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

    Neuronpedia

    INDEX
    Explanations

    references to criminal activity and associated legal terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adel
    -0.16
    ÑħодиÑĤÑĮ
    -0.16
    decorators
    -0.15
    illas
    -0.14
    iej
    -0.14
    otts
    -0.14
    itzer
    -0.14
    yst
    -0.13
     Discrim
    -0.13
     suicidal
    -0.13
    POSITIVE LOGITS
     crime
    0.45
     crimes
    0.39
     offense
    0.36
    crime
    0.34
     offenses
    0.34
     Crime
    0.31
     infra
    0.31
     offence
    0.30
     Off
    0.29
    -cr
    0.28
    Act Density 0.112%

    No Known Activations