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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly those indicating sentence boundaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    And
    -1.00
     you
    -0.95
     And
    -0.90
     Maybe
    -0.86
    Maybe
    -0.85
     maybe
    -0.82
     I
    -0.81
     yes
    -0.80
     so
    -0.77
     now
    -0.76
    POSITIVE LOGITS
    )");
    1.11
    )";
    1.09
    ividual
    1.03
    ".
    1.02
    $.
    1.01
    ")));
    1.00
    )"),
    0.95
    '},
    0.94
    };*/
    0.94
    "):
    0.94
    Act Density 1.011%

    No Known Activations