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

    Neuronpedia

    INDEX
    Explanations

    terms related to criminal records and checks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    criminal history check

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ๆ
    -0.34
     tang
    -0.34
     Hal
    -0.30
     Tre
    -0.30
    切り
    -0.29
     Bot
    -0.29
    Kur
    -0.29
     ๆ
    -0.29
     preserv
    -0.29
    })).
    -0.28
    POSITIVE LOGITS
     criminal
    1.23
    Criminal
    1.16
    criminal
    1.16
     Criminal
    1.15
     CRIMINAL
    1.06
     background
    1.05
     achtergrond
    1.00
     Background
    0.98
     antecedentes
    0.94
    background
    0.94
    Act Density 0.119%

    No Known Activations