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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize comparison or contrast

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

    not just or only

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    break
    -0.37
     instead
    -0.36
     cré
    -0.35
    æn
    -0.35
    断
    -0.34
    dataGridView
    -0.34
     updateTime
    -0.33
     TED
    -0.33
    Hod
    -0.33
    __':
    -0.32
    POSITIVE LOGITS
     autorytatywna
    0.85
    +#+#
    0.59
    Portály
    0.58
    deutig
    0.58
    AnchorStyles
    0.57
    kijken
    0.56
     zoude
    0.56
     وتسجيلات
    0.55
     anhänger
    0.54
     miniaturka
    0.49
    Act Density 0.017%

    No Known Activations