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

    Neuronpedia

    INDEX
    Explanations

    references to apocalyptic themes and catastrophic events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    鬼
    -0.08
    andal
    -0.07
    rvé
    -0.07
    éĶ¦
    -0.07
    åĵ
    -0.07
    ên
    -0.07
    ,...↵↵
    -0.07
    γκα
    -0.07
    agos
    -0.07
    raith
    -0.07
    POSITIVE LOGITS
     earth
    0.08
     Earth
    0.07
     Predict
    0.06
    earth
    0.06
     predictions
    0.06
     nuclear
    0.06
    Earth
    0.06
     warnings
    0.06
     planet
    0.06
     cata
    0.06
    Act Density 0.014%

    No Known Activations