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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    anmar
    -0.78
     Arist
    -0.68
     pursu
    -0.64
     measurement
    -0.62
     Yuan
    -0.60
     cou
    -0.60
    hetamine
    -0.60
     focal
    -0.60
     approximation
    -0.60
     Caval
    -0.60
    POSITIVE LOGITS
    rets
    1.02
    plet
    0.85
    ifax
    0.74
    RET
    0.73
     guid
    0.72
    ickr
    0.71
    bern
    0.70
    porary
    0.69
    yna
    0.69
    UFF
    0.68
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.