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

    Neuronpedia

    INDEX
    Explanations

    references to injuries and wounds

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

    physical injuries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.47
    ⓧ
    -0.45
     sails
    -0.44
     IMDG
    -0.43
     founders
    -0.42
     Solon
    -0.42
     advocates
    -0.41
     tetto
    -0.41
    verwijspagina
    -0.41
    Sol
    -0.41
    POSITIVE LOGITS
     injuries
    1.43
     Injuries
    1.35
    Injuries
    1.17
    juries
    0.96
     lesiones
    0.69
     blessures
    0.68
     blessé
    0.65
    ilarities
    0.59
     Injured
    0.57
     injured
    0.54
    Act Density 0.011%

    No Known Activations