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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "to" with varying frequency, indicating a focus on infinitive verbs or phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ivil
    -0.16
    976
    -0.15
    atar
    -0.14
    inder
    -0.14
    iyel
    -0.14
    nm
    -0.14
    INDER
    -0.13
     cũ
    -0.13
     rim
    -0.13
    ResultSet
    -0.13
    POSITIVE LOGITS
    elli
    0.14
    ÄĽn
    0.14
    upo
    0.14
    _salt
    0.14
    __,__
    0.13
    ợ
    0.13
    lak
    0.13
    arpa
    0.13
    à¸Ńà¸Ķ
    0.13
     Wikispecies
    0.13
    Act Density 0.039%

    No Known Activations