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

    Neuronpedia

    INDEX
    Explanations

    phrases related to stairs

    oai_token-act-pair · gpt-3.5-turbo

    references to staircases and elevators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    natureconservancy
    -0.74
    ucks
    -0.73
    vironment
    -0.73
    itarian
    -0.72
    zsche
    -0.72
    uala
    -0.70
    yright
    -0.69
    Cola
    -0.68
    essee
    -0.68
     Samoa
    -0.68
    POSITIVE LOGITS
    ways
    1.13
     stairs
    1.06
     stair
    0.99
    way
    0.99
     staircase
    0.95
    WAY
    0.93
     shaft
    0.87
    stairs
    0.85
     slope
    0.80
     hallway
    0.80
    Act Density 0.053%

    No Known Activations