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

    Neuronpedia

    INDEX
    Explanations

    adverbs modifying action verbs

    oai_token-act-pair · gpt-3.5-turbo

    adverbs and phrases indicating thoroughness or completeness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Choice
    -0.77
    soDeliveryDate
    -0.75
    quickShipAvailable
    -0.74
    76561
    -0.71
     terribly
    -0.67
     remarkably
    -0.65
    MpServer
    -0.63
    Reviewer
    -0.63
    soever
    -0.63
    LESS
    -0.62
    POSITIVE LOGITS
     engage
    1.28
     communicate
    1.27
     explore
    1.24
     utilize
    1.23
     evaluate
    1.22
     educate
    1.21
     integrate
    1.19
     compete
    1.17
     settle
    1.17
     participate
    1.17
    Act Density 0.139%

    No Known Activations