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

    Neuronpedia

    INDEX
    Explanations

    terms related to libraries and their value or effectiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aze
    -0.17
    jal
    -0.16
    lug
    -0.16
    agma
    -0.15
    osg
    -0.15
    iÄįka
    -0.15
    duit
    -0.14
    etur
    -0.14
    jong
    -0.14
    itored
    -0.13
    POSITIVE LOGITS
     Lib
    0.29
     libr
    0.29
     Library
    0.28
     bib
    0.28
     library
    0.28
    ALA
    0.27
     librarian
    0.27
     Serial
    0.26
     Libraries
    0.26
     Bib
    0.25
    Act Density 0.036%

    No Known Activations