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

    Neuronpedia

    INDEX
    Explanations

    the opening of a text with a specific tag or special marker

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    曖昧さ回避
    -0.70
    GEBURTSDATUM
    -0.69
    aarrggbb
    -0.64
    expandindo
    -0.62
    eadilan
    -0.62
    andaag
    -0.61
    клопе
    -0.61
    mány
    -0.60
     ddelweddau
    -0.60
    UnsafeEnabled
    -0.59
    POSITIVE LOGITS
     expressed
    0.74
     MessageBoxIcon
    0.65
    躇
    0.64
     feelings
    0.62
     reactions
    0.61
     surprised
    0.60
     voiced
    0.57
     expressions
    0.57
    expressed
    0.56
     expresses
    0.54
    Act Density 0.365%

    No Known Activations