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

    Neuronpedia

    INDEX
    Explanations

    examples of accusations or criticisms involving misconduct or mistakes

    oai_token-act-pair · gpt-3.5-turbo

    references to investigations and allegations of misconduct

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aphael
    -0.76
     nationalism
    -0.73
     Hawking
    -0.73
     congr
    -0.72
     Ideas
    -0.71
    Brexit
    -0.70
     Euros
    -0.70
     dream
    -0.69
    osphere
    -0.69
     immortality
    -0.68
    POSITIVE LOGITS
     misconduct
    1.50
     violations
    1.46
     audits
    1.36
     deficiencies
    1.36
     failings
    1.32
     improper
    1.32
     mishand
    1.30
     failures
    1.29
     improperly
    1.28
     negligent
    1.27
    Act Density 0.916%

    No Known Activations