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

    Neuronpedia

    INDEX
    Explanations

    references to categories and classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ickle
    -0.16
    éal
    -0.15
    autorelease
    -0.15
    ors
    -0.15
    breaker
    -0.14
    uckle
    -0.14
    uary
    -0.14
    ayd
    -0.14
     Grat
    -0.14
    ardin
    -0.14
    POSITIVE LOGITS
    (Category
    0.18
    alars
    0.18
    åĪ¥
    0.17
    /categories
    0.16
    atsby
    0.16
    OfWork
    0.16
    .dex
    0.16
    hood
    0.15
    gram
    0.15
    td
    0.14
    Act Density 0.036%

    No Known Activations