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

    Neuronpedia

    INDEX
    Explanations

    unusual or significant textual elements, possibly related to unique experiences or strong emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     leider
    -0.16
    Sadly
    -0.16
     Sadly
    -0.15
     accordingly
    -0.15
     либо
    -0.14
     Various
    -0.14
     Unfortunately
    -0.14
    Unfortunately
    -0.14
     sadly
    -0.14
    ardon
    -0.14
    POSITIVE LOGITS
     such
    0.76
     so
    0.66
    such
    0.59
     SUCH
    0.56
    å¦ĤæѤ
    0.54
    è¿Ļä¹Ī
    0.52
     à¤ĩतन
    0.51
     Such
    0.49
    Such
    0.47
    éĤ£ä¹Ī
    0.41
    Act Density 0.628%

    No Known Activations