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

    Neuronpedia

    INDEX
    Explanations

    references to police or law enforcement agencies

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
    AsUp
    -1.02
     ſever
    -0.96
     themſelves
    -0.91
     ainfi
    -0.91
     Theſe
    -0.91
     Jefus
    -0.83
     ſche
    -0.82
     Reſ
    -0.82
     Monfieur
    -0.82
     raiſ
    -0.81
    POSITIVE LOGITS
     served
    0.53
     staff
    0.52
     serve
    0.50
     del
    0.49
    nonatomic
    0.49
     servizio
    0.47
    </b>
    0.47
    staff
    0.45
    制
    0.45
     stuff
    0.44
    Act Density 0.019%

    No Known Activations