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

    Neuronpedia

    INDEX
    Explanations

    forms of phenomena or concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to different types or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hots
    -0.63
     VIDEOS
    -0.63
    bley
    -0.62
     Watching
    -0.62
    ĸļ
    -0.61
    ghan
    -0.61
    iets
    -0.60
     Wand
    -0.59
     Ammo
    -0.58
     bark
    -0.58
    POSITIVE LOGITS
    aldehyde
    1.44
    idable
    1.17
    ative
    1.09
    atter
    1.01
    ality
    0.97
    atted
    0.95
    ulating
    0.95
    ulas
    0.93
    ul
    0.93
    ula
    0.91
    Act Density 0.024%

    No Known Activations