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

    Neuronpedia

    INDEX
    Explanations

    text related to legal or procedural matters

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "urs"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Clarkson
    -0.76
     Schn
    -0.68
    ISON
    -0.66
     Fuj
    -0.65
     Berkshire
    -0.65
     Ramos
    -0.64
     Slater
    -0.63
     Metatron
    -0.62
     Iw
    -0.61
     Butcher
    -0.61
    POSITIVE LOGITS
    uits
    1.17
    hip
    1.16
    uit
    1.12
    urs
    0.99
    geons
    0.95
    rences
    0.94
    cript
    0.94
    alez
    0.92
    orrow
    0.91
    ĸļ
    0.91
    Act Density 0.020%

    No Known Activations