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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "Tak" with different numbers following it which seem to represent relevance levels

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Tak" or variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    theless
    -0.75
     Grind
    -0.68
    ORPG
    -0.65
    pherd
    -0.64
    isters
    -0.63
     casualty
    -0.62
     prevailing
    -0.60
     deduction
    -0.59
     breakup
    -0.59
     guiActiveUnfocused
    -0.58
    POSITIVE LOGITS
    amaru
    1.14
    istani
    1.09
    atsuki
    1.08
    umar
    0.93
    ables
    0.93
    anu
    0.91
    onga
    0.89
    uning
    0.88
    amura
    0.87
    arte
    0.87
    Act Density 0.041%

    No Known Activations