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

    Neuronpedia

    INDEX
    Explanations

    words related to criminal activities and incidents

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    laus
    -1.07
    anson
    -1.06
    annot
    -0.97
     Marketable
    -0.93
    glomer
    -0.88
    à¥
    -0.87
    ï¸ı
    -0.85
    oku
    -0.85
    uten
    -0.85
    emonic
    -0.85
    POSITIVE LOGITS
     premises
    1.25
     courtyard
    1.16
     precinct
    1.08
     courthouse
    1.08
    stead
    1.05
    yard
    1.03
     balcony
    1.03
    wife
    1.02
     doorstep
    1.00
     depot
    0.97
    Act Density 2.239%

    No Known Activations