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

    Neuronpedia

    INDEX
    Explanations

    URLs within a text

    oai_token-act-pair · gpt-3.5-turbo

    content related to stories and news articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    veland
    -0.89
    amina
    -0.80
    emouth
    -0.78
    apons
    -0.76
    xit
    -0.76
    untarily
    -0.75
    chy
    -0.74
    assi
    -0.74
    ornia
    -0.73
    untled
    -0.73
    POSITIVE LOGITS
     unfolding
    0.99
     narrated
    0.91
     Narr
    0.86
     poems
    0.85
     fiction
    0.81
     Hemp
    0.79
     novels
    0.79
     unfold
    0.78
     prol
    0.77
     rewritten
    0.77
    Act Density 0.419%

    No Known Activations