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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to categorization and classification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ialis
    -0.16
    TW
    -0.16
    olumn
    -0.16
    irie
    -0.15
    immer
    -0.15
    antas
    -0.14
    ass
    -0.14
    iv
    -0.13
    ender
    -0.13
    elyn
    -0.13
    POSITIVE LOGITS
    emouth
    0.17
    ÅĻÃŃž
    0.16
    sei
    0.15
    OGLE
    0.15
    ripp
    0.14
    lish
    0.14
    kinson
    0.14
    ailer
    0.14
    cms
    0.14
    bilt
    0.14
    Act Density 0.020%

    No Known Activations