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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and structures commonly used in equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mandela
    -0.65
    icha
    -0.63
     Guen
    -0.62
     déb
    -0.59
     Anderson
    -0.59
    tegen
    -0.58
    AfterClass
    -0.56
     up
    -0.56
    tiq
    -0.56
    adne
    -0.55
    POSITIVE LOGITS
    }{
    1.44
    )}{
    1.27
    {}{
    1.17
    |}{
    1.11
    )}}{
    1.08
    }}{
    1.08
    ]}{
    1.07
    _{
    1.04
     }{
    1.02
    __':
    0.98
    Act Density 0.174%

    No Known Activations