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

    Neuronpedia

    INDEX
    Explanations

    mentions of individuals and their actions or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals and their roles or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CONTIN
    -0.64
    Compl
    -0.58
     âĵĺ
    -0.58
     rematch
    -0.58
    unless
    -0.57
    ':
    -0.55
    maxwell
    -0.55
    STER
    -0.52
    CAR
    -0.52
    ravings
    -0.52
    POSITIVE LOGITS
     unsuccessfully
    0.90
     earlier
    0.86
     last
    0.74
     previous
    0.70
     beforehand
    0.68
    terday
    0.67
     womb
    0.64
     ago
    0.64
     unsuccessful
    0.63
     originally
    0.58
    Act Density 1.783%

    No Known Activations