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

    Neuronpedia

    INDEX
    Explanations

    terms related to games, physical competition, and strategies

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to strategy and decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anwhile
    -0.56
     meanwhile
    -0.49
    emale
    -0.46
    odore
    -0.46
    inav
    -0.46
    razil
    -0.45
    velt
    -0.45
    enegger
    -0.45
    named
    -0.45
     Twain
    -0.44
    POSITIVE LOGITS
    )).
    0.52
    .</
    0.50
    ).
    0.47
    $.
    0.45
    ".
    0.45
    '.
    0.45
    %.
    0.44
     insur
    0.43
    SI
    0.43
    .).
    0.43
    Act Density 3.131%

    No Known Activations