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

    Neuronpedia

    INDEX
    Explanations

    references to data structure definitions and associated attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sensitivity
    -0.67
    satellite
    -0.64
    ercises
    -0.63
    Eqn
    -0.61
    samurai
    -0.59
    ourism
    -0.59
    </caption>
    -0.58
    airplane
    -0.57
    figurine
    -0.57
    FTFY
    -0.56
    POSITIVE LOGITS
    str
    0.78
    bootstrapcdn
    0.75
    cas
    0.75
    has
    0.74
    出版年
    0.74
    sp
    0.71
    ta
    0.69
    ok
    0.68
    ab
    0.67
    ids
    0.67
    Act Density 0.213%

    No Known Activations