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

    Neuronpedia

    INDEX
    Explanations

    references to destruction and damage caused by disasters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Tube
    -0.16
    readcr
    -0.14
    inkel
    -0.14
     Tubes
    -0.14
     surplus
    -0.14
    avaÅŁ
    -0.14
    IFE
    -0.14
    Dyn
    -0.13
    inas
    -0.13
    å®ī
    -0.13
    POSITIVE LOGITS
     damage
    0.21
     Damage
    0.19
     DAMAGE
    0.17
    damage
    0.17
    iag
    0.17
    liž
    0.16
    wand
    0.16
    견
    0.15
    amage
    0.15
    iegel
    0.15
    Act Density 0.080%

    No Known Activations