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

    Neuronpedia

    INDEX
    Explanations

    words associated with experience and dependence on others

    oai_token-act-pair · gemini-2.0-flash

    prepositions and words indicating relationships

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    もしれません
    -0.47
     kanssa
    -0.44
    hdessä
    -0.42
    ässä
    -0.40
    いしい
    -0.39
     města
    -0.39
    joje
    -0.39
    app
    -0.38
    træ
    -0.37
    kuuta
    -0.37
    POSITIVE LOGITS
     by
    2.05
     oleh
    1.57
     By
    1.52
    by
    1.44
    By
    1.39
     bởi
    1.32
     przez
    1.27
     BY
    1.27
     ידי
    1.21
     pelos
    1.16
    Act Density 4.157%

    No Known Activations