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

    Neuronpedia

    INDEX
    Explanations

    instances of the pronoun "I" and other references to personal experiences or actions

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

    First-person pronouns followed by verbs

    np_acts-logits-general · gemini-2.0-flash

    when followed by a pronoun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     transférez
    -0.68
    AddTagHelper
    -0.68
    sizeCache
    -0.68
     nigdy
    -0.67
    ParallelGroup
    -0.65
    never
    -0.65
     aimer
    -0.64
     никогда
    -0.63
    WebElementEntity
    -0.63
    StoryboardSegue
    -0.62
    POSITIVE LOGITS
     comes
    0.70
     väl
    0.70
     inevitably
    0.68
     reaches
    0.67
     finally
    0.66
     enters
    0.64
     goes
    0.62
     arrives
    0.62
     occurs
    0.60
     WHEN
    0.60
    Act Density 0.298%

    No Known Activations