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

    Neuronpedia

    INDEX
    Explanations

    concepts related to ambiguity and uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    point
    -0.17
    ä¸į足
    -0.16
    eria
    -0.15
    out
    -0.15
    erno
    -0.15
     Rouge
    -0.15
    AZE
    -0.15
    OrUpdate
    -0.14
    ÏģÏĮ
    -0.14
    -eyed
    -0.14
    POSITIVE LOGITS
    /un
    0.40
    (Un
    0.23
    HostException
    0.20
    /il
    0.20
    ables
    0.19
    vably
    0.19
    ness
    0.18
    anness
    0.18
    /null
    0.18
    ly
    0.18
    Act Density 0.187%

    No Known Activations