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

    Neuronpedia

    INDEX
    Explanations

    words related to academic titles and matters of importance or urgency

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     brav
    -0.68
     conversion
    -0.67
     plat
    -0.65
     punch
    -0.65
     shelves
    -0.65
     chast
    -0.65
     sarc
    -0.63
     redes
    -0.63
     blast
    -0.63
     delight
    -0.62
    POSITIVE LOGITS
    ents
    1.46
    ential
    1.41
    ency
    1.40
    encies
    1.37
    ences
    1.37
    entials
    1.28
    iencies
    1.28
    ited
    1.25
    ently
    1.25
    itors
    1.25
    Act Density 0.194%

    No Known Activations