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

    Neuronpedia

    INDEX
    Explanations

    words related to replacement or substitution

    oai_token-act-pair · gpt-3.5-turbo

    terms related to substitution or change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    raq
    -0.97
    hest
    -0.73
    zag
    -0.69
    WA
    -0.67
    mpeg
    -0.66
     Reasons
    -0.66
    eb
    -0.65
    arta
    -0.65
    Developer
    -0.64
    vern
    -0.63
    POSITIVE LOGITS
     obsolete
    0.83
    ments
    0.81
    orate
    0.77
    atives
    0.76
    utions
    0.73
    mented
    0.71
    itute
    0.71
     bulbs
    0.69
     redundant
    0.69
    ative
    0.69
    Act Density 0.029%

    No Known Activations