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

    Neuronpedia

    INDEX
    Explanations

    references to war and conflict

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uled
    -0.15
    ÃŃr
    -0.14
    entai
    -0.14
    ÂŃi
    -0.14
    اÛĮر
    -0.13
     freak
    -0.13
    arrants
    -0.13
    .xy
    -0.13
    269
    -0.13
    606
    -0.13
    POSITIVE LOGITS
     conflict
    0.44
     conflicts
    0.38
     host
    0.36
     war
    0.34
     Conflict
    0.33
    conf
    0.31
    -conf
    0.30
    Conflict
    0.28
     wars
    0.28
     confl
    0.26
    Act Density 0.156%

    No Known Activations