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

    Neuronpedia

    INDEX
    Explanations

    relevant terms denoting a personal or political nature

    oai_token-act-pair · gpt-3.5-turbo

    terms related to personal and political experiences or themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osphere
    -0.70
    ioxide
    -0.68
    otaur
    -0.67
    bey
    -0.67
    ournal
    -0.66
    irit
    -0.65
    iage
    -0.65
    secution
    -0.65
    mosp
    -0.65
     Appears
    -0.64
    POSITIVE LOGITS
     enough
    1.10
    arily
    0.97
    isable
    0.88
    istically
    0.87
    aneously
    0.82
    izable
    0.80
    nell
    0.78
     nonetheless
    0.76
    itably
    0.73
     corrid
    0.70
    Act Density 0.408%

    No Known Activations