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

    Neuronpedia

    INDEX
    Explanations

    expressions of surprise or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    úÄįast
    -0.15
    otta
    -0.15
    oke
    -0.15
    'e
    -0.15
    оÑĤÑĮ
    -0.14
    lington
    -0.14
    -most
    -0.14
    stm
    -0.14
     Wayback
    -0.14
    %s
    -0.14
    POSITIVE LOGITS
    to
    0.19
    for
    0.18
    (
    0.17
    with
    0.16
    AND
    0.16
    [
    0.16
     ↵↵
    0.16
    enk
    0.15
    714
    0.15
    .(
    0.15
    Act Density 0.028%

    No Known Activations