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

    Neuronpedia

    INDEX
    Explanations

    conditional statements or clauses indicating exceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    authier
    -0.72
    /***/
    -0.70
    fought
    -0.67
     Lea
    -0.66
    ɵɵelementEnd
    -0.66
    ịa
    -0.65
    psons
    -0.65
    fortawesome
    -0.63
     různ
    -0.61
     Sear
    -0.60
    POSITIVE LOGITS
     unless
    2.39
    unless
    2.23
     Unless
    2.19
    Unless
    2.15
    除非
    1.35
     until
    1.22
     untill
    1.16
     kecuali
    1.12
     UNTIL
    1.09
     Until
    1.05
    Act Density 0.090%

    No Known Activations