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

    Neuronpedia

    INDEX
    Explanations

    references to introductions and forewords in texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iete
    -0.15
    lian
    -0.15
     Papers
    -0.14
    jon
    -0.14
     Shades
    -0.14
    iÄįky
    -0.14
    patrick
    -0.14
    umber
    -0.14
    613
    -0.14
     multic
    -0.14
    POSITIVE LOGITS
    ลาย
    0.17
    attern
    0.16
    ailer
    0.15
    verted
    0.14
    бÑĥÑĢг
    0.14
    ohl
    0.14
    ãĥĶãĥ¼
    0.13
     purpose
    0.13
    uffix
    0.13
    anya
    0.13
    Act Density 0.024%

    No Known Activations