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

    Neuronpedia

    INDEX
    Explanations

    different forms of punctuation marks and commas in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    keywords after punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſch
    -0.68
     "-";
    -0.68
     ſche
    -0.66
    ')))
    -0.64
     '-';
    -0.64
     faſt
    -0.63
     Reſ
    -0.60
    )))));
    -0.59
     '))
    -0.59
    ')));
    -0.59
    POSITIVE LOGITS
     kasarigan
    0.63
     <>",
    0.56
     $,
    0.53
    /,
    0.52
     otomatig
    0.51
    $,
    0.50
     orgánico
    0.49
    (_,
    0.49
    (),
    0.48
    (@"%@",
    0.47
    Act Density 0.155%

    No Known Activations