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

    Neuronpedia

    INDEX
    Explanations

    quantifiable metrics related to size, scope, or amount

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Aspect
    -0.16
    æĸ¹éĿ¢
    -0.15
    tep
    -0.14
     lifecycle
    -0.14
     preliminary
    -0.14
    onest
    -0.13
     Dich
    -0.13
    iyim
    -0.13
     (
    -0.13
     early
    -0.13
    POSITIVE LOGITS
    coverage
    0.21
     coverage
    0.19
     detail
    0.18
    éĩı
    0.17
     amount
    0.17
     Coverage
    0.17
     колиÑĩеÑģÑĤва
    0.17
    Coverage
    0.17
     cantidad
    0.17
    /details
    0.16
    Act Density 0.020%

    No Known Activations