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

    Neuronpedia

    INDEX
    Explanations

    phrases related to returning or going back to a previous state or location

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iesel
    -0.15
    ern
    -0.14
    back
    -0.14
     Bail
    -0.14
    olio
    -0.14
     mist
    -0.14
    hle
    -0.14
    ëŀ¨
    -0.14
    erner
    -0.13
    омеÑĢ
    -0.13
    POSITIVE LOGITS
    tracking
    0.20
    slash
    0.18
    à¥įवव
    0.16
    adow
    0.15
    logged
    0.15
     into
    0.15
    slashes
    0.15
    jedn
    0.15
    lashes
    0.15
    yards
    0.14
    Act Density 0.039%

    No Known Activations