Known Activations