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

    Neuronpedia

    INDEX
    Explanations

    information related to statistics and data

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and statistics related to population or user metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wcsstore
    -0.78
    tnc
    -0.78
    natureconservancy
    -0.76
    osite
    -0.76
    dit
    -0.76
    bra
    -0.69
    ilateral
    -0.66
    fml
    -0.65
     rpm
    -0.64
     opposite
    -0.64
    POSITIVE LOGITS
     Including
    1.08
     Thousands
    0.93
     Hundreds
    0.92
     Tens
    0.85
    quartered
    0.83
     counting
    0.83
     Dozens
    0.80
     Millions
    0.78
     Approximately
    0.77
     includ
    0.77
    Act Density 0.734%

    No Known Activations