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

    Neuronpedia

    INDEX
    Explanations

    phrases that express negation or the absence of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Something
    -0.69
     aquilo
    -0.69
     tourne
    -0.68
     fascic
    -0.67
     immerhin
    -0.66
     peels
    -0.66
     dû
    -0.66
    DataAnnotations
    -0.66
     auquel
    -0.65
     Scro
    -0.64
    POSITIVE LOGITS
     no
    0.83
     нет
    0.74
     free
    0.68
     empty
    0.67
     clear
    0.65
     “
    0.63
     ไม่มี
    0.63
    Нет
    0.63
     pure
    0.62
     room
    0.62
    Act Density 0.179%

    No Known Activations