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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    riage
    -0.76
     Cec
    -0.68
    SHIP
    -0.63
     SERVICE
    -0.63
     Rocket
    -0.60
     FORM
    -0.60
     BRE
    -0.60
    quet
    -0.59
     Capacity
    -0.59
     Petro
    -0.58
    POSITIVE LOGITS
    uders
    0.83
    âĶģ
    0.74
    avorable
    0.70
    ĻĤ
    0.68
     lows
    0.68
     digits
    0.67
    rough
    0.67
    usions
    0.66
    Prev
    0.64
    cknowled
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.