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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate continuity or repetition over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    n
    -0.56
    lar
    -0.52
    Isa
    -0.51
    A
    -0.49
    ar
    -0.49
     Обра
    -0.49
    def
    -0.49
    gefü
    -0.49
    larımız
    -0.49
    o
    -0.48
    POSITIVE LOGITS
    tagHelperRunner
    1.06
    HOUT
    1.01
    throughout
    0.99
     defaultstate
    0.92
     throughout
    0.91
     typelib
    0.88
    enumi
    0.85
    ########.
    0.81
    AddTagHelper
    0.77
     vicenda
    0.75
    Act Density 0.041%

    No Known Activations