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

    Neuronpedia

    INDEX
    Explanations

    characters and patterns commonly used in programming or regex expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acho
    -0.17
    aul
    -0.16
    ëħ
    -0.15
    æīĢ
    -0.15
    ample
    -0.15
    à¸į
    -0.14
    ãĥ¼ãĥĹ
    -0.14
    asses
    -0.14
     Zem
    -0.14
    浦
    -0.13
    POSITIVE LOGITS
    +
    0.20
    +↵
    0.17
    ]+
    0.16
    *
    0.15
    )+
    0.15
    +:
    0.15
    IPA
    0.14
    )*
    0.14
    ){
    0.14
    {
    0.14
    Act Density 0.036%

    No Known Activations