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

    Neuronpedia

    INDEX
    Explanations

    references to aims and goals related to improving systems or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Following "in" or "on" and a gerund/-ing verb

    np_acts-logits-general · gemini-2.0-flash

    improving conditions or outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ьаж
    -0.72
    WebVitals
    -0.67
    Spending
    -0.65
    adaptiveStyles
    -0.64
     Spending
    -0.63
    تقاوى
    -0.62
    참고
    -0.61
     verzichten
    -0.59
     resorting
    -0.58
     spending
    -0.57
    POSITIVE LOGITS
     improving
    1.47
     enhancing
    1.40
     helping
    1.35
     ensuring
    1.27
     promoting
    1.24
     protecting
    1.22
     facilitating
    1.20
     mitigating
    1.19
     reducing
    1.18
    improving
    1.16
    Act Density 0.539%

    No Known Activations