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

    Neuronpedia

    INDEX
    Explanations

    references to notes or annotations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    teenth
    -0.19
    iggs
    -0.17
    nek
    -0.17
     nutshell
    -0.17
    dest
    -0.15
    _notifier
    -0.15
     misd
    -0.15
    stood
    -0.15
    esty
    -0.15
    ms
    -0.15
    POSITIVE LOGITS
    books
    0.34
    book
    0.28
    lessly
    0.25
    booking
    0.25
    -taking
    0.23
    edly
    0.23
     Bene
    0.22
    Pad
    0.20
    ably
    0.20
    able
    0.20
    Act Density 0.042%

    No Known Activations