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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    	pstmt
    -0.08
    man
    -0.07
    ason
    -0.07
     Air
    -0.07
     nginx
    -0.07
     running
    -0.07
    ɴ
    -0.07
    aring
    -0.07
     squad
    -0.07
     Jeh
    -0.07
    POSITIVE LOGITS
    精华
    0.07
     tempor
    0.07
    烘干
    0.07
     fused
    0.07
     noodles
    0.07
    (properties
    0.06
    スキル
    0.06
    🥠
    0.06
     deceived
    0.06
    馥
    0.06
    Act Density 0.019%

    No Known Activations