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

    Neuronpedia

    INDEX
    Explanations

    repeated or emphasized punctuation marks at the end of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ī
    -2.60
    Īĺ
    -2.53
    ¼
    -2.41
    Į
    -2.39
    ª
    -2.36
    -2.30
    -2.30
    ↵
    -2.30
    ↵
    -2.30
    ↵
    -2.30
    POSITIVE LOGITS
     Cochrane
    1.74
    uscript
    1.69
     herself
    1.57
    ceedings
    1.49
    beck
    1.48
    arf
    1.46
    ÃŁe
    1.40
    aft
    1.39
     decre
    1.37
    енÑĤ
    1.35
    Act Density 3.561%

    No Known Activations