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

    Neuronpedia

    INDEX
    Explanations

    phrases related to documentation and reporting

    oai_token-act-pair · gpt-3.5-turbo

    the presence of periods or sentence endings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ogene
    -0.78
     dep
    -0.72
     currently
    -0.72
     ongoing
    -0.71
    soDeliveryDate
    -0.71
     pronoun
    -0.67
     expires
    -0.67
     anticip
    -0.66
     will
    -0.66
     purse
    -0.65
    POSITIVE LOGITS
     Eventually
    1.18
     Then
    1.13
     Was
    1.10
     Ultimately
    1.05
     Initially
    1.03
     Later
    1.02
     Moreover
    1.01
     Didn
    1.01
     Had
    1.01
     Were
    1.00
    Act Density 0.725%

    No Known Activations