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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal identity and self-acceptance

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     centrif
    -1.09
     Khart
    -1.05
     Fg
    -1.03
     nephe
    -1.02
     daf
    -1.00
     Augu
    -1.00
     dci
    -0.98
     pixabay
    -0.97
     auri
    -0.97
     olx
    -0.96
    POSITIVE LOGITS
    <bos>
    0.94
     courage
    0.62
     disclose
    0.59
     disclosure
    0.57
     gradually
    0.56
     transitioning
    0.56
     bravely
    0.55
     openly
    0.55
     sexuality
    0.54
     slowly
    0.54
    Act Density 0.369%

    No Known Activations