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

    Neuronpedia

    INDEX
    Explanations

    words with a focus on physical actions or activities performed by people

    oai_token-act-pair · gpt-3.5-turbo

    occurrences and variations of the letter 'g'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ideal
    -0.79
    etheless
    -0.69
     starters
    -0.61
    tenance
    -0.60
     Pis
    -0.59
     PATH
    -0.59
     AVG
    -0.57
     Exile
    -0.57
     questioning
    -0.57
     derog
    -0.57
    POSITIVE LOGITS
    ourmet
    1.42
    auntlet
    1.39
    ilded
    1.36
    rafted
    1.30
    ospels
    1.27
    auntlets
    1.27
    reek
    1.24
    remlin
    1.23
    umption
    1.23
    ulp
    1.22
    Act Density 0.027%

    No Known Activations