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

    Neuronpedia

    INDEX
    Explanations

    statements and terminology related to theoretical proofs in scientific papers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icari
    -0.14
     actionTypes
    -0.13
    Ñģли
    -0.13
     famously
    -0.13
    Berry
    -0.13
    Fu
    -0.13
     Naw
    -0.12
    itto
    -0.12
    emoc
    -0.12
    ener
    -0.12
    POSITIVE LOGITS
    à¸ĩาà¸Ļ
    0.14
    tÃŃ
    0.14
    otate
    0.14
    akhir
    0.14
    afil
    0.14
    /stdc
    0.13
    lope
    0.13
    loh
    0.13
    elage
    0.13
    ignKey
    0.13
    Act Density 0.215%

    No Known Activations