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

    Neuronpedia

    INDEX
    Explanations

    time-related information, such as dates and appointments

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to political positions and power transitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Collider
    -0.75
     catalog
    -0.73
    rouse
    -0.72
    Cod
    -0.72
    pac
    -0.71
     detector
    -0.71
    omorph
    -0.70
    Origin
    -0.70
     bins
    -0.68
    Feed
    -0.67
    POSITIVE LOGITS
     democratically
    1.01
    elected
    0.98
     elections
    0.94
    bernatorial
    0.94
     impeachment
    0.93
     appointed
    0.91
    election
    0.88
     appoint
    0.88
     charisma
    0.86
     hereditary
    0.85
    Act Density 0.524%

    No Known Activations