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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating diverse or various types of something

    oai_token-act-pair · gpt-3.5-turbo

    references to diversity or multiple options in contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    roit
    -0.77
    rollers
    -0.74
    robe
    -0.74
    minster
    -0.71
    jin
    -0.71
    ossier
    -0.70
    abad
    -0.69
    avement
    -0.69
    eded
    -0.68
    amina
    -0.68
    POSITIVE LOGITS
    ensical
    0.82
     variety
    0.74
     Flavoring
    0.71
     incarn
    0.70
     assortment
    0.70
    icult
    0.70
     thereof
    0.69
     ways
    0.66
    WAYS
    0.65
     vari
    0.64
    Act Density 0.016%

    No Known Activations