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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     dstg
    -0.85
    izoph
    -0.76
    atche
    -0.72
     Emin
    -0.71
    edi
    -0.71
    ndra
    -0.70
     Rohing
    -0.70
    raints
    -0.69
    scill
    -0.69
    ampires
    -0.67
    POSITIVE LOGITS
     turnaround
    0.65
     navigate
    0.65
     violet
    0.63
     determine
    0.62
     pink
    0.61
     blue
    0.61
     negotiate
    0.61
     commemorate
    0.61
     progress
    0.60
     unite
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.