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

    Neuronpedia

    INDEX
    Explanations

    programming code related to masks and variables

    oai_token-act-pair · gpt-3.5-turbo

    hexadecimal values and related syntax in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    venants
    -0.73
    hari
    -0.70
     Progressive
    -0.68
     Huss
    -0.67
     attrition
    -0.66
     immersion
    -0.66
    pedia
    -0.65
     moderation
    -0.64
     Bundes
    -0.64
     Airbnb
    -0.63
    POSITIVE LOGITS
    ffff
    1.57
    FFFF
    1.56
    fff
    1.33
    0000
    1.31
    00000
    1.28
    000000
    1.26
    0000000
    1.24
    0010
    1.16
    0100
    1.16
    00000000
    1.16
    Act Density 0.055%

    No Known Activations