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

    Neuronpedia

    INDEX
    Explanations

    instructions or steps related to cooking or crafting

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and their usage within sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¬¼
    -0.60
    nces
    -0.59
    endo
    -0.57
    ledged
    -0.55
     Pigs
    -0.54
    é¾
    -0.53
    ocaly
    -0.53
    odore
    -0.53
    ance
    -0.52
     Citizen
    -0.52
    POSITIVE LOGITS
     then
    1.23
     preferably
    1.21
    then
    1.17
     THEN
    1.02
     ensuring
    1.00
     avoiding
    1.00
     thereby
    0.96
     allowing
    0.95
     ideally
    0.95
     minimizing
    0.94
    Act Density 0.172%

    No Known Activations