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

    Neuronpedia

    INDEX
    Explanations

    phrases relating to actions, particularly those involving plans, accomplishments, and collaborative efforts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jefus
    -1.10
     houſe
    -1.10
     Chriftian
    -1.09
     purpoſe
    -1.08
     متعلقه
    -1.07
     ſtate
    -1.04
     fubject
    -1.03
     ISNI
    -1.02
    mybatisplus
    -1.01
     greateſt
    -1.01
    POSITIVE LOGITS
     also
    0.75
    :
    0.63
     
    0.59
     often
    0.56
     usually
    0.52
     have
    0.51
     a
    0.51
     much
    0.51
     no
    0.49
     even
    0.48
    Act Density 0.444%

    No Known Activations