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

    Neuronpedia

    INDEX
    Explanations

    references to notes or annotations in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    teenth
    -0.18
     nutshell
    -0.17
     misd
    -0.15
    uster
    -0.15
    nek
    -0.15
    stood
    -0.15
    maal
    -0.15
    soever
    -0.15
    ll
    -0.14
    iggs
    -0.14
    POSITIVE LOGITS
    books
    0.32
    book
    0.27
    ably
    0.25
    booking
    0.24
    lessly
    0.23
    able
    0.22
    edly
    0.22
    -taking
    0.21
    -worthy
    0.21
    Pad
    0.21
    Act Density 0.045%

    No Known Activations