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

    Neuronpedia

    INDEX
    Explanations

    the conjunction "and" or similar words that connect ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -1.09
     houſe
    -1.04
     purpoſe
    -0.99
     ſeveral
    -0.98
     Jefus
    -0.97
     Chriftian
    -0.96
     greateſt
    -0.95
     cauſe
    -0.95
     ſmall
    -0.94
     fubject
    -0.92
    POSITIVE LOGITS
     And
    0.83
     if
    0.65
     But
    0.65
     e
    0.63
     A
    0.60
     а
    0.60
     
    0.59
    BorderFactory
    0.59
    rungsseite
    0.57
     also
    0.56
    Act Density 0.002%

    No Known Activations