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

    Neuronpedia

    INDEX
    Explanations

    pronouns and verbs that indicate personal relationships or actions

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

    phrases starting with by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     utafitiHapana
    -0.73
    parsedMessage
    -0.71
    PyExc
    -0.68
    ValueStyle
    -0.68
    arangay
    -0.60
    CppMethod
    -0.60
     CURIAM
    -0.60
     autorytatywna
    -0.60
     nahilalakip
    -0.58
     للاسماء
    -0.58
    POSITIVE LOGITS
     by
    0.35
    帖最后由
    0.33
     satisfait
    0.27
    enabled
    0.27
     maso
    0.26
    jusi
    0.26
    hithe
    0.25
    webElementXpaths
    0.25
     distribu
    0.25
     verificación
    0.25
    Act Density 0.113%

    No Known Activations