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

    Neuronpedia

    INDEX
    Explanations

    words related to geopolitical situations and events, particularly those involving the name "Gonski"

    oai_token-act-pair · gpt-3.5-turbo

    the word "ki" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nard
    -0.69
    rique
    -0.68
    icals
    -0.68
    shire
    -0.67
    %]
    -0.65
    icist
    -0.65
    ication
    -0.64
    mort
    -0.63
     Leban
    -0.61
    icity
    -0.61
    POSITIVE LOGITS
    wi
    1.18
    pper
    1.13
    hao
    1.04
    yo
    0.98
    utenant
    0.98
    pping
    0.95
    yah
    0.91
    ota
    0.90
    oji
    0.90
    Äĩ
    0.89
    Act Density 0.016%

    No Known Activations