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

    Neuronpedia

    INDEX
    Explanations

    sections or divisions of text, particularly labeled parts or segments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erator
    -0.19
    aring
    -0.17
    erin
    -0.17
    ared
    -0.16
    ought
    -0.15
    aths
    -0.15
    pline
    -0.15
    wart
    -0.15
    ëĭĪëĭ¤
    -0.15
    zimmer
    -0.15
    POSITIVE LOGITS
    icular
    0.34
    icipation
    0.30
    aking
    0.28
    icip
    0.27
    isans
    0.27
    ake
    0.26
    ook
    0.25
    ially
    0.25
    ners
    0.24
    isan
    0.24
    Act Density 0.031%

    No Known Activations