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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "take" in different contexts or phrases

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

    take followed by common phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ukunfts
    -0.44
     initComponents
    -0.42
    mott
    -0.41
     companyId
    -0.40
    illou
    -0.40
    sterreich
    -0.40
    borderColor
    -0.39
     felizes
    -0.39
    errorMsg
    -0.39
    BorderFactory
    -0.38
    POSITIVE LOGITS
    take
    2.13
    TAKE
    2.02
    Take
    2.00
     Take
    1.92
     TAKE
    1.81
     take
    1.72
    takes
    1.60
    taken
    1.55
    taking
    1.45
    Takes
    1.43
    Act Density 0.008%

    No Known Activations