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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     oversee
    0.52
     overseeing
    0.51
     oversees
    0.46
     opiek
    0.46
     astrophys
    0.46
     anonymously
    0.45
     collaborating
    0.45
     pecan
    0.45
     jokingly
    0.45
     rallied
    0.44
    POSITIVE LOGITS
    燡
    0.52
    一つの
    0.48
     ਇਕ
    0.46
    一日
    0.45
    一段
    0.44
     kapas
    0.44
     Estudio
    0.43
     едно
    0.43
    Preliminary
    0.43
    ENSION
    0.43
    Act Density 0.005%

    No Known Activations