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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     marches
    -0.63
     MK
    -0.62
     coma
    -0.61
     boiling
    -0.60
     surgery
    -0.60
     bailout
    -0.59
     bleed
    -0.57
     signatures
    -0.56
     wash
    -0.55
    anders
    -0.55
    POSITIVE LOGITS
    Ready
    0.83
    req
    0.76
    fort
    0.73
    icult
    0.72
    ournal
    0.72
    tif
    0.72
    vice
    0.70
    ustomed
    0.70
    breaker
    0.69
    availability
    0.68
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.