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

    Neuronpedia

    INDEX
    Explanations

    references to news articles

    oai_token-act-pair · gpt-3.5-turbo

    special formatting or unique tokens that signify the end of a section or document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     manif
    -0.49
    schild
    -0.48
    eday
    -0.47
     nearest
    -0.45
     bom
    -0.45
    sic
    -0.44
     challeng
    -0.44
    aturdays
    -0.44
     Pric
    -0.43
    iqueness
    -0.43
    POSITIVE LOGITS
    Associated
    0.61
    Streamer
    0.59
    UTERS
    0.57
    Reuters
    0.53
     GOODMAN
    0.53
    PRESS
    0.52
     largeDownload
    0.51
    Press
    0.48
     Rohingya
    0.48
    CNN
    0.48
    Act Density 0.541%

    No Known Activations