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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating measurement over time or significant quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     overall
    -0.44
    getCurrentUser
    -0.35
     override
    -0.33
     overlying
    -0.32
     overview
    -0.32
     Overall
    -0.31
    DetailComponent
    -0.30
     overwhelming
    -0.29
    moveToFirst
    -0.29
    ãy
    -0.28
    POSITIVE LOGITS
     ujednoznacz
    0.75
    tures
    0.75
     hinweg
    0.74
    ruling
    0.72
    lord
    0.72
    seer
    0.72
     poveznice
    0.70
    lords
    0.69
    :✨
    0.69
    tly
    0.67
    Act Density 0.267%

    No Known Activations