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

    Neuronpedia

    INDEX
    Explanations

    repeated instances of the word "the" and references to significant announcements or launches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Å¡t
    -0.16
    opy
    -0.14
     Illegal
    -0.14
    uml
    -0.14
     ÙħاÙĦ
    -0.14
     vin
    -0.14
     illegal
    -0.13
    olian
    -0.13
    orr
    -0.13
    of
    -0.13
    POSITIVE LOGITS
    kud
    0.17
     escorte
    0.17
    ignum
    0.17
    anches
    0.14
     existence
    0.14
    ynamo
    0.14
    utions
    0.14
    ogie
    0.14
    pons
    0.14
    eÄį
    0.14
    Act Density 0.125%

    No Known Activations