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

    Neuronpedia

    INDEX
    Explanations

    phrases related to combining things 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
    bell
    -0.85
    wa
    -0.78
    ways
    -0.78
    der
    -0.77
    keeper
    -0.74
    mouth
    -0.73
    mo
    -0.73
    den
    -0.73
    etheless
    -0.72
    facing
    -0.72
    POSITIVE LOGITS
    ãĤ¤ãĥĪ
    1.09
     combine
    1.08
     Combine
    1.02
     combines
    0.95
    ãĤ¼ãĤ¦ãĤ¹
    0.80
    uations
    0.80
    INO
    0.77
    ibilities
    0.77
    ãĤ©
    0.77
     combining
    0.76
    Act Density 0.007%

    No Known Activations