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

    Neuronpedia

    INDEX
    Explanations

    references to identity and behavior dynamics within social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preceding "actually" or "but"

    np_acts-logits-general · gemini-2.0-flash

    contrast between appearance and reality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -0.77
    PerformLayout
    -0.69
    queryInterface
    -0.61
    yntaxException
    -0.58
     ویکی‌پدیا
    -0.55
    awaiter
    -0.53
     خارجية
    -0.51
    aarrggbb
    -0.50
    AddTagHelper
    -0.48
    oredCriteria
    -0.47
    POSITIVE LOGITS
     actually
    1.86
    actually
    1.77
     Actually
    1.74
    Actually
    1.67
     ACTUALLY
    1.48
    实际上
    1.45
    其实是
    1.43
     sebenarnya
    1.40
     actuality
    1.30
    其實
    1.29
    Act Density 0.417%

    No Known Activations