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

    Neuronpedia

    INDEX
    Explanations

    specific instances or mentions of the word "distraction"

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "distribution" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    glers
    -1.12
    swick
    -1.00
    tes
    -0.98
    ppo
    -0.82
    terday
    -0.74
    ENA
    -0.74
    gery
    -0.72
    cair
    -0.71
    uberty
    -0.70
     Slater
    -0.69
    POSITIVE LOGITS
    ribut
    1.29
    ributed
    1.22
    inguished
    1.09
    ribute
    1.07
    ribution
    1.06
    illery
    1.02
    ortion
    1.00
    rict
    0.99
    Dist
    0.97
    enfranch
    0.96
    Act Density 0.003%

    No Known Activations