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

    Neuronpedia

    INDEX
    Explanations

    references to languages and cultural identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anford
    -0.17
    utton
    -0.17
     Cunning
    -0.16
    458
    -0.16
    ạm
    -0.15
    ully
    -0.15
    ignum
    -0.15
    unate
    -0.15
    obre
    -0.14
    cona
    -0.14
    POSITIVE LOGITS
     dialect
    0.28
     Standard
    0.25
    Standard
    0.24
     spoken
    0.20
    æłĩåĩĨ
    0.19
    standard
    0.19
    -standard
    0.19
     STANDARD
    0.19
    spoken
    0.19
    æ¨Ļæºĸ
    0.18
    Act Density 0.037%

    No Known Activations