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

    Neuronpedia

    INDEX
    Explanations

    references to wheelchair accessibility and safety features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ael
    -0.18
    askell
    -0.17
    yw
    -0.15
     pl
    -0.14
    ियल
    -0.14
    yte
    -0.13
    onal
    -0.13
    995
    -0.13
    .sep
    -0.13
    .Tick
    -0.13
    POSITIVE LOGITS
     mobility
    0.35
     wheelchair
    0.35
     Mobility
    0.32
    mob
    0.31
     wheel
    0.31
     Wheel
    0.30
    Mob
    0.30
    Wheel
    0.28
    wheel
    0.27
     scooter
    0.24
    Act Density 0.053%

    No Known Activations