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

    Neuronpedia

    INDEX
    Explanations

    the word "whether" and its variations, indicating uncertainty or choice

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

    Whether followed by choices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ویکی‌پدی
    -0.55
     NEL
    -0.42
     furthermore
    -0.42
    --;
    -0.41
     tat
    -0.41
     FetchType
    -0.41
    FetchType
    -0.40
    tempted
    -0.40
    TAT
    -0.40
    [:]
    -0.40
    POSITIVE LOGITS
    Whether
    0.73
     Whether
    0.71
    whether
    0.53
     WHETHER
    0.47
    无论是
    0.47
    Whatever
    0.45
    DotNetBar
    0.45
    不论
    0.43
    Wherever
    0.43
     Whatever
    0.42
    Act Density 0.004%

    No Known Activations