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

    Neuronpedia

    INDEX
    Explanations

    references to professors and their related activities or attributions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific professors or academic titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MENTS
    -0.79
    boat
    -0.76
     leash
    -0.75
    RANT
    -0.72
     cruc
    -0.69
    boats
    -0.67
    doors
    -0.67
    witz
    -0.67
     ashore
    -0.66
    MENT
    -0.65
    POSITIVE LOGITS
    essors
    1.58
    iciency
    1.31
    iles
    1.27
    essor
    1.24
    icient
    1.16
    ession
    1.12
    ound
    1.04
    essed
    0.98
    ository
    0.98
    essions
    0.98
    Act Density 0.014%

    No Known Activations