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

    Neuronpedia

    INDEX
    Explanations

    numerical expressions of ratios or statistics related to health and demographics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eft
    -0.15
    clusive
    -0.14
    fork
    -0.14
    lest
    -0.14
    ENO
    -0.14
    chez
    -0.14
    ÙĬÙĨات
    -0.14
    dater
    -0.14
     Tud
    -0.14
    INY
    -0.13
    POSITIVE LOGITS
    -in
    0.26
     out
    0.21
     in
    0.20
     Hess
    0.17
    velt
    0.17
    ê¼
    0.16
     из
    0.15
     chances
    0.15
    UA
    0.15
    antha
    0.15
    Act Density 0.028%

    No Known Activations