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

    Neuronpedia

    INDEX
    Explanations

    elements related to iterative processes and their convergence behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     khoa
    -0.59
     card
    -0.59
    jure
    -0.58
     fact
    -0.58
     Schult
    -0.55
    Rudolf
    -0.52
     Bunting
    -0.52
    etted
    -0.51
    hadiran
    -0.51
    ═
    -0.50
    POSITIVE LOGITS
     []:
    1.67
    hasNext
    1.55
     convergence
    1.27
     Convergence
    1.15
    convergence
    1.14
    Convergence
    1.14
     converges
    1.13
    ContentAsync
    1.13
    mstyle
    1.07
     converge
    1.06
    Act Density 0.020%

    No Known Activations