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

    Neuronpedia

    INDEX
    Explanations

    words related to war and conflict

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to war and its consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Indigo
    -0.70
     Burr
    -0.70
    eele
    -0.69
    uez
    -0.68
     Scotch
    -0.67
    kson
    -0.64
     opin
    -0.63
    amiya
    -0.62
     Vec
    -0.61
    herty
    -0.61
    POSITIVE LOGITS
    related
    1.14
    seeking
    1.07
    induced
    1.07
    driven
    0.98
    themed
    0.98
    ridden
    0.96
    fighting
    0.96
    drug
    0.95
    machine
    0.95
    prone
    0.93
    Act Density 0.112%

    No Known Activations