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

    Neuronpedia

    INDEX
    Explanations

    symbols and formatting elements commonly found in code or mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     |↵
    -0.17
     âĶĤ
    -0.16
    Posted
    -0.15
    erin
    -0.15
     ·
    -0.15
     |
    -0.15
    omb
    -0.14
     âĶĥ
    -0.14
    æĪı
    -0.14
     âĢ¢
    -0.14
    POSITIVE LOGITS
    è§
    0.15
    render
    0.15
    ITHER
    0.14
    Ñĩи
    0.14
     âĵĺ
    0.14
    arness
    0.14
    |
    0.14
    .CopyTo
    0.14
    δα
    0.13
    urname
    0.13
    Act Density 0.001%

    No Known Activations