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

    Neuronpedia

    INDEX
    Explanations

    the occurrence of the word "which"

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

    which followed by verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WithIOException
    -0.64
    WireFormatLite
    -0.59
     ویکی‌پدی
    -0.57
     MainAxisSize
    -0.57
    RTEE
    -0.57
    hoeddwyd
    -0.56
     AssemblyCulture
    -0.56
    jspb
    -0.56
    Enllaces
    -0.56
    addCriterion
    -0.55
    POSITIVE LOGITS
    Taking
    0.38
     Taking
    0.36
     Moscou
    0.35
     الجمه
    0.34
    wieś
    0.33
    viertel
    0.33
    lorus
    0.33
    商品説明
    0.32
     Suez
    0.32
     anatom
    0.32
    Act Density 0.042%

    No Known Activations