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

    Neuronpedia

    INDEX
    Explanations

    percentage values and their context in a document

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

    percentage followed by words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.47
     Desenvolvimento
    -0.39
     which
    -0.38
     sitten
    -0.37
    zação
    -0.36
     করে
    -0.36
     keterampilan
    -0.36
     defaultstate
    -0.36
     mitä
    -0.35
    ระ
    -0.35
    POSITIVE LOGITS
     %.
    0.66
    (%)
    0.65
     \%
    0.65
     %,
    0.65
     (%)
    0.65
    %?
    0.64
    ()%
    0.63
    %",
    0.63
    \%
    0.63
    %.
    0.62
    Act Density 0.086%

    No Known Activations