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

    Neuronpedia

    INDEX
    Explanations

    terms related to data types, specifically floating-point numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     supply
    -0.38
    ter
    -0.37
     Supply
    -0.37
    ve
    -0.36
     ve
    -0.36
    var
    -0.35
    olar
    -0.35
    se
    -0.35
    for
    -0.33
     связанные
    -0.33
    POSITIVE LOGITS
     boo
    0.71
     تضيفلها
    0.68
     float
    0.68
    featureID
    0.66
    存于互联网档案馆
    0.66
     Boo
    0.63
    الحياه
    0.62
    ItemBackground
    0.62
     CreateTagHelper
    0.62
     Float
    0.61
    Act Density 0.208%

    No Known Activations