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

    Neuronpedia

    INDEX
    Explanations

    personal opinions

    oai_token-act-pair · gpt-3.5-turbo

    references to personal opinions or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Uriel
    -0.73
    etz
    -0.73
    itect
    -0.71
    wick
    -0.69
     guiIcon
    -0.67
     apiece
    -0.66
     Sakuya
    -0.66
    ibaba
    -0.65
     Izan
    -0.63
    vernment
    -0.63
    POSITIVE LOGITS
    opia
    1.14
    stery
    1.09
    ocard
    1.09
    anmar
    1.08
     own
    1.03
     favorite
    1.03
    opic
    1.00
    ths
    1.00
    riad
    0.97
    stic
    0.97
    Act Density 0.119%

    No Known Activations