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

    Neuronpedia

    INDEX
    Explanations

    references to destruction and survival in a wartime context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     drowning
    -0.16
    εÏģÏĮ
    -0.15
     Forgotten
    -0.15
    éģĭåĭķ
    -0.14
    @student
    -0.14
    ãĤ´ãĥª
    -0.14
    256
    -0.14
    362
    -0.13
     Grave
    -0.13
    声ãĤĴ
    -0.13
    POSITIVE LOGITS
     damage
    0.37
     destroyed
    0.36
     destruction
    0.34
    destroy
    0.31
     Damage
    0.31
     rubble
    0.31
     damaged
    0.30
     debris
    0.30
    damage
    0.29
     DAMAGE
    0.29
    Act Density 0.180%

    No Known Activations