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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    -0.17
    uales
    -0.16
    est
    -0.16
    sell
    -0.15
    athers
    -0.15
    friend
    -0.15
    ichert
    -0.15
    ales
    -0.15
    led
    -0.14
    pers
    -0.14
    POSITIVE LOGITS
    th
    0.20
    ivec
    0.17
    cy
    0.17
    ëł
    0.17
    ewise
    0.17
    /current
    0.17
    TeV
    0.16
        ↵    ↵
    0.16
    iner
    0.16
    ãĥ¥
    0.16
    Act Density 0.083%

    No Known Activations