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

    Neuronpedia

    INDEX
    Explanations

    references to returning or going back

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idel
    -0.20
     backgrounds
    -0.19
     background
    -0.18
    _backup
    -0.18
     Background
    -0.18
     backups
    -0.18
    naire
    -0.17
     backs
    -0.17
     backlight
    -0.17
    èĥĮæĻ¯
    -0.17
    POSITIVE LOGITS
    tracking
    0.36
    slash
    0.30
    tracked
    0.29
    side
    0.29
    seat
    0.27
    slashes
    0.27
    tracks
    0.27
    door
    0.27
     home
    0.27
    logged
    0.27
    Act Density 0.054%

    No Known Activations