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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "An" followed by a person's name

    oai_token-act-pair · gpt-3.5-turbo

    the repeated reference to a specific name or term

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     minus
    -0.61
     sterling
    -0.60
     backwards
    -0.60
     FIGHT
    -0.59
     sides
    -0.59
    âĸº
    -0.58
     bottom
    -0.57
     home
    -0.55
     naming
    -0.54
     GOODMAN
    -0.54
    POSITIVE LOGITS
    omaly
    1.32
    nette
    1.29
    alogue
    1.26
    ubis
    1.21
    omal
    1.12
    ibal
    1.12
    xious
    1.11
    esthesia
    1.10
    ophe
    1.08
    alogy
    1.07
    Act Density 0.023%

    No Known Activations