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

    Neuronpedia

    INDEX
    Explanations

    references to building or constructing things, both in a physical and metaphorical sense

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ances
    -0.72
     solicitation
    -0.70
    writers
    -0.68
    ANCE
    -0.68
     aloud
    -0.67
    plain
    -0.67
    seek
    -0.67
    ĸļ
    -0.66
     directions
    -0.66
    zee
    -0.64
    POSITIVE LOGITS
     infrastructure
    0.99
     groundwork
    0.90
     footh
    0.88
     foothold
    0.85
     rapport
    0.83
     reputation
    0.81
     foundation
    0.80
    aganda
    0.79
     anew
    0.79
     momentum
    0.78
    Act Density 0.398%

    No Known Activations