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

    Neuronpedia

    INDEX
    Explanations

    references to specific units and their features in product descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ovie
    -0.17
    cola
    -0.15
    uja
    -0.15
    æ´¥
    -0.14
    bor
    -0.14
    gil
    -0.14
    s
    -0.14
    AMED
    -0.13
    eko
    -0.13
    pt
    -0.13
    POSITIVE LOGITS
    ulario
    0.15
    unden
    0.15
    UBLE
    0.14
    OCUS
    0.14
    ToFit
    0.14
    onas
    0.14
     REGARD
    0.14
    LOBAL
    0.14
    erli
    0.13
    refix
    0.13
    Act Density 0.848%

    No Known Activations