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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing uncertainty or expectation about future events

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    awtextra
    -0.79
    RRect
    -0.64
     [*]
    -0.63
    MigrationBuilder
    -0.63
    thenReturn
    -0.62
    AddTagHelper
    -0.61
    IVEREF
    -0.61
    __":
    -0.61
    DECREF
    -0.60
    ingeki
    -0.60
    POSITIVE LOGITS
     estimés
    0.51
     jste
    0.50
    PROXY
    0.50
     parcs
    0.49
     byste
    0.49
     proxy
    0.49
    Proxy
    0.48
    proxy
    0.48
    chero
    0.47
    ########.
    0.47
    Act Density 0.009%

    No Known Activations