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

    Neuronpedia

    INDEX
    Explanations

    phrases related to leaving or escaping a situation

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the action of leaving or exiting a situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cious
    -0.76
    cius
    -0.67
    inski
    -0.67
     heartbeat
    -0.61
     millenn
    -0.60
    etary
    -0.60
    ingham
    -0.59
     Rounds
    -0.57
    kefeller
    -0.57
     Few
    -0.57
    POSITIVE LOGITS
    stretched
    1.04
    doors
    1.01
    fitted
    0.91
    rage
    0.87
    door
    0.87
    posts
    0.84
    ta
    0.83
    smart
    0.81
    wards
    0.80
    skirts
    0.80
    Act Density 0.040%

    No Known Activations