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

    Neuronpedia

    INDEX
    Explanations

    numerical references, particularly those associated with citations or document retrieval dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iscard
    -0.16
     sandwich
    -0.14
    ature
    -0.14
    ilters
    -0.14
    aren
    -0.14
    eger
    -0.14
    acerb
    -0.13
     ìļ©
    -0.13
    ieten
    -0.13
    ocket
    -0.13
    POSITIVE LOGITS
    âĨij
    0.28
     âĨij
    0.22
    ^
    0.22
    Wik
    0.20
     Media
    0.19
    Ret
    0.19
     ^
    0.18
     Template
    0.18
     ^↵
    0.17
    -ret
    0.17
    Act Density 0.013%

    No Known Activations