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

    Neuronpedia

    INDEX
    Explanations

    instances of people and their actions in a political context

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Darling
    -0.65
    ........
    -0.64
    ANK
    -0.64
    ........................
    -0.64
    ................
    -0.63
     recess
    -0.63
     Meadows
    -0.61
     dimensions
    -0.60
     Ens
    -0.58
     Sioux
    -0.58
    POSITIVE LOGITS
    odcast
    0.94
    isd
    0.83
    ever
    0.81
     interacted
    0.80
     benefited
    0.80
     accompanies
    0.79
    isf
    0.78
     participated
    0.77
    oping
    0.75
    ppers
    0.74
    Act Density 0.158%

    No Known Activations