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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     stroke
    -0.69
     shell
    -0.66
     ways
    -0.62
    ãĥ
    -0.60
    BTC
    -0.60
     Ships
    -0.59
     path
    -0.56
     Mining
    -0.56
    laws
    -0.56
     subtle
    -0.55
    POSITIVE LOGITS
    ragon
    0.82
    quez
    0.76
    alm
    0.74
    aired
    0.74
    imar
    0.71
    zzo
    0.71
    ometimes
    0.70
    ovan
    0.69
    lda
    0.68
    hub
    0.68
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.