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

    Neuronpedia

    INDEX
    Explanations

    percentage values

    oai_token-act-pair · gpt-3.5-turbo

    references to percentages and statistics related to economic data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zos
    -0.69
    beit
    -0.66
    ãĤ©
    -0.65
    flies
    -0.59
    \\\\\\\\\\\\\\\\
    -0.58
    pecially
    -0.58
     istg
    -0.57
    vised
    -0.57
    Keys
    -0.56
    rities
    -0.55
    POSITIVE LOGITS
    +.
    0.90
     ABV
    0.88
    +,
    0.77
    +)
    0.71
    -+
    0.71
    xual
    0.70
     GDP
    0.67
     APR
    0.66
     chance
    0.65
     occupancy
    0.64
    Act Density 0.041%

    No Known Activations