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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "to" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    halb
    -0.16
    hod
    -0.15
    elder
    -0.15
    à¥Įर
    -0.14
    iren
    -0.14
    akh
    -0.14
    aurant
    -0.14
    ky
    -0.14
    uri
    -0.13
    íĦ´
    -0.13
    POSITIVE LOGITS
     bear
    0.27
    bear
    0.24
     fruition
    0.20
     table
    0.19
     boil
    0.19
    Bear
    0.18
     forefront
    0.17
     fore
    0.17
     attention
    0.17
     notice
    0.17
    Act Density 0.045%

    No Known Activations