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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Half
    -0.07
    三天
    -0.07
    assignments
    -0.07
    =db
    -0.07
    gly
    -0.07
    (dev
    -0.07
     dpi
    -0.07
    greater
    -0.07
    Presence
    -0.07
     TAX
    -0.06
    POSITIVE LOGITS
     moistur
    0.07
    فات
    0.07
    ﭷ
    0.07
    🎪
    0.07
    蜈
    0.07
    👯
    0.07
     ol
    0.07
     fus
    0.07
    瓶
    0.07
     şekilde
    0.06
    Act Density 0.029%

    No Known Activations