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

    Neuronpedia

    INDEX
    Explanations

    negations where something is not happening

    oai_token-act-pair · gpt-3.5-turbo

    negations related to various subjects or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etimes
    -0.75
     Communities
    -0.67
     Opportun
    -0.64
    larg
    -0.63
     RTX
    -0.62
     evaluations
    -0.60
     Pist
    -0.59
     Marks
    -0.58
     Exposure
    -0.57
     assessments
    -0.57
    POSITIVE LOGITS
     shy
    1.12
     bothered
    1.04
    icably
    1.03
     necessarily
    0.98
     bud
    0.95
     exactly
    0.93
     disappoint
    0.92
     thrilled
    0.87
     officially
    0.84
    orious
    0.84
    Act Density 0.232%

    No Known Activations