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

    Neuronpedia

    INDEX
    Explanations

    references to additional features and similar items across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lÆ°Æ¡ng
    -0.15
    imli
    -0.15
    uu
    -0.14
    etak
    -0.14
    443
    -0.13
    /Framework
    -0.13
    rico
    -0.13
    opensource
    -0.13
    azor
    -0.13
    433
    -0.13
    POSITIVE LOGITS
     features
    0.26
     things
    0.20
     items
    0.20
    features
    0.19
     elements
    0.19
     stuff
    0.19
     anc
    0.18
     aspects
    0.18
     Features
    0.18
     FEATURES
    0.18
    Act Density 0.507%

    No Known Activations