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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the act of closing or shutting down

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ç´ł
    -0.18
    amp
    -0.16
    ashi
    -0.16
    rome
    -0.15
    ku
    -0.15
    uant
    -0.15
    redit
    -0.14
    serter
    -0.14
    éc
    -0.14
    uite
    -0.14
    POSITIVE LOGITS
    /open
    0.18
    -caption
    0.17
    pering
    0.16
    exels
    0.16
    stellen
    0.16
    -door
    0.15
    -eyed
    0.15
    usercontent
    0.15
    elsif
    0.15
    -quarters
    0.14
    Act Density 0.045%

    No Known Activations