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

    Neuronpedia

    INDEX
    Explanations

    phrases related to categories or types of things

    oai_token-act-pair · gpt-3.5-turbo

    terms indicating categories, types, or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     footprints
    -0.69
     VIDEOS
    -0.60
     Bars
    -0.59
     balloons
    -0.55
    assies
    -0.55
    !!!!!
    -0.53
    tics
    -0.53
     Doors
    -0.53
     seals
    -0.53
     puppies
    -0.52
    POSITIVE LOGITS
     of
    0.94
    atical
    0.82
    of
    0.77
    atum
    0.73
    Of
    0.72
    ridge
    0.72
    meal
    0.70
     dozen
    0.69
     Of
    0.69
    ically
    0.68
    Act Density 0.212%

    No Known Activations