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

    Neuronpedia

    INDEX
    Explanations

    phrases related to uncontrollable negative spirals or downward trends

    oai_token-act-pair · gpt-3.5-turbo

    terms related to spirals and vortexes, particularly in a metaphorical or conceptual context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BAT
    -0.77
    Ay
    -0.76
     Baz
    -0.75
     Luxem
    -0.70
     ----
    -0.64
    idates
    -0.64
    emen
    -0.64
    dis
    -0.62
    Ass
    -0.62
    Content
    -0.62
    POSITIVE LOGITS
     spiral
    3.93
     spir
    2.98
     Spiral
    2.39
     vortex
    1.30
     snowball
    1.27
     Spir
    1.26
    spir
    1.24
     escal
    1.21
     plunge
    1.17
     unravel
    1.16
    Act Density 0.023%

    No Known Activations