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

    Neuronpedia

    INDEX
    Explanations

    terms related to philosophical and legal theoretical concepts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -1.12
     s
    -0.60
     (
    -0.60
     g
    -0.57
     e
    -0.57
     t
    -0.56
     and
    -0.56
     Sy
    -0.56
    ↵↵
    -0.56
     c
    -0.56
    POSITIVE LOGITS
     meis
    1.85
     fatis
    1.82
     vns
    1.74
     paff
    1.73
     vne
    1.68
     fua
    1.64
     marte
    1.64
     ftu
    1.64
     fta
    1.63
     waer
    1.63
    Act Density 0.209%

    No Known Activations