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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     mates
    -0.69
     Polic
    -0.67
    ó
    -0.66
     Newman
    -0.64
    uphem
    -0.63
     Slater
    -0.63
    senal
    -0.61
     dehuman
    -0.61
     incorpor
    -0.60
     Swan
    -0.58
    POSITIVE LOGITS
    umbledore
    0.78
    ython
    0.76
    EY
    0.75
    JECT
    0.72
    ECA
    0.70
    dj
    0.67
    leck
    0.66
    IES
    0.65
     Jace
    0.65
    deck
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.