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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     nou
    -0.08
     Bowen
    -0.08
    Park
    -0.08
    首位
    -0.07
    ISS
    -0.07
    okit
    -0.07
    Tho
    -0.07
    enh
    -0.07
     Draft
    -0.07
    Fight
    -0.07
    POSITIVE LOGITS
    .Runtime
    0.07
     climates
    0.07
     initWithStyle
    0.07
    🌧
    0.07
    יכות
    0.07
     unintention
    0.07
     ambition
    0.07
    _energy
    0.06
    ߘ
    0.06
    robots
    0.06
    Act Density 0.031%

    No Known Activations