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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    omsky
    -0.86
    ulia
    -0.73
    hua
    -0.71
    eln
    -0.71
    lda
    -0.68
    odore
    -0.67
    rison
    -0.67
    prints
    -0.67
    ultz
    -0.67
    illon
    -0.67
    POSITIVE LOGITS
    ãĥĦ
    0.76
    slave
    0.67
     Corker
    0.66
    ãĤ´
    0.65
     Cumber
    0.65
     Stranger
    0.64
     PIT
    0.63
     Refugee
    0.62
     forge
    0.60
     bye
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.