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

    Neuronpedia

    INDEX
    Explanations

    programming-related keywords or structure in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    脚注の使い方
    -1.14
     Majefty
    -1.11
     myſelf
    -1.11
     itſelf
    -1.09
     pleaſure
    -1.07
     purpoſe
    -1.07
     Reſ
    -1.05
    saraba
    -1.05
    UserScript
    -1.03
     houſe
    -1.02
    POSITIVE LOGITS
    <bos>
    0.79
     "
    0.71
    '
    0.67
     
    0.61
     The
    0.50
     K
    0.49
     A
    0.48
    "
    0.48
     '
    0.47
    .
    0.47
    Act Density 0.469%

    No Known Activations