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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing contrasts and comparisons between different perspectives or approaches

    oai_token-act-pair · gpt-3.5-turbo

    topics related to legal matters and political commentary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ore
    -0.69
    vernment
    -0.66
    abase
    -0.63
    irie
    -0.62
    orc
    -0.61
    cel
    -0.61
     retro
    -0.59
    Els
    -0.59
    ceed
    -0.58
     overdue
    -0.57
    POSITIVE LOGITS
     whichever
    0.72
    depending
    0.72
     Therefore
    0.71
     causation
    0.65
    apo
    0.64
     Either
    0.64
     Hence
    0.63
     depending
    0.63
    Therefore
    0.62
    energy
    0.60
    Act Density 0.552%

    No Known Activations