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

    Neuronpedia

    INDEX
    Explanations

    terms related to scientific research and experimental investigation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    featureID
    -0.75
    AddTagHelper
    -0.74
    OGND
    -0.74
    AndEndTag
    -0.68
     Paglinawan
    -0.67
    Personendaten
    -0.62
    InsertCommand
    -0.61
    ArgumentParser
    -0.60
     BoxDecoration
    -0.59
    WireFormatLite
    -0.59
    POSITIVE LOGITS
    NUMX
    0.63
     demografica
    0.61
     again
    0.58
    niająca
    0.54
    んぼ
    0.53
     επίσης
    0.52
    ibid
    0.52
    ‍♂️
    0.51
    vodu
    0.51
    inaudible
    0.51
    Act Density 1.222%

    No Known Activations