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

    Neuronpedia

    INDEX
    Explanations

    periods and other punctuation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ^(@)
    -1.23
    сылкі
    -1.08
     itſelf
    -1.07
    MLLoader
    -1.06
    IUrlHelper
    -1.05
     ་་
    -1.03
     doubtnut
    -1.01
     Efq
    -0.99
     ARXIV
    -0.99
     ―――――
    -0.98
    POSITIVE LOGITS
    ↵
    1.27
    ↵↵
    1.26
    .
    1.07
     
    0.99
    <bos>
    0.99
    '
    0.94
    <eos>
    0.94
    ))
    0.93
    ’
    0.93
    ).
    0.92
    Act Density 2.116%

    No Known Activations