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

    Neuronpedia

    INDEX
    Explanations

    actions or steps in a process

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     ILCS
    -0.80
     charism
    -0.59
     Ago
    -0.59
    essen
    -0.57
    authent
    -0.57
    iot
    -0.56
     Kara
    -0.56
    hab
    -0.56
     OL
    -0.54
     Tai
    -0.54
    POSITIVE LOGITS
     outweigh
    1.25
     outwe
    1.19
     varies
    1.17
     coincides
    1.17
     coincided
    1.15
     exceeds
    1.13
     depends
    1.11
     depended
    1.06
     reflects
    1.05
     differs
    1.02
    Act Density 1.134%

    No Known Activations