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

    Neuronpedia

    INDEX
    Explanations

    citations and formal references to news articles or reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    \Context
    -0.16
    imson
    -0.16
    asca
    -0.16
    ROUGH
    -0.15
     Ïĥαν
    -0.14
     ÑĦакÑĤи
    -0.14
    stvo
    -0.14
    _trampoline
    -0.14
    iros
    -0.14
     اÙĪÙĦ
    -0.13
    POSITIVE LOGITS
     week
    0.19
     Else
    0.16
     continues
    0.16
    SizeMode
    0.15
    Else
    0.15
     Brill
    0.15
     weekly
    0.15
     continuing
    0.15
    sume
    0.15
     news
    0.15
    Act Density 0.246%

    No Known Activations