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

    Neuronpedia

    INDEX
    Explanations

    expressions related to confusion or lack of clarity

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

    "what" or variants of "what"

    np_acts-logits-general · gemini-2.0-flash

    see what

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.76
     SUDOC
    -0.70
    httphttps
    -0.69
    alnız
    -0.67
    WebElementEntity
    -0.61
    ագրություններ
    -0.60
     ویکی‌پدیا
    -0.59
     resourceCulture
    -0.56
    Derbyniad
    -0.55
     newBuilder
    -0.55
    POSITIVE LOGITS
     what
    3.93
    what
    3.09
    What
    2.52
     What
    2.48
     WHAT
    2.39
    WHAT
    2.16
     whats
    1.93
    whats
    1.77
     hva
    1.75
     hvad
    1.74
    Act Density 0.823%

    No Known Activations