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

    Neuronpedia

    INDEX
    Explanations

    references to registration related to legal or official processes

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     vort
    -0.76
     utop
    -0.63
     ideolog
    -0.63
     isoli
    -0.60
     konserv
    -0.60
     massiv
    -0.60
     Kategor
    -0.58
     poros
    -0.58
     verba
    -0.58
     sexu
    -0.58
    POSITIVE LOGITS
     registrations
    1.35
     register
    1.33
     registration
    1.32
     registering
    1.29
     registered
    1.27
     registers
    1.24
     unregistered
    1.18
     Registration
    1.17
     REGISTER
    1.16
     Registers
    1.16
    Act Density 0.078%

    No Known Activations