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

    Neuronpedia

    INDEX
    Explanations

    references to legal claims and evidence in a courtroom context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     encantan
    -0.56
     gustan
    -0.56
     quelcon
    -0.55
     coppia
    -0.51
     copertina
    -0.50
     celui
    -0.49
     defaultstate
    -0.49
    libatkan
    -0.48
     varandra
    -0.47
     auxquelles
    -0.47
    POSITIVE LOGITS
     own
    1.13
    %");
    1.08
    "]);
    1.05
    '));
    1.03
    )");
    0.99
    )');
    0.98
    "):
    0.96
    }');
    0.96
    ]").
    0.96
    "));
    0.94
    Act Density 0.182%

    No Known Activations