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

    Neuronpedia

    INDEX
    Explanations

    references to pairs or collections of items in a structured format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     big
    -0.15
    _constructor
    -0.15
    enga
    -0.15
     pace
    -0.15
     Constructors
    -0.14
    edir
    -0.13
     Demp
    -0.13
     BIG
    -0.13
    Interop
    -0.13
    è¿
    -0.13
    POSITIVE LOGITS
    tures
    0.17
    mts
    0.16
    ings
    0.16
    ofire
    0.16
    æķ¬
    0.15
    asc
    0.15
     ÙĪÛĮÚ©ÛĮ
    0.14
    /vendors
    0.14
    üzel
    0.14
    mt
    0.14
    Act Density 0.012%

    No Known Activations