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

    Neuronpedia

    INDEX
    Explanations

    phrases that use parentheses or similar structures in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uko
    -0.15
     Kür
    -0.15
    isContained
    -0.15
    ãģĵãģ¨ãģ¯
    -0.14
     cân
    -0.14
    ida
    -0.14
    onis
    -0.14
    uke
    -0.14
     serg
    -0.14
    iren
    -0.13
    POSITIVE LOGITS
     semi
    0.16
    æłª
    0.16
    afa
    0.15
     partly
    0.15
     almost
    0.15
     mostly
    0.15
    ISC
    0.15
    almost
    0.14
    near
    0.14
    -)
    0.14
    Act Density 0.059%

    No Known Activations