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

    Neuronpedia

    INDEX
    Explanations

    large numerical values or statistics

    oai_token-act-pair · gpt-3.5-turbo

    commas in numerical or statistical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahu
    -0.72
    ¬¼
    -0.68
    riad
    -0.65
    onym
    -0.65
    olo
    -0.59
    irie
    -0.59
    THING
    -0.57
     interaction
    -0.57
    ilyn
    -0.57
    igen
    -0.56
    POSITIVE LOGITS
     respectively
    1.19
    000
    1.13
    Downloadha
    0.89
     whereas
    0.88
    depending
    0.87
     according
    0.86
     including
    0.85
     namely
    0.83
    elsius
    0.82
     huh
    0.79
    Act Density 0.539%

    No Known Activations