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

    Neuronpedia

    INDEX
    Explanations

    news headlines reporting crimes and arrests

    oai_token-act-pair · gpt-3.5-turbo

    instances of arrests and legal actions involving individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gleaming
    -0.80
     mathemat
    -0.76
    Newsletter
    -0.74
    çļ
    -0.73
     Machines
    -0.72
    ¥µ
    -0.72
    ãĤ´
    -0.70
    æ©Ł
    -0.69
     coffers
    -0.69
     Transactions
    -0.69
    POSITIVE LOGITS
     accidentally
    0.90
    hunt
    0.80
     hospitalized
    0.78
     accused
    0.77
     suspected
    0.74
     convicted
    0.74
     allegedly
    0.74
    daughter
    0.73
     sentenced
    0.73
     hanged
    0.73
    Act Density 0.424%

    No Known Activations