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

    Neuronpedia

    INDEX
    Explanations

    sentences ending in a period

    oai_token-act-pair · gpt-3.5-turbo

    sentence-ending punctuation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     glim
    -0.93
     volunte
    -0.81
    isbury
    -0.78
     entreprene
    -0.77
     powering
    -0.77
    ahime
    -0.74
     achie
    -0.74
     tradem
    -0.73
     millenn
    -0.73
     workspace
    -0.72
    POSITIVE LOGITS
     Furthermore
    1.71
     Similarly
    1.70
     Nevertheless
    1.69
     Moreover
    1.69
     Nonetheless
    1.68
     Likewise
    1.64
     Lastly
    1.57
     Interestingly
    1.56
     Thus
    1.53
     Additionally
    1.53
    Act Density 0.592%

    No Known Activations