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

    Neuronpedia

    INDEX
    Explanations

    words related to actions or conditions involving leaving or separating from a group

    oai_token-act-pair · gpt-3.5-turbo

    gerunds and participles related to actions and behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ashe
    -0.68
     poly
    -0.64
     Jes
    -0.62
     reproduction
    -0.60
     Bert
    -0.60
     unfocusedRange
    -0.59
     soc
    -0.59
     Jenn
    -0.57
     Jos
    -0.57
     DT
    -0.57
    POSITIVE LOGITS
    aving
    4.34
    aved
    2.85
    aves
    2.45
    ave
    2.14
    avers
    1.95
    avement
    1.72
    aver
    1.58
    avery
    1.42
    aping
    1.28
    avin
    1.28
    Act Density 0.016%

    No Known Activations