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

    Neuronpedia

    INDEX
    Explanations

    explicit mentions of the number "36"

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to voting or survey results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    prises
    -0.84
    olicy
    -0.83
    liga
    -0.79
    ItemTracker
    -0.75
    anke
    -0.74
    arte
    -0.74
    eele
    -0.72
    prise
    -0.71
    alties
    -0.71
    oken
    -0.70
    POSITIVE LOGITS
    00
    1.00
    th
    0.90
    36
    0.73
    01
    0.73
    50
    0.71
    ZI
    0.70
    75
    0.68
    TH
    0.68
    650
    0.68
    375
    0.67
    Act Density 0.027%

    No Known Activations