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

    Neuronpedia

    INDEX
    Explanations

    words related to construction activities

    oai_token-act-pair · gpt-3.5-turbo

    references to construction activities and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    andra
    -0.80
    unin
    -0.74
    romeda
    -0.72
     Cele
    -0.72
    isters
    -0.70
    chenko
    -0.66
    olic
    -0.65
    itudes
    -0.64
     Burk
    -0.64
    eva
    -0.64
    POSITIVE LOGITS
     boom
    0.81
     crane
    0.80
     machinery
    0.80
     underway
    0.80
    smanship
    0.79
     crews
    0.78
     materials
    0.77
     projects
    0.76
     sites
    0.75
     worker
    0.72
    Act Density 0.033%

    No Known Activations