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

    Neuronpedia

    INDEX
    Explanations

    references to professors or experts by using the title "Prof"

    oai_token-act-pair · gpt-3.5-turbo

    references to professors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MENTS
    -0.82
     leash
    -0.77
     cruc
    -0.72
    MENT
    -0.69
    RANT
    -0.69
    wolves
    -0.68
     awoken
    -0.68
     ashore
    -0.68
    doors
    -0.67
    wolf
    -0.65
    POSITIVE LOGITS
    essors
    1.58
    essor
    1.31
    iciency
    1.25
    iles
    1.18
    icient
    1.13
    ession
    1.09
    ound
    1.05
    ository
    1.00
    essions
    0.96
    inctions
    0.95
    Act Density 0.005%

    No Known Activations