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

    Neuronpedia

    INDEX
    Explanations

    instances of references or citations in academic writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Laurent
    -0.17
    ply
    -0.16
     POD
    -0.16
    zan
    -0.15
    ve
    -0.14
    ves
    -0.14
    468
    -0.14
    EDI
    -0.14
     pol
    -0.14
     Chat
    -0.14
    POSITIVE LOGITS
    ieme
    0.15
    oine
    0.15
    tsy
    0.15
    è´
    0.14
    CESS
    0.14
    utan
    0.14
    елик
    0.14
    roph
    0.14
     Kauf
    0.14
    urum
    0.13
    Act Density 0.025%

    No Known Activations