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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, specifically commas

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    robe
    -0.73
    cell
    -0.71
    irc
    -0.71
    enture
    -0.70
    ety
    -0.64
     simulator
    -0.63
    adelphia
    -0.63
    hoe
    -0.63
    inar
    -0.62
    orn
    -0.61
    POSITIVE LOGITS
     albeit
    1.40
     namely
    1.26
     although
    1.06
     including
    1.01
     barring
    1.01
     according
    0.98
     whereas
    0.96
     however
    0.96
     insofar
    0.95
     though
    0.94
    Act Density 0.987%

    No Known Activations