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

    Neuronpedia

    INDEX
    Explanations

    sentences ending in a colon indicating a direct quote or statement

    oai_token-act-pair · gpt-3.5-turbo

    instances of dialogue or quotes in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aban
    -0.60
    iage
    -0.55
    idas
    -0.55
    irements
    -0.55
    irable
    -0.55
    roit
    -0.54
    ible
    -0.54
    vable
    -0.54
    ADS
    -0.54
    ults
    -0.53
    POSITIVE LOGITS
     "'
    1.45
     "âĢ¦
    1.34
     "...
    1.29
     "
    1.28
     ""
    1.27
     "[
    1.26
     "@
    1.24
     "(
    1.20
     "#
    1.20
     '[
    1.19
    Act Density 0.082%

    No Known Activations