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

    Neuronpedia

    INDEX
    Explanations

    terms related to workplace conditions and ergonomics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    work
    -0.19
    atak
    -0.17
    room
    -0.17
    elles
    -0.16
    boy
    -0.16
    word
    -0.15
    lifetime
    -0.15
    infeld
    -0.15
    field
    -0.15
    wand
    -0.15
    POSITIVE LOGITS
    ed
    0.22
    ing
    0.21
    ers
    0.17
    ting
    0.17
    ped
    0.16
    /down
    0.16
    /off
    0.16
    e
    0.15
    eer
    0.15
    ping
    0.15
    Act Density 0.201%

    No Known Activations