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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating positive or negative impact

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating causal relationships or significant impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Memor
    -0.72
     sale
    -0.70
     dies
    -0.65
     Sale
    -0.64
     nig
    -0.63
     likes
    -0.63
     Anniversary
    -0.62
     tables
    -0.62
     Writ
    -0.61
     socket
    -0.61
    POSITIVE LOGITS
    FML
    1.13
     overshadow
    0.96
     outweigh
    0.93
     attest
    0.88
     complicate
    0.88
     suffice
    0.85
    quickShipAvailable
    0.85
     outwe
    0.83
     warranted
    0.82
     preclude
    0.81
    Act Density 0.348%

    No Known Activations