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

    Neuronpedia

    INDEX
    Explanations

    sentences containing short phrases referring to an action or state followed by a period

    oai_token-act-pair · gpt-3.5-turbo

    sentence endings and punctuation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     volunte
    -0.96
     corrid
    -0.94
     pione
    -0.94
     carbohyd
    -0.91
     earthqu
    -0.90
     tradem
    -0.89
     entreprene
    -0.89
    Þ
    -0.88
     teasp
    -0.88
     practition
    -0.87
    POSITIVE LOGITS
     Therefore
    1.43
     Furthermore
    1.43
     Consequently
    1.43
     Moreover
    1.39
     Likewise
    1.34
     Hence
    1.30
     Additionally
    1.29
     Thus
    1.28
     Secondly
    1.28
     Worse
    1.26
    Act Density 0.568%

    No Known Activations