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

    Neuronpedia

    INDEX
    Explanations

    discussions about health risks and preventative care measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     shoes
    -0.51
     investors
    -0.50
     winning
    -0.47
     starts
    -0.47
     facing
    -0.46
    queryInterface
    -0.45
     concerts
    -0.45
     network
    -0.44
     credits
    -0.44
     etc
    -0.44
    POSITIVE LOGITS
     despatched
    0.66
     cowl
    0.61
     whereas
    0.60
     solely
    0.59
    Whereas
    0.58
     metropolis
    0.58
     mannequin
    0.56
     doable
    0.56
    Particular
    0.56
     utilizing
    0.54
    Act Density 0.104%

    No Known Activations