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

    Neuronpedia

    INDEX
    Explanations

    repeated references to "this" or "these" objects in various contexts

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

    pointing to this

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dominal
    -0.50
     ویکی‌پدی
    -0.49
    Cactus
    -0.46
    Opportun
    -0.44
    Abigail
    -0.43
    angliski
    -0.43
     Opportun
    -0.41
    BuildContext
    -0.40
    dchen
    -0.40
    GenerationType
    -0.39
    POSITIVE LOGITS
    これ
    1.78
     これ
    1.40
    それ
    1.22
    コレ
    0.96
    これで
    0.90
    これに
    0.85
    これを
    0.78
    これが
    0.73
    これは
    0.70
    あれ
    0.69
    Act Density 0.007%

    No Known Activations