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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    itching
    -0.83
    itches
    -0.79
    elled
    -0.78
    imbabwe
    -0.76
    bledon
    -0.74
    pled
    -0.72
    brance
    -0.71
     Sabha
    -0.69
    iminary
    -0.69
    cham
    -0.69
    POSITIVE LOGITS
     chars
    0.69
     checkout
    0.68
     unlimited
    0.65
     bubble
    0.64
     Disclosure
    0.64
     solvent
    0.63
     vacuum
    0.63
     bubbles
    0.62
     infinite
    0.62
     empty
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.