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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Cantor
    -0.72
    INGS
    -0.66
     unic
    -0.65
    Type
    -0.65
     accredited
    -0.62
     defeat
    -0.61
     defeats
    -0.61
     compat
    -0.60
    atisf
    -0.60
     Constantine
    -0.59
    POSITIVE LOGITS
    ministic
    0.80
    rum
    0.79
    lied
    0.78
    icum
    0.76
    lde
    0.76
    ove
    0.74
    Bay
    0.72
    mal
    0.72
    ohan
    0.72
    hesis
    0.71
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.