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

    Neuronpedia

    INDEX
    Explanations

    words related to returning or moving back to a previous state or location

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     background
    -0.17
    isko
    -0.17
    background
    -0.17
    idel
    -0.17
     backgrounds
    -0.16
    Background
    -0.16
    naire
    -0.16
    맥
    -0.16
     Background
    -0.15
    raž
    -0.15
    POSITIVE LOGITS
    wards
    0.27
    slash
    0.25
    lashes
    0.23
    ronym
    0.22
    logged
    0.22
    side
    0.22
    slashes
    0.21
    yards
    0.21
    tracking
    0.21
    /front
    0.20
    Act Density 0.062%

    No Known Activations