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

    Neuronpedia

    INDEX
    Explanations

    numerical and statistical data

    oai_token-act-pair · gpt-3.5-turbo

    mathematical notation or statistical data representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dish
    -0.67
     Freed
    -0.62
    elist
    -0.61
     Deliver
    -0.60
     Shrine
    -0.58
     chars
    -0.58
     Ferdinand
    -0.58
     Sabbath
    -0.58
     Hornets
    -0.57
     Wake
    -0.57
    POSITIVE LOGITS
    appa
    0.87
     estimate
    0.82
    âĪĴ
    0.73
     estimating
    0.70
    Compare
    0.70
     obser
    0.69
    heter
    0.68
     explan
    0.67
    ternity
    0.66
    proxy
    0.66
    Act Density 0.049%

    No Known Activations