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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    £ı
    -0.77
    Ħ¢
    -0.73
    agus
    -0.71
     foregoing
    -0.67
    metry
    -0.66
    ©¶æ
    -0.66
     anecd
    -0.64
    onement
    -0.64
    hiba
    -0.63
     Settlement
    -0.61
    POSITIVE LOGITS
    gravity
    0.72
    furt
    0.71
    ukong
    0.65
    ibles
    0.64
    naire
    0.64
    crew
    0.64
    allic
    0.64
    support
    0.63
    aligned
    0.62
    idable
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.