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

    Neuronpedia

    INDEX
    Explanations

    phrases related to plans, strategies, and visions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express plans or visions for the future

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    entimes
    -0.71
    arov
    -0.70
    Laughs
    -0.69
    Champ
    -0.69
    inho
    -0.69
    Claim
    -0.68
    quickShipAvailable
    -0.68
    wick
    -0.67
    edin
    -0.67
    ctors
    -0.66
    POSITIVE LOGITS
     future
    1.15
     improving
    0.99
     integrating
    0.99
     constructing
    0.98
     improvement
    0.97
     transforming
    0.97
     maximizing
    0.95
     reforming
    0.94
     dealing
    0.90
     tomorrow
    0.90
    Act Density 0.285%

    No Known Activations