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

    Neuronpedia

    INDEX
    Explanations

    references to academic citations and publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Audiodateien
    -0.91
    קישורים
    -0.83
     InputDecoration
    -0.80
     lenker
    -0.79
    ագրություններ
    -0.78
    NUMX
    -0.77
     (§
    -0.76
    ‽
    -0.70
    Begriffsklä
    -0.70
    !—
    -0.70
    POSITIVE LOGITS
     diatas
    0.79
     ,
    0.69
    .,
    0.65
     :
    0.60
     didalam
    0.60
     llego
    0.59
      
    0.57
     coté
    0.57
    .....
    0.56
     bellow
    0.55
    Act Density 0.331%

    No Known Activations