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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    aint
    -0.29
    uent
    -0.27
    tings
    -0.26
    ailer
    -0.25
    ainers
    -0.25
    onnement
    -0.24
    -process
    -0.24
     mut
    -0.24
     strapped
    -0.24
    egot
    -0.23
    POSITIVE LOGITS
    ä¸įä¸ĭ
    0.28
    æķĻèĤ²èµĦæºIJ
    0.27
    çĽĬ
    0.26
    è¾¹ç¼ĺ
    0.24
    çĿ«
    0.24
    å®ļéĩı
    0.24
    cele
    0.24
     MyBase
    0.24
    åŁİå¸Ĥåıijå±ķ
    0.24
    社
    0.23
    Act Density 0.002%

    No Known Activations

    This feature has no known activations.