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

    Neuronpedia

    INDEX
    Explanations

    references to combat and fighting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tre
    -0.91
     TType
    -0.89
    Tre
    -0.81
     Tre
    -0.81
    deelte
    -0.74
    i
    -0.71
     tục
    -0.69
     obligé
    -0.69
     deciso
    -0.68
    tre
    -0.68
    POSITIVE LOGITS
     combat
    2.22
     Combat
    2.12
    combat
    2.03
    Combat
    1.96
     combats
    1.36
     combate
    1.05
     combatants
    1.02
     combating
    0.95
     kombat
    0.89
     combatt
    0.86
    Act Density 0.054%

    No Known Activations