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

    Neuronpedia

    INDEX
    Explanations

    positive sentiments and expressions of satisfaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alez
    -0.15
    irl
    -0.14
    inem
    -0.14
    æĺĩ
    -0.14
     clutter
    -0.13
    asper
    -0.13
     Serif
    -0.13
    меÑĤÑĮ
    -0.13
    itan
    -0.13
    aph
    -0.13
    POSITIVE LOGITS
     quality
    0.27
    quality
    0.23
     Quality
    0.20
    Quality
    0.20
    -quality
    0.20
     arrived
    0.18
    è´¨éĩı
    0.17
     ë°°ìĨ¡
    0.17
    ë°°ìĨ¡
    0.17
     shipped
    0.17
    Act Density 0.134%

    No Known Activations