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

    Neuronpedia

    INDEX
    Explanations

    information related to community projects or initiatives

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     fta
    -1.37
     Juf
    -1.30
     Abbé
    -1.22
     tremb
    -1.19
     curé
    -1.17
     ftu
    -1.15
     Sén
    -1.15
     fays
    -1.14
     Mlle
    -1.14
     Messieurs
    -1.13
    POSITIVE LOGITS
     ensure
    0.89
     maximize
    0.87
     provide
    0.87
     create
    0.86
     minimize
    0.82
     achieve
    0.80
     bring
    0.76
     encourage
    0.75
     make
    0.74
     improve
    0.73
    Act Density 0.352%

    No Known Activations