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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    iott
    -0.71
    namese
    -0.71
    vati
    -0.69
     resid
    -0.68
     footing
    -0.67
     prosecut
    -0.66
     hemor
    -0.66
     planner
    -0.63
     impulse
    -0.61
     disproportion
    -0.61
    POSITIVE LOGITS
     Amateur
    0.76
    uther
    0.75
    plet
    0.74
    idding
    0.72
    atel
    0.69
    utical
    0.68
    udos
    0.68
    olicited
    0.68
    ysical
    0.67
    reens
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.