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

    Neuronpedia

    INDEX
    Explanations

    phrases related to criminal activities and incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ftagPool
    -0.54
    SwingConstants
    -0.50
     maybe
    -0.49
    昔
    -0.48
     pasti
    -0.47
     old
    -0.47
     change
    -0.47
    Демографія
    -0.47
    wikidata
    -0.46
    λαμβ
    -0.46
    POSITIVE LOGITS
     Subsequently
    0.81
    Witnesses
    0.81
     للمعارف
    0.81
     Police
    0.79
    Police
    0.79
     witnesses
    0.78
     prosecutors
    0.78
     investigators
    0.78
     Subsequent
    0.77
    Investigators
    0.76
    Act Density 0.329%

    No Known Activations