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

    Neuronpedia

    INDEX
    Explanations

    phrases with the word "light" in them

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "light" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     outs
    -0.66
     MSI
    -0.64
     Producer
    -0.64
    appa
    -0.63
     orders
    -0.62
     organic
    -0.58
     authors
    -0.58
     producers
    -0.57
     à¨
    -0.57
     lottery
    -0.57
    POSITIVE LOGITS
    ight
    4.69
    ights
    2.37
    IGHT
    2.09
    ighting
    2.05
    IGHTS
    1.67
    ighter
    1.59
    sight
    1.53
    ighters
    1.40
     Sight
    1.31
    igh
    1.18
    Act Density 0.013%

    No Known Activations