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

    Neuronpedia

    INDEX
    Explanations

    invalid or incorrect email addresses

    oai_token-act-pair · gpt-3.5-turbo

    references to email addresses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rd
    -0.73
    imposed
    -0.70
    rub
    -0.69
    aft
    -0.69
    bang
    -0.66
    axis
    -0.65
    ranged
    -0.64
     reflex
    -0.63
     acquitted
    -0.63
    dr
    -0.62
    POSITIVE LOGITS
     address
    1.10
     addresses
    1.01
     Address
    1.00
    address
    0.98
    Address
    0.84
    holder
    0.82
    holders
    0.81
     addr
    0.79
     NETWORK
    0.73
    =\"
    0.73
    Act Density 0.013%

    No Known Activations