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

    Neuronpedia

    INDEX
    Explanations

    phrases related to movement or action

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "out" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     turnover
    -0.66
     Emin
    -0.63
     consolidated
    -0.62
    matically
    -0.62
     examiner
    -0.62
    cious
    -0.62
    anooga
    -0.61
     heartbeat
    -0.61
    iferation
    -0.61
     result
    -0.61
    POSITIVE LOGITS
    stretched
    1.25
    fitted
    1.18
    doors
    1.00
    ouk
    0.90
    bur
    0.86
    ta
    0.82
    door
    0.82
    odon
    0.81
    skirts
    0.80
    posts
    0.80
    Act Density 0.074%

    No Known Activations