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

    Neuronpedia

    INDEX
    Explanations

    Twitter handles

    oai_token-act-pair · gpt-3.5-turbo

    handles or usernames associated with Twitter accounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ACTIONS
    -0.89
     Ninth
    -0.81
    CONCLUS
    -0.81
     Scheme
    -0.79
     Conservation
    -0.75
     Conclusion
    -0.71
     Warrant
    -0.70
     ANG
    -0.69
     Enabled
    -0.69
     Directory
    -0.69
    POSITIVE LOGITS
    yp
    1.05
    mc
    1.00
    _
    1.00
    ecd
    1.00
    fd
    0.99
    fp
    0.96
    biz
    0.95
    erk
    0.94
    etr
    0.93
    df
    0.93
    Act Density 0.165%

    No Known Activations