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

    Neuronpedia

    INDEX
    Explanations

    terms related to the concept of defense

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    samt
    -0.56
    hoga
    -0.55
     Bros
    -0.55
    >{@
    -0.52
    badlogic
    -0.51
     Lawrence
    -0.50
     bed
    -0.50
    tage
    -0.49
    Lawrence
    -0.49
     means
    -0.48
    POSITIVE LOGITS
     defend
    2.96
     defended
    2.69
     defending
    2.57
     defends
    2.51
     Defend
    2.33
     DEFEND
    1.91
     défend
    1.80
     défendre
    1.75
     defender
    1.62
     defenders
    1.60
    Act Density 0.096%

    No Known Activations