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

    Neuronpedia

    INDEX
    Explanations

    mentions of legal consequences and imprisonment

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    yip
    -1.12
    rians
    -1.05
    xit
    -1.03
     Bundes
    -0.90
     ITS
    -0.89
     Happ
    -0.89
     Lynd
    -0.88
    ãĤ¤ãĥĪ
    -0.87
     Alic
    -0.87
    soDeliveryDate
    -0.87
    POSITIVE LOGITS
    broken
    1.37
    house
    1.24
    break
    1.23
    breakers
    1.23
    breaks
    1.20
    breaking
    1.16
    stead
    1.13
    itory
    1.12
    ishment
    1.08
     jails
    1.07
    Act Density 0.506%

    No Known Activations