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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    fect
    -0.72
     die
    -0.68
     sans
    -0.64
     Fidel
    -0.63
     perish
    -0.60
     dissenting
    -0.60
    ives
    -0.60
     Constantine
    -0.59
    ynski
    -0.59
    åħī
    -0.59
    POSITIVE LOGITS
    ihara
    0.77
    ffield
    0.72
    days
    0.70
    ilk
    0.67
    videos
    0.67
    iltr
    0.66
    borgh
    0.66
    ikini
    0.65
    ourney
    0.65
    oking
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.