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

    Neuronpedia

    INDEX
    Explanations

    references to legal actions or lawsuits

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rup
    -0.74
    enary
    -0.71
    sylv
    -0.70
    scribe
    -0.69
    hash
    -0.68
    fred
    -0.68
    pec
    -0.67
    uci
    -0.67
    orem
    -0.67
    cell
    -0.67
    POSITIVE LOGITS
     namely
    1.36
     albeit
    1.34
     though
    1.09
     although
    1.07
     according
    0.97
     prompting
    0.96
     however
    0.95
     including
    0.94
     especially
    0.93
     stemming
    0.93
    Act Density 0.397%

    No Known Activations