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

    Neuronpedia

    INDEX
    Explanations

    words related to fluidity, including physical fluids and abstract concepts like flexibility and conditional states

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of fluids

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ################
    -0.79
    ãģ®å
    -0.78
    BOOK
    -0.76
    ulhu
    -0.74
    ãģ«
    -0.72
    ä½ľ
    -0.72
    olkien
    -0.71
    ||||
    -0.71
    éĥ
    -0.70
    ODUCT
    -0.70
    POSITIVE LOGITS
     fluid
    1.19
     fluids
    1.02
    pedia
    1.00
    ity
    0.97
    ious
    0.96
     resusc
    0.92
    iltration
    0.87
    ly
    0.86
    ially
    0.86
    icity
    0.86
    Act Density 0.012%

    No Known Activations