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

    Neuronpedia

    INDEX
    Explanations

    occurrences of introductory words or phrases indicating a new section or thought in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    $MESS
    -0.22
    owing
    -0.21
    serrat
    -0.21
    paring
    -0.20
    plevel
    -0.18
    leccion
    -0.18
    complete
    -0.17
    give
    -0.17
    ersiz
    -0.17
     \č↵
    -0.16
    POSITIVE LOGITS
    odore
    0.56
    adays
    0.54
    etheless
    0.42
    atre
    0.38
    atomy
    0.32
    bsites
    0.32
    tlement
    0.29
    achusetts
    0.29
    jamin
    0.28
    stitute
    0.28
    Act Density 0.718%

    No Known Activations