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

    Neuronpedia

    INDEX
    Explanations

    terms related to construction activities

    oai_token-act-pair · gpt-3.5-turbo

    references to construction activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    leon
    -0.73
    bern
    -0.72
     Ago
    -0.72
    unin
    -0.71
    ml
    -0.69
    zee
    -0.68
     Haram
    -0.67
    romeda
    -0.66
    isters
    -0.66
     Cele
    -0.65
    POSITIVE LOGITS
    smanship
    0.92
     construction
    0.77
     ethic
    0.77
    Construction
    0.76
     underway
    0.76
     machinery
    0.75
     erection
    0.75
    STRUCT
    0.75
    worker
    0.74
     projects
    0.73
    Act Density 0.024%

    No Known Activations