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

    Neuronpedia

    INDEX
    Explanations

    references to the self and personal attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Undertaker
    -0.54
     INVENTION
    -0.54
    هد
    -0.54
    дру
    -0.52
     scand
    -0.52
    AddressBook
    -0.51
    нор
    -0.51
     opio
    -0.49
     postIndex
    -0.49
     erw
    -0.48
    POSITIVE LOGITS
    elfare
    0.86
    iſter
    0.85
    ratulations
    0.81
    CppMethod
    0.78
    ITERATURE
    0.77
    ργο
    0.77
     ſch
    0.76
    İY
    0.75
     houſe
    0.74
     Jefus
    0.74
    Act Density 0.200%

    No Known Activations