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

    Neuronpedia

    INDEX
    Explanations

    references to significant historical dates or events

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

    Referring to decades (e.g., 1970s, 1980s)

    np_acts-logits-general · gemini-2.0-flash

    decades

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    //
    -0.93
    IsMutable
    -0.83
    UserScript
    -0.78
    <?
    -0.74
    FormTagHelper
    -0.72
    
    -0.69
    richTextPanel
    -0.68
     myſelf
    -0.68
     protoimpl
    -0.67
    }],
    -0.67
    POSITIVE LOGITS
    s
    0.72
    ’
    0.61
    '
    0.60
    ies
    0.57
    年代
    0.54
    es
    0.53
    ết
    0.50
    ′
    0.46
    ´
    0.46
    a
    0.43
    Act Density 0.077%

    No Known Activations