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

    Neuronpedia

    INDEX
    Explanations

    information related to crime, arrests, and police incidents

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    inav
    -0.83
     Which
    -0.78
     Extend
    -0.75
     entails
    -0.75
    omial
    -0.74
     Highlights
    -0.74
    Which
    -0.71
    ependence
    -0.70
    eers
    -0.67
    ESE
    -0.67
    POSITIVE LOGITS
    nt
    1.13
     able
    1.11
     supposed
    1.08
     rumored
    1.02
     briefed
    1.00
     greeted
    1.00
     bitten
    0.99
     tasked
    0.99
     unable
    0.99
     born
    0.98
    Act Density 1.914%

    No Known Activations