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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     difficulties
    0.60
    矚
    0.60
     reportedly
    0.59
     apparently
    0.59
     caractéristique
    0.58
     notoriously
    0.57
     difficultés
    0.57
     সৌম
    0.57
     בעי
    0.57
     supposedly
    0.57
    POSITIVE LOGITS
    相当于
    1.10
     akin
    1.05
    就像
    0.94
     অনেকটা
    0.89
     equivalent
    0.83
    类似于
    0.83
    equivalent
    0.82
     glorified
    0.80
     σαν
    0.79
     analogous
    0.78
    Act Density 0.931%

    No Known Activations