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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "Used."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ķ
    -1.55
    ®
    -1.55
    hematic
    -1.51
     drinking
    -1.49
    bsite
    -1.43
    mma
    -1.43
    night
    -1.40
     crawl
    -1.40
     toe
    -1.38
    ERY
    -1.38
    POSITIVE LOGITS
    ![**
    1.67
     wisely
    1.61
    ***
    1.44
     Clause
    1.43
    iah
    1.41
    atti
    1.39
    backs
    1.38
    soever
    1.37
     Himself
    1.35
    _(
    1.34
    Act Density 0.204%

    No Known Activations