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

    Neuronpedia

    INDEX
    Explanations

    adverbs and adverbial phrases, which describe the manner or circumstances of an action

    oai_token-act-pair · gpt-3.5-turbo

    adverbs that indicate frequency, manner, or degree

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.74
    ASE
    -0.70
     Wish
    -0.65
    channelAvailability
    -0.59
    gettable
    -0.58
    ukemia
    -0.58
    UGH
    -0.58
    omorphic
    -0.57
    scribe
    -0.57
    ntil
    -0.57
    POSITIVE LOGITS
     applies
    1.37
     revolves
    1.36
     reflects
    1.35
     extends
    1.34
     qualifies
    1.33
     encompasses
    1.33
     involves
    1.32
     exists
    1.32
     affects
    1.32
     occurs
    1.30
    Act Density 0.207%

    No Known Activations