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

    Neuronpedia

    INDEX
    Explanations

    sentences where a strong opinion is expressed

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically periods and commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ombo
    -0.86
     condol
    -0.69
    ominated
    -0.68
     accounted
    -0.68
    auga
    -0.65
    emed
    -0.65
    mouth
    -0.64
     consisted
    -0.63
    agu
    -0.62
    robe
    -0.61
    POSITIVE LOGITS
     Says
    1.07
     His
    1.03
     He
    0.99
     Speaking
    0.99
     Recently
    0.92
    His
    0.91
     Meanwhile
    0.90
     Currently
    0.89
    Adds
    0.87
     Specifically
    0.85
    Act Density 0.621%

    No Known Activations