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

    Neuronpedia

    INDEX
    Explanations

    contextual phrases and expressions related to mathematical independence and scaling properties

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     marito
    -0.52
     fédé
    -0.50
     trifft
    -0.49
    TagHelper
    -0.48
    もちゃ
    -0.48
     Nevertheless
    -0.47
    Nevertheless
    -0.47
     trotzdem
    -0.47
     poitrine
    -0.47
    RunWith
    -0.46
    POSITIVE LOGITS
    AndEndTag
    0.73
     <<<<<<<<<<<<<<
    0.73
    ConstraintMaker
    0.68
     الرياضيه
    0.63
    Geplaatst
    0.57
    ISTRATION
    0.57
    ,‎
    0.56
    habhar
    0.56
    msgTypes
    0.55
    doGet
    0.52
    Act Density 0.057%

    No Known Activations