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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating authorship or attribution in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the word "by" indicating authorship or attribution.

    oai_token-act-pair · gpt-4oTriggered by @timna
    New Auto-Interp
    Negative Logits
    hæng
    -0.60
     ErrIntOverflow
    -0.57
     Chwiliwch
    -0.56
     nonatomic
    -0.56
    ########.
    -0.55
    )}
    -0.55
    ểm
    -0.54
    yarnpkg
    -0.52
    ræ
    -0.49
    IsContent
    -0.49
    POSITIVE LOGITS
     geslacht
    0.75
     emeritus
    0.65
     Emeritus
    0.63
    RTEX
    0.60
     Professor
    0.60
    Notae
    0.56
     homomorphism
    0.54
    recrow
    0.53
     fotogra
    0.52
     mathematician
    0.52
    Act Density 0.284%

    No Known Activations