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

    Neuronpedia

    INDEX
    Explanations

    references to authority or leadership roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     plomb
    -0.49
    出口
    -0.45
    pop
    -0.44
     prêtres
    -0.44
     død
    -0.43
    čios
    -0.43
     evolução
    -0.41
     avancée
    -0.41
     cest
    -0.41
     conclure
    -0.40
    POSITIVE LOGITS
     nahilalakip
    1.06
     AssemblyCulture
    0.98
     Numerade
    0.95
     NSCoder
    0.92
    InitVars
    0.89
     препратки
    0.89
    EndProject
    0.88
     esternos
    0.87
    DockStyle
    0.86
     immediately
    0.86
    Act Density 0.281%

    No Known Activations