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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Vaughan
    -0.95
    ĸļ
    -0.94
     Vaugh
    -0.79
    otaur
    -0.78
     Westbrook
    -0.76
     Constantine
    -0.75
     Constantin
    -0.73
     Oaks
    -0.73
     RTX
    -0.72
     CES
    -0.72
    POSITIVE LOGITS
    activ
    0.71
     directives
    0.67
    URE
    0.67
    AIN
    0.66
    FLAG
    0.65
    DATA
    0.65
    cand
    0.64
     shorthand
    0.64
    clair
    0.64
    resent
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.