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

    Neuronpedia

    INDEX
    Explanations

    conjunctions like "and" that connect phrases or ideas

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions, particularly "And," as connectors in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģĨ
    -0.73
    iosyncr
    -0.68
    spir
    -0.63
    icc
    -0.62
    operator
    -0.62
    éĹĺ
    -0.61
    iets
    -0.60
    ahime
    -0.59
    entials
    -0.59
    interstitial
    -0.58
    POSITIVE LOGITS
     furthermore
    1.32
     secondly
    1.29
     yeah
    1.18
     then
    1.17
    romeda
    1.16
     moreover
    1.10
     yet
    1.09
     besides
    1.07
     guess
    1.07
     frankly
    1.05
    Act Density 0.109%

    No Known Activations