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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    teness
    -0.78
    neum
    -0.76
    gd
    -0.74
    ¶æ
    -0.72
    rift
    -0.69
    viks
    -0.69
    phrine
    -0.68
    ools
    -0.67
    reetings
    -0.66
    VG
    -0.66
    POSITIVE LOGITS
    !--
    0.66
     Daniels
    0.64
     Heard
    0.63
     surrogate
    0.61
     barriers
    0.61
     Kasich
    0.61
     Santorum
    0.61
     Berry
    0.60
     Diaz
    0.59
     Rubio
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.