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

    Neuronpedia

    INDEX
    Explanations

    instances of damage and injury caused by various events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    surrounding "damage" or "damages"

    np_acts-logits-general · gemini-2.0-flash

    damage or destruction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    exitRule
    -0.62
     betweenstory
    -0.58
     tartalomajánló
    -0.55
    __':
    -0.54
     autorytatywna
    -0.54
     zí
    -0.52
    +#+#
    -0.50
     onts
    -0.49
    peño
    -0.49
     bientôt
    -0.49
    POSITIVE LOGITS
     damage
    2.93
     Damage
    2.48
    damage
    2.43
    Damage
    2.35
     damages
    2.28
     DAMAGE
    2.26
     damaged
    2.08
    DAMAGE
    1.94
     destruction
    1.90
     Damages
    1.89
    Act Density 0.345%

    No Known Activations