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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    .restaurant
    -0.07
     DEV
    -0.07
     inviting
    -0.07
     Mar
    -0.06
     distur
    -0.06
     arrivals
    -0.06
     bomb
    -0.06
     Seite
    -0.06
    special
    -0.06
    ᴠ
    -0.06
    POSITIVE LOGITS
    offsetof
    0.07
    ["
    0.07
    قدس
    0.07
     עוסק
    0.07
    焚烧
    0.07
     abandonment
    0.07
     Calculates
    0.07
    找出
    0.07
    崇尚
    0.07
    linear
    0.07
    Act Density 0.068%

    No Known Activations