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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their relationships in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     مرئيه
    -1.35
     otomatig
    -1.30
     <=",
    -1.25
    AddTagHelper
    -1.24
     nahilalakip
    -1.24
    InjectAttribute
    -1.20
     unknownFields
    -1.20
    IsMutable
    -1.20
    TagMode
    -1.18
    OGND
    -1.17
    POSITIVE LOGITS
     It
    0.94
     That
    0.77
     They
    0.75
     However
    0.69
     it
    0.67
     Its
    0.65
     But
    0.63
     She
    0.63
     This
    0.62
     I
    0.62
    Act Density 0.311%

    No Known Activations