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

    Neuronpedia

    INDEX
    Explanations

    various forms of the word "no" or its equivalents in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NUMX
    -0.59
     autorytatywna
    -0.58
     gynhyrchwyd
    -0.57
    liferay
    -0.56
    umenter
    -0.54
    ukka
    -0.53
    zedł
    -0.53
    Preheat
    -0.52
    обходи
    -0.52
    kuva
    -0.52
    POSITIVE LOGITS
    но
    1.04
    ло
    0.85
     تضيفلها
    0.69
    во
    0.69
    НО
    0.66
    чено
    0.65
    зно
    0.63
    ło
    0.62
    ęło
    0.60
    +#+#
    0.58
    Act Density 1.992%

    No Known Activations