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

    Neuronpedia

    INDEX
    Explanations

    commas and the connection of clauses within complex sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igg
    -0.16
    yun
    -0.14
    ailer
    -0.14
    ieder
    -0.14
    ленно
    -0.14
     biz
    -0.14
    ONGL
    -0.13
    ÑıÑĤ
    -0.13
    .detect
    -0.13
    odash
    -0.13
    POSITIVE LOGITS
    obl
    0.15
    ĥģ
    0.14
    andi
    0.14
    ãĥ³ãĤ¬
    0.13
    еж
    0.13
    flation
    0.13
    ζÏĮ
    0.13
    lsru
    0.13
     ìłģ
    0.13
     ê
    0.13
    Act Density 0.066%

    No Known Activations