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

    Neuronpedia

    INDEX
    Explanations

    references to specific items or concepts, particularly those denoted with "this."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oret
    -0.19
    kud
    -0.16
    erdale
    -0.15
    ant
    -0.15
    奴
    -0.14
    iginal
    -0.14
    orrent
    -0.14
    antor
    -0.14
    orem
    -0.14
    ÑĥÑĢн
    -0.13
    POSITIVE LOGITS
    ãĥ¼ãĥī
    0.17
    anas
    0.14
    ARCH
    0.14
     rapidly
    0.14
    uzu
    0.13
    اÙĬات
    0.13
    -pointer
    0.13
    OKEN
    0.13
    licken
    0.13
    erval
    0.13
    Act Density 0.068%

    No Known Activations