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

    Neuronpedia

    INDEX
    Explanations

    verb phrases indicating starting or embarking on a journey or task

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the initiation of actions or journeys

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eries
    -0.64
    aird
    -0.62
    ery
    -0.60
    Kings
    -0.58
    leness
    -0.58
    illard
    -0.56
    avorable
    -0.55
     Marketable
    -0.55
    itu
    -0.55
    oir
    -0.55
    POSITIVE LOGITS
     anew
    0.90
    fitted
    0.88
     to
    0.83
     towards
    0.80
     boldly
    0.77
     toward
    0.77
    posts
    0.75
     exploring
    0.70
     upon
    0.69
    tracks
    0.69
    Act Density 0.043%

    No Known Activations