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

    Neuronpedia

    INDEX
    Explanations

    references to personal identity and ownership

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

    possessive pronouns and self-references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.59
    SuppressLint
    -0.46
    
    -0.46
    irited
    -0.45
     ſche
    -0.44
     оригіналу
    -0.43
    {#
    -0.43
     समीक्षाओं
    -0.43
     meisje
    -0.43
    ⓧ
    -0.43
    POSITIVE LOGITS
     own
    0.56
    自己
    0.51
    自己是
    0.50
    MessageTagHelper
    0.47
    自分は
    0.47
    自己的
    0.47
    自己在
    0.47
     فريبيس
    0.45
    themselves
    0.43
     themselves
    0.42
    Act Density 0.069%

    No Known Activations