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

    Neuronpedia

    INDEX
    Explanations

    negations or statements of absence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kadang
    -0.57
     sometimes
    -0.54
     algunos
    -0.51
     parfois
    -0.51
     alguns
    -0.51
    sometimes
    -0.51
     altamente
    -0.50
     algunas
    -0.50
     algumas
    -0.49
    Some
    -0.49
    POSITIVE LOGITS
     discernible
    1.04
     discer
    0.95
     appreciable
    0.92
     obvious
    0.90
     detectable
    0.90
     indication
    0.87
     noticeable
    0.87
    出版年
    0.86
     need
    0.85
     mention
    0.85
    Act Density 0.496%

    No Known Activations