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

    Neuronpedia

    INDEX
    Explanations

    elements related to accessibility and disabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imary
    -0.14
    uxtap
    -0.14
    romium
    -0.14
     starving
    -0.14
     bore
    -0.14
    aravel
    -0.14
    erif
    -0.13
    acos
    -0.13
     Hay
    -0.13
    ether
    -0.13
    POSITIVE LOGITS
     wheelchair
    0.31
     Disabled
    0.31
     disabled
    0.29
     accessibility
    0.29
     Accessibility
    0.28
     disability
    0.26
     Disability
    0.25
    Accessibility
    0.25
     Wheel
    0.24
    disabled
    0.24
    Act Density 0.092%

    No Known Activations