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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases or questions typically indicating choice or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulihan
    -0.70
     Ballard
    -0.67
     Pires
    -0.63
    RenderAtEndOf
    -0.60
     Mundi
    -0.57
    خوری
    -0.55
    לע
    -0.54
     Medici
    -0.54
     fejl
    -0.54
     okazji
    -0.53
    POSITIVE LOGITS
     whether
    3.93
    whether
    3.56
     Whether
    3.27
     WHETHER
    3.23
    Whether
    3.16
     apakah
    2.01
    是否
    1.86
     是否
    1.61
     regardless
    1.49
    是否有
    1.46
    Act Density 0.071%

    No Known Activations