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

    Neuronpedia

    INDEX
    Explanations

    terms related to password fields and security in user interfaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FRING
    -0.17
    versations
    -0.16
    zel
    -0.16
    zell
    -0.16
    awai
    -0.15
    ucs
    -0.15
    way
    -0.14
    uro
    -0.14
    obar
    -0.14
     susp
    -0.14
    POSITIVE LOGITS
    ickers
    0.17
    .Meta
    0.15
     EVAL
    0.15
    dub
    0.14
    ην
    0.14
    icker
    0.14
    unittest
    0.14
    айÑĤ
    0.14
     Playground
    0.13
     side
    0.13
    Act Density 0.002%

    No Known Activations