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

    Neuronpedia

    INDEX
    Explanations

    instances of the pronoun "I."

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

    I followed by verb agreement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     amplio
    -0.37
     extranjeros
    -0.36
     libremente
    -0.32
     tourisme
    -0.31
     recueil
    -0.31
     húmedo
    -0.31
     douce
    -0.31
     disparos
    -0.30
     medios
    -0.30
     inicio
    -0.30
    POSITIVE LOGITS
    ChildScrollView
    1.07
    iſchen
    0.96
    ſicht
    0.96
    ſſung
    0.95
    <unused74>
    0.93
    <unused51>
    0.92
    <unused76>
    0.92
    <unused41>
    0.92
    enablog
    0.92
    [@BOS@]
    0.92
    Act Density 0.036%

    No Known Activations