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

    Neuronpedia

    INDEX
    Explanations

    mentions of criminal acts or individuals involved in criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    references to criminal activity and individuals engaged in such activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahon
    -0.78
    tz
    -0.77
    emin
    -0.74
    zl
    -0.70
    independence
    -0.68
    printed
    -0.68
    mark
    -0.68
    equality
    -0.67
    ilde
    -0.67
     cushion
    -0.66
    POSITIVE LOGITS
     mastermind
    1.13
     lurking
    1.06
     who
    1.01
     gangs
    1.00
     prey
    1.00
     sentenced
    1.00
     abusing
    0.95
     hiding
    0.94
     traffickers
    0.94
     traff
    0.94
    Act Density 0.137%

    No Known Activations