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

    Neuronpedia

    INDEX
    Explanations

    references to alternative perspectives or additional elements in a discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edly
    -0.15
    tsky
    -0.15
    ilar
    -0.15
    bben
    -0.15
    ÑĨенÑĤÑĢа
    -0.14
     пÑĢик
    -0.14
    uese
    -0.14
    ling
    -0.14
    adan
    -0.14
    οÏĤ
    -0.14
    POSITIVE LOGITS
     two
    0.22
     three
    0.20
     part
    0.17
    hand
    0.16
    iator
    0.16
    ws
    0.15
    three
    0.15
     half
    0.15
    iginal
    0.15
    two
    0.15
    Act Density 0.035%

    No Known Activations