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

    Neuronpedia

    INDEX
    Explanations

    Twitter retweets

    oai_token-act-pair · gpt-3.5-turbo

    references to retweets on social media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iasis
    -0.88
    stract
    -0.66
    alities
    -0.64
     pregnant
    -0.64
    tained
    -0.62
    cium
    -0.61
    ocene
    -0.60
     Rockefeller
    -0.59
    cised
    -0.59
     cir
    -0.59
    POSITIVE LOGITS
    Ãī
    1.28
    TY
    0.99
    BF
    0.95
    PC
    0.90
    TE
    0.87
    LM
    0.86
    irtual
    0.84
    IA
    0.83
    ITCH
    0.78
    RP
    0.78
    Act Density 0.018%

    No Known Activations