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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "millennium" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ansom
    -0.16
    ÙĨدÙĩ
    -0.15
     dabei
    -0.14
    zen
    -0.14
    tah
    -0.14
     neighbouring
    -0.14
    ëĦ
    -0.13
    umm
    -0.13
     neighbour
    -0.13
    unma
    -0.13
    POSITIVE LOGITS
    arda
    0.18
    loub
    0.16
    ugin
    0.16
    Hierarchy
    0.16
    баÑĩ
    0.16
    esel
    0.15
    ibble
    0.15
    tej
    0.15
    SCO
    0.15
    lrt
    0.14
    Act Density 0.003%

    No Known Activations