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

    Neuronpedia

    INDEX
    Explanations

    combinations of specific syllables or phonetic patterns in words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     duo
    -0.16
    uchi
    -0.15
    ruz
    -0.14
     Kens
    -0.14
     MI
    -0.14
     ga
    -0.14
     crude
    -0.14
    abr
    -0.14
    nor
    -0.14
    oria
    -0.14
    POSITIVE LOGITS
    lias
    0.16
    ODO
    0.15
    ستاÙĨ
    0.15
    ustering
    0.14
    BackStack
    0.14
    ãĤĤãģªãģĦ
    0.14
    gre
    0.14
    ازÙħ
    0.14
    gres
    0.14
    elsing
    0.14
    Act Density 0.071%

    No Known Activations