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

    Neuronpedia

    INDEX
    Explanations

    instances of code-related formatting and escape characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    áÄį
    -0.16
    edn
    -0.16
    ooth
    -0.14
    askell
    -0.14
    oop
    -0.14
    ãĥ¼ãĥĪ
    -0.14
    opak
    -0.13
    arro
    -0.13
    =wx
    -0.13
    etti
    -0.13
    POSITIVE LOGITS
    олÑĮкÑĥ
    0.14
    eree
    0.14
    ember
    0.14
    ugs
    0.13
    ãģ«ãģ¨
    0.13
    .yy
    0.13
     Stub
    0.13
    onda
    0.13
    ÑĨеп
    0.13
    estre
    0.13
    Act Density 0.024%

    No Known Activations