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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    alle
    -0.81
    aign
    -0.72
    uo
    -0.72
    ala
    -0.71
    aga
    -0.71
    antam
    -0.65
    stood
    -0.64
    uchi
    -0.64
    Ĥİ
    -0.63
    egu
    -0.62
    POSITIVE LOGITS
    theless
    0.88
     EVENTS
    0.75
     DRAG
    0.73
    GBT
    0.72
    FTWARE
    0.71
    eenth
    0.68
     UCHIJ
    0.68
     shalt
    0.68
     grep
    0.65
     Nicotine
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.