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

    Neuronpedia

    INDEX
    Explanations

    phrases followed by a conclusion or transition

    oai_token-act-pair · gpt-3.5-turbo

    punctuation, particularly periods and commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cade
    -0.88
    ividual
    -0.80
    uly
    -0.79
     boutique
    -0.79
    eatured
    -0.79
    ogle
    -0.75
    zman
    -0.73
    apper
    -0.73
    omics
    -0.72
    emaker
    -0.72
    POSITIVE LOGITS
     Luckily
    1.19
     Slowly
    1.14
     Thankfully
    1.12
     Fortunately
    1.07
     Suddenly
    1.06
     Dumbledore
    1.02
     Someone
    1.02
     Something
    1.01
     Eventually
    1.01
     Though
    1.01
    Act Density 0.429%

    No Known Activations