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

    references to the Obama and Bush administrations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     plur
    -0.72
     starters
    -0.72
     redress
    -0.69
     Cobra
    -0.67
     happ
    -0.67
     interval
    -0.66
     chamber
    -0.66
     opener
    -0.65
     umb
    -0.65
     conjecture
    -0.64
    POSITIVE LOGITS
    inspired
    1.41
    affiliated
    1.38
    approved
    1.36
    backed
    1.34
    appointed
    1.33
    induced
    1.33
    controlled
    1.31
    owned
    1.31
    dominated
    1.29
    sponsored
    1.29
    Act Density 0.130%

    No Known Activations