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

    Neuronpedia

    INDEX
    Explanations

    occurrences of brackets or similar punctuation marks

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

    presented, scientific context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AnimationsModule
    -0.63
     ainfi
    -0.57
    yarnpkg
    -0.54
     ſever
    -0.49
     mauva
    -0.46
     avoient
    -0.45
    ymce
    -0.44
     feroit
    -0.44
     pouvoit
    -0.44
     borse
    -0.43
    POSITIVE LOGITS
    \]
    2.33
     \]
    1.05
    }\]
    1.01
    \]
    0.63
    endregion
    0.61
    Personensuche
    0.57
    %\]
    0.56
     [*]
    0.56
    \[
    0.54
    *}$
    0.54
    Act Density 0.119%

    No Known Activations