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

    Neuronpedia

    INDEX
    Explanations

    adverbs that convey importance or emphasis

    oai_token-act-pair · gpt-3.5-turbo

    adverbs and adjectives that express intensity or manner

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     treasure
    -0.64
     direction
    -0.64
     period
    -0.63
    frac
    -0.61
    tnc
    -0.61
     plate
    -0.60
    ËĪ
    -0.60
     canvas
    -0.60
    clusively
    -0.59
    marine
    -0.59
    POSITIVE LOGITS
    inct
    0.75
    ccording
    0.73
    entimes
    0.72
     Detected
    0.69
     Asked
    0.69
    ortunately
    0.69
     Speaking
    0.68
     Charity
    0.67
     Removal
    0.67
    cknowled
    0.66
    Act Density 0.076%

    No Known Activations