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

    Neuronpedia

    INDEX
    Explanations

    discussions about bans and prohibitions related to various topics and regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ä¸įæĸŃ
    -0.18
    ãĥªãĥ¼ãĤº
    -0.15
     ><?
    -0.15
    onth
    -0.14
    .examples
    -0.14
    aura
    -0.14
     xu
    -0.14
    ä¸įåIJĮçļĦ
    -0.13
    builtin
    -0.13
    ongo
    -0.13
    POSITIVE LOGITS
     certain
    0.24
     anyone
    0.22
     sale
    0.22
     Certain
    0.22
     entry
    0.21
     imports
    0.21
    Certain
    0.21
     use
    0.20
    ish
    0.19
    ished
    0.18
    Act Density 0.231%

    No Known Activations