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

    Neuronpedia

    INDEX
    Explanations

    adverbs describing the quality of actions or events

    oai_token-act-pair · gpt-3.5-turbo

    intensifiers or adverbs that emphasize quality or degree

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    interstitial
    -0.70
    enting
    -0.63
    ds
    -0.62
     Operating
    -0.61
     Aad
    -0.60
    endants
    -0.59
     Peaks
    -0.58
    raved
    -0.58
    orial
    -0.58
     Shining
    -0.57
    POSITIVE LOGITS
     differently
    1.20
     smoothly
    1.20
    successfully
    1.19
     quietly
    1.18
     aggressively
    1.15
     cautiously
    1.15
     efficiently
    1.14
    gently
    1.12
     quickly
    1.12
     swiftly
    1.12
    Act Density 0.112%

    No Known Activations