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

    Neuronpedia

    INDEX
    Explanations

    causal relationships within the text

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

    causes or constitutes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -0.60
    TargetApi
    -0.57
    Personendaten
    -0.57
     وتسجيلات
    -0.55
     оригіналу
    -0.51
    Diweddarwch
    -0.50
    httphttps
    -0.50
    CardBody
    -0.50
    原始内容存档于
    -0.50
     nahilalakip
    -0.49
    POSITIVE LOGITS
     stanowi
    0.45
     predstav
    0.41
     provoca
    0.41
     вызывает
    0.40
     sprawia
    0.35
     Freude
    0.34
     CreateTagHelper
    0.34
    "])
    0.34
     difficulty
    0.34
     представляет
    0.33
    Act Density 0.026%

    No Known Activations