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

    Neuronpedia

    INDEX
    Explanations

    proper names, particularly those of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Benedict
    -0.16
    ascar
    -0.15
    orian
    -0.15
     Sample
    -0.14
    ayers
    -0.14
    borg
    -0.14
    orum
    -0.14
     Flying
    -0.14
    ÃŃd
    -0.14
    ÃŃda
    -0.14
    POSITIVE LOGITS
    ael
    0.28
    elson
    0.21
    ail
    0.21
    ayla
    0.20
    elsen
    0.18
    aukee
    0.18
    itary
    0.17
     Bowman
    0.16
    kk
    0.15
    dash
    0.15
    Act Density 0.007%

    No Known Activations