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

    Neuronpedia

    INDEX
    Explanations

    preferences or choices made by individuals

    oai_token-act-pair · gpt-3.5-turbo

    expressions of preference or choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    brance
    -0.93
    idem
    -0.70
    bish
    -0.69
    orig
    -0.67
    gren
    -0.67
    breakers
    -0.67
    $$
    -0.63
    breaker
    -0.63
    ı
    -0.62
    infeld
    -0.62
    POSITIVE LOGITS
    rals
    0.83
     embodiments
    0.77
     anonymity
    0.73
    ably
    0.70
    quickShipAvailable
    0.68
     solitude
    0.65
     endings
    0.64
     lifestyles
    0.64
     staying
    0.63
     embodiment
    0.62
    Act Density 0.029%

    No Known Activations