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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases indicating exceptions or prerequisites

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    migrationBuilder
    -0.71
    펙
    -0.66
    fono
    -0.65
     EAT
    -0.64
     Beatty
    -0.64
    ịa
    -0.63
    ioutil
    -0.63
    fought
    -0.63
     hearts
    -0.62
    Bibliographie
    -0.62
    POSITIVE LOGITS
     unless
    1.88
    unless
    1.80
     Unless
    1.74
    Unless
    1.71
     kecuali
    1.02
     until
    0.94
    除非
    0.93
     untill
    0.88
     UNTIL
    0.86
    until
    0.85
    Act Density 0.064%

    No Known Activations