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

    Neuronpedia

    INDEX
    Explanations

    Latin letters or special characters within the text

    oai_token-act-pair · gpt-3.5-turbo

    patterns of numerical data related to performance or trends

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     engagements
    -0.61
     amph
    -0.59
     biod
    -0.59
     engagement
    -0.58
     diving
    -0.57
     exposure
    -0.57
     furnished
    -0.57
    xual
    -0.56
    hement
    -0.56
     Cent
    -0.56
    POSITIVE LOGITS
    ³³³³³³³³
    1.03
    CVE
    0.96
    ³³³³
    0.96
    ³³³
    0.95
    Anonymous
    0.91
    Scroll
    0.88
    ³³³³³³³³³³³³³³³³
    0.87
    Labour
    0.85
    Posted
    0.84
    However
    0.83
    Act Density 0.499%

    No Known Activations