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

    Neuronpedia

    INDEX
    Explanations

    auth

    np_max-act · gemini-2.0-flash

    The neuron activates on tokens related to authentication/authorization (i.e. those containing the “auth” stem).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    components related to authentication processes.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     pile
    -0.10
     radius
    -0.08
     Dar
    -0.07
     trabal
    -0.07
     Pier
    -0.07
     �
    -0.07
     smallest
    -0.07
     competency
    -0.07
     Rocky
    -0.07
     percentile
    -0.07
    POSITIVE LOGITS
    auth
    0.09
    TH
    0.09
     auth
    0.09
    Authentication
    0.08
    th
    0.08
    .authentication
    0.08
    uth
    0.08
    (auth
    0.07
    _auth
    0.07
     authentic
    0.07
    Act Density 0.011%

    No Known Activations