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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating emphasis or importance

    oai_token-act-pair · gpt-3.5-turbo

    statements that express significant observations or insights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    endars
    -0.71
    ebook
    -0.69
    swick
    -0.67
    MpServer
    -0.66
     feces
    -0.62
    ihu
    -0.60
     eater
    -0.60
    acements
    -0.60
     scrub
    -0.57
    etimes
    -0.56
    POSITIVE LOGITS
     caveat
    0.87
     misconception
    0.87
    Quote
    0.85
     mantra
    0.80
     assumption
    0.78
     question
    0.78
     fallacy
    0.77
     oft
    0.77
     reason
    0.77
     recurring
    0.76
    Act Density 0.804%

    No Known Activations