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

    Neuronpedia

    INDEX
    Explanations

    specific mentions of libraries

    oai_token-act-pair · gpt-3.5-turbo

    mentions of libraries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antes
    -0.69
     stakes
    -0.67
     vent
    -0.66
    essen
    -0.66
     wed
    -0.65
     phen
    -0.63
     Dak
    -0.63
    rone
    -0.63
    Ò
    -0.63
    riots
    -0.63
    POSITIVE LOGITS
     Library
    3.96
     Libraries
    2.74
     library
    2.58
    Library
    2.55
     libraries
    2.15
    library
    1.90
    ibrarian
    1.60
     Archive
    1.59
    ibrary
    1.48
     Museum
    1.48
    Act Density 0.021%

    No Known Activations