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

    Neuronpedia

    INDEX
    Explanations

    construction and building-related terms, such as materials, structures, and techniques

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    agame
    -0.78
    undrum
    -0.74
    aminer
    -0.71
    agonist
    -0.69
    mma
    -0.66
    anse
    -0.66
    keleton
    -0.64
    uden
    -0.63
     Puzzle
    -0.63
     wearer
    -0.62
    POSITIVE LOGITS
     versions
    0.88
     quantities
    0.84
     equivalents
    0.81
     agreements
    0.80
     commitments
    0.78
    loads
    0.78
     replacements
    0.77
     copies
    0.76
     modifications
    0.76
     considerations
    0.75
    Act Density 0.648%

    No Known Activations