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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns followed by the verb "to be" in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    sentences starting with "It" and focusing on statements of perspective or experience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Eighth
    -0.75
    present
    -0.59
    itatively
    -0.59
    Major
    -0.58
     Passenger
    -0.57
     Lar
    -0.57
    nda
    -0.56
     Tur
    -0.56
    ielding
    -0.56
     Dayton
    -0.56
    POSITIVE LOGITS
     ain
    1.14
    chy
    1.10
     happened
    1.05
     seems
    1.05
    unes
    1.03
     wasn
    1.02
     hurts
    1.00
    iner
    0.99
     happens
    0.96
     mattered
    0.95
    Act Density 0.316%

    No Known Activations