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

    Neuronpedia

    INDEX
    Explanations

    terms related to words and vocabulary

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

    words and vocabulary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ISupport
    -0.56
    BeginInit
    -0.53
    SafeAreaView
    -0.46
    EndInit
    -0.46
     EconPapers
    -0.43
    sidemargin
    -0.43
    setVerticalGroup
    -0.43
     okaz
    -0.42
    inheritdoc
    -0.41
    EnableWeb
    -0.41
    POSITIVE LOGITS
     words
    0.78
     word
    0.74
    Word
    0.73
     Words
    0.68
    Words
    0.66
     Word
    0.66
     WORDS
    0.63
    words
    0.63
    word
    0.63
     vocabulary
    0.63
    Act Density 0.025%

    No Known Activations