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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    rag
    -0.75
    arta
    -0.73
    jen
    -0.72
    orea
    -0.71
    arding
    -0.70
    ffee
    -0.70
    orf
    -0.70
    othal
    -0.69
     ][
    -0.68
    izo
    -0.68
    POSITIVE LOGITS
     crest
    0.81
     smoot
    0.74
    MpServer
    0.71
    staking
    0.70
    inventoryQuantity
    0.70
     Radius
    0.66
     horizont
    0.65
     pse
    0.65
     heights
    0.63
     Yiannopoulos
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.