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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "friend"

    oai_token-act-pair · gpt-3.5-turbo

    references to friendships or mentions of friends

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aeda
    -0.82
    tarians
    -0.80
    cale
    -0.79
     ceilings
    -0.78
     chloride
    -0.70
    overe
    -0.67
    plets
    -0.67
    mberg
    -0.66
    elsius
    -0.65
    Frames
    -0.62
    POSITIVE LOGITS
    lier
    1.31
    liness
    1.28
    lies
    1.19
    liest
    1.15
    friend
    0.94
    ship
    0.92
    ships
    0.88
    hesis
    0.85
    finder
    0.84
    hetical
    0.79
    Act Density 0.038%

    No Known Activations