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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    essor
    -0.79
    urai
    -0.79
    ħĭ
    -0.77
    alam
    -0.76
    ubi
    -0.76
    hov
    -0.75
    ukong
    -0.72
    lator
    -0.72
    xual
    -0.69
    arate
    -0.68
    POSITIVE LOGITS
     declass
    0.67
     PLAN
    0.66
     Jury
    0.65
     reefs
    0.64
     basis
    0.63
    eous
    0.62
     Vatican
    0.61
     repr
    0.61
     PLA
    0.60
     Benghazi
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.