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

    Neuronpedia

    INDEX
    Explanations

    specific legal terminology and their associated sections and citations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Anſ
    -1.03
     myſelf
    -1.02
     purpoſe
    -0.96
     ſind
    -0.95
     auffi
    -0.94
     Houſe
    -0.93
    ſelf
    -0.92
     Efq
    -0.92
     pleaſure
    -0.92
     perſon
    -0.92
    POSITIVE LOGITS
     
    0.49
     universal
    0.49
     m
    0.48
     M
    0.47
     an
    0.46
     v
    0.46
     p
    0.45
     var
    0.45
     I
    0.44
     im
    0.44
    Act Density 0.007%

    No Known Activations