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

    Neuronpedia

    INDEX
    Explanations

    structural elements commonly found in programming or mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IsMutable
    -1.04
    )";
    -1.03
    )");
    -0.97
    ]';
    -0.96
     bezeichneter
    -0.93
    )';
    -0.93
    }';
    -0.91
    ]');
    -0.89
    }');
    -0.88
    ."));
    -0.88
    POSITIVE LOGITS
     -
    0.61
    šanai
    0.57
    ⓘ
    0.57
    님
    0.56
    :+:
    0.54
    rąg
    0.53
    ثار
    0.53
    様
    0.51
    factories
    0.51
     is
    0.51
    Act Density 0.203%

    No Known Activations