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

    Neuronpedia

    INDEX
    Explanations

    terms related to sensitivity and confidentiality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    VersionUID
    -0.47
    AndroidJUnit
    -0.46
     Anbau
    -0.44
     Popov
    -0.43
    awtextra
    -0.43
    獲
    -0.43
    experiment
    -0.42
    اصله
    -0.42
    usammen
    -0.42
     Gelände
    -0.42
    POSITIVE LOGITS
     protoimpl
    0.68
     sensitive
    0.67
     Sensitive
    0.65
     Chwiliwch
    0.58
    DispatchToProps
    0.58
     delicate
    0.56
    Sensitive
    0.56
    sensitive
    0.55
    敏感
    0.51
    mappedBy
    0.51
    Act Density 0.233%

    No Known Activations