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

    Neuronpedia

    INDEX
    Explanations

    phrases related to intensity or extremeness

    oai_token-act-pair · gpt-3.5-turbo

    adverbs and adjectives that express intensity or degree

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ö¼
    -0.65
    utsche
    -0.64
    ¿½
    -0.64
     rule
    -0.62
     cuff
    -0.59
     buckle
    -0.59
     Kaiser
    -0.57
    ugh
    -0.55
     scrimmage
    -0.54
    orem
    -0.54
    POSITIVE LOGITS
    urated
    0.82
     someday
    0.77
    morrow
    0.77
    versible
    0.74
    oaded
    0.72
    soDeliveryDate
    0.72
     tomorrow
    0.70
    ioned
    0.69
    readable
    0.68
    idered
    0.68
    Act Density 0.554%

    No Known Activations