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

    Neuronpedia

    INDEX
    Explanations

    the word "Neighbors."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "neighbors"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     GST
    -0.74
     speeding
    -0.71
     tune
    -0.71
     meal
    -0.70
     hand
    -0.68
     complete
    -0.65
     haste
    -0.63
     setting
    -0.63
     combined
    -0.63
     speed
    -0.62
    POSITIVE LOGITS
    bors
    4.61
    bour
    1.99
    bor
    1.82
    poon
    1.24
    poons
    1.14
    rals
    1.10
    vals
    1.09
    bies
    1.00
    bys
    0.99
    ewitness
    0.99
    Act Density 0.006%

    No Known Activations