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

    Neuronpedia

    INDEX
    Explanations

    Proper nouns, specifically names or titles in foreign languages

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Il."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lished
    -0.79
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.75
    è¦ļéĨĴ
    -0.73
     BaseType
    -0.71
    oÄŁ
    -0.70
    é¾įå¥ij士
    -0.70
    */(
    -0.68
     CoC
    -0.66
    ELL
    -0.66
    blance
    -0.64
    POSITIVE LOGITS
    ibrary
    1.10
    usions
    0.95
    usive
    0.94
    vl
    0.87
    umin
    0.86
    uminati
    0.86
    ustration
    0.84
    iter
    0.84
    ugi
    0.82
    uding
    0.81
    Act Density 0.014%

    No Known Activations