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

    Neuronpedia

    INDEX
    Explanations

    pronouns and verbs referring to oneself

    oai_token-act-pair · gpt-3.5-turbo

    references to self-related actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    heny
    -0.80
    veyard
    -0.74
    rought
    -0.73
    vertisements
    -0.71
    microsoft
    -0.70
    grain
    -0.70
    profits
    -0.70
     revolutions
    -0.68
    amazon
    -0.68
    sweet
    -0.67
    POSITIVE LOGITS
     personally
    0.73
     himself
    0.73
     profess
    0.71
     underwater
    0.71
     confessed
    0.70
     mate
    0.69
     submar
    0.66
     unworthy
    0.65
     remorse
    0.65
     onstage
    0.64
    Act Density 0.029%

    No Known Activations