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

    Neuronpedia

    INDEX
    Explanations

    proper names of various individuals

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Disclaimer
    -0.76
     caveats
    -0.66
     archived
    -0.66
     understatement
    -0.65
    cknowled
    -0.64
     observations
    -0.63
     considerations
    -0.63
     denotes
    -0.63
    Requirements
    -0.62
     roadmap
    -0.61
    POSITIVE LOGITS
     Jr
    1.21
     aka
    1.08
     III
    1.04
     Sr
    1.02
    anski
    0.93
    ovich
    0.92
    gaard
    0.89
    opoulos
    0.88
    enegger
    0.87
    sson
    0.86
    Act Density 0.349%

    No Known Activations