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

    Neuronpedia

    INDEX
    Explanations

    various forms of the Danish word for 'self' or related expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chwitz
    -0.15
    tn
    -0.15
    eum
    -0.14
    kee
    -0.14
    ÅĻÃŃz
    -0.14
    ç§
    -0.14
    ay
    -0.14
    LETED
    -0.13
    é¾Ħ
    -0.13
    TagName
    -0.13
    POSITIVE LOGITS
    atre
    0.19
    ater
    0.17
    atomy
    0.16
     Kens
    0.16
    ãĤ¶ãĥ¼
    0.14
    etheless
    0.14
    _KERNEL
    0.14
     nabÃŃ
    0.14
    ills
    0.14
    OfWork
    0.14
    Act Density 0.054%

    No Known Activations