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

    Neuronpedia

    INDEX
    Explanations

    the start of paragraphs or sections in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ed
    -1.11
    InputBorder
    -0.87
     تضيفلها
    -0.82
    Tikang
    -0.81
     BoxDecoration
    -0.79
     Newberry
    -0.78
    плек
    -0.78
     Hertz
    -0.76
     Eddy
    -0.75
     Newbury
    -0.75
    POSITIVE LOGITS
    ↵↵↵
    1.78
    ↵↵↵↵
    1.12
    __*/
    1.02
    ↵↵↵↵↵↵
    1.01
    ↵↵↵↵↵
    1.01
    ↵↵↵↵↵↵↵
    0.99
    ↵↵↵↵↵↵↵↵↵
    0.87
    にほんブログ村
    0.84
    ↵↵↵↵↵↵↵↵
    0.84
    ↵↵↵↵↵↵↵↵↵↵↵
    0.83
    Act Density 0.040%

    No Known Activations