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

    Neuronpedia

    INDEX
    Explanations

    instances of combining various elements or components together

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "combine" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    den
    -0.84
    luster
    -0.78
    emb
    -0.75
    der
    -0.74
    ways
    -0.73
    cknow
    -0.70
    worms
    -0.70
    way
    -0.69
    wa
    -0.69
    mo
    -0.69
    POSITIVE LOGITS
    ãĤ¤ãĥĪ
    0.89
    ibilities
    0.87
     combine
    0.82
    halla
    0.81
     combines
    0.80
    ively
    0.78
    uations
    0.77
     bundles
    0.75
     genders
    0.73
     sexes
    0.72
    Act Density 0.017%

    No Known Activations