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

    Neuronpedia

    INDEX
    Explanations

    names of political figures

    oai_token-act-pair · gpt-3.5-turbo

    prominent political figures and references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    actionDate
    -0.74
    contact
    -0.67
    Finish
    -0.67
     RTX
    -0.63
    onal
    -0.63
    )",
    -0.62
    due
    -0.61
    near
    -0.59
    ENC
    -0.59
    Copyright
    -0.59
    POSITIVE LOGITS
     embodies
    1.43
     certainly
    1.36
     undoubtedly
    1.28
     deserves
    1.25
     owes
    1.22
     lacks
    1.18
     ought
    1.18
     undeniably
    1.17
     surely
    1.16
     thri
    1.14
    Act Density 0.583%

    No Known Activations