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

    Neuronpedia

    INDEX
    Explanations

    references to academic research and scholarly work

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    indow
    -0.15
    ç§ĭ
    -0.15
    HandlerContext
    -0.15
    antal
    -0.15
    entric
    -0.14
    emoc
    -0.14
    serrat
    -0.14
    ovo
    -0.14
    etti
    -0.13
    ocab
    -0.13
    POSITIVE LOGITS
     interests
    0.23
     credits
    0.18
     interest
    0.18
    interest
    0.18
     resume
    0.18
     background
    0.18
     hobbies
    0.17
     current
    0.17
     recent
    0.17
    current
    0.17
    Act Density 0.082%

    No Known Activations