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

    Neuronpedia

    INDEX
    Explanations

    references to arrests and legal situations involving individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _FAULT
    -0.15
    EMPL
    -0.14
     Alv
    -0.14
    å±Ĭ
    -0.14
    _CTRL
    -0.14
    ุà¹Ī
    -0.14
    ISR
    -0.14
    .compiler
    -0.13
    val
    -0.13
    istle
    -0.13
    POSITIVE LOGITS
     arrest
    0.37
     arrested
    0.30
     Arrest
    0.28
     handc
    0.28
     jail
    0.27
     arresting
    0.26
     custody
    0.26
     arrests
    0.25
     detention
    0.25
     booking
    0.24
    Act Density 0.147%

    No Known Activations