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

    Neuronpedia

    INDEX
    Explanations

    phrases related to diplomatic statements and political discussions

    oai_token-act-pair · gpt-3.5-turbo

    sentences that conclude with a punctuation mark, particularly periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     quir
    -0.88
     nodd
    -0.75
     solo
    -0.72
     tack
    -0.72
     grip
    -0.71
     sideways
    -0.70
     cram
    -0.70
     impro
    -0.68
     lur
    -0.68
     heav
    -0.67
    POSITIVE LOGITS
     Accordingly
    1.50
     Therefore
    1.44
     Additionally
    1.42
     Furthermore
    1.40
     Moreover
    1.37
     However
    1.31
     Consequently
    1.30
     Unfortunately
    1.30
     Our
    1.28
     Ultimately
    1.25
    Act Density 0.366%

    No Known Activations