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

    Neuronpedia

    INDEX
    Explanations

    references to destruction and devastation in a community context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dea
    -0.15
     extrad
    -0.15
     деÑĢ
    -0.14
     extradition
    -0.14
    éģĭåĭķ
    -0.14
    352
    -0.13
    çĸĨ
    -0.13
    εÏģÏĮ
    -0.13
    iji
    -0.13
    exus
    -0.13
    POSITIVE LOGITS
     destruction
    0.36
     destroyed
    0.36
     damage
    0.33
    destroy
    0.32
     destroy
    0.30
     Destroy
    0.29
     Destruction
    0.28
    _destroy
    0.28
     rubble
    0.28
     Damage
    0.27
    Act Density 0.150%

    No Known Activations