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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating mathematical relationships or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Oswald
    -0.14
    ÑĢоÑģÑĤо
    -0.14
     Egypt
    -0.14
    /document
    -0.14
     proc
    -0.13
     ing
    -0.13
    dealer
    -0.13
    Ability
    -0.13
    /animate
    -0.13
    ãĥĭãĥĥãĤ¯
    -0.13
    POSITIVE LOGITS
    keley
    0.14
    uest
    0.14
    cheng
    0.14
    oq
    0.13
     Laud
    0.13
    lider
    0.13
     (()
    0.13
    omatic
    0.13
    ero
    0.13
    å¼
    0.13
    Act Density 0.145%

    No Known Activations