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

    Neuronpedia

    INDEX
    Explanations

    adjectives and comparative phrases associated with quality or success

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erah
    -0.16
     enough
    -0.16
     доÑģÑĤаÑĤоÑĩно
    -0.15
    akan
    -0.14
     Enough
    -0.14
    å¤Ł
    -0.14
     доÑģиÑĤÑĮ
    -0.14
     доÑģÑĤаÑĤ
    -0.14
    acos
    -0.14
    olest
    -0.14
    POSITIVE LOGITS
     than
    1.47
    than
    1.22
     Than
    1.11
     THAN
    1.11
    Than
    1.08
    -than
    1.06
    _than
    1.01
     niż
    0.79
     än
    0.77
     než
    0.76
    Act Density 0.750%

    No Known Activations