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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ACTED
    -0.75
     Favor
    -0.73
     Preferred
    -0.72
     heaven
    -0.70
     Drawn
    -0.67
     Dish
    -0.66
    ãĥīãĥ©
    -0.65
     Parables
    -0.65
     Swanson
    -0.64
     Saw
    -0.64
    POSITIVE LOGITS
     challeng
    0.85
    apest
    0.79
    awei
    0.79
    ashtra
    0.76
    ibaba
    0.73
    emouth
    0.72
     describ
    0.70
    agy
    0.69
    appers
    0.68
    oké
    0.67
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.