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

    Neuronpedia

    INDEX
    Explanations

    Informing/notifying

    np_max-act · gemini-2.0-flash

    messages related to leave requests.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron activates on words and forms that signal notifying or informing (e.g., “inform,” “informing,” “contact”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     seekers
    -0.08
     Prospect
    -0.07
     DAL
    -0.06
    orent
    -0.06
    .angle
    -0.06
     epoxy
    -0.06
     represent
    -0.06
     sour
    -0.06
    _round
    -0.06
    realm
    -0.06
    POSITIVE LOGITS
     informing
    0.09
     notifying
    0.08
     informed
    0.07
    Msg
    0.07
     notified
    0.07
    person
    0.06
    updates
    0.06
    qualified
    0.06
     notify
    0.06
     Nullable
    0.06
    Act Density 0.029%

    No Known Activations