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

    Neuronpedia

    INDEX
    Explanations

    the occurrence of the word "one" in various contexts

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

    each one followed by description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    richTextPanel
    -0.57
    Geplaatst
    -0.49
    OGND
    -0.47
     ویکی‌پدی
    -0.45
     propOrder
    -0.44
     playoffs
    -0.41
     дописавши
    -0.41
    chiat
    -0.41
    uarine
    -0.40
     parachute
    -0.40
    POSITIVE LOGITS
     everyone
    0.59
     ognuno
    0.56
     EVERYONE
    0.52
     ſche
    0.51
     everybody
    0.50
     Beſ
    0.48
     Theſe
    0.48
     Monfieur
    0.48
     newBuilder
    0.48
    WriteTagHelper
    0.47
    Act Density 0.005%

    No Known Activations