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

    Neuronpedia

    INDEX
    Explanations

    names and proper nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ouser
    -0.17
    sen
    -0.16
     Dan
    -0.16
     Ferd
    -0.16
    Dan
    -0.15
    oused
    -0.15
     Rudy
    -0.15
     fetisch
    -0.14
    eger
    -0.14
    ilon
    -0.14
    POSITIVE LOGITS
     Reese
    0.23
     Cele
    0.23
     Monterey
    0.22
     Kid
    0.20
     nic
    0.19
    Nic
    0.19
     BLL
    0.19
     Nic
    0.19
     Nicole
    0.18
     Mad
    0.18
    Act Density 0.000%

    No Known Activations