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

    Neuronpedia

    INDEX
    Explanations

    references to destruction and damage to communities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     extrad
    -0.16
    jur
    -0.15
    εÏĤ
    -0.15
    blr
    -0.14
    ensis
    -0.14
    ÑİÑĢ
    -0.14
    CREMENT
    -0.14
    dni
    -0.14
    resco
    -0.13
     restraining
    -0.13
    POSITIVE LOGITS
     destruction
    0.41
     destroyed
    0.40
    destroy
    0.36
     destroy
    0.36
     burned
    0.36
     Destruction
    0.34
     burnt
    0.34
     burning
    0.33
     Destroy
    0.33
     burn
    0.32
    Act Density 0.150%

    No Known Activations