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

    Neuronpedia

    INDEX
    Explanations

    phrases related to economic or geopolitical events

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     salute
    -0.78
     imperson
    -0.78
     abstinence
    -0.75
    lled
    -0.75
     humour
    -0.71
     dives
    -0.70
     allowance
    -0.69
     indul
    -0.69
    ascus
    -0.68
     diving
    -0.68
    POSITIVE LOGITS
     Alternatively
    1.62
     Ideally
    1.43
     Depending
    1.41
     Already
    1.38
     Assuming
    1.32
     Otherwise
    1.31
     Either
    1.31
     Moreover
    1.29
     Regardless
    1.28
     Currently
    1.26
    Act Density 0.540%

    No Known Activations