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

    Neuronpedia

    INDEX
    Explanations

    names containing the string "arn"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual or character, particularly names associated with "Arn."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mub
    -0.66
    ======
    -0.63
    INT
    -0.62
    ------------------------------------------------
    -0.58
    %]
    -0.58
    lda
    -0.58
    ppy
    -0.58
    pared
    -0.57
    kson
    -0.56
    FORM
    -0.55
    POSITIVE LOGITS
    ataka
    1.23
    aby
    0.97
    ement
    0.92
    ances
    0.89
    ings
    0.89
    ament
    0.87
    anth
    0.86
    ovan
    0.86
    ais
    0.85
    igans
    0.85
    Act Density 0.014%

    No Known Activations