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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns followed by strong confidence or certainty statements

    oai_token-act-pair · gpt-3.5-turbo

    the first-person and third-person pronouns indicating personal and collective experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stellar
    -0.79
     Globe
    -0.77
    eworthy
    -0.76
     Hague
    -0.71
     Confederation
    -0.66
    odder
    -0.62
     Leban
    -0.62
     Akron
    -0.61
    amia
    -0.61
     Yel
    -0.61
    POSITIVE LOGITS
    'll
    1.10
    've
    1.05
    'd
    0.99
    're
    0.98
     could
    0.82
     intend
    0.79
     owe
    0.79
    'm
    0.77
     shouldn
    0.77
    ould
    0.76
    Act Density 0.251%

    No Known Activations