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

    Neuronpedia

    INDEX
    Explanations

    conditional statements that introduce exceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    펙
    -0.77
    gatsby
    -0.72
     vuitton
    -0.72
     Gait
    -0.71
    ioutil
    -0.71
     Beatty
    -0.71
    authier
    -0.70
    Демографія
    -0.70
    Xna
    -0.68
    limia
    -0.68
    POSITIVE LOGITS
     unless
    1.46
     Unless
    1.32
    unless
    1.30
    Unless
    1.30
     дописавши
    0.78
     kecuali
    0.73
     otherwise
    0.71
     until
    0.71
    除非
    0.71
    Otherwise
    0.66
    Act Density 0.072%

    No Known Activations