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

    Neuronpedia

    INDEX
    Explanations

    phrases related to violations of international humanitarian law

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to violations of international humanitarian law

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    maxwell
    -0.89
     Edison
    -0.89
    upiter
    -0.87
     NASCAR
    -0.85
     Cary
    -0.83
     Chevy
    -0.82
    Tesla
    -0.78
     nerds
    -0.77
     CNBC
    -0.77
     smartest
    -0.77
    POSITIVE LOGITS
     violations
    1.32
     atrocities
    1.31
     ceasefire
    1.21
     genocide
    1.20
     abuses
    1.20
     impunity
    1.18
     inhuman
    1.15
     humanitarian
    1.14
     massacres
    1.14
     complicity
    1.11
    Act Density 1.094%

    No Known Activations