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

    Neuronpedia

    INDEX
    Explanations

    terms related to expressions and representation in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     EconPapers
    -0.44
    قایناق‌لار
    -0.43
     Fuhr
    -0.38
    Sucesor
    -0.38
     kasarigan
    -0.38
    Portail
    -0.38
     Mortimer
    -0.37
    webElementXpaths
    -0.36
     Circle
    -0.35
    fun
    -0.35
    POSITIVE LOGITS
     expresses
    0.78
     expressed
    0.78
     expressing
    0.74
     uttry
    0.70
     Express
    0.70
    expressed
    0.70
    Express
    0.69
    表示
    0.69
     expressions
    0.68
     EXPRESS
    0.68
    Act Density 1.600%

    No Known Activations