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

    Neuronpedia

    INDEX
    Explanations

    phrases transitioning to a new topic

    oai_token-act-pair · gpt-3.5-turbo

    instances of the conjunction "and" used to connect multiple statements or ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fell
    -0.76
    url
    -0.67
    sk
    -0.67
    atical
    -0.66
    lde
    -0.65
    ses
    -0.65
    pees
    -0.64
    ãģĨ
    -0.64
    steam
    -0.64
    viation
    -0.61
    POSITIVE LOGITS
    romeda
    1.16
    rea
    1.04
     furthermore
    1.03
    hra
    0.97
     secondly
    0.93
     moreover
    0.89
    rogens
    0.87
    alus
    0.86
    ersen
    0.84
     consequently
    0.84
    Act Density 0.072%

    No Known Activations