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

    Neuronpedia

    INDEX
    Explanations

    instances of conjunctions and phrases indicating relationships or connections between concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ering
    -0.17
    akra
    -0.15
    ä¾į
    -0.14
    ç
    -0.14
    ieres
    -0.14
    ermann
    -0.14
    ikan
    -0.13
    Ñĸдом
    -0.13
    ik
    -0.13
     trim
    -0.13
    POSITIVE LOGITS
     its
    0.19
    its
    0.16
    GMEM
    0.16
    .IContainer
    0.15
    {@
    0.15
    TI
    0.15
    Its
    0.15
    945
    0.15
    é»İ
    0.15
    Anchor
    0.14
    Act Density 0.185%

    No Known Activations