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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     ellipt
    -0.71
    enburg
    -0.60
     2048
    -0.60
    ldon
    -0.59
     fitt
    -0.58
    dc
    -0.57
     bye
    -0.57
    iani
    -0.56
    lus
    -0.56
     Manson
    -0.55
    POSITIVE LOGITS
    taboola
    0.76
    ankind
    0.76
    terday
    0.75
    ifted
    0.74
    emort
    0.73
    ansk
    0.70
    URR
    0.68
     hither
    0.67
    ocated
    0.66
    glers
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.