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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and specific formatting related to textual structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     but
    -0.89
     sometimes
    -0.86
     But
    -0.81
     parfois
    -0.80
    But
    -0.78
    but
    -0.78
     whatever
    -0.78
    Maybe
    -0.78
     How
    -0.77
    Sometimes
    -0.77
    POSITIVE LOGITS
    Commenting
    1.13
    According
    0.86
     According
    0.86
     commenting
    0.77
     Earlier
    0.74
     commented
    0.73
     Speaking
    0.72
    Speaking
    0.72
     Following
    0.71
     congratulated
    0.71
    Act Density 0.244%

    No Known Activations