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

    Neuronpedia

    INDEX
    Explanations

    names of individuals and entities in news articles

    oai_token-act-pair · gpt-3.5-turbo

    specific names and quantities related to people, locations, and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ',"
    -0.67
    uador
    -0.67
    apest
    -0.67
    anwhile
    -0.67
    qqa
    -0.63
    ESA
    -0.62
    cause
    -0.60
     '.
    -0.60
    hedon
    -0.59
    "]=>
    -0.59
    POSITIVE LOGITS
    ,
    0.94
    *,
    0.93
    ,,
    0.91
    ?,
    0.83
    ,[
    0.81
    !,
    0.79
    ®,
    0.78
    ,...
    0.72
     ,
    0.71
    ,)
    0.65
    Act Density 0.811%

    No Known Activations