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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating an increase or emphasis on additional information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    \{\\
    -0.64
     poffible
    -0.63
    numerusform
    -0.60
     houſe
    -0.59
     leaſt
    -0.58
     myſelf
    -0.58
     Majefty
    -0.57
     ſen
    -0.57
     greateſt
    -0.56
     Monfieur
    -0.56
    POSITIVE LOGITS
    등
    0.73
    etera
    0.70
     utafitiHapana
    0.65
     等
    0.63
     وسلم
    0.59
    راسیون
    0.59
    oredCriteria
    0.59
    UpInside
    0.58
     lainnya
    0.58
    AccessorTable
    0.57
    Act Density 0.179%

    No Known Activations