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

    Neuronpedia

    INDEX
    Explanations

    specific proper nouns, particularly related to meteorites and medical terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ts
    -0.30
    ta
    -0.26
    te
    -0.24
    tn
    -0.23
    td
    -0.23
    tem
    -0.23
    to
    -0.23
    ÑĤ
    -0.23
    tf
    -0.22
    hs
    -0.22
    POSITIVE LOGITS
    (es
    0.29
    ness
    0.24
    ’
    0.23
    '
    0.23
    d
    0.21
    cribe
    0.20
    det
    0.20
    den
    0.19
    ÙĨاÙħÙĩ
    0.19
    sing
    0.19
    Act Density 1.382%

    No Known Activations