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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the concept of transformation or change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     poitrine
    -0.43
    naies
    -0.41
     than
    -0.40
     Kindes
    -0.40
    وعة
    -0.40
    rrh
    -0.39
    b
    -0.39
     receta
    -0.38
     ніж
    -0.38
     hơn
    -0.37
    POSITIVE LOGITS
     насељу
    0.75
    '])->
    0.72
    ...')
    0.70
    lossians
    0.69
     BorderSide
    0.69
    ...');
    0.68
    "]));
    0.68
    dafx
    0.68
    utilisons
    0.66
    ]?.
    0.66
    Act Density 0.282%

    No Known Activations