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

    Neuronpedia

    INDEX
    Explanations

    references to containing or holding items or substances

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    Argumento
    -0.51
    buquerque
    -0.48
     Dallas
    -0.45
     Mumbai
    -0.45
    Figure
    -0.45
     Friday
    -0.44
    phi
    -0.44
    Big
    -0.43
    Friday
    -0.43
    Dallas
    -0.43
    POSITIVE LOGITS
     CONTAIN
    1.08
     Contain
    1.02
     contain
    1.01
     Contains
    0.92
    contain
    0.92
     poff
    0.91
     Containing
    0.91
     ftu
    0.90
     contains
    0.90
     aen
    0.88
    Act Density 0.075%

    No Known Activations