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

    Neuronpedia

    INDEX
    Explanations

    incidents related to slips or falls in various settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tube
    -0.16
    Tube
    -0.15
     towers
    -0.14
     tower
    -0.14
     hus
    -0.14
     Shakespeare
    -0.14
     Hanging
    -0.14
    hti
    -0.14
     Towers
    -0.14
     towering
    -0.14
    POSITIVE LOGITS
     surface
    0.23
     surfaces
    0.21
     ná»ģn
    0.20
     flooring
    0.20
    Surface
    0.20
     Surface
    0.19
    surface
    0.19
     carpet
    0.19
     Flooring
    0.19
     ground
    0.19
    Act Density 0.166%

    No Known Activations