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

    Neuronpedia

    INDEX
    Explanations

    comma punctuation marks

    oai_token-act-pair · gpt-3.5-turbo

    instances of punctuation, particularly commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Flavoring
    -0.69
     corrid
    -0.67
     PCR
    -0.66
    swick
    -0.66
     rulings
    -0.64
    uces
    -0.64
     raids
    -0.61
     Defeat
    -0.61
     punches
    -0.61
     mats
    -0.60
    POSITIVE LOGITS
     albeit
    0.86
     alas
    0.86
     unsurprisingly
    0.81
    wikipedia
    0.76
    necess
    0.74
    obar
    0.73
    opic
    0.71
     barring
    0.71
     yeah
    0.70
     namely
    0.70
    Act Density 0.126%

    No Known Activations