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

    Neuronpedia

    INDEX
    Explanations

    words related to terrorist attacks

    oai_token-act-pair · gpt-3.5-turbo

    references to terrorist attacks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Vale
    -0.73
    OVA
    -0.72
    VO
    -0.70
    glomer
    -0.69
    VALUE
    -0.69
    éĸ
    -0.68
    aver
    -0.68
    Intern
    -0.67
     ILCS
    -0.66
     Pinball
    -0.64
    POSITIVE LOGITS
     spree
    1.15
     bombings
    1.03
     perpetrated
    0.99
     bombing
    0.99
     attacks
    0.99
     bombers
    0.95
     killings
    0.87
    attack
    0.87
     attack
    0.87
     rampage
    0.86
    Act Density 0.054%

    No Known Activations