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

    Neuronpedia

    INDEX
    Explanations

    inquiries related to measurements and comparisons of values or identities

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

    Questions ending with question marks

    np_acts-logits-general · gemini-2.0-flash

    detecting questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     "")
    -1.00
     "");
    -0.92
    '),
    -0.88
    '))
    -0.88
    ++
    -0.86
     "").
    -0.86
    '];
    -0.85
    .")
    -0.85
    ()].
    -0.84
    .");
    -0.82
    POSITIVE LOGITS
    0.66
     дописавши
    0.63
     виправивши
    0.61
    <()>
    0.53
     Wallflower
    0.50
    ">
    0.49
    felves
    0.45
    '>
    0.45
    makeConstraints
    0.43
    appliquent
    0.42
    Act Density 0.304%

    No Known Activations