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

    Neuronpedia

    INDEX
    Explanations

    references to chess achievements and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .DEFINE
    -0.15
    кÑĢеÑĤ
    -0.15
     compar
    -0.14
    irling
    -0.14
    ault
    -0.14
    BALL
    -0.14
     cabbage
    -0.14
    _ctxt
    -0.14
    .freeze
    -0.13
    ष
    -0.13
    POSITIVE LOGITS
     Chess
    0.35
     chess
    0.34
    Chess
    0.33
     ÑĪаÑħ
    0.30
    æ£ĭ
    0.26
     Fischer
    0.23
     pawn
    0.23
     Pawn
    0.23
    Pawn
    0.22
     rating
    0.21
    Act Density 0.021%

    No Known Activations