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

    Neuronpedia

    INDEX
    Explanations

    words related to construction

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    andra
    -0.81
    unin
    -0.74
    Gene
    -0.69
    itudes
    -0.68
    romeda
    -0.68
    BILITIES
    -0.67
    bern
    -0.65
    isters
    -0.65
    olic
    -0.64
    arez
    -0.63
    POSITIVE LOGITS
     boom
    0.87
    smanship
    0.85
     underway
    0.83
     crews
    0.83
     projects
    0.82
     materials
    0.82
     crane
    0.82
     scaff
    0.78
     machinery
    0.77
     sites
    0.77
    Act Density 0.059%

    No Known Activations