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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks indicating the end of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    setVerticalGroup
    -1.16
     '\\;'
    -1.14
    styleType
    -1.11
    >\<^
    -1.07
    \<^
    -1.05
    Amicalement
    -1.04
    NUMX
    -1.04
    mybatisplus
    -1.03
     }}$}
    -1.01
     $_"
    -0.99
    POSITIVE LOGITS
    <eos>
    1.37
    ...
    0.94
    I
    0.91
     ...
    0.88
    http
    0.84
    The
    0.83
    …
    0.82
    A
    0.82
    ↵↵
    0.80
    ↵
    0.80
    Act Density 0.815%

    No Known Activations