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

    Neuronpedia

    INDEX
    Explanations

    instances of structured text or headings indicating new sections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.66
    </strong>
    -0.63
    </h1>
    -0.60
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.58
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.58
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.57
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.56
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.56
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.54
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.54
    POSITIVE LOGITS
     Савезне
    0.81
    TestingModule
    0.79
    QMetaType
    0.79
     autorytatywna
    0.79
    Autoritní
    0.79
    енча
    0.78
    sizeCache
    0.73
     culturelle
    0.72
     transfieras
    0.72
     NSCoder
    0.71
    Act Density 0.435%

    No Known Activations