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

    Neuronpedia

    INDEX
    Explanations

    references to people's identities and backgrounds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Nag
    -0.21
     Bale
    -0.19
     Ohio
    -0.19
     Saras
    -0.19
     Mara
    -0.18
     Sloven
    -0.18
     Nar
    -0.18
     Jer
    -0.17
     Cort
    -0.17
     NJ
    -0.16
    POSITIVE LOGITS
     Sutton
    0.50
     Kingston
    0.46
     Johnston
    0.37
     Gibson
    0.34
     Barton
    0.33
     Hilton
    0.33
     BYU
    0.33
     Horton
    0.32
     Brigham
    0.31
     Fulton
    0.31
    Act Density 0.066%

    No Known Activations