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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to formal processes or rules

    oai_token-act-pair · gpt-3.5-turbo

    references to formal processes and methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gets
    -0.79
    hab
    -0.76
     Flavoring
    -0.75
    agi
    -0.75
    minster
    -0.73
    bitious
    -0.72
    orf
    -0.72
    ku
    -0.69
    inese
    -0.69
    stocks
    -0.69
    POSITIVE LOGITS
     procedure
    0.97
     procedures
    0.92
     governing
    0.83
     whereby
    0.78
     safeguards
    0.77
     Procedure
    0.76
     manuals
    0.75
    ional
    0.75
     Procedures
    0.74
     droid
    0.72
    Act Density 0.050%

    No Known Activations