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

    Neuronpedia

    INDEX
    Explanations

    instances of the pronoun "I" and related self-referential phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ord
    -0.15
    uchs
    -0.14
     sworn
    -0.14
     swore
    -0.14
    ific
    -0.14
     were
    -0.13
    tatus
    -0.13
    ake
    -0.13
    were
    -0.13
    embros
    -0.13
    POSITIVE LOGITS
    ronic
    0.23
     mean
    0.21
     Mean
    0.18
    OW
    0.17
    Mean
    0.17
    HONE
    0.17
     therefore
    0.17
     certainly
    0.16
     wish
    0.16
     wonder
    0.16
    Act Density 0.262%

    No Known Activations