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

    Neuronpedia

    INDEX
    Explanations

    keywords related to catastrophic events or situations

    oai_token-act-pair · gpt-3.5-turbo

    references to catastrophic events or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tein
    -0.79
    Ģ
    -0.77
    endo
    -0.77
    ī
    -0.76
    Ķ
    -0.75
    uay
    -0.75
    spring
    -0.73
    alties
    -0.73
    rahim
    -0.73
    NSA
    -0.73
    POSITIVE LOGITS
     catastrophic
    1.10
     catast
    1.04
     catastrophe
    1.02
     disasters
    0.89
     meltdown
    0.86
     calam
    0.85
     devast
    0.83
     disaster
    0.83
     nightmares
    0.82
     crashes
    0.81
    Act Density 0.010%

    No Known Activations