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

    Neuronpedia

    INDEX
    Explanations

    pronouns and proper nouns related to a specific individual

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals, particularly focusing on pronouns and their associated actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hooting
    -0.86
    ³³³³³³³³³³³³³³³³
    -0.74
    Temperature
    -0.71
    ³³³³
    -0.70
     Engineers
    -0.69
     âĨij
    -0.68
    breeding
    -0.67
    Researchers
    -0.67
     Composite
    -0.65
     Genetic
    -0.64
    POSITIVE LOGITS
    zbollah
    1.26
     campaigned
    0.97
     appoint
    0.91
     speeches
    0.89
     aides
    0.87
    enegger
    0.87
     pard
    0.87
     administrations
    0.87
     promised
    0.86
     pledged
    0.86
    Act Density 0.350%

    No Known Activations