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

    Neuronpedia

    INDEX
    Explanations

    modal verbs and negative constructions indicating uncertainty or potentiality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elson
    -0.17
    uth
    -0.16
     Spo
    -0.15
    à¹Īà¸Ńà¸Ļ
    -0.15
    beck
    -0.14
    uteur
    -0.14
    ylvania
    -0.14
     trif
    -0.14
    äter
    -0.14
     Pell
    -0.14
    POSITIVE LOGITS
     HOLDER
    0.16
    ics
    0.16
    antal
    0.15
    stract
    0.15
    ugal
    0.15
    foon
    0.14
    ména
    0.14
    ierz
    0.14
    ivet
    0.13
    thur
    0.13
    Act Density 0.001%

    No Known Activations