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

    Neuronpedia

    INDEX
    Explanations

    references to different levels or floors in a building layout

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sauvages
    -0.70
    Clint
    -0.66
     Falta
    -0.61
     Clint
    -0.59
     sauvage
    -0.59
     jspb
    -0.56
    новниш
    -0.55
     reckoned
    -0.54
    aság
    -0.54
    errHandler
    -0.54
    POSITIVE LOGITS
     stairs
    1.15
     stair
    1.08
     staircase
    1.04
    stairs
    1.02
     Stairs
    0.97
     Stair
    0.93
    stair
    0.92
     stairway
    0.91
     upstairs
    0.91
    Stair
    0.89
    Act Density 0.089%

    No Known Activations