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

    Neuronpedia

    INDEX
    Explanations

    names of individuals involved in legal matters

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     perfon
    -1.00
     ftu
    -0.94
     aen
    -0.92
     affez
    -0.92
     tamen
    -0.87
     „,
    -0.82
     fatis
    -0.82
     haer
    -0.81
     thut
    -0.81
     fua
    -0.80
    POSITIVE LOGITS
     himself
    0.69
    ’
    0.61
    '
    0.59
     Himself
    0.53
     kendisi
    0.49
     during
    0.49
    himself
    0.48
     themselves
    0.47
     stesso
    0.47
     noexcept
    0.47
    Act Density 0.389%

    No Known Activations