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

    Neuronpedia

    INDEX
    Explanations

    phrases related to numeric comparisons or multiples

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases involving numerical values and ratios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PLA
    -0.81
    azel
    -0.74
    corn
    -0.69
     Leilan
    -0.68
    behind
    -0.68
    fy
    -0.67
    ama
    -0.64
    ongo
    -0.64
    nothing
    -0.63
    RAW
    -0.63
    POSITIVE LOGITS
     amount
    1.21
     size
    1.06
     thickness
    1.04
     usual
    1.03
     extent
    1.01
     average
    0.98
     diameter
    0.97
     height
    0.88
     volume
    0.86
     magnitude
    0.86
    Act Density 0.063%

    No Known Activations