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

    Neuronpedia

    INDEX
    Explanations

    references to smoke and smoking actions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    Sklici
    -0.73
     الحره
    -0.55
     كومونز
    -0.53
    Literatuur
    -0.53
    Zunanje
    -0.52
    Glej
    -0.50
    Tril
    -0.49
     censiti
    -0.48
    Mediabestanden
    -0.48
    Curt
    -0.47
    POSITIVE LOGITS
     smoke
    1.37
     Smoke
    1.21
     smokes
    1.19
     smoking
    1.17
     smoked
    1.13
     smokers
    1.12
    smoke
    1.12
    Smoke
    1.11
     smoker
    1.09
     Smoking
    1.07
    Act Density 0.054%

    No Known Activations