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

    Neuronpedia

    INDEX
    Explanations

    numerical values and mathematical expressions

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and mathematical operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ierrez
    -0.80
     Krug
    -0.73
    ortmund
    -0.72
    accompan
    -0.70
    hement
    -0.70
    urion
    -0.69
     Coul
    -0.67
    ãĥ¼ãĥĨãĤ£
    -0.67
     Schwe
    -0.66
     Ernst
    -0.64
    POSITIVE LOGITS
    px
    0.90
     ));
    0.88
     //[
    0.88
    0000
    0.88
     );
    0.86
     }
    0.83
    []
    0.82
    000000
    0.81
    00000000
    0.80
    )'
    0.80
    Act Density 0.123%

    No Known Activations