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

    Neuronpedia

    INDEX
    Explanations

    specific nouns and phrases indicative of importance or measurement in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elocity
    -0.17
     uprav
    -0.16
    ingerprint
    -0.15
    .documentation
    -0.14
    'aut
    -0.14
    .segment
    -0.14
    lessly
    -0.14
    ÑĩиÑģÑĤ
    -0.14
    graded
    -0.13
    ’aut
    -0.13
    POSITIVE LOGITS
    undy
    0.18
    .owl
    0.16
    _ttl
    0.15
    rlen
    0.15
    -alist
    0.15
    cies
    0.15
    opot
    0.14
    imet
    0.14
    apon
    0.14
     пеÑĢеб
    0.14
    Act Density 0.020%

    No Known Activations