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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their significance in writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     challeng
    -0.72
     forwarding
    -0.67
     bolted
    -0.66
     quir
    -0.65
     haul
    -0.65
     exclusively
    -0.65
     stout
    -0.64
     hars
    -0.63
     extinguished
    -0.62
     scourge
    -0.62
    POSITIVE LOGITS
     Anyway
    1.23
     Lastly
    1.20
     However
    1.19
     Therefore
    1.17
     Secondly
    1.10
     Additionally
    1.08
     Unfortunately
    1.08
     Otherwise
    1.05
     Moreover
    1.05
     Nevertheless
    1.05
    Act Density 0.534%

    No Known Activations