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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating completion or continuation of an action or state

    oai_token-act-pair · gpt-3.5-turbo

    the word "been" and its various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rones
    -0.75
    arta
    -0.70
     Bars
    -0.69
    achu
    -0.66
    ives
    -0.65
    anth
    -0.65
     fray
    -0.64
     Lowe
    -0.62
     Wid
    -0.61
    regate
    -0.61
    POSITIVE LOGITS
     able
    1.14
     seen
    0.99
     taken
    0.98
     deemed
    0.97
     treated
    0.96
     replaced
    0.95
     subjected
    0.95
    wolves
    0.93
     bitten
    0.92
     shown
    0.90
    Act Density 0.156%

    No Known Activations