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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    glass
    -0.92
    EStreamFrame
    -0.72
    gat
    -0.72
     Gleaming
    -0.69
    Haunted
    -0.67
    Prop
    -0.64
    watching
    -0.64
    lifting
    -0.63
     Thoughts
    -0.62
     Lyme
    -0.62
    POSITIVE LOGITS
    guyen
    0.71
    annel
    0.71
    heit
    0.64
    bourg
    0.62
     differentiation
    0.62
     exception
    0.60
    yz
    0.59
    ayette
    0.59
     unanim
    0.59
    ufact
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.