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

    Neuronpedia

    INDEX
    Explanations

    names of newspapers and journalists

    oai_token-act-pair · gpt-3.5-turbo

    end-of-text markers or formatting symbols in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    checked
    -0.73
    fing
    -0.71
    poon
    -0.71
     ensu
    -0.68
    ynchronous
    -0.66
    bomb
    -0.66
    AFTA
    -0.66
    axe
    -0.66
    yip
    -0.64
    hang
    -0.64
    POSITIVE LOGITS
     Story
    0.96
    Buy
    0.79
     ARTICLE
    0.78
     More
    0.72
     FILE
    0.70
     Officials
    0.70
     Former
    0.67
     NEW
    0.66
     Protesters
    0.66
     Voting
    0.65
    Act Density 0.047%

    No Known Activations