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

    Neuronpedia

    INDEX
    Explanations

    varying numbers or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    whitespace and indentation tokens in code.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
    請繼續往下閱讀
    -0.63
    hésite
    -0.49
    Datuak
    -0.48
    يميديا
    -0.47
     başına
    -0.45
     kasarigan
    -0.44
     orejas
    -0.44
     picioare
    -0.44
     ChromeDriver
    -0.44
     Italijani
    -0.44
    POSITIVE LOGITS
     intptr
    0.67
    にほんブログ村
    0.51
    ↵↵↵
    0.51
    ↵↵↵↵↵↵
    0.50
    ↵↵↵↵
    0.49
    ↵↵↵↵↵↵↵↵
    0.49
    ↵↵↵↵↵
    0.45
    ↵↵↵↵↵↵↵
    0.44
    .*")]
    0.41
    SourceChecksum
    0.41
    Act Density 0.359%

    No Known Activations