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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     precinct
    -0.68
     Centauri
    -0.67
    election
    -0.63
     arbitration
    -0.60
     approving
    -0.59
    fman
    -0.59
     endorsements
    -0.59
     prot
    -0.58
     persuasion
    -0.56
     youths
    -0.56
    POSITIVE LOGITS
    estone
    0.74
    rug
    0.71
    rist
    0.71
    estones
    0.70
    ser
    0.69
    flows
    0.65
    oes
    0.64
    assi
    0.63
    adh
    0.63
    aker
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.