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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ariat
    -0.70
    vier
    -0.68
     subst
    -0.65
     distinguish
    -0.65
     append
    -0.65
     distinguishes
    -0.64
     "_
    -0.63
     acqu
    -0.63
     enqu
    -0.62
     differentiated
    -0.61
    POSITIVE LOGITS
    å¸
    0.79
    asonic
    0.76
     Skydragon
    0.70
    tics
    0.69
    olate
    0.68
    til
    0.68
    sych
    0.67
    period
    0.67
    eous
    0.66
    astical
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.