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

    Neuronpedia

    INDEX
    Explanations

    quantitative measurements and their variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Diweddarwch
    -0.66
    rungsseite
    -0.64
    WithIOException
    -0.51
    fxml
    -0.50
    ंदीखरीदारी
    -0.50
    rrggbb
    -0.50
    NOPQRST
    -0.49
     krijgt
    -0.48
    Хьажоргаш
    -0.47
     gainera
    -0.47
    POSITIVE LOGITS
     amounted
    0.93
     autorytatywna
    0.90
     amounting
    0.81
     wynosi
    0.79
     beträgt
    0.75
     состави
    0.74
     составляет
    0.73
    CEED
    0.69
     составля
    0.69
    topping
    0.68
    Act Density 0.471%

    No Known Activations