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

    Neuronpedia

    INDEX
    Explanations

    quantities or amounts of things mentioned in the texts

    oai_token-act-pair · gpt-3.5-turbo

    phrases that quantify or refer to measurements or amounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -1.10
    \\\\\\\\
    -0.88
    edin
    -0.81
    ħĭ
    -0.81
    ÙIJ
    -0.81
    reys
    -0.78
    stocks
    -0.75
    Õ
    -0.74
    \'
    -0.73
    Ń·
    -0.73
    POSITIVE LOGITS
     allowable
    0.92
     accumulated
    0.91
     money
    0.88
     mileage
    0.86
     overlap
    0.85
     fines
    0.84
     energy
    0.83
     ingested
    0.80
     absorbed
    0.78
     effort
    0.78
    Act Density 0.047%

    No Known Activations