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

    Neuronpedia

    INDEX
    Explanations

    references to serious criminal behavior and offenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÅĻet
    -0.17
    yst
    -0.15
    ckett
    -0.15
    ceptor
    -0.14
    decorators
    -0.14
    주ìĿĺ
    -0.14
    otts
    -0.14
    arget
    -0.13
    assed
    -0.13
     Vulner
    -0.13
    POSITIVE LOGITS
     crime
    0.68
     crimes
    0.57
    crime
    0.54
     Crime
    0.53
    Crime
    0.45
     Crimes
    0.45
    -cr
    0.40
     offense
    0.40
     offenses
    0.39
    çĬ¯ç½ª
    0.37
    Act Density 0.168%

    No Known Activations