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

    Neuronpedia

    INDEX
    Explanations

    descriptors of a person's character and behavior, especially in terms of negative traits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lea
    -0.16
     å¡
    -0.15
    Encoder
    -0.15
    feit
    -0.15
    ought
    -0.15
    ãĥIJãĤ¹
    -0.14
     misunder
    -0.14
    UTILITY
    -0.14
     ÑģоÑĩ
    -0.14
    ieber
    -0.13
    POSITIVE LOGITS
     temper
    0.24
     drinking
    0.23
     mood
    0.23
     physical
    0.19
     prom
    0.19
     eg
    0.19
     drink
    0.18
     Drinking
    0.17
     temp
    0.17
    enge
    0.17
    Act Density 0.058%

    No Known Activations