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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating categories or types

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ONTAL
    -0.17
    InView
    -0.16
    _holder
    -0.15
    asje
    -0.13
     way
    -0.13
    istrovstvÃŃ
    -0.13
    ä¼¼çļĦ
    -0.13
    anan
    -0.13
     HOLDERS
    -0.13
     Way
    -0.13
    POSITIVE LOGITS
     ilk
    0.33
     origin
    0.32
     magnitude
    0.31
     nature
    0.27
     vintage
    0.26
    magnitude
    0.24
     importance
    0.23
     proven
    0.23
     caliber
    0.23
     stripe
    0.22
    Act Density 0.138%

    No Known Activations