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

    Neuronpedia

    INDEX
    Explanations

    terms related to favorable and adverse outcomes, particularly in health, economics, and social implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AxisAlignment
    -0.65
    DockStyle
    -0.65
    GOTREF
    -0.64
    UpInside
    -0.62
    tagHelperRunner
    -0.61
    IntoConstraints
    -0.57
    forRoot
    -0.55
    featureID
    -0.55
     onItemClick
    -0.54
    Wiley
    -0.54
    POSITIVE LOGITS
     outcome
    0.82
     outcomes
    0.78
     result
    0.75
    result
    0.69
     OUTCOMES
    0.68
     vibes
    0.67
     Outcomes
    0.66
    outcome
    0.66
     results
    0.64
     demean
    0.64
    Act Density 0.371%

    No Known Activations