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

    Neuronpedia

    INDEX
    Explanations

    descriptions of heroic acts and deeds, often in the context of challenging or dangerous situations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     jati
    -0.91
     idr
    -0.90
     disagre
    -0.89
     nece
    -0.87
     haer
    -0.85
     meis
    -0.85
     inev
    -0.84
     nuoc
    -0.84
     gend
    -0.84
     karte
    -0.84
    POSITIVE LOGITS
     heroism
    0.82
     bravery
    0.80
     heroic
    0.78
     courage
    0.78
     selfless
    0.76
     hero
    0.74
     courageous
    0.71
     heroes
    0.71
     dedication
    0.68
     admirable
    0.65
    Act Density 0.797%

    No Known Activations