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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a sudden change or significant event happening

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the concept of entirety or inclusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nes
    -0.72
    lees
    -0.71
    eller
    -0.67
    gee
    -0.67
    ritic
    -0.65
    ombat
    -0.64
    eday
    -0.64
    obyl
    -0.62
    archives
    -0.60
    ainer
    -0.59
    POSITIVE LOGITS
     sudden
    1.01
     us
    0.96
     eternity
    0.83
     them
    0.82
     these
    0.81
     humanity
    0.80
     those
    0.75
     humankind
    0.73
    ahu
    0.71
     Us
    0.71
    Act Density 0.065%

    No Known Activations