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

    Neuronpedia

    INDEX
    Explanations

    phrases that are used to transition between different parts of a text

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and connecting phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    spir
    -0.79
    ichen
    -0.72
    PLIED
    -0.71
    ãģĨ
    -0.67
    hab
    -0.65
    idad
    -0.65
    ãĤ¼ãĤ¦ãĤ¹
    -0.64
    avery
    -0.63
    outed
    -0.63
    impl
    -0.63
    POSITIVE LOGITS
     secondly
    1.28
     hey
    1.23
     yes
    1.12
     lest
    1.07
     vo
    1.06
     yeah
    1.06
     finally
    1.05
    romeda
    1.04
     furthermore
    1.02
     remember
    0.98
    Act Density 0.115%

    No Known Activations