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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly those indicating end-of-sentence or pause

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odore
    -0.36
    atre
    -0.20
    xiety
    -0.19
    adays
    -0.19
    foundland
    -0.17
    quarters
    -0.17
    ah
    -0.17
     же
    -0.16
    anmar
    -0.16
    credible
    -0.16
    POSITIVE LOGITS
    页éĿ¢åŃĺæ¡£å¤ĩ份
    0.27
     latter
    0.26
    phans
    0.18
    аж
    0.16
    ucer
    0.15
    EGIN
    0.15
    بار
    0.15
    eck
    0.14
    dır
    0.14
    ãģĤãĤĬ
    0.14
    Act Density 0.412%

    No Known Activations