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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "oil" and related terms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     meis
    -0.72
     poff
    -0.71
     fei
    -0.71
     foon
    -0.71
     mme
    -0.71
     fep
    -0.70
     aen
    -0.70
     fte
    -0.70
     autorytatywna
    -0.67
     myn
    -0.65
    POSITIVE LOGITS
     oil
    1.54
    Oil
    1.36
     Oil
    1.35
     OIL
    1.32
    oil
    1.32
     oils
    1.20
     Oils
    1.01
    OIL
    1.00
     油
    0.86
    油
    0.83
    Act Density 0.052%

    No Known Activations