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

    Neuronpedia

    INDEX
    Explanations

    incidents involving casualties, particularly from fires, explosions, and attacks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .Restr
    -0.16
    commit
    -0.15
    izzo
    -0.14
    AccessType
    -0.14
    angkan
    -0.14
    irate
    -0.14
     sensit
    -0.14
    ventus
    -0.14
     Crimes
    -0.14
    reo
    -0.13
    POSITIVE LOGITS
     Lac
    0.20
     train
    0.18
     infer
    0.18
     explosion
    0.17
     coach
    0.17
    urch
    0.17
     stamp
    0.16
     collapse
    0.16
     collision
    0.15
     tragedy
    0.15
    Act Density 0.129%

    No Known Activations