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

    Neuronpedia

    INDEX
    Explanations

    terms associated with unresolved issues or unknown situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    point
    -0.17
     Rouge
    -0.16
    pack
    -0.15
    ä¸į足
    -0.15
    OrUpdate
    -0.14
    izr
    -0.14
    ä¸į好
    -0.14
    ryn
    -0.14
    èµ·
    -0.14
    dependent
    -0.13
    POSITIVE LOGITS
    /un
    0.35
    (Un
    0.22
    ably
    0.19
    ables
    0.18
    /il
    0.18
    ertainty
    0.18
    ly
    0.17
    vably
    0.17
    HostException
    0.17
    anness
    0.17
    Act Density 0.158%

    No Known Activations