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

    Neuronpedia

    INDEX
    Explanations

    instances or references to rarity or unusual occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ertz
    -0.17
    aye
    -0.16
    emes
    -0.15
    amar
    -0.14
    onya
    -0.14
    orno
    -0.14
    raya
    -0.14
    249
    -0.13
    705
    -0.13
     Wonderland
    -0.13
    POSITIVE LOGITS
    faction
    0.26
    ities
    0.19
    ityEngine
    0.17
     occasions
    0.17
    ely
    0.17
    obil
    0.16
    LY
    0.16
    ily
    0.15
    SPA
    0.15
    jÃŃ
    0.15
    Act Density 0.021%

    No Known Activations