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

    Neuronpedia

    INDEX
    Explanations

    abbreviations or acronyms related to organizational or technical terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     uphill
    -0.62
     Alv
    -0.59
     undermin
    -0.59
     mism
    -0.59
     Miche
    -0.57
    street
    -0.56
    imental
    -0.55
     Heavenly
    -0.55
     Shinra
    -0.55
     priceless
    -0.55
    POSITIVE LOGITS
    rants
    0.74
    bow
    0.71
    kie
    0.70
     Noon
    0.70
    asters
    0.69
    beck
    0.69
    pling
    0.68
    pload
    0.67
    bors
    0.65
    eteen
    0.65
    Act Density 1.757%

    No Known Activations