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

    Neuronpedia

    INDEX
    Explanations

    words or phrases related to action-oriented features and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uckets
    -0.17
    ESH
    -0.17
    roker
    -0.15
    Ø´Ùĩ
    -0.15
    asser
    -0.15
    852
    -0.15
    ookies
    -0.15
    ANDLE
    -0.14
     voc
    -0.14
    848
    -0.14
    POSITIVE LOGITS
    edis
    0.15
    flags
    0.15
    .bits
    0.14
    OrUpdate
    0.13
    èĢħ
    0.13
    clar
    0.13
     mism
    0.13
    aar
    0.13
    íį¼
    0.13
    #
    0.13
    Act Density 0.084%

    No Known Activations