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

    Neuronpedia

    INDEX
    Explanations

    instances of transformation or change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BagConstraints
    -0.77
     pinulongan
    -0.76
    autoconfigure
    -0.72
     actionMode
    -0.72
    openConnection
    -0.70
    featureID
    -0.69
    hloromethane
    -0.67
    ++
    -0.67
    UnusedPrivate
    -0.67
    ObjectContext
    -0.66
    POSITIVE LOGITS
     become
    1.03
     Become
    0.85
     becomes
    0.82
    Become
    0.81
    become
    0.80
     jadi
    0.79
     became
    0.76
     becoming
    0.75
    变成
    0.70
    Becoming
    0.70
    Act Density 0.156%

    No Known Activations