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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    eeds
    -0.79
    farious
    -0.76
    ales
    -0.73
    ovic
    -0.73
     Alm
    -0.67
     Mayhem
    -0.66
    irin
    -0.65
    gomery
    -0.65
     Relax
    -0.65
     Noct
    -0.64
    POSITIVE LOGITS
    ãĤŃ
    0.78
    ãĤ»
    0.63
    pers
    0.63
     wig
    0.62
    lings
    0.61
    kered
    0.61
     glim
    0.58
    conn
    0.56
     pulp
    0.56
    ãĥı
    0.55
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.