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

    Neuronpedia

    INDEX
    Explanations

    repeated phrases or words within a text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     nostru
    -0.53
    retario
    -0.51
    Ор
    -0.50
    '
    -0.49
     Kruse
    -0.48
    .
    -0.47
     DOM
    -0.47
     houſe
    -0.47
     Sturm
    -0.47
     infringe
    -0.45
    POSITIVE LOGITS
    SequentialGroup
    0.88
     propOrder
    0.79
     same
    0.78
     mêmes
    0.74
    fastjson
    0.74
    Hochspringen
    0.73
    astéroïdes
    0.73
    Demikian
    0.73
    tagext
    0.72
     pinulongan
    0.71
    Act Density 0.275%

    No Known Activations