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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     honor
    -0.80
    PsyNetMessage
    -0.69
    ãĤ¼ãĤ¦ãĤ¹
    -0.67
    andr
    -0.66
    ãĤĭ
    -0.66
    ħ
    -0.66
    omas
    -0.66
     expel
    -0.65
    untarily
    -0.64
    amph
    -0.64
    POSITIVE LOGITS
    verse
    0.81
    hoff
    0.79
    HQ
    0.70
    NE
    0.70
    odd
    0.69
    gross
    0.68
    fund
    0.68
     NE
    0.66
    Pe
    0.66
    fy
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.