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

    Neuronpedia

    INDEX
    Explanations

    text related to physical or conceptual 'pieces' and their attributes or relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sit
    -0.17
    soever
    -0.16
    readcr
    -0.15
    arith
    -0.15
    shire
    -0.14
    rep
    -0.14
    igel
    -0.14
    zin
    -0.14
    .showMessageDialog
    -0.14
    amat
    -0.14
    POSITIVE LOGITS
    åĦ¿
    0.17
    itura
    0.16
    éIJĺ
    0.15
    pawn
    0.15
    LAT
    0.15
    íĴĪ
    0.14
    -parts
    0.14
    pieces
    0.14
    ɵ
    0.14
    etween
    0.14
    Act Density 0.039%

    No Known Activations