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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "tiny"

    oai_token-act-pair · gpt-3.5-turbo

    references to small or tiny objects and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inelli
    -0.76
    sem
    -0.75
    ItemImage
    -0.71
    iris
    -0.70
    chwitz
    -0.69
    ilee
    -0.68
    YR
    -0.66
    ership
    -0.65
    ophen
    -0.64
    ources
    -0.64
    POSITIVE LOGITS
     bit
    0.98
     fraction
    0.86
     tad
    0.86
     handful
    0.86
    pox
    0.85
     little
    0.84
    tiny
    0.82
     snippets
    0.81
     glimpse
    0.80
    atur
    0.79
    Act Density 0.057%

    No Known Activations