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

    Neuronpedia

    INDEX
    Explanations

    gerunds and actions related to departure or absence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nonatomic
    -0.52
     Cleansing
    -0.52
     cauſe
    -0.49
    kain
    -0.49
    ecimento
    -0.49
     ſy
    -0.49
    !(:
    -0.48
     Cleaning
    -0.48
     Marav
    -0.48
     iſt
    -0.47
    POSITIVE LOGITS
     requiring
    1.19
     having
    1.17
     needing
    1.16
     taking
    1.12
     relying
    1.12
     using
    1.06
     leaving
    1.05
     preferring
    1.04
     bringing
    1.04
     allowing
    1.02
    Act Density 0.636%

    No Known Activations