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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     millenn
    -0.87
     challeng
    -0.74
     encount
    -0.71
     enthusi
    -0.71
     reluct
    -0.68
    catentry
    -0.68
    ignore
    -0.67
     unbeliev
    -0.64
     reckon
    -0.62
    ailability
    -0.62
    POSITIVE LOGITS
    neau
    0.76
    puter
    0.74
    arnaev
    0.71
    wagen
    0.70
    bledon
    0.66
    lished
    0.66
    ebus
    0.66
    yss
    0.66
    perfect
    0.65
    merce
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.