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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    𝐫
    1.55
    dır
    1.45
    𝐚
    1.41
    𝐢
    1.34
    𝐩
    1.33
    𝐧
    1.26
    𝐝
    1.22
    𝐮
    1.20
    traits
    1.18
    ციის
    1.16
    POSITIVE LOGITS
    ारी
    1.19
    ücke
    1.09
    лее
    1.08
     capo
    1.07
    elom
    1.02
    )}$,
    1.02
    ()}\
    1.02
     nanos
    1.01
    िश्व
    1.00
     MDC
    1.00
    Act Density 0.000%

    No Known Activations