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

    Neuronpedia

    INDEX
    Explanations

    text related to construction, building, or creation

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Construct" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stice
    -0.73
    aris
    -0.64
    ullah
    -0.63
    abouts
    -0.62
    idon
    -0.62
     LIB
    -0.61
    alian
    -0.61
    arium
    -0.61
     Grad
    -0.60
    pak
    -0.59
    POSITIVE LOGITS
     Construct
    0.74
    Asset
    0.66
    ounce
    0.66
    ãĥĥ
    0.65
    krit
    0.64
    speech
    0.63
    Prime
    0.62
     newsp
    0.62
    raq
    0.61
     proble
    0.59
    Act Density 0.000%

    No Known Activations