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

    Neuronpedia

    INDEX
    Explanations

    lines of dialogue or direct quotations within a text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    出版年
    -1.18
    دانشنامهٔ
    -1.09
     للمعارف
    -0.99
     BorderRadius
    -0.96
    发表于
    -0.95
     Houſe
    -0.94
    ]--;
    -0.93
    ItemBackground
    -0.93
    хьтан
    -0.93
    DeleteBehavior
    -0.92
    POSITIVE LOGITS
    :
    1.29
    ↵↵
    0.77
    ↵
    0.75
     :
    0.67
     suivante
    0.64
    ↵↵↵
    0.63
     
    0.62
      
    0.60
    ：
    0.60
    :
    0.59
    Act Density 1.753%

    No Known Activations