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

    Neuronpedia

    INDEX
    Explanations

    references to pairs or partnerships in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    warts
    -0.18
    ibrary
    -0.17
    rea
    -0.16
     gian
    -0.16
    ÙĬÙĪÙĨ
    -0.16
    irsch
    -0.15
    essian
    -0.14
    jang
    -0.14
     createAction
    -0.14
    esian
    -0.14
    POSITIVE LOGITS
    /group
    0.22
    /single
    0.20
    .infinity
    0.18
    inci
    0.17
    -thirds
    0.17
    /div
    0.16
    (pair
    0.16
    à¹ģรà¸ģ
    0.16
    ä¼į
    0.15
    tures
    0.15
    Act Density 0.054%

    No Known Activations