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

    Neuronpedia

    INDEX
    Explanations

    references to questions or inquiries

    oai_token-act-pair · gpt-3.5-turbo

    inquiries about human perseverance and curiosity in challenging situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anwhile
    -0.70
    enegger
    -0.53
    vertisement
    -0.50
     thereafter
    -0.48
    çīĪ
    -0.47
    çĶ°
    -0.47
    allery
    -0.46
    staking
    -0.45
     doubtless
    -0.45
     respectively
    -0.45
    POSITIVE LOGITS
     anymore
    0.56
     crappy
    0.51
    ratom
    0.50
     shitty
    0.50
     ANY
    0.45
     crap
    0.44
     greatness
    0.44
     Saiyan
    0.44
     anything
    0.44
     wrong
    0.43
    Act Density 2.161%

    No Known Activations