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

    Neuronpedia

    INDEX
    Explanations

    content related to crises and the potential for disaster

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DataSource
    -0.15
     fetisch
    -0.15
    ()(
    -0.14
    úsqueda
    -0.14
    ctors
    -0.14
    èª
    -0.14
    336
    -0.14
     INTERRU
    -0.13
    åģ¶
    -0.13
    ÐļТ
    -0.13
    POSITIVE LOGITS
     disaster
    0.38
     catastrophe
    0.33
     Disaster
    0.32
     cata
    0.29
     dire
    0.29
     calam
    0.28
     doom
    0.27
     terminal
    0.25
     Arm
    0.25
     glo
    0.25
    Act Density 0.693%

    No Known Activations