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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    肪
    -0.08
    ayer
    -0.07
    _SCENE
    -0.07
    _trajectory
    -0.07
     ion
    -0.07
    ACP
    -0.07
    מפי
    -0.07
    ضر
    -0.06
    凱
    -0.06
    flag
    -0.06
    POSITIVE LOGITS
    history
    0.07
    耕地
    0.07
     VL
    0.06
     gras
    0.06
     rejected
    0.06
    _loaded
    0.06
     oy
    0.06
    ᡠ
    0.06
     sprz
    0.06
     obsł
    0.06
    Act Density 0.003%

    No Known Activations