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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Jub
    -0.79
    ©¶æ¥µ
    -0.76
     Trou
    -0.70
     Moody
    -0.66
     Uriel
    -0.65
    iour
    -0.63
     thunder
    -0.62
     glim
    -0.62
    ospel
    -0.62
    Ń·
    -0.61
    POSITIVE LOGITS
    productive
    0.78
    Pages
    0.70
    changes
    0.70
    cycles
    0.66
    ItemImage
    0.66
    ort
    0.65
    wagon
    0.65
    POSE
    0.63
    act
    0.63
    ña
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.