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

    Neuronpedia

    INDEX
    Explanations

    informal conversational transitions and interjections

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

    "By the way" or similar asides

    np_acts-logits-general · gemini-2.0-flash

    btw or by the way

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </caption>
    -0.68
    ']],
    -0.67
     CoreData
    -0.67
    ()?;
    -0.67
    ()");
    -0.66
    '},
    -0.65
    ArgsConstructor
    -0.65
    ."));
    -0.65
    ')));
    -0.64
    ')")
    -0.64
    POSITIVE LOGITS
     btw
    0.84
     why
    0.80
     BTW
    0.79
     forgot
    0.78
    Also
    0.72
    BTW
    0.70
    also
    0.68
     also
    0.68
    btw
    0.68
     congrats
    0.65
    Act Density 0.206%

    No Known Activations