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

    Neuronpedia

    INDEX
    Explanations

    conjunctions that connect phrases or clauses

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "And" used to introduce additional points or clauses in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ses
    -0.73
    fell
    -0.73
    sk
    -0.71
    pees
    -0.68
    ãģĨ
    -0.67
    1001
    -0.65
    url
    -0.63
    buck
    -0.63
    ema
    -0.62
    pt
    -0.62
    POSITIVE LOGITS
    romeda
    1.18
    rea
    1.06
     furthermore
    1.06
     therein
    0.97
    ersen
    0.94
     secondly
    0.94
     moreover
    0.91
    rogens
    0.90
     yes
    0.89
    hra
    0.89
    Act Density 0.075%

    No Known Activations