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

    Neuronpedia

    INDEX
    Explanations

    pronouns and their variations used in sentences

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

    you it there

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.67
    يميديا
    -0.65
    CloseOperation
    -0.65
    دانشنامهٔ
    -0.62
    Vidite
    -0.62
    Хьажоргаш
    -0.62
    idlertid
    -0.60
     Biôgrafia
    -0.59
     asym
    -0.59
    RegressionTest
    -0.59
    POSITIVE LOGITS
    tonode
    0.40
     they
    0.37
    they
    0.37
     оно
    0.36
    YOU
    0.36
    You
    0.35
     You
    0.35
     cortinas
    0.34
     esso
    0.34
     THEY
    0.34
    Act Density 0.233%

    No Known Activations