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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    æŬ
    -0.30
    æłªæ´²
    -0.26
    iser
    -0.26
    ãģĵãĤĮãģĭãĤī
    -0.25
    æľªæĿ¥
    -0.25
    vac
    -0.25
    TEX
    -0.24
    (mon
    -0.24
    容æĺĵ
    -0.24
     future
    -0.23
    POSITIVE LOGITS
    losion
    0.27
     krist
    0.27
    roach
    0.27
    MATCH
    0.26
     adoles
    0.26
    rots
    0.25
     translate
    0.25
    åĢĴåľ¨
    0.25
     MATCH
    0.24
    anonymous
    0.24
    Act Density 0.116%

    No Known Activations

    This feature has no known activations.