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

    Neuronpedia

    INDEX
    Explanations

    names and titles associated with political and cultural figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    920
    -0.15
    ispecies
    -0.14
    angu
    -0.14
     Uhr
    -0.14
    ight
    -0.13
     jedn
    -0.13
     cif
    -0.13
     dÃŃv
    -0.13
    awn
    -0.13
    awa
    -0.13
    POSITIVE LOGITS
     retirement
    0.20
     retired
    0.17
     widow
    0.17
     retire
    0.16
     Retirement
    0.16
    asti
    0.16
     retirees
    0.15
    STALL
    0.15
    bubble
    0.15
    anton
    0.14
    Act Density 0.238%

    No Known Activations