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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the disclosure of information, particularly in legal or regulatory contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Monfieur
    -0.84
     myſelf
    -0.77
    __":
    -0.76
     Efq
    -0.71
     Majefty
    -0.71
     itſelf
    -0.71
     leaſt
    -0.68
     Anſ
    -0.68
     ſche
    -0.66
     ſy
    -0.66
    POSITIVE LOGITS
    Publication
    0.54
    憾
    0.47
    reportError
    0.47
     resourceCulture
    0.46
    íu
    0.44
    ItemSelected
    0.44
    Abstract
    0.43
     unhappy
    0.43
    ̀
    0.42
    że
    0.42
    Act Density 0.055%

    No Known Activations