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

    Neuronpedia

    INDEX
    Explanations

    the frequency of punctuation marks, particularly periods and commas, in a text

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

    Follows initials/abbreviations

    np_acts-logits-general · gemini-2.0-flash

    J. initials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ßerdem
    -0.67
    ähteet
    -0.67
    enablog
    -0.64
    tangentMode
    -0.62
     esternos
    -0.62
     plufieurs
    -0.62
    tonode
    -0.61
    antMatchers
    -0.61
     AssemblyCulture
    -0.61
     navideñas
    -0.60
    POSITIVE LOGITS
    ."],
    0.49
    .$.
    0.45
     "];
    0.41
    .",
    0.41
    "]:
    0.41
    .');
    0.41
    .")
    0.41
    .";
    0.40
     J
    0.40
    >.</
    0.40
    Act Density 0.385%

    No Known Activations