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

    Neuronpedia

    INDEX
    Explanations

    instances of repetition or redundancy in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     overview
    -0.22
    overview
    -0.20
     Overview
    -0.20
    Overview
    -0.20
     Oversight
    -0.18
     overnight
    -0.16
    qi
    -0.16
    quate
    -0.16
    ship
    -0.16
    uality
    -0.16
    POSITIVE LOGITS
    tones
    0.31
    heard
    0.29
    lying
    0.29
    tures
    0.29
    board
    0.29
    alls
    0.29
    lord
    0.28
    ture
    0.28
    comes
    0.28
    hang
    0.27
    Act Density 0.140%

    No Known Activations