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

    Neuronpedia

    INDEX
    Explanations

    terms related to future possibilities or potentials

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    tein
    -0.78
    iencies
    -0.78
    ochet
    -0.74
    tha
    -0.74
    inas
    -0.69
    mt
    -0.68
    wo
    -0.68
    played
    -0.67
    raint
    -0.67
    ento
    -0.66
    POSITIVE LOGITS
     future
    1.12
     doom
    1.03
     futures
    0.99
     imminent
    0.95
     2030
    0.94
     impending
    0.91
     2020
    0.90
    llor
    0.89
     someday
    0.88
     2019
    0.86
    Act Density 5.159%

    No Known Activations