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

    expressing thanks and appreciation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Datuak
    -0.52
     <<<<<<<<<<<<<<
    -0.52
     rêver
    -0.47
     koszulka
    -0.46
     Verſ
    -0.45
    ombies
    -0.45
    AutoScaleMode
    -0.44
     themſelves
    -0.44
     mecánico
    -0.44
     scolaire
    -0.43
    POSITIVE LOGITS
     Many
    0.49
    多谢
    0.47
     thanks
    0.46
    谢谢
    0.44
     Regards
    0.44
     Thanks
    0.44
    幸いです
    0.43
     apologies
    0.43
    謝謝
    0.42
     Obrigado
    0.42
    Act Density 0.003%

    No Known Activations