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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their frequency in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    ; followed by numbers or parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused79>
    -1.38
    <unused8>
    -1.37
    <unused41>
    -1.37
    <unused68>
    -1.37
    <unused23>
    -1.37
    <unused3>
    -1.37
    <unused28>
    -1.37
    <unused52>
    -1.37
    <pad>
    -1.36
    [@BOS@]
    -1.36
    POSITIVE LOGITS
    .
    0.64
    ;
    0.59
    ↵
    0.49
    2
    0.48
     ;
    0.48
    ↵↵
    0.47
    );
    0.47
    。
    0.46
    3
    0.44
    ,
    0.41
    Act Density 0.028%

    No Known Activations