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

    Neuronpedia

    INDEX
    Explanations

    contractions, specifically identifying the word "isn't"

    oai_token-act-pair · gpt-3.5-turbo

    contractions and phrases that express doubt or questioning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cedes
    -0.65
    lly
    -0.59
    laun
    -0.59
    leaders
    -0.59
     embroiled
    -0.58
    collect
    -0.58
    perty
    -0.58
     indebted
    -0.57
     filib
    -0.57
     facult
    -0.56
    POSITIVE LOGITS
    ometimes
    0.73
    hee
    0.67
    ?),
    0.66
    ttp
    0.65
     Thou
    0.63
    )),
    0.62
    )?
    0.61
    ?).
    0.60
    uits
    0.60
    9999
    0.60
    Act Density 0.094%

    No Known Activations