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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     ""↵
    -0.08
     eligibility
    -0.08
     frame
    -0.07
    市区
    -0.07
    (num
    -0.07
     café
    -0.07
    	width
    -0.07
     ""
↵
    -0.07
    encer
    -0.07
    叙述
    -0.07
    POSITIVE LOGITS
     Ком
    0.07
    	RTLR
    0.07
    핌
    0.07
     BUFF
    0.07
     geme
    0.07
     oblig
    0.06
    😘
    0.06
     phil
    0.06
    结婚
    0.06
    Phil
    0.06
    Act Density 0.002%

    No Known Activations