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

    Neuronpedia

    INDEX
    Explanations

    repeated occurrences of the word "Max" or variations thereof, indicating a focus on the concept of "maximum."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    piel
    -0.34
    instrument
    -0.32
    kuuta
    -0.32
    ComponentModel
    -0.30
     cartila
    -0.30
     Pellegrini
    -0.29
    replies
    -0.28
     Johansson
    -0.28
    bye
    -0.28
    epam
    -0.28
    POSITIVE LOGITS
     Max
    3.48
     max
    3.47
    Max
    3.38
    max
    3.20
     MAX
    3.11
    MAX
    3.03
     maximum
    2.56
    マックス
    2.53
     Maximum
    2.48
     maximal
    2.39
    Act Density 0.119%

    No Known Activations