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

    Neuronpedia

    INDEX
    Explanations

    conjunctions signaling a shift in focus or topic

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "And" used to connect ideas or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ses
    -0.78
    ãģĨ
    -0.68
    1001
    -0.66
    pees
    -0.65
    olves
    -0.62
    iking
    -0.61
    lde
    -0.60
    fell
    -0.60
    url
    -0.60
    lication
    -0.59
    POSITIVE LOGITS
    romeda
    1.24
    rea
    1.11
     furthermore
    1.08
     therein
    1.03
     although
    1.00
    ersen
    0.99
     secondly
    0.99
     moreover
    0.94
    ré
    0.92
    rogens
    0.92
    Act Density 0.079%

    No Known Activations