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

    Neuronpedia

    INDEX
    Explanations

    elements related to mathematical operations and dimensions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hcp
    -0.17
    amar
    -0.15
    ropol
    -0.15
    edException
    -0.15
    essel
    -0.14
    ĮĴ
    -0.14
    ighbors
    -0.14
     addCriterion
    -0.14
     sparing
    -0.14
    ults
    -0.14
    POSITIVE LOGITS
    robat
    0.16
    apore
    0.15
     dear
    0.14
    igkeit
    0.14
     Neb
    0.14
    Luck
    0.14
    vi
    0.13
    Grammar
    0.13
    untime
    0.13
    Vi
    0.13
    Act Density 0.009%

    No Known Activations