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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to terrorist attacks and their impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Arrest
    -0.16
    388
    -0.15
    648
    -0.15
    ahoo
    -0.15
    389
    -0.15
     Loot
    -0.14
    .myapplication
    -0.14
    RAP
    -0.13
    agos
    -0.13
     éķ·
    -0.13
    POSITIVE LOGITS
     attack
    0.39
     attacks
    0.34
    attack
    0.27
     Attacks
    0.26
     Attack
    0.26
    attacks
    0.26
     attacked
    0.25
     attach
    0.24
     twin
    0.23
     blasts
    0.23
    Act Density 0.136%

    No Known Activations