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

    Neuronpedia

    INDEX
    Explanations

    references to libraries and their functions or evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     commissions
    -0.15
    PPER
    -0.14
    duit
    -0.14
     rigs
    -0.14
    .protobuf
    -0.14
    endi
    -0.13
    çĽĬ
    -0.13
    asant
    -0.13
    nof
    -0.13
    еÑģа
    -0.13
    POSITIVE LOGITS
     libr
    0.45
     library
    0.44
     Library
    0.43
     librarian
    0.43
     Libraries
    0.39
    Library
    0.37
    library
    0.36
     Lib
    0.36
     libraries
    0.36
    -library
    0.35
    Act Density 0.210%

    No Known Activations