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

    Neuronpedia

    INDEX
    Explanations

    specific entities or items of interest, such as players in a game, dates, steps in a process, and locations

    oai_token-act-pair · gpt-3.5-turbo

    references to players and their rankings or statistics in a game

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ascus
    -0.64
     uncomp
    -0.60
     glim
    -0.58
     hars
    -0.57
    rave
    -0.57
     decentral
    -0.57
    ãĥ³ãĤ¸
    -0.56
    isers
    -0.56
     millenn
    -0.56
    lycer
    -0.54
    POSITIVE LOGITS
    b
    1.27
     b
    1.16
     iii
    1.07
     ii
    1.06
    B
    1.01
    II
    1.01
    ii
    0.96
    iii
    0.96
     B
    0.95
    cb
    0.94
    Act Density 0.084%

    No Known Activations