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

    Neuronpedia

    INDEX
    Explanations

    quotations and statements attributed to various sources

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly colons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ensu
    -0.60
     reckoning
    -0.58
     collision
    -0.56
     totem
    -0.56
     piping
    -0.54
     veter
    -0.53
     grease
    -0.53
     sights
    -0.52
     giveaway
    -0.52
     gore
    -0.52
    POSITIVE LOGITS
     "âĢ¦
    1.60
     "[
    1.56
     "...
    1.53
     "'
    1.49
     "(
    1.25
    ↵
    1.24
     ""
    1.21
     '[
    1.19
     "
    1.19
     "@
    1.15
    Act Density 0.122%

    No Known Activations