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

    Neuronpedia

    INDEX
    Explanations

    references to returning or going back to previous locations or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SETTING
    -0.15
    alic
    -0.15
    à¥įà¤ł
    -0.15
    ãĥ³ãĥij
    -0.15
    ium
    -0.14
     setting
    -0.14
    setting
    -0.14
    ycin
    -0.14
    idlo
    -0.14
    åıĸ
    -0.14
    POSITIVE LOGITS
     original
    0.22
     originals
    0.18
    -original
    0.17
    original
    0.16
     оÑĢиг
    0.16
     Original
    0.15
    ige
    0.15
    previous
    0.14
    ạch
    0.14
    (original
    0.14
    Act Density 0.105%

    No Known Activations