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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    an
    1.72
    as
    1.70
    im
    1.62
    ara
    1.59
    erte
    1.49
    ina
    1.48
    ian
    1.45
    son
    1.42
    ic
    1.38
    ie
    1.38
    POSITIVE LOGITS
     diminu
    1.33
     JFK
    1.22
    ✔️
    1.21
    十大
    1.20
     repug
    1.20
    省略
    1.19
     laparoscopic
    1.18
     categor
    1.16
     torque
    1.16
     disguise
    1.16
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.