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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Zac
    -0.71
    LOG
    -0.69
     Bert
    -0.68
    ãĥŁ
    -0.67
     Compass
    -0.67
     Gemini
    -0.67
    nick
    -0.66
     Medals
    -0.66
    æĿ
    -0.66
     Tav
    -0.64
    POSITIVE LOGITS
    azer
    0.74
    galitarian
    0.73
    roxy
    0.72
    orney
    0.70
     grain
    0.69
    enium
    0.68
    yrim
    0.68
    iary
    0.67
    iaries
    0.67
    ahl
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.