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

    Neuronpedia

    INDEX
    Explanations

    phrases containing first person pronouns

    oai_token-act-pair · gpt-3.5-turbo

    first-person pronouns and expressions of personal opinions or expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gutenberg
    -0.73
    ibrary
    -0.68
     proto
    -0.63
     Rolls
    -0.63
     etiquette
    -0.62
     Occupations
    -0.60
    iquette
    -0.59
     selves
    -0.59
     passers
    -0.58
     hers
    -0.58
    POSITIVE LOGITS
    'm
    1.20
     guess
    1.19
     think
    1.15
     believe
    1.14
     doubt
    1.13
     suppose
    1.13
     reckon
    1.08
     hope
    1.05
     presume
    1.03
     suspect
    1.01
    Act Density 0.184%

    No Known Activations