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

    Neuronpedia

    INDEX
    Explanations

    proper nouns with a focus on their unique identifiers or attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ancias
    -0.17
    edImage
    -0.16
    i
    -0.16
    (defvar
    -0.15
    и
    -0.15
    åı£
    -0.14
    arin
    -0.14
    atten
    -0.14
    y
    -0.14
    ÛĮات
    -0.14
    POSITIVE LOGITS
    dy
    0.27
    nesday
    0.27
    ding
    0.26
    dit
    0.24
    ele
    0.23
    eker
    0.23
    die
    0.23
    anken
    0.22
    dings
    0.21
    ev
    0.21
    Act Density 0.050%

    No Known Activations