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

    Neuronpedia

    INDEX
    Explanations

    contextually important transition words and phrases that indicate relationships or comparisons

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

    followed by prepositions

    np_acts-logits-general · gemini-2.0-flash

    contrastive and additive phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -0.67
    ↵↵
    -0.65
    ↵
    -0.63
    TO
    -0.59
    FOR
    -0.56
     (
    -0.55
     I
    -0.54
    Of
    -0.53
    FROM
    -0.52
    ,
    -0.52
    POSITIVE LOGITS
    aarrggbb
    1.21
     مرئيه
    1.08
    ValueStyle
    1.07
     '\\;'
    1.05
     estekak
    1.03
     BoxDecoration
    1.01
     CreateTagHelper
    1.01
    AddTagHelper
    0.99
    AddHtmlAttribute
    0.96
     الرياضيه
    0.96
    Act Density 1.061%

    No Known Activations