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

    Neuronpedia

    INDEX
    Explanations

    symbols and their usage in digital communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eda
    -0.16
    oho
    -0.16
    indr
    -0.15
    fec
    -0.15
    hos
    -0.15
    еÑĢÑĤи
    -0.15
    ekim
    -0.15
    éné
    -0.15
    agina
    -0.14
    anza
    -0.14
    POSITIVE LOGITS
     already
    0.28
     Already
    0.24
    already
    0.23
    Already
    0.21
    endale
    0.20
     nat
    0.17
    atura
    0.16
     Ñĥже
    0.16
     nature
    0.16
     déjÃł
    0.16
    Act Density 0.007%

    No Known Activations