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

    Neuronpedia

    INDEX
    Explanations

    phrases related to leaving or exiting a place or situation

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing a desire to escape or leave a situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eries
    -0.61
    ery
    -0.61
     capt
    -0.59
     upkeep
    -0.58
     Bulg
    -0.58
     Hera
    -0.58
     heartbeat
    -0.58
     Brach
    -0.57
     Yamato
    -0.55
    asus
    -0.53
    POSITIVE LOGITS
    stretched
    1.04
    doors
    1.02
    door
    1.01
    fitted
    0.98
    ta
    0.98
    smart
    0.92
    bur
    0.90
    skirts
    0.83
    rage
    0.79
    posts
    0.77
    Act Density 0.038%

    No Known Activations