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

    Neuronpedia

    INDEX
    Explanations

    references to a specific location or entity named "Des"

    oai_token-act-pair · gpt-3.5-turbo

    the name "Des" and similar tokens associated with it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    glers
    -0.85
    Reviewer
    -0.83
    hetti
    -0.77
     Penguin
    -0.68
     breeze
    -0.67
    enhagen
    -0.66
     Contra
    -0.60
    ancial
    -0.60
     tremend
    -0.59
    atown
    -0.59
    POSITIVE LOGITS
     Moines
    1.20
    perate
    1.19
    ync
    1.17
    criptions
    1.13
    erve
    1.11
    cend
    1.11
    irable
    1.01
    erves
    0.99
    ire
    0.98
    ired
    0.97
    Act Density 0.011%

    No Known Activations