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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating direction or purpose

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vit
    -0.14
     gì
    -0.14
    asin
    -0.14
    oud
    -0.14
    _Framework
    -0.13
     iÅŁte
    -0.13
    ancock
    -0.13
    rut
    -0.13
     suites
    -0.13
    toi
    -0.13
    POSITIVE LOGITS
     Outreach
    0.15
    oplast
    0.15
    echa
    0.15
     ëĪĦ
    0.15
    entions
    0.14
     Güven
    0.14
    imenti
    0.14
    á»ĥm
    0.14
    Ñĩно
    0.14
    DL
    0.13
    Act Density 0.289%

    No Known Activations