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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of spelling and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yo
    -0.17
    nap
    -0.16
    ales
    -0.16
    ements
    -0.15
    eday
    -0.15
    lad
    -0.15
    fst
    -0.15
    dz
    -0.15
    yles
    -0.15
    adolu
    -0.14
    POSITIVE LOGITS
    ings
    0.20
    checker
    0.19
    wort
    0.19
    indrome
    0.19
    binding
    0.18
     doom
    0.17
    icious
    0.17
    berger
    0.16
    лÑİ
    0.16
    wick
    0.15
    Act Density 0.007%

    No Known Activations