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

    Neuronpedia

    INDEX
    Explanations

    people's actions or attributes

    oai_token-act-pair · gpt-3.5-turbo

    the word "who" in various contexts, often referring to individuals or groups involved in actions or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Delicious
    -0.65
    OUND
    -0.64
    ogue
    -0.63
     Connection
    -0.62
     srfAttach
    -0.61
     Decay
    -0.61
     Bound
    -0.59
    UGE
    -0.59
    PORT
    -0.59
    ranging
    -0.58
    POSITIVE LOGITS
     knows
    1.45
     thinks
    1.40
     loves
    1.40
     understands
    1.38
     cares
    1.37
     hates
    1.35
     wants
    1.35
     wears
    1.33
     prefers
    1.30
     enjoys
    1.30
    Act Density 0.124%

    No Known Activations