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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    465
    -0.16
    vsp
    -0.16
    775
    -0.16
    946
    -0.16
    268
    -0.15
    reich
    -0.15
    852
    -0.15
    butt
    -0.15
    710
    -0.15
    945
    -0.15
    POSITIVE LOGITS
    ections
    0.16
    èĦ
    0.15
    rosso
    0.14
    γι
    0.13
     Palm
    0.13
     Dough
    0.13
     Mats
    0.13
    Hello
    0.13
    ouden
    0.13
    OTS
    0.13
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.