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

    Neuronpedia

    INDEX
    Explanations

    phrases that express the concept of options or alternatives involving "one," "two," "day," "week," "year," or "story."

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

    "or" followed by a number

    np_acts-logits-general · gemini-2.0-flash

    or two or so

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    
    -0.68
    DataPropertyName
    -0.62
    ="@+
    -0.60
     equal
    -0.59
    andrea
    -0.58
     iprot
    -0.56
    <tfoot>
    -0.56
    metz
    -0.55
    KommentareTeilen
    -0.53
    στό
    -0.51
    POSITIVE LOGITS
     two
    1.41
    two
    1.28
     deux
    1.17
    Two
    1.08
     TWO
    1.03
     Two
    1.03
     zwei
    1.00
    TWO
    0.92
     δύο
    0.91
     duas
    0.89
    Act Density 0.064%

    No Known Activations