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

    Neuronpedia

    INDEX
    Explanations

    references to reporting incidents to the police

    oai_token-act-pair · gpt-3.5-turbo

    references to law enforcement and legal authorities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lives
    -0.67
     Purg
    -0.67
    tein
    -0.66
    ãĥ£
    -0.64
     cop
    -0.60
     Tik
    -0.59
     wonders
    -0.57
     perfect
    -0.56
    lost
    -0.56
     dominates
    -0.56
    POSITIVE LOGITS
    DERR
    0.87
    istrate
    0.73
     beforehand
    0.71
    ¶ħ
    0.67
     requesting
    0.66
    mbuds
    0.66
    mbudsman
    0.66
    Internal
    0.64
    usk
    0.64
     examiner
    0.64
    Act Density 0.373%

    No Known Activations