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

    Neuronpedia

    INDEX
    Explanations

    sequential phrases indicating steps or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     incontri
    -0.45
     lewat
    -0.41
     dépass
    -0.40
     économiques
    -0.40
     incontra
    -0.40
     SimpleName
    -0.39
     financières
    -0.39
    wiada
    -0.38
     tegen
    -0.38
     воспринима
    -0.38
    POSITIVE LOGITS
     Daarna
    0.96
     Anschließend
    0.94
     Danach
    0.94
     Afterwards
    0.92
    SequentialGroup
    0.90
     then
    0.89
     estekak
    0.89
     THEN
    0.88
    aarrggbb
    0.88
     Then
    0.87
    Act Density 0.419%

    No Known Activations