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

    Neuronpedia

    INDEX
    Explanations

    phrases related to consumption or acquisition of products or services

    oai_token-act-pair · gpt-3.5-turbo

    instances of punctuation marks and sentence endings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     previously
    -0.72
    senal
    -0.72
     synthes
    -0.68
     market
    -0.67
     intending
    -0.65
     illegally
    -0.64
     intend
    -0.64
     approved
    -0.64
     Aval
    -0.63
     herself
    -0.63
    POSITIVE LOGITS
    Anyway
    1.16
    Advertisement
    1.15
    Perhaps
    1.05
    Sure
    1.05
    Consider
    1.05
    Sometimes
    1.04
    Indeed
    1.03
    Yet
    1.03
    Newsletter
    1.03
    Except
    1.02
    Act Density 0.538%

    No Known Activations