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

    Neuronpedia

    INDEX
    Explanations

    examples or instances that illustrate a point or concept

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¤ãĤ¯
    -0.16
    rhs
    -0.15
    acher
    -0.15
    obo
    -0.15
    okit
    -0.14
    ide
    -0.14
    ukan
    -0.14
     lep
    -0.14
    ams
    -0.13
    orte
    -0.13
    POSITIVE LOGITS
    illage
    0.20
     nimi
    0.15
    outu
    0.15
    707
    0.14
    DL
    0.14
     COS
    0.13
    ÙĨØ´
    0.13
    608
    0.13
    äl
    0.13
    TURE
    0.13
    Act Density 0.019%

    No Known Activations