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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns 'I' or 'my'

    oai_token-act-pair · gpt-3.5-turbo

    first-person pronouns indicating personal experience or perspective

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jarrett
    -0.74
    terday
    -0.66
    tnc
    -0.65
     Mosul
    -0.63
     totality
    -0.62
    icist
    -0.62
    alter
    -0.61
     Rockefeller
    -0.61
    abama
    -0.61
    lihood
    -0.60
    POSITIVE LOGITS
    'm
    1.36
    've
    1.13
    EEE
    1.07
    'll
    1.04
    WB
    1.00
    WI
    0.97
    'd
    0.96
     suppose
    0.90
     am
    0.89
    OTA
    0.89
    Act Density 0.281%

    No Known Activations