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

    Neuronpedia

    INDEX
    Explanations

    text related to explanations and descriptions of processes or advancements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     BoxFit
    -0.37
     ویکی‌پدی
    -0.36
    Tembelea
    -0.33
     désolés
    -0.33
     JUGA
    -0.31
     boasting
    -0.31
    Behold
    -0.31
    peza
    -0.31
     Golden
    -0.31
    หลวง
    -0.30
    POSITIVE LOGITS
    الحياه
    0.57
     eſſ
    0.53
     ſche
    0.51
     myſelf
    0.50
    parsedMessage
    0.50
    pushFollow
    0.49
    ſelf
    0.48
    QMetaType
    0.48
     iſt
    0.48
     poffible
    0.47
    Act Density 1.764%

    No Known Activations