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

    Neuronpedia

    INDEX
    Explanations

    references to specific places or entities such as "Dunkirk," "DD," "Django," and "Delhi."

    oai_token-act-pair · gpt-3.5-turbo

    references to specific historical events and locations or notable figures associated with them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sburgh
    -0.77
    itudes
    -0.74
    âĸĪâĸĪ
    -0.73
    ships
    -0.69
    ulators
    -0.67
    ambo
    -0.64
    ament
    -0.63
    akia
    -0.62
    ocene
    -0.62
    hell
    -0.61
    POSITIVE LOGITS
    ynamic
    0.92
    hyde
    0.88
    ynam
    0.86
    etermination
    0.86
    ependent
    0.84
    cember
    0.83
    etermin
    0.82
    iscovery
    0.81
    NF
    0.79
    iamond
    0.78
    Act Density 0.295%

    No Known Activations