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

    Neuronpedia

    INDEX
    Explanations

    hyperlinks or instructions for further information

    oai_token-act-pair · gpt-3.5-turbo

    calls to action urging readers to click for more information or resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vernment
    -0.69
     payoff
    -0.64
     facult
    -0.64
     nurs
    -0.64
     recovers
    -0.61
     lapt
    -0.60
     practise
    -0.60
     precision
    -0.59
     correctness
    -0.58
     blockers
    -0.58
    POSITIVE LOGITS
     Forbes
    0.70
     www
    0.66
    anu
    0.65
    ANI
    0.64
    gur
    0.63
    ORTS
    0.63
    ItemImage
    0.60
     Hemp
    0.59
    ARE
    0.59
    english
    0.59
    Act Density 0.101%

    No Known Activations