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

    Neuronpedia

    INDEX
    Explanations

    references to water-related objects or substances

    oai_token-act-pair · gpt-3.5-turbo

    references to water

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eering
    -0.81
    Reloaded
    -0.68
    ificant
    -0.66
    ures
    -0.65
     millenn
    -0.65
    Files
    -0.64
     Rove
    -0.63
    pta
    -0.62
    ablishment
    -0.61
    asio
    -0.61
    POSITIVE LOGITS
    melon
    1.81
    tight
    1.35
    colour
    1.27
    falls
    1.22
    mel
    1.06
    color
    1.06
    proof
    1.05
    loo
    0.99
    marks
    0.97
     soluble
    0.97
    Act Density 0.052%

    No Known Activations