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

    Neuronpedia

    INDEX
    Explanations

    legal terminology and specific phrases related to court proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ::*;
    -0.67
    ++);
    -0.63
    )");
    -0.62
     antaranya
    -0.62
    )");
    -0.62
    ")->
    -0.61
    ){$
    -0.58
    )();
    -0.58
    "]="
    -0.57
     exempel
    -0.57
    POSITIVE LOGITS
     without
    1.14
     assuming
    1.08
     having
    1.00
    without
    0.97
     needing
    0.96
     WITHOUT
    0.92
     despite
    0.91
     lacking
    0.90
     habiendo
    0.90
    WITHOUT
    0.87
    Act Density 0.323%

    No Known Activations