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

    Neuronpedia

    INDEX
    Explanations

    statements related to politics and legal issues

    oai_token-act-pair · gpt-3.5-turbo

    statements or phrases related to accusations and legal actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ~/
    -0.76
    lease
    -0.71
     partName
    -0.66
    entary
    -0.66
     Pinball
    -0.66
     Monthly
    -0.66
    urry
    -0.65
    ilde
    -0.64
    ktop
    -0.62
    enhagen
    -0.62
    POSITIVE LOGITS
    ".[
    0.84
     terrorists
    0.83
     rapists
    0.79
     unfairly
    0.78
     terrorism
    0.78
     "
    0.77
     extremism
    0.76
     criminals
    0.76
     worse
    0.75
     "âĢ¦
    0.75
    Act Density 1.568%

    No Known Activations