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

    Neuronpedia

    INDEX
    Explanations

    sentences that end with a particular punctuation mark followed by a specific word or phrase

    oai_token-act-pair · gpt-3.5-turbo

    instances of numerical data and related phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lifes
    -0.74
     mint
    -0.72
     doomed
    -0.72
     fairy
    -0.71
     sucker
    -0.70
     stem
    -0.70
     melted
    -0.70
     hero
    -0.70
     pse
    -0.70
     buggy
    -0.69
    POSITIVE LOGITS
    Lastly
    2.10
    Finally
    2.09
    Similarly
    2.07
    Additionally
    2.03
    Furthermore
    1.95
    Another
    1.95
    Likewise
    1.92
    Moreover
    1.87
    Other
    1.85
    Interestingly
    1.80
    Act Density 0.437%

    No Known Activations