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

    Neuronpedia

    INDEX
    Explanations

    references to stairs and related structures in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UIL
    -0.16
    IPA
    -0.15
     tab
    -0.14
    grave
    -0.14
     Shack
    -0.14
     menus
    -0.13
     horizon
    -0.13
     IconData
    -0.13
    osa
    -0.13
    nod
    -0.13
    POSITIVE LOGITS
     stairs
    0.43
     staircase
    0.41
     stair
    0.40
     flight
    0.38
     steps
    0.38
     flights
    0.37
     Flight
    0.32
     spiral
    0.31
    stairs
    0.31
    flight
    0.31
    Act Density 0.045%

    No Known Activations