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

    Neuronpedia

    INDEX
    Explanations

    references to former officials or individuals in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Marburg
    -0.92
     sneeze
    -0.85
     Trish
    -0.80
     Belleville
    -0.76
    Trish
    -0.75
     Angio
    -0.74
     Sien
    -0.74
     épis
    -0.74
     Kull
    -0.72
     fubject
    -0.70
    POSITIVE LOGITS
     former
    1.25
     Former
    1.23
    Former
    1.23
    former
    1.01
    ancien
    0.95
     ex
    0.93
     ehemalige
    0.92
     ehemaligen
    0.91
    Formerly
    0.89
     ehemal
    0.89
    Act Density 0.062%

    No Known Activations