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

    Neuronpedia

    INDEX
    Explanations

    decimals related to measurements

    oai_token-act-pair · gpt-3.5-turbo

    numerical values followed by a decimal point

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pty
    -0.74
    ĸļ
    -0.74
    quit
    -0.64
    elia
    -0.64
    geist
    -0.62
    stru
    -0.62
    strings
    -0.60
    stration
    -0.59
    swick
    -0.59
    és
    -0.59
    POSITIVE LOGITS
    Thirty
    0.84
    WD
    0.81
     gallon
    0.79
    ield
    0.77
    inch
    0.76
    ths
    0.76
    0000
    0.75
    678
    0.75
    mL
    0.74
    GHz
    0.72
    Act Density 0.035%

    No Known Activations