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

    Neuronpedia

    INDEX
    Explanations

    sentences or phrases expressing personal reflections or inner thoughts

    oai_token-act-pair · gpt-3.5-turbo

    sentences with emotional reflections and self-awareness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tesy
    -0.85
     pione
    -0.82
     teasp
    -0.79
     carbohyd
    -0.78
    CVE
    -0.76
    Þ
    -0.75
     distribut
    -0.73
     intended
    -0.72
    affer
    -0.72
    rov
    -0.70
    POSITIVE LOGITS
     Maybe
    1.38
     Eventually
    1.37
     Slowly
    1.34
     Somehow
    1.29
     Suddenly
    1.28
     Sometimes
    1.26
     Something
    1.24
     Especially
    1.24
     Everything
    1.24
     Whatever
    1.24
    Act Density 0.484%

    No Known Activations