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

    Neuronpedia

    INDEX
    Explanations

    special characters and numbers

    oai_token-act-pair · gpt-3.5-turbo

    symbolic representations and their associated numeric values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odium
    -0.83
    olit
    -0.76
    orem
    -0.73
    okin
    -0.72
    stru
    -0.72
    opsy
    -0.71
     tremend
    -0.70
     gestation
    -0.70
    orno
    -0.70
     simplest
    -0.70
    POSITIVE LOGITS
    ª
    1.45
    Ùĩ
    1.07
    ĭ
    0.99
    âĶĢâĶĢ
    0.97
    Ùİ
    0.95
    ت
    0.94
    ¬
    0.93
    Ùħ
    0.93
    ²
    0.90
    ¨
    0.90
    Act Density 0.004%

    No Known Activations