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

    Neuronpedia

    INDEX
    Explanations

    phrases related to returning to a previous state or activity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "get back."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     JPM
    -0.60
    uously
    -0.59
     bis
    -0.58
    uary
    -0.57
     Crowd
    -0.57
     Us
    -0.56
     Sullivan
    -0.56
     understatement
    -0.56
     viz
    -0.56
    glers
    -0.55
    POSITIVE LOGITS
    packs
    0.95
    doors
    0.93
    tracking
    0.91
    dated
    0.90
    door
    0.88
    stab
    0.87
    ported
    0.87
    gam
    0.84
    seat
    0.84
    trace
    0.83
    Act Density 0.029%

    No Known Activations