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

    Neuronpedia

    INDEX
    Explanations

    conjunctions connecting different pieces of information

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "And" at the start of sentences or phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ses
    -0.73
    ãģĨ
    -0.71
    olves
    -0.66
    lication
    -0.65
    1001
    -0.64
    pees
    -0.59
    outine
    -0.59
    fell
    -0.57
    Ô
    -0.57
    iking
    -0.56
    POSITIVE LOGITS
    romeda
    1.21
     therein
    1.17
    rea
    1.16
     although
    1.13
     furthermore
    1.12
    ersen
    1.06
    ré
    1.06
     secondly
    1.05
     moreover
    1.01
    rogens
    1.00
    Act Density 0.086%

    No Known Activations