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

    Neuronpedia

    INDEX
    Explanations

    statements related to criminal accusations

    oai_token-act-pair · gpt-3.5-turbo

    references to accusations and allegations of sexual misconduct

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nutshell
    -0.51
     premie
    -0.47
     Playoff
    -0.46
    -)
    -0.46
     Markets
    -0.45
     abound
    -0.44
     AMERICA
    -0.44
     Currently
    -0.44
    isible
    -0.44
     âĢº
    -0.43
    POSITIVE LOGITS
     incrim
    0.60
     burgl
    0.57
     medication
    0.56
     morphine
    0.54
     pills
    0.54
     unlawful
    0.53
     narcotics
    0.52
     intoxicated
    0.52
     curfew
    0.51
     burglary
    0.50
    Act Density 2.245%

    No Known Activations