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

    Neuronpedia

    INDEX
    Explanations

    expressions of quantity or frequency

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

    "many" or similar quantifiers

    np_acts-logits-general · gemini-2.0-flash

    many, some, most

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    J
    -0.56
    E
    -0.54
    X
    -0.53
    <bos>
    -0.52
    Ch
    -0.51
    /
    -0.51
    etc
    -0.51
    C
    -0.51
    Q
    -0.50
    I
    -0.50
    POSITIVE LOGITS
    Brainz
    0.86
    %\]
    0.86
    ]:
    0.85
    >--}}
    0.85
    }}]{
    0.85
    "]);
    0.85
    NUMX
    0.83
    .}(
    0.83
    '],
    0.82
    >\<^
    0.80
    Act Density 0.808%

    No Known Activations