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

    Neuronpedia

    INDEX
    Explanations

    nouns and their related descriptors, indicating a focus on unique and popular items or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    croft
    -0.15
    uchar
    -0.15
    êm
    -0.15
    ancode
    -0.15
    utex
    -0.15
    ãģŁãģı
    -0.14
    inerary
    -0.14
    алом
    -0.14
    úb
    -0.14
    \grid
    -0.14
    POSITIVE LOGITS
     answer
    0.27
     Holy
    0.27
     go
    0.26
     bomb
    0.26
     holy
    0.25
     definition
    0.25
     king
    0.24
     talk
    0.24
     Rolls
    0.23
     bee
    0.23
    Act Density 0.119%

    No Known Activations