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

    Neuronpedia

    INDEX
    Explanations

    references to specific names or labels, possibly pertaining to various entities or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rungsseite
    -1.09
     مرئيه
    -0.83
    الحياه
    -0.83
    verwijspagina
    -0.80
     autorytatywna
    -0.78
    EndProject
    -0.74
    nationality
    -0.74
     للمعارف
    -0.73
     ujednoznacz
    -0.72
     doubtnut
    -0.72
    POSITIVE LOGITS
    則是
    0.52
     M
    0.51
    fortawesome
    0.51
     P
    0.46
    </strong>
    0.46
     G
    0.46
    lich
    0.45
     F
    0.45
     V
    0.45
     W
    0.44
    Act Density 0.685%

    No Known Activations