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

    Neuronpedia

    INDEX
    Explanations

    references to specific individuals or entities in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rima
    -0.74
     Devan
    -0.70
    UCH
    -0.67
    iVar
    -0.66
     Ellen
    -0.64
     Lom
    -0.64
     Velas
    -0.64
    rique
    -0.64
    thold
    -0.62
     Mura
    -0.61
    POSITIVE LOGITS
    Datuak
    1.08
    Portail
    1.01
    Tembelea
    0.95
     Portail
    0.92
    antaranya
    0.88
     sää
    0.83
     Paglinawan
    0.78
     Pallas
    0.77
     religieuses
    0.77
     bezeichneter
    0.76
    Act Density 2.408%

    No Known Activations