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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "mother."

    oai_token-act-pair · gpt-3.5-turbo

    references to "mother" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Flavoring
    -0.91
    okers
    -0.80
    kefeller
    -0.78
    NRS
    -0.76
    vernment
    -0.72
    raviolet
    -0.72
    idian
    -0.68
    ratulations
    -0.65
    EY
    -0.65
    umbn
    -0.64
    POSITIVE LOGITS
    hood
    1.15
    ship
    1.00
    hesis
    0.99
    heses
    0.91
    hetical
    0.88
    hetically
    0.86
    load
    0.84
     Teresa
    0.84
    ships
    0.83
    boards
    0.81
    Act Density 0.027%

    No Known Activations