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

    Neuronpedia

    INDEX
    Explanations

    references to 'half' or portions thereof across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     وتسجيلات
    -0.92
    })));
    -0.88
     يتيمه
    -0.87
    Bibliographie
    -0.84
     ]}
    -0.82
    )}</
    -0.79
     }],
    -0.79
     للاسماء
    -0.79
    }}/>
    -0.79
    )]);
    -0.77
    POSITIVE LOGITS
     half
    1.79
     Half
    1.72
    Half
    1.66
    half
    1.64
     HALF
    1.59
    HALF
    1.42
     halves
    1.29
    半
    1.14
     metade
    1.01
     halve
    0.99
    Act Density 0.107%

    No Known Activations