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

    Neuronpedia

    INDEX
    Explanations

    whether a statement is negated or not

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating negation or the concept of 'not'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    riad
    -0.65
     Quarterly
    -0.61
    æ©Ł
    -0.61
     Kazakh
    -0.60
     Yuan
    -0.59
     Armory
    -0.58
    omics
    -0.58
    antha
    -0.58
    eteenth
    -0.58
    edience
    -0.58
    POSITIVE LOGITS
    epad
    1.19
    hin
    1.14
    ched
    0.92
     depending
    0.92
     necessarily
    0.89
     anymore
    0.83
    eworthy
    0.83
    ches
    0.82
    ifies
    0.80
     versa
    0.75
    Act Density 0.059%

    No Known Activations