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

    Neuronpedia

    INDEX
    Explanations

    phrases related to uncertainty and the process of evaluation or assessment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preceding "whether"

    np_acts-logits-general · gemini-2.0-flash

    whether to determine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ceğini
    -0.63
    osoba
    -0.58
    ']?>
    -0.54
    Portale
    -0.53
    ChildScrollView
    -0.53
    __["
    -0.51
     Cytometry
    -0.49
    odeficiency
    -0.49
    rénées
    -0.48
    KEYCODE
    -0.48
    POSITIVE LOGITS
     whether
    3.59
    whether
    3.04
     Whether
    2.78
    Whether
    2.63
     WHETHER
    2.53
     apakah
    2.06
    是否
    2.03
     是否
    1.75
    是否有
    1.65
    能否
    1.54
    Act Density 0.679%

    No Known Activations