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

    Neuronpedia

    INDEX
    Explanations

    sentences featuring parentheses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    (
    -0.30
    *
    -0.30
    [
    -0.26
     (
    -0.26
    ↵
    -0.24
    /
    -0.23
    $
    -0.20
    !
    -0.20
    :
    -0.20
    _
    -0.20
    POSITIVE LOGITS
    which
    0.27
    aka
    0.25
    or
    0.25
    ...)↵
    0.24
    with
    0.24
    see
    0.24
    for
    0.24
    âĢ¦)
    0.21
    from
    0.21
    as
    0.21
    Act Density 0.425%

    No Known Activations