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

    the concept of "coming back."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     understatement
    -0.75
    \\\\\\\\
    -0.69
    orst
    -0.61
    âĢ¢âĢ¢
    -0.61
    ĺħ
    -0.60
    aspx
    -0.59
    "]=>
    -0.59
    AIN
    -0.58
    ================================
    -0.57
    ¤
    -0.57
    POSITIVE LOGITS
    seat
    0.85
    home
    0.81
    door
    0.81
    packs
    0.75
    doors
    0.75
    wards
    0.74
    roth
    0.74
    roads
    0.73
     home
    0.72
    woods
    0.71
    Act Density 0.022%

    No Known Activations