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

    Neuronpedia

    INDEX
    Explanations

    mentions of numeric values or statistics

    oai_token-act-pair · gpt-3.5-turbo

    sentences that express statistical or factual information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     applause
    -0.72
     awaited
    -0.72
     wake
    -0.69
     cringe
    -0.69
     imagined
    -0.68
     thrill
    -0.68
     splash
    -0.66
     clutch
    -0.66
     inspiration
    -0.66
     realism
    -0.65
    POSITIVE LOGITS
     Therefore
    1.30
     Consequently
    1.19
     Moreover
    1.13
     Hence
    1.13
     Nevertheless
    1.12
     Nonetheless
    1.11
     Additionally
    1.10
     Presumably
    1.09
     However
    1.09
     Furthermore
    1.07
    Act Density 0.590%

    No Known Activations