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

    Neuronpedia

    INDEX
    Explanations

    past tense verbs and their related grammatical forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    missive
    -0.17
    his
    -0.15
    wik
    -0.14
    üyük
    -0.14
    afs
    -0.14
     hes
    -0.14
     trá»Ŀi
    -0.14
    others
    -0.13
    ESH
    -0.13
    .TXT
    -0.13
    POSITIVE LOGITS
     er
    0.35
     ele
    0.20
     hij
    0.19
    'er
    0.15
    305
    0.15
     erosion
    0.15
    _er
    0.15
    nte
    0.15
    .er
    0.14
     ekip
    0.14
    Act Density 0.013%

    No Known Activations