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

    Neuronpedia

    INDEX
    Explanations

    comparative adjectives that describe improvements or advantages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ediÄŁi
    -0.16
    ismet
    -0.16
    atori
    -0.15
    ÙĨÚ¯ÛĮ
    -0.15
    edis
    -0.15
     XCT
    -0.14
    acier
    -0.14
    edef
    -0.14
    ATAB
    -0.14
    esel
    -0.14
    POSITIVE LOGITS
     than
    0.66
    than
    0.49
     THAN
    0.43
     then
    0.43
     Than
    0.41
    Than
    0.39
    _than
    0.39
     tha
    0.37
     tan
    0.36
     än
    0.35
    Act Density 0.124%

    No Known Activations