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" used in various contexts, particularly related to return or recurrence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     understatement
    -0.67
    rez
    -0.64
    icipated
    -0.63
    aspx
    -0.62
    orst
    -0.61
    "]=>
    -0.61
     Telescope
    -0.61
    alion
    -0.61
    esan
    -0.60
    anto
    -0.60
    POSITIVE LOGITS
    doors
    0.94
    packs
    0.88
    door
    0.86
    stories
    0.83
    seat
    0.82
    tracking
    0.82
    wards
    0.82
    home
    0.80
    GROUND
    0.80
    fires
    0.78
    Act Density 0.043%

    No Known Activations