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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    witch
    -0.79
    ifact
    -0.74
    arians
    -0.70
    ocide
    -0.68
    yip
    -0.67
    inctions
    -0.67
    eers
    -0.66
    avers
    -0.65
    quickShipAvailable
    -0.65
    uctor
    -0.64
    POSITIVE LOGITS
     midst
    1.33
     vicinity
    1.25
     backyard
    1.13
     pockets
    1.09
     bloodstream
    1.04
     estimation
    1.00
     orbit
    0.99
     pocket
    0.96
     womb
    0.96
     favor
    0.92
    Act Density 0.295%

    No Known Activations