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

    Neuronpedia

    INDEX
    Explanations

    negations and expressions of uncertainty

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    rungsseite
    -1.01
     kaynağından
    -0.90
    __*/
    -0.87
    utnik
    -0.79
    -0.75
     ostavi
    -0.71
    حياته
    -0.69
    дә
    -0.67
    efeller
    -0.66
    ontal
    -0.65
    POSITIVE LOGITS
     NDEBUG
    0.63
     élector
    0.63
    obiety
    0.62
     silenzio
    0.55
     Gren
    0.54
     yeter
    0.54
     atlik
    0.54
     häls
    0.53
     menopause
    0.53
    !
    0.52
    Act Density 0.010%

    No Known Activations