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

    Neuronpedia

    INDEX
    Explanations

    terms related to bearings in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pexpr
    -0.65
     stumps
    -0.62
     aufgestellt
    -0.62
    toBeTruthy
    -0.60
    javadoc
    -0.59
    Kale
    -0.59
    pernicus
    -0.59
    HomeAsUpEnabled
    -0.58
    outheast
    -0.58
    ⇑
    -0.57
    POSITIVE LOGITS
     Bearing
    0.96
     bearing
    0.92
     stick
    0.83
    Bearing
    0.73
     adopt
    0.72
    bearing
    0.67
     bearings
    0.65
     reference
    0.63
     Stick
    0.63
     adoption
    0.60
    Act Density 0.114%

    No Known Activations