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

    Neuronpedia

    INDEX
    Explanations

    negative declarations or negations

    oai_token-act-pair · gpt-3.5-turbo

    repeated expressions of negation or the absence of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    haul
    -0.80
    antis
    -0.70
    UME
    -0.69
    Broad
    -0.69
    Stra
    -0.68
    asts
    -0.67
    rib
    -0.66
    orts
    -0.65
    CD
    -0.65
    ordes
    -0.65
    POSITIVE LOGITS
     appetite
    0.81
     shortage
    0.79
     overlap
    0.77
     precedent
    0.76
     hesitation
    0.74
     unanim
    0.73
     evidence
    0.73
     chance
    0.72
     detectable
    0.71
     buried
    0.67
    Act Density 0.086%

    No Known Activations