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

    Neuronpedia

    INDEX
    Explanations

    instances of arrests and police interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ANDROID
    -0.16
    .unpack
    -0.15
     ÑĢев
    -0.14
    merc
    -0.14
    å±Ĭ
    -0.14
     scor
    -0.14
    ινÏĮ
    -0.14
    ãģĹãģ®
    -0.13
    äl
    -0.13
    eyJ
    -0.13
    POSITIVE LOGITS
     arrest
    0.66
     arrested
    0.56
     Arrest
    0.56
     arrests
    0.56
     arresting
    0.50
     detain
    0.42
     appreh
    0.42
    -ar
    0.38
     detention
    0.37
     detained
    0.36
    Act Density 0.237%

    No Known Activations