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

    Neuronpedia

    INDEX
    Explanations

    phrases related to numbers and quantities

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Approach
    -0.82
    eda
    -0.78
    ĸļ
    -0.73
     mentality
    -0.72
     approach
    -0.68
     backdrop
    -0.67
    apult
    -0.66
     methodology
    -0.64
     Religion
    -0.64
     Rampage
    -0.64
    POSITIVE LOGITS
     acres
    1.29
     miles
    1.03
     pounds
    1.03
     hectares
    0.98
     households
    0.96
     gallons
    0.96
     tonnes
    0.93
     tons
    0.92
     subscribers
    0.92
     ounces
    0.92
    Act Density 0.321%

    No Known Activations