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

    Neuronpedia

    INDEX
    Explanations

    references to award-winning accomplishments or individuals

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to award-winning accomplishments in various fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    seless
    -0.81
    adas
    -0.76
    thia
    -0.70
    Īè
    -0.65
    adra
    -0.65
    aucuses
    -0.65
     semblance
    -0.65
    idon
    -0.65
    rir
    -0.64
    olen
    -0.64
    POSITIVE LOGITS
     author
    1.01
     novelist
    0.96
     actress
    0.95
     journalist
    0.89
     Pulitzer
    0.84
     writer
    0.82
     poet
    0.82
     composer
    0.80
     artist
    0.79
     filmmaker
    0.79
    Act Density 0.089%

    No Known Activations