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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing size or scale

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "tiny."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chwitz
    -0.85
    yrinth
    -0.81
     largeDownload
    -0.79
    ources
    -0.77
    orthy
    -0.73
    CLASSIFIED
    -0.72
    lain
    -0.71
     confir
    -0.70
    ilee
    -0.70
    iris
    -0.69
    POSITIVE LOGITS
     bit
    0.97
    pox
    0.92
     fraction
    0.91
    tiny
    0.86
     fractions
    0.84
     handful
    0.84
     slice
    0.83
     tiny
    0.82
     (<
    0.80
     tad
    0.80
    Act Density 0.029%

    No Known Activations