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

    Neuronpedia

    INDEX
    Explanations

    instances of violence and conflict in historical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Италијани
    -0.49
     funcionales
    -0.48
     henvisninger
    -0.46
    BagConstraints
    -0.45
     '\\;'
    -0.45
     princesas
    -0.42
    delwed
    -0.41
     estekak
    -0.40
     instruções
    -0.39
    colgante
    -0.39
    POSITIVE LOGITS
     massacre
    0.59
     massac
    0.59
     horrific
    0.57
    Incre
    0.55
     slaughtered
    0.55
     carnage
    0.55
     tragedy
    0.54
     massacres
    0.54
     slaugh
    0.53
     decim
    0.53
    Act Density 0.384%

    No Known Activations