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

    Neuronpedia

    INDEX
    Explanations

    visual formatting elements and numeric identifiers in the document

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     tartalomajánló
    -0.84
     propOrder
    -0.79
    ьаж
    -0.79
    InjectAttribute
    -0.76
    -0.76
    featureID
    -0.75
    afficheront
    -0.73
     betweenstory
    -0.73
    تقاوى
    -0.72
    Vidite
    -0.71
    POSITIVE LOGITS
    IAm
    0.47
     Lagi
    0.45
     Boogie
    0.45
     absolutely
    0.44
     matang
    0.44
    BEGIN
    0.43
    ilanth
    0.43
     seriously
    0.43
     gelo
    0.43
    Inde
    0.42
    Act Density 0.078%

    No Known Activations