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

    Neuronpedia

    INDEX
    Explanations

    contractions of the verb "do not."

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "don't" or its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EStreamFrame
    -0.85
    cffffcc
    -0.72
    EStream
    -0.71
    ategory
    -0.66
    DOC
    -0.66
    ULT
    -0.66
    abama
    -0.62
    wcs
    -0.62
    OTOS
    -0.61
    udic
    -0.61
    POSITIVE LOGITS
    't
    1.40
    atives
    1.05
    ned
    1.02
    ning
    0.97
    nie
    0.93
    kie
    0.84
    uts
    0.83
    ations
    0.82
     Draper
    0.82
    ners
    0.80
    Act Density 0.051%

    No Known Activations