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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    rahim
    -0.83
     caucuses
    -0.77
     psi
    -0.65
     CTR
    -0.65
    bang
    -0.63
     moder
    -0.63
     Shank
    -0.62
     Dover
    -0.61
     wool
    -0.61
     fuzz
    -0.59
    POSITIVE LOGITS
    service
    0.76
    NT
    0.73
    RF
    0.70
    rx
    0.70
    ilst
    0.70
    atics
    0.67
    RO
    0.66
    ESA
    0.66
    rf
    0.65
    AS
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.