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

    Neuronpedia

    INDEX
    Explanations

    mention of personal matters or information

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -1.19
    UMP
    -0.78
    REG
    -0.73
    LER
    -0.72
    GGGG
    -0.72
    tower
    -0.71
    ÄŁ
    -0.69
    vous
    -0.69
     Twain
    -0.68
    noon
    -0.68
    POSITIVE LOGITS
    ised
    1.28
    ization
    1.13
    ized
    1.11
    izing
    1.07
    ities
    1.06
    isation
    1.06
    izations
    1.03
     belongings
    1.02
    isations
    1.01
    izes
    0.98
    Act Density 0.377%

    No Known Activations