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

    Neuronpedia

    INDEX
    Explanations

    phrases related to significant events or actions

    oai_token-act-pair · gpt-3.5-turbo

    sentence-ending punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tremend
    -0.76
    anus
    -0.73
     overboard
    -0.73
     closet
    -0.70
     hust
    -0.70
     peers
    -0.69
     ascend
    -0.68
     glim
    -0.67
     addon
    -0.67
     rooting
    -0.67
    POSITIVE LOGITS
     Afterwards
    1.03
     Lastly
    1.03
     Additionally
    1.01
     Finally
    0.98
     However
    0.98
     Furthermore
    0.96
     Moreover
    0.94
     Eventually
    0.93
     Therefore
    0.92
     Nevertheless
    0.90
    Act Density 0.694%

    No Known Activations