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

    Neuronpedia

    INDEX
    Explanations

    occurrences of pronouns referring to people or entities

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

    pronoun followed by verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.83
    ChildScrollView
    -0.79
    征詢我
    -0.72
    twimg
    -0.71
    gypte
    -0.68
    featureID
    -0.68
     ProtoMessage
    -0.67
    aarrggbb
    -0.65
     ddelwed
    -0.65
    KEYCODE
    -0.64
    POSITIVE LOGITS
    The
    0.61
    It
    0.54
    Is
    0.53
    In
    0.52
     It
    0.50
    We
    0.47
     The
    0.47
    This
    0.47
     Is
    0.46
    He
    0.46
    Act Density 0.176%

    No Known Activations