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

    Neuronpedia

    INDEX
    Explanations

    dialogues or expressions of emotions and actions in interactions between characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nearly
    -0.17
    ais
    -0.16
     Kew
    -0.16
    aisy
    -0.15
     Nearly
    -0.15
    áng
    -0.14
    inka
    -0.14
    oli
    -0.14
    aise
    -0.14
     perpet
    -0.14
    POSITIVE LOGITS
     McGregor
    0.16
    erdem
    0.15
    اسطة
    0.15
    _allocate
    0.15
    etting
    0.14
    .scalablytyped
    0.14
    ä¸ĸç´Ģ
    0.14
    FETCH
    0.14
    veÅĻej
    0.14
     Ãľl
    0.14
    Act Density 0.054%

    No Known Activations