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

    Neuronpedia

    INDEX
    Explanations

    symbols and whitespace characters in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    '},
    -0.76
    typeorm
    -0.66
     /\.(
    -0.66
    rabbitmq
    -0.65
    riwal
    -0.63
    lint
    -0.61
    :^{
    -0.61
    ́ng
    -0.60
    "],
    -0.60
    ']],
    -0.60
    POSITIVE LOGITS
    ↵↵↵↵↵
    0.91
    ↵↵↵↵↵↵
    0.91
    ↵↵↵↵
    0.89
    ↵↵↵
    0.89
    ↵↵↵↵↵↵↵
    0.80
    ↵↵↵↵↵↵↵↵
    0.78
    ↵↵↵↵↵↵↵↵↵↵
    0.75
    ↵↵↵↵↵↵↵↵↵↵↵
    0.73
    にほんブログ村
    0.71
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.71
    Act Density 0.057%

    No Known Activations