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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Aviation
    0.11
     حسين
    0.11
    尼亚克
    0.11
    сон
    0.11
     مليون
    0.10
     Ocean
    0.10
     ČR
    0.10
    çay
    0.10
     Nasional
    0.10
     December
    0.10
    POSITIVE LOGITS
     is
    0.13
     can
    0.13
     get
    0.12
     gets
    0.12
     uses
    0.12
     give
    0.11
     you
    0.11
     tonic
    0.11
     involves
    0.11
     nouns
    0.11
    Act Density 0.005%

    No Known Activations