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

    Neuronpedia

    INDEX
    Explanations

    references to data transfer and data structure management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hel
    -0.18
     hel
    -0.16
    verb
    -0.15
     punct
    -0.14
    æ¼Ķ
    -0.14
    ise
    -0.14
     sentence
    -0.14
     pazar
    -0.14
     Hut
    -0.13
     verb
    -0.13
    POSITIVE LOGITS
     structures
    0.31
     structure
    0.29
     structs
    0.28
    struct
    0.28
     struct
    0.27
    ç»ĵæŀĦ
    0.26
     Structures
    0.25
    structure
    0.25
     STRUCT
    0.25
    structures
    0.24
    Act Density 0.139%

    No Known Activations