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

    Neuronpedia

    INDEX
    Explanations

    references to destruction, suffering, and the impact of conflict on communities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     restraining
    -0.16
    eca
    -0.15
    ÑİÑĢ
    -0.15
    jur
    -0.14
     поÑģк
    -0.14
     extrad
    -0.14
    iji
    -0.14
    cesso
    -0.14
    iez
    -0.14
    _cg
    -0.13
    POSITIVE LOGITS
     destruction
    0.50
     destroy
    0.50
     destroyed
    0.49
    destroy
    0.47
     Destroy
    0.46
    .destroy
    0.43
     DEST
    0.42
    _destroy
    0.41
     destroying
    0.41
     destroys
    0.41
    Act Density 0.273%

    No Known Activations