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

    Neuronpedia

    INDEX
    Explanations

    legal and procedural terms related to law and regulations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Citiz
    -0.93
     beh
    -0.92
     Savior
    -0.87
    miah
    -0.87
     Myster
    -0.85
     Morning
    -0.83
     pu
    -0.82
     WARN
    -0.81
     proport
    -0.81
     nutrit
    -0.81
    POSITIVE LOGITS
    âĢ¦)
    1.19
    cases
    1.19
    iii
    1.15
    âĢ¦]
    1.10
    band
    1.08
    hd
    1.05
    iv
    1.01
    ii
    1.00
    102
    0.99
    single
    0.98
    Act Density 0.108%

    No Known Activations