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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    cup
    -0.64
    mpire
    -0.64
    wine
    -0.63
    mond
    -0.62
     panc
    -0.60
    bury
    -0.60
     Sweet
    -0.60
     cider
    -0.59
    itcher
    -0.59
     á
    -0.58
    POSITIVE LOGITS
    href
    0.77
    Reply
    0.69
    rontal
    0.69
    earch
    0.68
    activation
    0.68
    agnetic
    0.67
    respond
    0.64
    ordinate
    0.62
    anim
    0.62
    vernment
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.