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

    Neuronpedia

    INDEX
    Explanations

    names of actors and their corresponding roles in films

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     vPvB
    -0.83
    Geplaatst
    -0.66
     مرئيه
    -0.65
     grads
    -0.62
     graduate
    -0.61
     propOrder
    -0.61
    +#+#
    -0.61
     gái
    -0.61
    AccessorTable
    -0.61
     canlynol
    -0.60
    POSITIVE LOGITS
     retired
    1.16
    Retired
    1.01
     Retired
    0.97
    retired
    0.92
     retirement
    0.91
     retirees
    0.91
    老人
    0.90
     pensioners
    0.89
     elderly
    0.88
    👵
    0.88
    Act Density 0.582%

    No Known Activations