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

    Neuronpedia

    INDEX
    Explanations

    words and phrases that pertain to avoidance or evading specific situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sutherland
    -0.73
     publiques
    -0.72
    ImageField
    -0.67
     extérieures
    -0.66
     vertes
    -0.66
     iParam
    -0.64
    JMenu
    -0.64
    mesg
    -0.64
     privées
    -0.63
     Verantwortung
    -0.63
    POSITIVE LOGITS
    avoid
    2.02
     Avoid
    1.99
     avoid
    1.97
    Avoid
    1.96
     AVOID
    1.90
     avoided
    1.89
     avoiding
    1.89
     avoidance
    1.81
     avoids
    1.79
     Avoidance
    1.78
    Act Density 0.063%

    No Known Activations