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

    Neuronpedia

    INDEX
    Explanations

    references to the word "back" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ioxide
    -0.17
    ought
    -0.15
    peria
    -0.15
    elps
    -0.15
    ziel
    -0.15
    ikipedia
    -0.14
    eldon
    -0.14
     Liberation
    -0.14
    PGA
    -0.14
    eka
    -0.14
    POSITIVE LOGITS
    woods
    0.23
    hoe
    0.22
    seat
    0.22
    gam
    0.21
    country
    0.21
    lit
    0.20
    stre
    0.20
    lot
    0.20
    scatter
    0.19
    room
    0.19
    Act Density 0.019%

    No Known Activations