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

    Neuronpedia

    INDEX
    Explanations

    technical terms or jargon related to programming or structured data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CRET
    -0.19
    lect
    -0.15
     fract
    -0.15
    зÑĮ
    -0.15
    izoph
    -0.14
    ocus
    -0.14
    982
    -0.13
    _expired
    -0.13
     factorial
    -0.13
    244
    -0.13
    POSITIVE LOGITS
    -fed
    0.17
     Burr
    0.15
    sequ
    0.15
     Vita
    0.15
    -Star
    0.15
    ruk
    0.14
    inta
    0.14
    veral
    0.14
    pon
    0.14
    ilen
    0.14
    Act Density 0.393%

    No Known Activations