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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal or academic discourse

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, especially periods at the end of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     glim
    -1.07
     volunte
    -0.89
     neighb
    -0.87
     reluct
    -0.86
     satell
    -0.86
     gobl
    -0.84
     strugg
    -0.84
     powering
    -0.84
     entreprene
    -0.82
     unden
    -0.80
    POSITIVE LOGITS
     Similarly
    1.60
     Furthermore
    1.52
     Moreover
    1.48
     Likewise
    1.46
     Additionally
    1.42
     Nevertheless
    1.40
     Nonetheless
    1.39
     Presumably
    1.36
     Thus
    1.35
     Consequently
    1.33
    Act Density 0.554%

    No Known Activations