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

    Neuronpedia

    INDEX
    Explanations

    sentences with strong emotional language

    oai_token-act-pair · gpt-3.5-turbo

    sentences that express strong emotions or negative sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     interpreter
    -0.76
    uly
    -0.75
    emaker
    -0.75
     emanc
    -0.72
    itionally
    -0.72
     intended
    -0.71
     favourable
    -0.71
     organis
    -0.71
     exclusively
    -0.71
    umerous
    -0.70
    POSITIVE LOGITS
     Anyway
    1.27
     Especially
    1.24
     ;)
    1.18
     Seriously
    1.14
     Maybe
    1.13
     Whatever
    1.12
     Anything
    1.09
     Literally
    1.09
     Besides
    1.09
     Something
    1.08
    Act Density 0.864%

    No Known Activations