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

    Neuronpedia

    INDEX
    Explanations

    terms related to criminal activity and law enforcement responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilig
    -0.16
    isoft
    -0.15
     maybe
    -0.15
    inux
    -0.14
    aybe
    -0.14
    fault
    -0.14
    ạp
    -0.14
     ден
    -0.14
    sik
    -0.13
    缣
    -0.13
    POSITIVE LOGITS
    llib
    0.15
     aforementioned
    0.14
    uby
    0.14
    eres
    0.14
     Roths
    0.13
     Arnold
    0.13
     Success
    0.13
     separate
    0.13
     Kemp
    0.13
     success
    0.13
    Act Density 0.023%

    No Known Activations