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

    Neuronpedia

    INDEX
    Explanations

    references to law enforcement actions and detainee rights

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

    after "arrest" or "arrested"

    np_acts-logits-general · gemini-2.0-flash

    arrested or detained

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     upvote
    -0.63
     &___
    -0.63
     AssemblyCulture
    -0.62
    TypedDataSet
    -0.61
     pellic
    -0.60
    ArgsConstructor
    -0.59
     HttpNotFound
    -0.56
     propOrder
    -0.54
     noDo
    -0.54
    ueger
    -0.54
    POSITIVE LOGITS
     arrest
    1.50
     arrested
    1.32
     arrests
    1.30
     Arrest
    1.18
    arrest
    1.17
     arresting
    1.17
    Arrest
    1.09
     detain
    0.98
     detained
    0.93
     Arrested
    0.89
    Act Density 0.581%

    No Known Activations