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

    Neuronpedia

    INDEX
    Explanations

    the opening brackets used in programming syntax, specifically instances of the "[]" notation

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

    brackets and dollar signs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Trigger
    -0.39
     cár
    -0.38
     Turquie
    -0.37
     ondes
    -0.37
    >')
    -0.36
    GenerationType
    -0.35
    Sensitivity
    -0.34
     actionTypes
    -0.33
     Allemagne
    -0.33
    )')
    -0.32
    POSITIVE LOGITS
     [[
    2.19
    =[[
    1.55
    ([[
    1.48
     [['
    1.25
    [[
    1.23
     {{{
    0.99
     [][]
    0.89
     {{
    0.87
    [['
    0.86
     "{{
    0.85
    Act Density 0.005%

    No Known Activations