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

    Neuronpedia

    INDEX
    Explanations

    references to game-related actions and locations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bun
    -0.66
    ãĥ¯ãĥ³
    -0.65
    ||||
    -0.63
     Bak
    -0.62
     Broad
    -0.62
     Fitz
    -0.62
    ModLoader
    -0.61
    ãĤ¨ãĥ«
    -0.60
     Bus
    -0.59
     Burk
    -0.59
    POSITIVE LOGITS
    urrency
    0.87
    iencies
    0.87
    irs
    0.86
    lege
    0.83
    romeda
    0.83
    ogue
    0.79
    etts
    0.78
    ends
    0.78
    etimes
    0.77
    ets
    0.77
    Act Density 0.223%

    No Known Activations