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

    Neuronpedia

    INDEX
    Explanations

    phrases related to health and safety risks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GraphicsUnit
    -0.75
    UnusedPrivate
    -0.60
    NegativeButton
    -0.59
    Portale
    -0.58
     définiti
    -0.57
    $_['
    -0.56
    الحياه
    -0.56
     religieuses
    -0.56
    fromnode
    -0.55
    PositiveButton
    -0.55
    POSITIVE LOGITS
     يتيمه
    0.72
     odkazy
    0.67
    \{\\
    0.58
    Jegyzetek
    0.57
    nonatomic
    0.54
    EndInit
    0.51
    \}\\
    0.51
    tuan
    0.50
     insuffisamment
    0.50
    matchCondition
    0.49
    Act Density 0.050%

    No Known Activations