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

    Neuronpedia

    INDEX
    Explanations

    thought-provoking hypothetical questions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ardon
    -0.16
    ylum
    -0.15
    arov
    -0.15
    apı
    -0.14
    leur
    -0.14
    asp
    -0.14
    inyin
    -0.14
    ecast
    -0.14
    uky
    -0.14
    phem
    -0.14
    POSITIVE LOGITS
    ycop
    0.15
    à¹īาà¸ĩ
    0.15
    ello
    0.14
    borough
    0.14
     Duy
    0.14
     your
    0.14
    rape
    0.13
    bilder
    0.13
     sæ
    0.13
     sideways
    0.13
    Act Density 0.098%

    No Known Activations