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

    Neuronpedia

    INDEX
    Explanations

    references to napkins

    oai_token-act-pair · gpt-3.5-turbo

    references to naps and specific sports teams, particularly in a critical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    les
    -0.80
    water
    -0.75
    ishly
    -0.72
    ly
    -0.72
    Bron
    -0.71
    Keys
    -0.71
    ness
    -0.70
    Compan
    -0.65
    velt
    -0.64
    lying
    -0.63
    POSITIVE LOGITS
    oleon
    0.85
    nesday
    0.79
    AAF
    0.79
    ĸļ
    0.77
    edia
    0.77
    mington
    0.75
    merce
    0.72
     CTR
    0.71
    plex
    0.71
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.70
    Act Density 0.064%

    No Known Activations