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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating inviting or summarizing information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.76
     kasarigan
    -0.67
     betweenstory
    -0.59
     Meksiku
    -0.54
    Хьажоргаш
    -0.54
    writeFieldEnd
    -0.50
     gynhyrchwyd
    -0.49
     Comprometido
    -0.47
    ViewImports
    -0.47
    んですか
    -0.47
    POSITIVE LOGITS
     below
    0.90
     briefly
    0.83
     brief
    0.76
     👇
    0.68
    below
    0.66
     Below
    0.66
    Below
    0.65
    👇
    0.64
     quick
    0.64
    ↓↓
    0.63
    Act Density 0.551%

    No Known Activations