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

    Neuronpedia

    INDEX
    Explanations

    references to human existence and characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elper
    -0.16
    abile
    -0.15
    undle
    -0.15
    erton
    -0.14
     åĨĨ
    -0.14
    odega
    -0.14
    ephy
    -0.14
    å£
    -0.14
    olem
    -0.14
    elm
    -0.13
    POSITIVE LOGITS
     hol
    0.16
     Brooks
    0.16
    aret
    0.16
    780
    0.14
    697
    0.14
    Hu
    0.14
    éĢļ
    0.14
     Wyn
    0.14
     Maver
    0.14
    Åĵ
    0.13
    Act Density 0.071%

    No Known Activations