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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     מאת
    -0.07
    quirrel
    -0.07
    .transfer
    -0.07
     سبحان
    -0.07
    สไต
    -0.07
     streams
    -0.07
    绔
    -0.07
    slots
    -0.07
     Oktober
    -0.07
    为广大
    -0.07
    POSITIVE LOGITS
     depressing
    0.08
    DAC
    0.07
    'R
    0.07
     instruction
    0.07
    iciel
    0.07
     chop
    0.07
     żeby
    0.07
     finishing
    0.07
    调节
    0.07
    控制
    0.07
    Act Density 0.003%

    No Known Activations