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

    Neuronpedia

    INDEX
    Explanations

    references to incidents involving arrests and legal actions

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

    man charged or faces charges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InjectAttribute
    -0.62
     esternos
    -0.61
     HttpNotFound
    -0.54
    ंदीखरीदारी
    -0.53
     înc
    -0.53
     помню
    -0.52
     Picchu
    -0.51
    المشاركات
    -0.51
     كومونز
    -0.50
    𑄴
    -0.50
    POSITIVE LOGITS
     arrest
    0.45
     arrested
    0.32
    #+#
    0.29
    Jäh
    0.27
    omiast
    0.27
    Arrest
    0.27
    ]")]
    0.27
     jurisdic
    0.27
    rédients
    0.26
     javafx
    0.26
    Act Density 0.045%

    No Known Activations