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

    Neuronpedia

    INDEX
    Explanations

    first-person singular pronouns followed by modal verbs

    oai_token-act-pair · gpt-3.5-turbo

    first-person pronouns and expressions of personal thoughts or intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adra
    -0.84
    ante
    -0.69
    iment
    -0.69
    mentioned
    -0.66
    holding
    -0.64
    Footnote
    -0.64
    Same
    -0.63
    catentry
    -0.62
     reminders
    -0.62
    edition
    -0.60
    POSITIVE LOGITS
    osaurs
    0.79
    ovie
    0.78
    iuses
    0.69
    uchi
    0.65
    uin
    0.64
    usha
    0.64
     Bout
    0.62
    ould
    0.61
     RAND
    0.61
     provoking
    0.61
    Act Density 0.196%

    No Known Activations