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

    Neuronpedia

    INDEX
    Explanations

    punctuation and formatting within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    >\<^
    -1.40
     $_"
    -1.38
     }}$}
    -1.38
    NUMX
    -1.37
     Efq
    -1.36
    \<^
    -1.34
     ―――――
    -1.31
    〢
    -1.29
     GenerationType
    -1.29
    )");
    -1.28
    POSITIVE LOGITS
    <eos>
    1.79
    ↵
    1.44
    ↵↵
    1.38
    ↵↵↵
    1.28
    ↵↵↵↵
    1.25
    http
    1.22
    https
    1.14
    \\
    1.11
    <strong>
    1.10
    The
    1.09
    Act Density 0.831%

    No Known Activations