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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    enthal
    -0.76
    ipers
    -0.75
    nyder
    -0.73
     murd
    -0.69
    iegel
    -0.69
     unden
    -0.67
     destro
    -0.66
    anism
    -0.66
    ouls
    -0.66
    hovah
    -0.66
    POSITIVE LOGITS
     Rhodes
    0.71
    heit
    0.71
    ¬¼
    0.69
    ory
    0.68
     label
    0.67
     Tour
    0.65
    arat
    0.63
    Progress
    0.61
     energetic
    0.60
    clusively
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.