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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     people
    0.51
    0.47
     outsiders
    0.47
    一个
    0.46
     English
    0.44
     Satan
    0.44
     Grandma
    0.44
     God
    0.43
     Anthony
    0.43
     L
    0.42
    POSITIVE LOGITS
    óso
    0.45
    🍙
    0.40
    🗻
    0.40
    ⛩
    0.39
    🍣
    0.39
    🖼
    0.39
    🧖
    0.39
    🛹
    0.39
    🕝
    0.39
     from
    0.38
    Act Density 0.000%

    No Known Activations