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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks used to denote speech or quotations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    '));
    -1.13
    }');
    -1.08
    ]');
    -1.03
    %");
    -1.02
    ...');
    -1.02
    ")));
    -0.96
    )');
    -0.96
    _
    -0.94
    .";
    -0.92
    }';
    -0.92
    POSITIVE LOGITS
    “
    1.99
     “
    1.93
     "
    1.62
    ("
    1.51
     ‘
    1.43
    (“
    1.43
    ，“
    1.41
    =”
    1.36
    ="
    1.34
     „
    1.31
    Act Density 0.519%

    No Known Activations