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

    Neuronpedia

    INDEX
    Explanations

    words associated with emotions and complex descriptions of human experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illis
    -0.15
    inton
    -0.14
     addCriterion
    -0.14
    inel
    -0.14
    phins
    -0.14
     оÑĢг
    -0.14
    illi
    -0.14
     FactoryBot
    -0.13
    berman
    -0.13
    leans
    -0.13
    POSITIVE LOGITS
     Quadr
    0.17
     Roose
    0.15
     quadr
    0.15
    liest
    0.14
    SMART
    0.14
    ype
    0.14
    anean
    0.14
     Braun
    0.13
    ander
    0.13
     Gra
    0.13
    Act Density 0.016%

    No Known Activations