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

    Neuronpedia

    INDEX
    Explanations

    instances of commas, indicating pauses or separations in lists or clauses

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

    linking verbs and conjunctions after commas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ...");
    -0.49
    ...');
    -0.44
    ...".
    -0.44
    '];?>
    -0.43
    }}}}
    -0.42
    ━━━━
    -0.41
    ..."
    -0.41
    }/>
    -0.40
    ...
    -0.40
     aesthetic
    -0.40
    POSITIVE LOGITS
    middels
    0.64
    awtextra
    0.63
     is
    0.59
     has
    0.57
    withIdentifier
    0.56
    brigens
    0.56
     والتي
    0.55
     will
    0.55
     kasarigan
    0.54
    Gön
    0.54
    Act Density 0.101%

    No Known Activations