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

    Neuronpedia

    INDEX
    Explanations

    specific mentions of dates or time periods

    oai_token-act-pair · gpt-3.5-turbo

    empty or whitespace sections within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     beforehand
    -0.59
    herer
    -0.58
    .*
    -0.58
    *.
    -0.57
    /"
    -0.56
     besides
    -0.56
     alongside
    -0.55
     whenever
    -0.54
    -$
    -0.54
    aria
    -0.53
    POSITIVE LOGITS
     foregoing
    0.80
     Clintons
    0.74
    orem
    0.66
     Houth
    0.65
     same
    0.65
     smallest
    0.65
    oret
    0.65
    ses
    0.65
    resa
    0.64
     remainder
    0.64
    Act Density 0.729%

    No Known Activations