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

    Neuronpedia

    INDEX
    Explanations

    specific mentions of a "portion" of something within a text

    oai_token-act-pair · gpt-3.5-turbo

    references to segments or parts of a whole

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    generic
    -0.77
    Trend
    -0.71
    verbs
    -0.68
    ATHER
    -0.67
     Fighters
    -0.65
    NM
    -0.63
    raid
    -0.62
    urat
    -0.62
     darling
    -0.61
     opio
    -0.60
    POSITIVE LOGITS
     thereof
    1.08
    ials
    0.80
     of
    0.75
     ILCS
    0.75
    icularly
    0.71
    aler
    0.70
    OTUS
    0.70
     guiActiveUn
    0.69
    meal
    0.68
    edly
    0.67
    Act Density 0.023%

    No Known Activations