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

    Neuronpedia

    INDEX
    Explanations

    concepts related to memory loss and identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģijãĤĮãģ©
    -0.17
    eker
    -0.16
    ãģ°ãģĭãĤĬ
    -0.16
    ãģªãģ®
    -0.16
    eyin
    -0.16
    umlu
    -0.15
    ãģ¨æĢĿãģĨ
    -0.15
    kola
    -0.15
    ä¼łå¥ĩ
    -0.14
    ãģªãĤĵãģ¦
    -0.14
    POSITIVE LOGITS
    âĺĨ
    0.17
    ãĥ¼ãĥ¼
    0.17
    ãĢĪ
    0.16
     McCart
    0.16
     incom
    0.15
     tens
    0.14
     huh
    0.14
    âĶĢâĶĢ
    0.14
     McG
    0.14
    jug
    0.14
    Act Density 0.004%

    No Known Activations