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

    Neuronpedia

    INDEX
    Explanations

    references to personal pronouns and direct address in the text

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

    giving me or us

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    verifyException
    -0.45
    ","");
    -0.45
    BorderFactory
    -0.44
    userModel
    -0.41
    queryString
    -0.41
    DataMember
    -0.41
     jScrollPane
    -0.40
     userType
    -0.39
     "<?
    -0.39
    AutoField
    -0.39
    POSITIVE LOGITS
     fået
    0.59
    有过
    0.56
    Provides
    0.56
     Obtén
    0.53
     Tenemos
    0.53
    give
    0.53
    Tienen
    0.52
     punya
    0.52
     bekommen
    0.52
     get
    0.52
    Act Density 0.021%

    No Known Activations