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

    Neuronpedia

    INDEX
    Explanations

    specific nouns describing abstract concepts or physical objects

    oai_token-act-pair · gpt-3.5-turbo

    references to various categories, groups, or collections of things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Doors
    -0.50
     lobb
    -0.45
    ··
    -0.44
     invites
    -0.44
     Budd
    -0.43
     Advocate
    -0.43
     behalf
    -0.43
    abad
    -0.43
     Eng
    -0.42
    odore
    -0.42
    POSITIVE LOGITS
     of
    1.03
    luster
    0.79
    Of
    0.79
     Of
    0.77
    icularly
    0.76
     thereof
    0.75
     OF
    0.69
    aditional
    0.69
    idable
    0.66
    atical
    0.64
    Act Density 0.433%

    No Known Activations