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

    Neuronpedia

    INDEX
    Explanations

    references to damage or harm

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

    "damage"

    np_acts-logits-general · gemini-2.0-flash

    damage and its consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Према
    -0.69
     rega
    -0.48
    tet
    -0.48
     tartalomajánló
    -0.48
     noirs
    -0.46
    otho
    -0.45
     zee
    -0.45
    /*---
    -0.45
     Ours
    -0.45
     Übung
    -0.44
    POSITIVE LOGITS
     damage
    1.21
     Damage
    1.18
     DAMAGE
    1.11
    Damage
    1.08
    damage
    1.08
     damages
    1.04
     Damages
    1.01
     Dama
    0.98
     Damaged
    0.98
    Dama
    0.97
    Act Density 0.134%

    No Known Activations