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

    Neuronpedia

    INDEX
    Explanations

    references to compromise in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     consultato
    -0.76
    日閲覧
    -0.71
    دانشنامهٔ
    -0.69
    consulté
    -0.66
    发表于
    -0.62
    Hozzáférés
    -0.60
    RegressionTest
    -0.60
     Seeder
    -0.59
    setOrder
    -0.59
    serif
    -0.58
    POSITIVE LOGITS
     cube
    1.20
     Cube
    1.10
     cub
    1.06
    cube
    1.03
     Cubes
    0.91
     cubes
    0.91
    Cube
    0.91
     Cub
    0.90
    Cub
    0.83
    cub
    0.81
    Act Density 0.160%

    No Known Activations