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

    percentages in statistical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     BIOS
    -0.64
    ForgeModLoader
    -0.64
    ITED
    -0.61
    XT
    -0.61
     Leilan
    -0.60
    GD
    -0.59
    ARP
    -0.58
     Sakuya
    -0.56
    RAW
    -0.56
     kindly
    -0.56
    POSITIVE LOGITS
     cent
    1.05
     capita
    0.92
    uvian
    0.90
    secut
    0.87
    missive
    0.84
    secution
    0.84
    CENT
    0.84
    tains
    0.83
    malink
    0.81
    ousand
    0.81
    Act Density 0.020%

    No Known Activations