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

    Neuronpedia

    INDEX
    Explanations

    names of people and specific locations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    icably
    -0.80
    ccess
    -0.74
     exerted
    -0.71
    pport
    -0.70
     relativity
    -0.70
     advisable
    -0.70
     exempted
    -0.69
    akuya
    -0.69
     unde
    -0.69
     condem
    -0.69
    POSITIVE LOGITS
    fish
    1.20
    tails
    1.18
    pipe
    1.11
    tail
    1.11
    water
    1.09
    weed
    1.08
    sticks
    1.07
    hound
    1.06
    Fish
    1.05
    grass
    1.04
    Act Density 0.211%

    No Known Activations