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

    Neuronpedia

    INDEX
    Explanations

    conditional statements and uncertainty in expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jago
    -0.82
     يتيمه
    -0.73
    SBATCH
    -0.72
    jmniej
    -0.70
     hapa
    -0.70
     jdbcTemplate
    -0.70
     اكتوبر
    -0.69
     kasarigan
    -0.69
    Obrázky
    -0.69
     MCT
    -0.68
    POSITIVE LOGITS
     whether
    1.15
     WHETHER
    1.04
    whether
    0.98
     Whether
    0.93
    Whether
    0.86
     apakah
    0.83
     האם
    0.77
     是否
    0.71
    {#
    0.69
    是否
    0.69
    Act Density 0.121%

    No Known Activations