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

    Neuronpedia

    INDEX
    Explanations

    words related to criticism or challenges

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "by" indicating causation or authorship

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    raq
    -0.85
    eva
    -0.80
    yssey
    -0.77
    apest
    -0.76
     largeDownload
    -0.75
    ivia
    -0.74
    engine
    -0.74
    thal
    -0.74
    bay
    -0.73
    ettle
    -0.73
    POSITIVE LOGITS
     virtue
    1.08
    products
    0.92
     sheer
    0.89
     successive
    0.82
     fiat
    0.77
     multiplying
    0.73
     gravity
    0.72
     Hurricane
    0.70
     bureaucracy
    0.70
     technological
    0.69
    Act Density 0.131%

    No Known Activations