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

    Neuronpedia

    INDEX
    Explanations

    references to singular concepts or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ones
    -0.18
    amp
    -0.14
    ÎķÎł
    -0.14
    related
    -0.13
    ad
    -0.13
    imeter
    -0.13
    ãĥ¼ãĥĭ
    -0.13
    ible
    -0.13
    relevant
    -0.13
    midd
    -0.13
    POSITIVE LOGITS
    onta
    0.17
    venta
    0.17
    -third
    0.17
     particular
    0.16
    -half
    0.15
    ertz
    0.14
     of
    0.14
    enville
    0.14
    FINITY
    0.14
    ÃĶNG
    0.14
    Act Density 0.153%

    No Known Activations