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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    spection
    -0.72
     Diss
    -0.71
    ASED
    -0.67
     IPM
    -0.62
     Hels
    -0.62
     Dish
    -0.62
     RD
    -0.61
     Lans
    -0.61
    assisted
    -0.61
    glas
    -0.61
    POSITIVE LOGITS
    ippery
    0.84
    autical
    0.75
    ictionary
    0.73
    ernels
    0.73
    abulary
    0.72
    alysis
    0.71
    umat
    0.71
    orsche
    0.69
    ippi
    0.69
    eca
    0.69
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.