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

    Neuronpedia

    INDEX
    Explanations

    names of characters

    oai_token-act-pair · gpt-3.5-turbo

    the definite article "the."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elaide
    -0.70
    staking
    -0.69
    icho
    -0.68
     repay
    -0.65
     advances
    -0.64
    APD
    -0.64
     resorted
    -0.64
     indulge
    -0.62
     anarchism
    -0.62
    ictional
    -0.60
    POSITIVE LOGITS
    ses
    0.93
     longest
    0.90
     oldest
    0.87
     earliest
    0.85
    ocracy
    0.83
     same
    0.83
     largest
    0.82
     fastest
    0.81
    ater
    0.80
     latter
    0.80
    Act Density 0.117%

    No Known Activations