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

    Neuronpedia

    INDEX
    Explanations

    references to construction activities or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -1.12
    tvguidetime
    -1.04
     Мексичка
    -0.95
     ainfi
    -0.95
    -0.95
     doulou
    -0.93
     réguli
    -0.93
     Yann
    -0.92
     chré
    -0.92
     préfé
    -0.92
    POSITIVE LOGITS
     construction
    2.02
     Construction
    1.86
    Construction
    1.81
    construction
    1.66
     constructions
    1.57
     construct
    1.56
     construc
    1.51
     CONSTRUCTION
    1.48
     constructed
    1.46
     Construct
    1.44
    Act Density 0.065%

    No Known Activations