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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    abouts
    -0.88
    tim
    -0.86
    aun
    -0.85
    stru
    -0.67
     trace
    -0.66
     piv
    -0.64
    facebook
    -0.64
    fund
    -0.64
     transitioned
    -0.63
    estone
    -0.63
    POSITIVE LOGITS
     ILCS
    0.77
    amins
    0.71
     censor
    0.70
    cill
    0.67
     righteousness
    0.66
     actionGroup
    0.65
     censorship
    0.65
    thora
    0.65
    MENT
    0.63
    piracy
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.