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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Congratulations
    -0.16
    anson
    -0.16
    ácil
    -0.15
    obic
    -0.15
     congratulations
    -0.15
    upply
    -0.14
     congrat
    -0.14
    OLA
    -0.14
    Äĥng
    -0.14
     Hav
    -0.14
    POSITIVE LOGITS
     thank
    0.20
    ãģĤãĤĬãģĮãģ¨ãģĨãģĶãģĸ
    0.19
     Thank
    0.18
     fen
    0.17
     Fen
    0.17
    Thank
    0.16
     THANK
    0.16
    thank
    0.16
    è°¢
    0.16
    ILED
    0.15
    Act Density 0.094%

    No Known Activations