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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ovych
    -0.73
    estine
    -0.69
    ulhu
    -0.68
     Mara
    -0.64
    ¬¼
    -0.63
    arios
    -0.63
    oken
    -0.63
    aea
    -0.62
     surviving
    -0.62
    ode
    -0.62
    POSITIVE LOGITS
    pent
    0.78
    Coun
    0.77
    iership
    0.70
    Agg
    0.66
     pier
    0.66
    incial
    0.63
    tips
    0.63
    inqu
    0.61
    pair
    0.61
    irlf
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.