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

    Neuronpedia

    INDEX
    Explanations

    personal stories or anecdotes

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     apiece
    -0.79
    itect
    -0.75
     Uriel
    -0.69
    ibaba
    -0.68
    arians
    -0.66
    illac
    -0.65
    س
    -0.65
    aphael
    -0.64
    etz
    -0.64
    illary
    -0.63
    POSITIVE LOGITS
    anmar
    1.33
    stery
    1.31
     own
    1.26
     favorite
    1.18
    opic
    1.14
    ocard
    1.13
    opia
    1.13
     favourite
    1.12
    riad
    1.11
     husband
    1.09
    Act Density 0.431%

    No Known Activations