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

    Neuronpedia

    INDEX
    Explanations

    references to pairs or combinations of items or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    two things or people together

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    stdlib
    -0.54
    FXML
    -0.50
     Roosevelt
    -0.50
    oosevelt
    -0.49
     Gron
    -0.49
    /**
    -0.46
     Ludo
    -0.45
    Brun
    -0.44
     Cannabis
    -0.44
    Aten
    -0.43
    POSITIVE LOGITS
     pair
    2.23
     Pair
    1.99
    pair
    1.90
    Pair
    1.87
     PAIR
    1.77
     pairs
    1.66
     paire
    1.66
    PAIR
    1.51
     Pairs
    1.47
     coppia
    1.32
    Act Density 0.012%

    No Known Activations