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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Fallout
    -0.08
     Klan
    -0.07
    保证金
    -0.07
    黄昏
    -0.07
    asures
    -0.07
     Definition
    -0.07
    _FIX
    -0.07
     arsenal
    -0.07
     crackdown
    -0.06
    _contrib
    -0.06
    POSITIVE LOGITS
    ₨
    0.07
     iteration
    0.07
    dür
    0.07
     директор
    0.06
     bob
    0.06
    ío
    0.06
    >"+↵
    0.06
     BY
    0.06
    ándose
    0.06
    irate
    0.06
    Act Density 0.009%

    No Known Activations