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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    arer
    -0.73
    hemy
    -0.67
    enthal
    -0.67
    rique
    -0.67
    xus
    -0.64
    oulos
    -0.63
    ~~~~
    -0.63
    angered
    -0.62
    olkien
    -0.61
    plates
    -0.60
    POSITIVE LOGITS
     Polk
    0.62
     Stead
    0.61
     warr
    0.60
     plan
    0.59
    seen
    0.59
    ufact
    0.57
     RED
    0.56
     Dept
    0.56
    ELY
    0.56
     Direction
    0.56
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.