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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     astr
    -0.08
    hotel
    -0.07
    <html
    -0.07
     Johnny
    -0.07
     Obj
    -0.07
    (dummy
    -0.06
    .shortcuts
    -0.06
    packet
    -0.06
    h
    -0.06
     induced
    -0.06
    POSITIVE LOGITS
    �
    0.07
    ﺁ
    0.07
    עשי
    0.07
    ᴼ
    0.07
     grounded
    0.07
    得到
    0.07
    應
    0.07
    生产设备
    0.07
    РО
    0.07
     unreliable
    0.07
    Act Density 0.016%

    No Known Activations