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

    Neuronpedia

    INDEX
    Explanations

    questions about definitions and characteristics of terms or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Majefty
    -0.79
    BagConstraints
    -0.65
    iency
    -0.60
    awtextra
    -0.60
     Houſe
    -0.60
     Dich
    -0.59
     poffible
    -0.59
     Chaco
    -0.59
     myſelf
    -0.58
     mergeFrom
    -0.58
    POSITIVE LOGITS
    Whats
    0.69
    whats
    0.67
     vad
    0.66
     Whats
    0.66
    gameserver
    0.64
     kasarigan
    0.62
     what
    0.62
     Skate
    0.60
    GraphicsUnit
    0.58
    hares
    0.58
    Act Density 0.126%

    No Known Activations