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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Esper
    0.68
     constitutional
    0.61
     Szeged
    0.60
     Profesor
    0.60
     delet
    0.59
    Planck
    0.59
     mouthful
    0.59
     professores
    0.59
     Eurasian
    0.59
     pessimistic
    0.58
    POSITIVE LOGITS
    过程
    0.68
    abilidad
    0.68
    捻
    0.65
    作用
    0.63
     चक्र
    0.62
    herr
    0.62
    效果
    0.61
    频率
    0.61
    ains
    0.60
    UIT
    0.59
    Act Density 0.001%

    No Known Activations