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

    Neuronpedia

    INDEX
    Explanations

    pronouns and verbs indicating comparison or amount

    oai_token-act-pair · gpt-3.5-turbo

    references to the subject "they" in various contexts relating to perceptions or evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Christy
    -0.68
     Fine
    -0.67
     Brig
    -0.61
     reinforcement
    -0.61
    urai
    -0.60
     Lieutenant
    -0.59
     Lt
    -0.58
     Vine
    -0.58
     Mint
    -0.57
     Superior
    -0.55
    POSITIVE LOGITS
    ago
    0.86
    usual
    0.79
     imagined
    0.79
    fters
    0.78
     ourselves
    0.75
     yourselves
    0.71
    immigrant
    0.70
     herself
    0.70
     usual
    0.70
     intended
    0.69
    Act Density 0.086%

    No Known Activations