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

    Neuronpedia

    INDEX
    Explanations

    references to chairs and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Metzger
    -0.63
    pezif
    -0.62
     foule
    -0.61
    Bullets
    -0.58
     bandes
    -0.58
    ely
    -0.58
    bels
    -0.58
    sk
    -0.57
     Pascual
    -0.57
     blé
    -0.57
    POSITIVE LOGITS
     chair
    3.89
     Chair
    3.73
    Chair
    3.51
     CHAIR
    3.43
     chairs
    3.41
    chair
    3.40
     Chairs
    3.25
    chairs
    2.94
    CHAIR
    2.93
    Chairs
    2.92
    Act Density 0.035%

    No Known Activations