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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     calculus
    -0.77
    gaard
    -0.72
    blance
    -0.71
     tongues
    -0.69
     Tsu
    -0.68
    =-=-=-=-=-=-=-=-
    -0.67
    --------------------------------------------------------
    -0.67
    TON
    -0.66
    FACE
    -0.65
     Niet
    -0.65
    POSITIVE LOGITS
    oyal
    0.74
    ule
    0.73
    itialized
    0.72
    orn
    0.68
    anny
    0.67
    inth
    0.61
    enced
    0.60
    elf
    0.60
     Abram
    0.60
     Swamp
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.