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

    Neuronpedia

    INDEX
    Explanations

    punctuations and quotations used in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    '));
    -1.12
    )";
    -1.00
    ]');
    -0.97
    `,
    -0.96
    }');
    -0.94
    )");
    -0.94
    .";
    -0.93
    '):
    -0.93
    ")));
    -0.91
    %");
    -0.91
    POSITIVE LOGITS
    ("
    1.56
    ]=="
    1.44
     "
    1.40
    ="
    1.36
    :@"
    1.34
    !("
    1.31
    “
    1.25
    ('
    1.22
    _("
    1.19
    ["
    1.18
    Act Density 0.148%

    No Known Activations