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

    Neuronpedia

    INDEX
    Explanations

    references to specific dates

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and their relation to sentence structure or pauses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ouble
    -0.74
    phant
    -0.69
    imates
    -0.67
    irable
    -0.66
    iciency
    -0.64
    irms
    -0.64
    phan
    -0.64
    Requires
    -0.62
    oms
    -0.62
    Explore
    -0.61
    POSITIVE LOGITS
     incidentally
    1.00
     yeah
    0.95
     he
    0.93
     shortly
    0.86
     huh
    0.84
     when
    0.82
     congr
    0.82
     eh
    0.82
     during
    0.79
     hadn
    0.78
    Act Density 0.442%

    No Known Activations