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

    Neuronpedia

    INDEX
    Explanations

    terms related to legal justification

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Oleg
    -0.68
    ql
    -0.63
    숙
    -0.63
     pebbles
    -0.63
     Andrei
    -0.61
    труд
    -0.60
     Adrien
    -0.60
     sant
    -0.59
                
    -0.59
     člove
    -0.59
    POSITIVE LOGITS
    Jus
    1.08
     Jus
    1.07
    Justification
    0.97
     Justification
    0.96
    ]));
    0.90
     gius
    0.89
    jus
    0.88
    tifications
    0.85
     justifying
    0.84
    justify
    0.82
    Act Density 0.006%

    No Known Activations