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

    Neuronpedia

    INDEX
    Explanations

    the pronoun "I" and variations of its form

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

    "I" followed by a modal verb or supposition

    np_acts-logits-general · gemini-2.0-flash

    first-person opinion or possibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CloseOperation
    -1.07
     pinulongan
    -0.86
     ivelany
    -0.85
    AccessorTable
    -0.85
    localctx
    -0.78
    ]")]
    -0.76
     Eſ
    -0.76
    ConstraintMaker
    -0.75
    Jeografia
    -0.75
    Personensuche
    -0.74
    POSITIVE LOGITS
     am
    1.03
     myself
    1.00
     guess
    0.83
     personally
    0.74
     miei
    0.74
    ’
    0.70
     Myself
    0.70
    '
    0.70
     have
    0.68
     can
    0.65
    Act Density 0.237%

    No Known Activations