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

    Neuronpedia

    INDEX
    Explanations

    statements that include conjunctions and related phrases

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

    Follows the word "and"

    np_acts-logits-general · gemini-2.0-flash

    lists joined by and

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    They
    -0.69
    they
    -0.68
    I
    -0.67
    K
    -0.62
    A
    -0.61
    W
    -0.61
    it
    -0.59
    E
    -0.59
    1
    -0.59
    D
    -0.58
    POSITIVE LOGITS
     other
    1.02
    pecially
    0.92
    ]<<"
    0.92
    ]='\
    0.92
     ?>/
    0.92
    )";
    0.91
    ratulations
    0.91
    ignty
    0.90
    "):
    0.90
    .}(
    0.90
    Act Density 0.720%

    No Known Activations