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

    Neuronpedia

    INDEX
    Explanations

    academic citations and references within scientific text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     otherwise
    -0.15
    ori
    -0.14
     you
    -0.14
     afterward
    -0.14
     Particularly
    -0.13
     afterwards
    -0.13
    ettel
    -0.13
     everything
    -0.13
    apr
    -0.13
    olarity
    -0.13
    POSITIVE LOGITS
     recent
    0.34
    recent
    0.30
     recently
    0.28
     Recent
    0.27
    Recent
    0.26
     Recently
    0.26
    Recently
    0.26
     Until
    0.26
     until
    0.25
    Until
    0.25
    Act Density 0.131%

    No Known Activations