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

    Neuronpedia

    INDEX
    Explanations

    phrases related to returning or revisiting something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "back."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    "]=>
    -0.67
     understatement
    -0.66
     Conrad
    -0.66
    ================================
    -0.64
     prerequisite
    -0.62
     Telescope
    -0.60
    orst
    -0.59
    alion
    -0.58
     delegation
    -0.57
     Crowd
    -0.56
    POSITIVE LOGITS
    doors
    0.93
    tracking
    0.88
    door
    0.84
    home
    0.84
    packs
    0.82
    stairs
    0.79
    seat
    0.78
    swing
    0.77
    wards
    0.77
    track
    0.76
    Act Density 0.026%

    No Known Activations