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

    Neuronpedia

    INDEX
    Explanations

    adjectives and nouns associated with boldness or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idal
    -0.17
    rawn
    -0.17
    chen
    -0.15
    MAS
    -0.15
    isel
    -0.15
    ảo
    -0.15
    erna
    -0.15
    hood
    -0.15
    pond
    -0.15
    ¢åįķ
    -0.14
    POSITIVE LOGITS
    ness
    0.17
    ienes
    0.17
    lessness
    0.15
    ful
    0.15
    tur
    0.14
     Bind
    0.14
    ole
    0.14
    avin
    0.14
    stad
    0.14
    yw
    0.14
    Act Density 0.023%

    No Known Activations