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

    Neuronpedia

    INDEX
    Explanations

    references to personal experiences and emotions related to creativity and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     yourselves
    -0.17
     ourselves
    -0.15
    èªł
    -0.15
     hood
    -0.14
    opak
    -0.14
    leur
    -0.14
     Ñģоп
    -0.14
    обов
    -0.14
    ç´
    -0.13
     Lake
    -0.13
    POSITIVE LOGITS
     himself
    0.29
     his
    0.19
     personally
    0.19
     Himself
    0.18
     seinem
    0.15
     personal
    0.15
    his
    0.15
    омеÑĢ
    0.14
    kazy
    0.14
     pesso
    0.14
    Act Density 0.455%

    No Known Activations