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

    Neuronpedia

    INDEX
    Explanations

    references to induction into the Hall of Fame

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Hall of Fame

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     eleph
    -0.76
     Gork
    -0.70
     oppos
    -0.65
    ften
    -0.63
    uyomi
    -0.61
    ropolitan
    -0.61
    itars
    -0.60
    ting
    -0.59
     lightly
    -0.59
    ted
    -0.58
    POSITIVE LOGITS
    iday
    1.38
    Hall
    1.13
    aday
    1.07
    ibur
    1.05
     Hall
    1.05
    oran
    1.00
    gren
    1.00
    hall
    0.90
    way
    0.89
    ows
    0.88
    Act Density 0.008%

    No Known Activations