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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the potential impact of actions on different aspects of society or the economy

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and phrases indicating causation or condition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wic
    -0.90
    married
    -0.77
    lass
    -0.77
    DragonMagazine
    -0.74
    estern
    -0.73
    lication
    -0.70
    ached
    -0.69
    aws
    -0.68
     Latest
    -0.68
    ials
    -0.68
    POSITIVE LOGITS
     thereby
    1.18
     consequently
    1.04
     hence
    0.98
     thus
    0.98
     promotes
    0.97
     reduces
    0.92
     enhances
    0.92
     reduce
    0.90
     therefore
    0.89
     prevents
    0.89
    Act Density 0.282%

    No Known Activations