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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases expressing quantity or degree

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

    Comparison using comparative adjectives

    np_acts-logits-general · gemini-2.0-flash

    identifies comparative structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     To
    -0.65
     G
    -0.61
    To
    -0.60
     M
    -0.56
    FROM
    -0.55
     I
    -0.53
    with
    -0.52
     
    -0.52
     O
    -0.51
     Re
    -0.51
    POSITIVE LOGITS
    IndentedString
    1.28
    GEBURTSDATUM
    1.21
     then
    1.15
     autorytatywna
    1.13
     مرئيه
    1.10
     تانيه
    1.08
     للاسماء
    1.07
    Rhestr
    1.06
    tagHelperRunner
    1.05
     ainfi
    1.05
    Act Density 0.162%

    No Known Activations