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

    Neuronpedia

    INDEX
    Explanations

    references to stairs, staircases, and access points within structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    анка
    -0.16
    grave
    -0.15
     downstream
    -0.15
    layer
    -0.14
    tl
    -0.14
     vale
    -0.14
    olla
    -0.14
    osto
    -0.14
    tons
    -0.14
     os
    -0.14
    POSITIVE LOGITS
     stairs
    0.20
    -step
    0.18
     stair
    0.17
    stairs
    0.16
    leading
    0.16
    .steps
    0.15
     step
    0.15
     steps
    0.15
     stepped
    0.15
     staircase
    0.15
    Act Density 0.028%

    No Known Activations