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

    Neuronpedia

    INDEX
    Explanations

    abbreviations or codes, particularly related to scientific or technical terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    it
    -0.16
    its
    -0.15
    ulously
    -0.14
    ulin
    -0.14
    rog
    -0.13
    ivant
    -0.13
    ethyst
    -0.13
    ¢åįķ
    -0.13
    Ðĩ
    -0.13
     cov
    -0.13
    POSITIVE LOGITS
    anus
    0.17
    íķĻ기
    0.17
    rott
    0.16
    isson
    0.16
    mÃŃ
    0.15
    tro
    0.15
    íķĻê³¼
    0.15
    gon
    0.15
    λά
    0.15
    Recommended
    0.14
    Act Density 0.055%

    No Known Activations