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

    Neuronpedia

    INDEX
    Explanations

    terms related to copyright and proper citation practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sus
    -0.18
    sus
    -0.15
    ocker
    -0.15
    arp
    -0.14
    ock
    -0.14
    -stop
    -0.14
     trick
    -0.14
    osemite
    -0.13
     th
    -0.13
    reak
    -0.13
    POSITIVE LOGITS
    声
    0.15
    vida
    0.15
     intox
    0.15
    aware
    0.14
    indic
    0.14
    ixa
    0.14
    αιν
    0.14
    icontrol
    0.14
    ÑĥлÑĮ
    0.14
    ëł¹
    0.14
    Act Density 0.012%

    No Known Activations