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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating known truths or widely accepted facts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oder
    -0.07
    ieri
    -0.07
     Perr
    -0.07
    addle
    -0.06
    æŁ´
    -0.06
     ones
    -0.06
    aley
    -0.06
    erson
    -0.06
     bubble
    -0.06
    -door
    -0.06
    POSITIVE LOGITS
    ANDLE
    0.07
    ấn
    0.07
    ignon
    0.07
    身
    0.07
    atta
    0.06
    CLU
    0.06
    ergus
    0.06
    illez
    0.06
    andler
    0.06
    edido
    0.06
    Act Density 0.032%

    No Known Activations