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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ãĤ¼ãĤ¦ãĤ¹
    -0.98
    idth
    -0.96
     liquidity
    -0.79
     unlaw
    -0.75
    ciating
    -0.74
    ĸļ
    -0.71
    Pokemon
    -0.69
    ħĭ
    -0.68
    culus
    -0.68
    merce
    -0.68
    POSITIVE LOGITS
    rav
    0.70
    abin
    0.63
     Sun
    0.62
    rano
    0.62
     Torch
    0.61
     unconscious
    0.61
    sac
    0.60
    apt
    0.60
     Rational
    0.59
    rig
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.