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

    Neuronpedia

    INDEX
    Explanations

    references to relationships or connections between entities or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ä¹Ī
    -0.17
    osit
    -0.16
     cả
    -0.15
    ickle
    -0.15
    _firestore
    -0.15
    ायन
    -0.15
     дÑĢÑĥгого
    -0.14
    -urlencoded
    -0.14
    another
    -0.14
    ãĥ¼ãĤº
    -0.14
    POSITIVE LOGITS
    /am
    0.33
     sexes
    0.27
     two
    0.24
     them
    0.23
     genders
    0.22
     Ñģобой
    0.22
     ÑģобоÑİ
    0.20
    âĢĮاÙĦÙħÙĦÙĦÛĮ
    0.19
     equals
    0.19
     generations
    0.19
    Act Density 0.058%

    No Known Activations