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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ijah
    -0.69
    ãģĨ
    -0.68
    arthed
    -0.68
    inder
    -0.63
    edition
    -0.63
    ffic
    -0.62
     Camb
    -0.61
    tons
    -0.60
     bustling
    -0.60
    æĸ¹
    -0.59
    POSITIVE LOGITS
    sighted
    0.70
     Hist
    0.67
     Policies
    0.66
     nomine
    0.66
    pter
    0.64
     Jere
    0.63
    aukee
    0.63
    dor
    0.62
     Orche
    0.62
    edIn
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.