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

    Neuronpedia

    INDEX
    Explanations

    instances of returning or return actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "return" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ussen
    -0.74
    boss
    -0.64
    creen
    -0.64
    Cola
    -0.64
    bis
    -0.62
    mology
    -0.61
    astics
    -0.60
    vern
    -0.60
    ahi
    -0.60
    stood
    -0.60
    POSITIVE LOGITS
     home
    0.94
     HOME
    0.84
    home
    0.80
    ees
    0.80
    nil
    0.73
     postage
    0.70
     safely
    0.70
    owship
    0.68
     alive
    0.68
    pring
    0.67
    Act Density 0.035%

    No Known Activations