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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "separate" and related concepts indicating distinctness or individual components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vet
    -0.15
    ram
    -0.15
    ÑģоÑĤ
    -0.14
    ло
    -0.14
    ln
    -0.14
    ottes
    -0.13
    li
    -0.13
    ruptcy
    -0.13
    ute
    -0.13
    icina
    -0.13
    POSITIVE LOGITS
    ürk
    0.17
    aland
    0.16
    -sex
    0.16
     à¹Ĩ
    0.15
    iators
    0.15
     biá»ĩt
    0.15
    éijij
    0.15
    ĶåĽŀ
    0.15
    ures
    0.15
     Andrews
    0.15
    Act Density 0.032%

    No Known Activations