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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    う
    -0.08
     Direction
    -0.07
     transit
    -0.07
    Intersection
    -0.06
    車
    -0.06
     Which
    -0.06
     dah
    -0.06
     dus
    -0.06
    "x
    -0.06
    abic
    -0.06
    POSITIVE LOGITS
    _cores
    0.08
    بناء
    0.07
    generation
    0.07
    .INPUT
    0.07
    '])↵↵
    0.07
     Marco
    0.07
     ***↵
    0.07
     Rob
    0.07
    :')
    0.07
    🛠
    0.06
    Act Density 0.966%

    No Known Activations