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

    Neuronpedia

    INDEX
    Explanations

    the occurrence of a specific punctuation mark or symbol

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aign
    -0.17
    lington
    -0.16
    ...\
    -0.16
    recht
    -0.16
     Wayback
    -0.15
    trinsic
    -0.15
    úÄįast
    -0.15
    gia
    -0.15
    erus
    -0.14
    ......↵↵
    -0.14
    POSITIVE LOGITS
    (
    0.26
    to
    0.20
    a
    0.19
    an
    0.19
    /Dk
    0.17
    .(
    0.17
     ↵↵
    0.16
    we
    0.16
    Ø©
    0.16
    for
    0.15
    Act Density 0.034%

    No Known Activations