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

    Neuronpedia

    INDEX
    Explanations

    instances of the conjunction "and" in various contexts

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

    comparative adjectives after 'and'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     -
    -0.43
    wohnt
    -0.35
    fxml
    -0.35
    '-
    -0.34
    )-
    -0.34
    ]-
    -0.33
     —
    -0.33
    )$-
    -0.33
     Reif
    -0.33
    }$-
    -0.33
    POSITIVE LOGITS
     faster
    0.92
     leſs
    0.88
    faster
    0.87
     healthier
    0.87
    MigrationBuilder
    0.85
    smaller
    0.84
     smarter
    0.83
     bigger
    0.82
     clearer
    0.81
    Faster
    0.80
    Act Density 0.032%

    No Known Activations