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

    Neuronpedia

    INDEX
    Explanations

    strings or patterns that include special characters and formatting symbols

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

    code syntax and special characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.64
    Harbor
    -0.58
     Harbor
    -0.58
    ********/
    -0.58
    "],
    -0.57
    ?}",
    -0.56
    hitheater
    -0.56
     Savior
    -0.56
    ßte
    -0.55
    ."],
    -0.55
    POSITIVE LOGITS
     '{
    0.72
     '<
    0.68
     '(
    0.63
     '\\
    0.62
     '&
    0.61
     ‘
    0.61
     '@
    0.60
     '='
    0.60
     '[
    0.60
     '
    0.60
    Act Density 0.018%

    No Known Activations