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

    Neuronpedia

    INDEX
    Explanations

    numeric sequences related to measurements or probabilities

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

    materials-13-03111

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    !*\
    -0.34
    <bos>
    -0.30
    TagMode
    -0.29
    MessageState
    -0.27
    uminense
    -0.27
    ’
    -0.26
     NSCoder
    -0.25
    #![
    -0.23
    +:+
    -0.22
     isKindOfClass
    -0.22
    POSITIVE LOGITS
    GillaGilla
    0.65
    ஦
    0.63
    <unused41>
    0.63
    <unused8>
    0.63
    <unused19>
    0.62
    <unused17>
    0.62
    <unused21>
    0.62
    <unused28>
    0.62
    [@BOS@]
    0.62
    <unused16>
    0.62
    Act Density 0.463%

    No Known Activations