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

    Neuronpedia

    INDEX
    Explanations

    references to cherished relationships with family and close ones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uttle
    -0.17
    uning
    -0.16
    -Length
    -0.15
    utin
    -0.15
    ãĤ¹ãĥĨ
    -0.14
    nal
    -0.14
     Cres
    -0.14
    ibal
    -0.14
    ÏģÏį
    -0.14
    pawn
    -0.14
    POSITIVE LOGITS
     Superior
    0.16
    irie
    0.16
     Kad
    0.15
     preced
    0.14
    ior
    0.14
    odies
    0.14
    ä¼¼
    0.14
    oki
    0.13
     borrow
    0.13
    /un
    0.13
    Act Density 0.008%

    No Known Activations