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

    Neuronpedia

    INDEX
    Explanations

    references or quotes from external sources

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "citing" and its variations, indicating references to sources or reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ould
    -0.74
    vic
    -0.73
    ipeg
    -0.71
    orld
    -0.71
    igmatic
    -0.69
    ians
    -0.68
    icum
    -0.65
    iland
    -0.65
    ascript
    -0.64
    ét
    -0.64
    POSITIVE LOGITS
     warnings
    0.84
     sources
    0.80
     unnamed
    0.78
     exemptions
    0.73
     fears
    0.71
     exceptions
    0.70
     NK
    0.68
     threats
    0.68
     citing
    0.67
     keywords
    0.67
    Act Density 0.023%

    No Known Activations