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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating ownership or possession

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -1.78
     myſelf
    -1.70
     pleaſure
    -1.70
     Efq
    -1.69
     houſe
    -1.62
    ſelf
    -1.61
     faſt
    -1.61
     ſtate
    -1.59
    ſelves
    -1.58
     purpoſe
    -1.57
    POSITIVE LOGITS
     a
    1.10
     
    1.07
     and
    1.07
    <eos>
    1.05
     in
    1.05
     an
    1.05
     is
    1.05
     the
    1.05
     I
    1.04
     for
    0.94
    Act Density 3.562%

    No Known Activations